├── .gitignore ├── LICENSE ├── MANIFEST.in ├── README.md ├── docs ├── Makefile ├── make.bat └── source │ ├── conf.py │ ├── index.rst │ ├── modules.rst │ ├── pyoe.OEBench.ADBench.baseline.rst │ ├── pyoe.OEBench.ADBench.rst │ ├── pyoe.OEBench.rst │ ├── pyoe.algorithms.rst │ ├── pyoe.dataloaders.rst │ ├── pyoe.metrics.rst │ ├── pyoe.models.rst │ └── pyoe.rst ├── examples ├── example_1.py ├── example_2.py ├── example_3.py ├── example_4.py ├── example_5.py ├── example_6.py ├── example_7.py ├── example_8.py └── example_9.py ├── images └── pyoe.png ├── pyoe ├── OEBench │ ├── ADBench │ │ ├── .gitattributes │ │ ├── .gitignore │ │ ├── LICENSE │ │ ├── MANIFEST.in │ │ ├── README.md │ │ ├── __init__.py │ │ ├── baseline │ │ │ ├── DAGMM │ │ │ │ ├── .gitignore │ │ │ │ ├── forward_step.py │ │ │ │ ├── main.py │ │ │ │ ├── model.py │ │ │ │ ├── preprocess.py │ │ │ │ ├── run.py │ │ │ │ ├── test.py │ │ │ │ ├── train.py │ │ │ │ └── utils │ │ │ │ │ └── utils.py │ │ │ ├── DeepSAD │ │ │ │ ├── LICENSE │ │ │ │ ├── README.md │ │ │ │ ├── ae_results.json │ │ │ │ ├── imgs │ │ │ │ │ └── fig1.png │ │ │ │ ├── log.txt │ │ │ │ ├── requirements.txt │ │ │ │ ├── results.json │ │ │ │ └── src │ │ │ │ │ ├── base │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── base_dataset.py │ │ │ │ │ ├── base_net.py │ │ │ │ │ ├── base_trainer.py │ │ │ │ │ ├── odds_dataset.py │ │ │ │ │ └── torchvision_dataset.py │ │ │ │ │ ├── baseline_SemiDGM.py │ │ │ │ │ ├── baseline_isoforest.py │ │ │ │ │ ├── baseline_kde.py │ │ │ │ │ ├── baseline_ocsvm.py │ │ │ │ │ ├── baseline_ssad.py │ │ │ │ │ ├── baselines │ │ │ │ │ ├── SemiDGM.py │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── isoforest.py │ │ │ │ │ ├── kde.py │ │ │ │ │ ├── ocsvm.py │ │ │ │ │ ├── shallow_ssad │ │ │ │ │ │ ├── __init__.py │ │ │ │ │ │ └── ssad_convex.py │ │ │ │ │ └── ssad.py │ │ │ │ │ ├── datasets │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── cifar10.py │ │ │ │ │ ├── fmnist.py │ │ │ │ │ ├── main.py │ │ │ │ │ ├── mnist.py │ │ │ │ │ ├── odds.py │ │ │ │ │ └── preprocessing.py │ │ │ │ │ ├── deepsad.py │ │ │ │ │ ├── networks │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── cifar10_LeNet.py │ │ │ │ │ ├── dgm.py │ │ │ │ │ ├── fmnist_LeNet.py │ │ │ │ │ ├── inference │ │ │ │ │ │ └── distributions.py │ │ │ │ │ ├── layers │ │ │ │ │ │ ├── standard.py │ │ │ │ │ │ └── stochastic.py │ │ │ │ │ ├── main.py │ │ │ │ │ ├── mlp.py │ │ │ │ │ ├── mnist_LeNet.py │ │ │ │ │ └── vae.py │ │ │ │ │ ├── optim │ │ │ │ │ ├── DeepSAD_trainer.py │ │ │ │ │ ├── SemiDGM_trainer.py │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── ae_trainer.py │ │ │ │ │ ├── vae_trainer.py │ │ │ │ │ └── variational.py │ │ │ │ │ ├── run.py │ │ │ │ │ └── utils │ │ │ │ │ ├── __init__.py │ │ │ │ │ ├── config.py │ │ │ │ │ ├── misc.py │ │ │ │ │ └── visualization │ │ │ │ │ └── plot_images_grid.py │ │ │ ├── DevNet │ │ │ │ ├── run.py │ │ │ │ └── utils.py │ │ │ ├── FEAWAD │ │ │ │ ├── run.py │ │ │ │ └── toolsdev.py │ │ │ ├── FTTransformer │ │ │ │ └── run.py │ │ │ ├── GANomaly │ │ │ │ ├── fit.py │ │ │ │ ├── model.py │ │ │ │ └── run.py │ │ │ ├── PReNet │ │ │ │ ├── fit.py │ │ │ │ ├── model.py │ │ │ │ ├── run.py │ │ │ │ └── utils.py │ │ │ ├── PyOD.py │ │ │ ├── REPEN │ │ │ │ ├── model.py │ │ │ │ ├── run.py │ │ │ │ └── utils.py │ │ │ ├── Supervised.py │ │ │ └── __init__.py │ │ ├── data_generator.py │ │ ├── datasets │ │ │ └── README.md │ │ ├── demo.ipynb │ │ ├── figs │ │ │ ├── ADBench.png │ │ │ ├── ADBenchV2.png │ │ │ ├── Algorithms.png │ │ │ ├── MNIST-C.png │ │ │ ├── MVTec-AD(ViT).png │ │ │ └── MVTec-AD.png │ │ ├── myutils.py │ │ ├── other_utils │ │ │ ├── gmm │ │ │ │ ├── LICENSE.md │ │ │ │ ├── README.md │ │ │ │ ├── example.png │ │ │ │ ├── example.py │ │ │ │ ├── gmm.py │ │ │ │ ├── test.py │ │ │ │ └── utils.py │ │ │ └── utils.py │ │ └── run.py │ ├── README.md │ ├── __init__.py │ ├── arf.py │ ├── armnet.py │ ├── cluster.py │ ├── dataset │ │ └── README.md │ ├── dataset_experiment_info │ │ ├── 5cities │ │ │ ├── beijing │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── chengdu │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── guangzhou │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── shanghai │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ └── shenyang │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ ├── KDDCUP99 │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── airbnb │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── airlines │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── allstate_claims_severity │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── beijingPM2.5 │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── beijing_multisite │ │ │ ├── aotizhongxin │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── changping │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── dingling │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── dongsi │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── guanyuan │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── gucheng │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── huairou │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── nongzhanguan │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── shunyi │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── tiantan │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── wanliu │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ └── wanshouxingong │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ ├── bike_sharing_demand │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── bitcoin │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── covtype │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── election │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── electricity_prices │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── energy_prediction │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── household │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── overall_missing_value_stats.json │ │ │ └── schema.json │ │ ├── insects │ │ │ ├── abrupt_balanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── abrupt_imbalanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── gradual_balanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── gradual_imbalanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── incremental_abrupt_balanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── incremental_abrupt_imbalanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── incremental_balanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── incremental_imbalanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── incremental_reoccurring_balanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ ├── incremental_reoccurring_imbalanced │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ │ └── out-of-control │ │ │ │ ├── info.json │ │ │ │ ├── missing_value_by_window_stats.json │ │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ │ ├── one_dimensional_drift_stats.json │ │ │ │ ├── outliers_stats_each_window.json │ │ │ │ ├── outliers_stats_overall.json │ │ │ │ ├── overall_missing_value_stats.json │ │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ │ └── schema.json │ │ ├── italian_city_airquality │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── news_popularity │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── noaa │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── rialto │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── room_occupancy │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── rssi │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── safe_driver │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── taxi_ride_duration │ │ │ ├── info.json │ │ │ └── schema.json │ │ ├── tetouan │ │ │ ├── info.json │ │ │ ├── missing_value_by_window_stats.json │ │ │ ├── multi_dimensional_drift_stats.json │ │ │ ├── one_dimensional_drift_stats.json │ │ │ ├── outliers_stats_each_window.json │ │ │ ├── outliers_stats_overall.json │ │ │ ├── overall_missing_value_stats.json │ │ │ ├── pca_one_dimensional_drift_stats.json │ │ │ └── schema.json │ │ ├── traffic_volumn │ │ │ ├── info.json │ │ │ └── schema.json │ │ └── weather_indian_cities │ │ │ ├── Bhubhneshwar │ │ │ ├── info.json │ │ │ └── schema.json │ │ │ ├── Rajasthan │ │ │ ├── info.json │ │ │ └── schema.json │ │ │ ├── bangalore │ │ │ ├── info.json │ │ │ └── schema.json │ │ │ ├── chennai │ │ │ ├── info.json │ │ │ └── schema.json │ │ │ ├── delhi │ │ │ ├── info.json │ │ │ └── schema.json │ │ │ ├── lucknow │ │ │ ├── info.json │ │ │ └── schema.json │ │ │ └── mumbai │ │ │ ├── info.json │ │ │ └── schema.json │ ├── dataset_experiment_results.csv │ ├── dataset_selection.py │ ├── entmax.py │ ├── ewc.py │ ├── experiments.py │ ├── figures │ │ ├── cluster.pdf │ │ ├── cluster.png │ │ ├── flowchart.png │ │ └── flowchart2.png │ ├── layers.py │ ├── model.py │ ├── outliers.py │ ├── pipeline.py │ ├── run.sh │ └── stream_cluster.py ├── __init__.py ├── __version__.py ├── algorithms │ ├── __init__.py │ ├── loss.py │ └── trainer.py ├── dataloaders │ ├── __init__.py │ ├── base.py │ └── pipeline.py ├── metrics │ ├── __init__.py │ └── metrics.py ├── models │ ├── __init__.py │ ├── models.py │ └── networks.py ├── preprocessors.py └── utils.py ├── requirements.txt └── setup.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | env/ 12 | build/ 13 | develop-eggs/ 14 | dist/ 15 | downloads/ 16 | eggs/ 17 | .eggs/ 18 | lib/ 19 | lib64/ 20 | parts/ 21 | sdist/ 22 | var/ 23 | *.egg-info/ 24 | .installed.cfg 25 | *.egg 26 | 27 | # PyInstaller 28 | # Usually these files are written by a python script from a template 29 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 30 | *.manifest 31 | *.spec 32 | 33 | # Installer logs 34 | pip-log.txt 35 | pip-delete-this-directory.txt 36 | 37 | # Unit test / coverage reports 38 | htmlcov/ 39 | .tox/ 40 | .coverage 41 | .coverage.* 42 | .cache 43 | nosetests.xml 44 | coverage.xml 45 | *,cover 46 | .hypothesis/ 47 | 48 | # Translations 49 | *.mo 50 | *.pot 51 | 52 | # Django stuff: 53 | *.log 54 | local_settings.py 55 | 56 | # Flask stuff: 57 | instance/ 58 | .webassets-cache 59 | 60 | # Scrapy stuff: 61 | .scrapy 62 | 63 | # Sphinx documentation 64 | docs/_build/ 65 | 66 | # PyBuilder 67 | target/ 68 | 69 | # IPython Notebook 70 | .ipynb_checkpoints 71 | 72 | # pyenv 73 | .python-version 74 | 75 | # celery beat schedule file 76 | celerybeat-schedule 77 | 78 | # dotenv 79 | .env 80 | 81 | # virtualenv 82 | venv/ 83 | ENV/ 84 | 85 | # Spyder project settings 86 | .spyderproject 87 | 88 | # Rope project settings 89 | .ropeproject 90 | *.npy 91 | *.pkl 92 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2024 Yiqun Diao, Chengfan Liao 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /MANIFEST.in: -------------------------------------------------------------------------------- 1 | include README.md LICENSE 2 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- 1 | # Minimal makefile for Sphinx documentation 2 | # 3 | 4 | # You can set these variables from the command line, and also 5 | # from the environment for the first two. 6 | SPHINXOPTS ?= 7 | SPHINXBUILD ?= sphinx-build 8 | SOURCEDIR = source 9 | BUILDDIR = build 10 | 11 | # Put it first so that "make" without argument is like "make help". 12 | help: 13 | @$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 14 | 15 | .PHONY: help Makefile 16 | 17 | # Catch-all target: route all unknown targets to Sphinx using the new 18 | # "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS). 19 | %: Makefile 20 | @$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O) 21 | -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- 1 | @ECHO OFF 2 | 3 | pushd %~dp0 4 | 5 | REM Command file for Sphinx documentation 6 | 7 | if "%SPHINXBUILD%" == "" ( 8 | set SPHINXBUILD=sphinx-build 9 | ) 10 | set SOURCEDIR=source 11 | set BUILDDIR=build 12 | 13 | %SPHINXBUILD% >NUL 2>NUL 14 | if errorlevel 9009 ( 15 | echo. 16 | echo.The 'sphinx-build' command was not found. Make sure you have Sphinx 17 | echo.installed, then set the SPHINXBUILD environment variable to point 18 | echo.to the full path of the 'sphinx-build' executable. Alternatively you 19 | echo.may add the Sphinx directory to PATH. 20 | echo. 21 | echo.If you don't have Sphinx installed, grab it from 22 | echo.https://www.sphinx-doc.org/ 23 | exit /b 1 24 | ) 25 | 26 | if "%1" == "" goto help 27 | 28 | %SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% 29 | goto end 30 | 31 | :help 32 | %SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O% 33 | 34 | :end 35 | popd 36 | -------------------------------------------------------------------------------- /docs/source/conf.py: -------------------------------------------------------------------------------- 1 | # Configuration file for the Sphinx documentation builder. 2 | # 3 | # For the full list of built-in configuration values, see the documentation: 4 | # https://www.sphinx-doc.org/en/master/usage/configuration.html 5 | 6 | # -- Project information ----------------------------------------------------- 7 | # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information 8 | 9 | project = 'pyoe' 10 | copyright = '2024, Chengfan Liao' 11 | author = 'Chengfan Liao' 12 | release = '0.1.2' 13 | 14 | # -- Path setup -------------------------------------------------------------- 15 | # https://www.sphinx-doc.org/en/master/usage/configuration.html#path-setup 16 | 17 | import os 18 | import sys 19 | sys.path.insert(0, os.path.abspath('../../')) 20 | 21 | # -- General configuration --------------------------------------------------- 22 | # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration 23 | 24 | extensions = [ 25 | 'sphinx.ext.autodoc', 26 | 'sphinx.ext.napoleon', 27 | 'sphinx.ext.doctest', 28 | 'sphinx.ext.intersphinx', 29 | 'sphinx.ext.todo', 30 | 'sphinx.ext.mathjax', 31 | # 'sphinx.ext.coverage', 32 | ] 33 | 34 | templates_path = ['_templates'] 35 | exclude_patterns = [] 36 | 37 | # -- Options for HTML output ------------------------------------------------- 38 | # https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output 39 | 40 | html_theme = 'sphinx_material' 41 | html_static_path = ['_static'] 42 | -------------------------------------------------------------------------------- /docs/source/index.rst: -------------------------------------------------------------------------------- 1 | .. pyoe documentation master file, created by 2 | sphinx-quickstart on Thu Sep 5 12:42:47 2024. 3 | You can adapt this file completely to your liking, but it should at least 4 | contain the root `toctree` directive. 5 | 6 | Welcome to pyoe's documentation! 7 | ================================ 8 | 9 | .. toctree:: 10 | :maxdepth: 2 11 | :caption: Contents: 12 | 13 | 14 | 15 | Indices and tables 16 | ================== 17 | 18 | * :ref:`genindex` 19 | * :ref:`modindex` 20 | * :ref:`search` 21 | -------------------------------------------------------------------------------- /docs/source/modules.rst: -------------------------------------------------------------------------------- 1 | pyoe 2 | ==== 3 | 4 | .. toctree:: 5 | :maxdepth: 4 6 | 7 | pyoe 8 | -------------------------------------------------------------------------------- /docs/source/pyoe.OEBench.ADBench.baseline.rst: -------------------------------------------------------------------------------- 1 | pyoe.OEBench.ADBench.baseline package 2 | ===================================== 3 | 4 | Submodules 5 | ---------- 6 | 7 | pyoe.OEBench.ADBench.baseline.PyOD module 8 | ----------------------------------------- 9 | 10 | .. automodule:: pyoe.OEBench.ADBench.baseline.PyOD 11 | :members: 12 | :undoc-members: 13 | :show-inheritance: 14 | 15 | pyoe.OEBench.ADBench.baseline.Supervised module 16 | ----------------------------------------------- 17 | 18 | .. automodule:: pyoe.OEBench.ADBench.baseline.Supervised 19 | :members: 20 | :undoc-members: 21 | :show-inheritance: 22 | 23 | Module contents 24 | --------------- 25 | 26 | .. automodule:: pyoe.OEBench.ADBench.baseline 27 | :members: 28 | :undoc-members: 29 | :show-inheritance: 30 | -------------------------------------------------------------------------------- /docs/source/pyoe.OEBench.ADBench.rst: -------------------------------------------------------------------------------- 1 | pyoe.OEBench.ADBench package 2 | ============================ 3 | 4 | Subpackages 5 | ----------- 6 | 7 | .. toctree:: 8 | :maxdepth: 4 9 | 10 | pyoe.OEBench.ADBench.baseline 11 | 12 | Submodules 13 | ---------- 14 | 15 | pyoe.OEBench.ADBench.data\_generator module 16 | ------------------------------------------- 17 | 18 | .. automodule:: pyoe.OEBench.ADBench.data_generator 19 | :members: 20 | :undoc-members: 21 | :show-inheritance: 22 | 23 | pyoe.OEBench.ADBench.myutils module 24 | ----------------------------------- 25 | 26 | .. automodule:: pyoe.OEBench.ADBench.myutils 27 | :members: 28 | :undoc-members: 29 | :show-inheritance: 30 | 31 | pyoe.OEBench.ADBench.run module 32 | ------------------------------- 33 | 34 | .. automodule:: pyoe.OEBench.ADBench.run 35 | :members: 36 | :undoc-members: 37 | :show-inheritance: 38 | 39 | Module contents 40 | --------------- 41 | 42 | .. automodule:: pyoe.OEBench.ADBench 43 | :members: 44 | :undoc-members: 45 | :show-inheritance: 46 | -------------------------------------------------------------------------------- /docs/source/pyoe.algorithms.rst: -------------------------------------------------------------------------------- 1 | pyoe.algorithms package 2 | ======================= 3 | 4 | Submodules 5 | ---------- 6 | 7 | pyoe.algorithms.loss module 8 | --------------------------- 9 | 10 | .. automodule:: pyoe.algorithms.loss 11 | :members: 12 | :undoc-members: 13 | :show-inheritance: 14 | 15 | pyoe.algorithms.trainer module 16 | ------------------------------ 17 | 18 | .. automodule:: pyoe.algorithms.trainer 19 | :members: 20 | :undoc-members: 21 | :show-inheritance: 22 | 23 | Module contents 24 | --------------- 25 | 26 | .. automodule:: pyoe.algorithms 27 | :members: 28 | :undoc-members: 29 | :show-inheritance: 30 | -------------------------------------------------------------------------------- /docs/source/pyoe.dataloaders.rst: -------------------------------------------------------------------------------- 1 | pyoe.dataloaders package 2 | ======================== 3 | 4 | Submodules 5 | ---------- 6 | 7 | pyoe.dataloaders.base module 8 | ---------------------------- 9 | 10 | .. automodule:: pyoe.dataloaders.base 11 | :members: 12 | :undoc-members: 13 | :show-inheritance: 14 | 15 | pyoe.dataloaders.pipeline module 16 | -------------------------------- 17 | 18 | .. automodule:: pyoe.dataloaders.pipeline 19 | :members: 20 | :undoc-members: 21 | :show-inheritance: 22 | 23 | Module contents 24 | --------------- 25 | 26 | .. automodule:: pyoe.dataloaders 27 | :members: 28 | :undoc-members: 29 | :show-inheritance: 30 | -------------------------------------------------------------------------------- /docs/source/pyoe.metrics.rst: -------------------------------------------------------------------------------- 1 | pyoe.metrics package 2 | ==================== 3 | 4 | Submodules 5 | ---------- 6 | 7 | pyoe.metrics.metrics module 8 | --------------------------- 9 | 10 | .. automodule:: pyoe.metrics.metrics 11 | :members: 12 | :undoc-members: 13 | :show-inheritance: 14 | 15 | Module contents 16 | --------------- 17 | 18 | .. automodule:: pyoe.metrics 19 | :members: 20 | :undoc-members: 21 | :show-inheritance: 22 | -------------------------------------------------------------------------------- /docs/source/pyoe.models.rst: -------------------------------------------------------------------------------- 1 | pyoe.models package 2 | =================== 3 | 4 | Submodules 5 | ---------- 6 | 7 | pyoe.models.models module 8 | ------------------------- 9 | 10 | .. automodule:: pyoe.models.models 11 | :members: 12 | :undoc-members: 13 | :show-inheritance: 14 | 15 | pyoe.models.networks module 16 | --------------------------- 17 | 18 | .. automodule:: pyoe.models.networks 19 | :members: 20 | :undoc-members: 21 | :show-inheritance: 22 | 23 | Module contents 24 | --------------- 25 | 26 | .. automodule:: pyoe.models 27 | :members: 28 | :undoc-members: 29 | :show-inheritance: 30 | -------------------------------------------------------------------------------- /docs/source/pyoe.rst: -------------------------------------------------------------------------------- 1 | pyoe package 2 | ============ 3 | 4 | Subpackages 5 | ----------- 6 | 7 | .. toctree:: 8 | :maxdepth: 4 9 | 10 | pyoe.OEBench 11 | pyoe.algorithms 12 | pyoe.dataloaders 13 | pyoe.metrics 14 | pyoe.models 15 | 16 | Submodules 17 | ---------- 18 | 19 | pyoe.preprocessors module 20 | ------------------------- 21 | 22 | .. automodule:: pyoe.preprocessors 23 | :members: 24 | :undoc-members: 25 | :show-inheritance: 26 | 27 | pyoe.utils module 28 | ----------------- 29 | 30 | .. automodule:: pyoe.utils 31 | :members: 32 | :undoc-members: 33 | :show-inheritance: 34 | 35 | Module contents 36 | --------------- 37 | 38 | .. automodule:: pyoe 39 | :members: 40 | :undoc-members: 41 | :show-inheritance: 42 | -------------------------------------------------------------------------------- /examples/example_1.py: -------------------------------------------------------------------------------- 1 | import os 2 | import pyoe 3 | import logging 4 | 5 | # INFO level logging for more detailed output 6 | logger = logging.getLogger() 7 | logger.setLevel(logging.INFO) 8 | 9 | 10 | def set_env_vars(): 11 | # Set environment variables for distributed training 12 | os.environ["MASTER_ADDR"] = "localhost" 13 | os.environ["MASTER_PORT"] = "12345" 14 | os.environ["WORLD_SIZE"] = str(world_size) 15 | 16 | 17 | # if using multi-process for training, all codes with regard to training should 18 | # be put in the `if __name__ == "__main__":` block 19 | if __name__ == "__main__": 20 | # using pre-prepared dataset and load them into a dataloader 21 | dataloader = pyoe.Dataloader(dataset_name="dataset_experiment_info/beijingPM2.5") 22 | 23 | # initialize the model, trainer and preprocessor 24 | model = pyoe.MlpModel(dataloader=dataloader, device="cuda") 25 | preprocessor = pyoe.Preprocessor(missing_fill="knn2") 26 | trainer = pyoe.NaiveTrainer( 27 | dataloader=dataloader, model=model, preprocessor=preprocessor, epochs=16 28 | ) 29 | 30 | # train the model using single process 31 | # trainer.train() 32 | 33 | # train the model using multiple processes 34 | world_size = 4 35 | set_env_vars() 36 | pyoe.MultiProcessTrainer(world_size, dataloader, trainer, preprocessor).train() 37 | 38 | # using a effective metric to evaluate the model 39 | print( 40 | f"Average MSELoss: {pyoe.metrics.EffectivenessMetric(dataloader, model).measure()}" 41 | ) 42 | -------------------------------------------------------------------------------- /examples/example_2.py: -------------------------------------------------------------------------------- 1 | import pyoe 2 | 3 | dataloader = pyoe.Dataloader(dataset_name="dataset_experiment_info/beijingPM2.5") 4 | model = pyoe.MlpModel(dataloader=dataloader, device="cuda") 5 | preprocessor = pyoe.Preprocessor(missing_fill="knn2") 6 | trainer = pyoe.IcarlTrainer(dataloader=dataloader, model=model, preprocessor=preprocessor) 7 | trainer.train() 8 | print(f"Average MSELoss: {pyoe.metrics.EffectivenessMetric(dataloader, model).measure()}") 9 | -------------------------------------------------------------------------------- /examples/example_3.py: -------------------------------------------------------------------------------- 1 | import pyoe 2 | from torch.utils.data import DataLoader as TorchDataLoader 3 | 4 | dataloader = pyoe.Dataloader(dataset_name="dataset_experiment_info/beijingPM2.5") 5 | model = pyoe.XStreamDetectorModel(dataloader=dataloader) 6 | torch_dataloader = TorchDataLoader(dataloader, batch_size=10240) 7 | for X, y, _ in torch_dataloader: 8 | print(model.get_outlier(X), model.get_outlier_with_stream_model(X)) 9 | -------------------------------------------------------------------------------- /examples/example_4.py: -------------------------------------------------------------------------------- 1 | import pyoe 2 | 3 | dataloader = pyoe.Dataloader(dataset_name="dataset_experiment_info/beijingPM2.5") 4 | print(pyoe.metrics.DriftDelayMetric(dataloader).measure()) 5 | -------------------------------------------------------------------------------- /examples/example_5.py: -------------------------------------------------------------------------------- 1 | # import the library PyOE 2 | import pyoe 3 | 4 | # load data and detect concept drift 5 | dataloader = pyoe.Dataloader(dataset_name="dataset_experiment_info/beijingPM2.5") 6 | # change the list below with ground truth... 7 | ground_truth_example = [100, 1000, 10000] 8 | 9 | print(pyoe.metrics.DriftDelayMetric(dataloader).measure(ground_truth_example)) 10 | -------------------------------------------------------------------------------- /examples/example_6.py: -------------------------------------------------------------------------------- 1 | import pyoe 2 | from torch.utils.data import DataLoader as TorchDataLoader 3 | 4 | # prepare dataloader, model, preprocessor and trainer, and then train the model 5 | dataloader = pyoe.Dataloader(dataset_name="OD_datasets/AT") 6 | model = pyoe.CluStreamModel(dataloader=dataloader) 7 | preprocessor = pyoe.Preprocessor(missing_fill="knn2") 8 | trainer = pyoe.ClusterTrainer(dataloader=dataloader, model=model, preprocessor=preprocessor, epochs=16) 9 | trainer.train() 10 | 11 | # predict which cluster these data points belong to 12 | torch_dataloader = TorchDataLoader(dataloader, batch_size=32, shuffle=True) 13 | for X, y, _ in torch_dataloader: 14 | print(X, model.predict_cluster(X)) 15 | -------------------------------------------------------------------------------- /examples/example_7.py: -------------------------------------------------------------------------------- 1 | import pyoe 2 | import matplotlib.pyplot as plt 3 | 4 | # prepare dataloader, model, preprocessor and trainer 5 | prediction_length = 16 6 | dataloader = pyoe.TimeSeriesDataloader(dataset_name="financial_datasets/AAA") 7 | model = pyoe.ChronosModel( 8 | dataloader, device="cuda", prediction_length=prediction_length, model_path="tiny" 9 | ) 10 | 11 | # train the model 12 | X, y = dataloader.get_data(), dataloader.get_target() 13 | model.train_forecast(X, y) 14 | 15 | # split the data and predict 16 | X_front, y_front = X[:-prediction_length], y[:-prediction_length] 17 | y_pred = model.predict_forecast(X_front, y_front) 18 | print(y["target"].values[-prediction_length:], y_pred["mean"].to_numpy()) 19 | 20 | # plot the prediction 21 | y_prev = y["target"].values[-prediction_length * 2 :] 22 | x_prev = range(len(y_prev)) 23 | y_pred = y_pred["mean"].to_numpy() 24 | x_pred = range(prediction_length, prediction_length + len(y_pred)) 25 | 26 | plt.plot(x_prev, y_prev, label="Previous") 27 | plt.plot(x_pred, y_pred, label="Predicted") 28 | plt.savefig("example_7.png") 29 | -------------------------------------------------------------------------------- /examples/example_8.py: -------------------------------------------------------------------------------- 1 | import pyoe 2 | import torch 3 | from river import cluster 4 | from typing import Literal 5 | from torch.utils.data import DataLoader as TorchDataLoader 6 | 7 | 8 | class KMeansNet(pyoe.ClusterNet): 9 | """ 10 | KMeans network for clustering 11 | """ 12 | 13 | def __init__(self) -> None: 14 | """ 15 | Initialize the ODAC network. 16 | """ 17 | super().__init__(cluster.KMeans()) 18 | 19 | 20 | class KMeansModel(pyoe.ModelTemplate): 21 | """ 22 | KMeans model for clustering 23 | """ 24 | 25 | def __init__( 26 | self, 27 | dataloader: pyoe.Dataloader, 28 | ensemble: int = 1, 29 | device: Literal["cpu"] = "cpu", 30 | ): 31 | super().__init__(dataloader, ensemble, device) 32 | self.model_type = "odac" 33 | self.net = KMeansNet() 34 | 35 | def process_model(self, **kwargs): 36 | pass 37 | 38 | def train_cluster(self, X: torch.Tensor): 39 | self.net.fit(X) 40 | 41 | def predict_cluster(self, X: torch.Tensor) -> torch.Tensor: 42 | return self.net(X) 43 | 44 | 45 | # prepare dataloader, model, preprocessor and trainer, and then train the model 46 | dataloader = pyoe.Dataloader(dataset_name="OD_datasets/AT") 47 | model = KMeansModel(dataloader=dataloader) 48 | preprocessor = pyoe.Preprocessor(missing_fill="knn2") 49 | trainer = pyoe.ClusterTrainer(dataloader=dataloader, model=model, preprocessor=preprocessor, epochs=16) 50 | trainer.train() 51 | 52 | # predict which cluster these data points belong to 53 | torch_dataloader = TorchDataLoader(dataloader, batch_size=32, shuffle=True) 54 | for X, y, _ in torch_dataloader: 55 | print(X, model.predict_cluster(X)) 56 | -------------------------------------------------------------------------------- /examples/example_9.py: -------------------------------------------------------------------------------- 1 | import pyoe 2 | import numpy as np 3 | import pandas as pd 4 | import matplotlib.pyplot as plt 5 | 6 | """ 7 | Prepare a time series dataset. 8 | """ 9 | # spawn a time series dataset using 'y = x**2 + r' and save it to a file 10 | x = np.linspace(0, 10, 100) 11 | y = x**2 + np.random.normal(0, 1, 100) 12 | # spawn the 'date' column with 1-day intervals 13 | date = pd.date_range(start="2020-01-01", periods=100, freq="D") 14 | df = pd.DataFrame({"date": date, "y": y}) 15 | df.to_csv("./data/financial_datasets/dataset_test.csv", index=False) 16 | 17 | """ 18 | Train a model on the dataset and predict the next 10 days. 19 | """ 20 | # prepare dataloader, model, preprocessor and trainer 21 | prediction_length = 10 22 | dataloader = pyoe.TimeSeriesDataloader(dataset_name="financial_datasets/dataset_test", predicted_label="y") 23 | model = pyoe.ChronosModel(dataloader, device="cuda", prediction_length=prediction_length, model_path="tiny") 24 | 25 | # train the model 26 | X, y = dataloader.get_data(), dataloader.get_target() 27 | model.train_forecast(X, y) 28 | 29 | # split the data and predict 30 | X_front, y_front = X[:-prediction_length], y[:-prediction_length] 31 | y_pred = model.predict_forecast(X_front, y_front) 32 | print(y["target"].values[-prediction_length:], y_pred["mean"].to_numpy()) 33 | 34 | # plot the prediction 35 | y_prev = y["target"].values[-prediction_length * 2 :] 36 | x_prev = range(len(y_prev)) 37 | y_pred = y_pred["mean"].to_numpy() 38 | x_pred = range(prediction_length, prediction_length + len(y_pred)) 39 | 40 | plt.plot(x_prev, y_prev, label="Previous") 41 | plt.plot(x_pred, y_pred, label="Predicted") 42 | plt.savefig("example_9.png") 43 | -------------------------------------------------------------------------------- /images/pyoe.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/images/pyoe.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/.gitattributes: -------------------------------------------------------------------------------- 1 | docs/* linguist-documentation 2 | datasets/* linguist-documentation 3 | notebooks/*.ipynb linguist-documentation 4 | *.ipynb linguist-documentation 5 | examples/*.ipynb linguist-documentation=false 6 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/.gitignore: -------------------------------------------------------------------------------- 1 | __pycache__/ 2 | .cache/ 3 | .pytest_cache 4 | __pycache__ 5 | .idea/ 6 | .vscode/ 7 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/LICENSE: -------------------------------------------------------------------------------- 1 | BSD 2-Clause License 2 | 3 | Copyright (c) 2022, Mickey (Minqi) 4 | All rights reserved. 5 | 6 | Redistribution and use in source and binary forms, with or without 7 | modification, are permitted provided that the following conditions are met: 8 | 9 | 1. Redistributions of source code must retain the above copyright notice, this 10 | list of conditions and the following disclaimer. 11 | 12 | 2. Redistributions in binary form must reproduce the above copyright notice, 13 | this list of conditions and the following disclaimer in the documentation 14 | and/or other materials provided with the distribution. 15 | 16 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 17 | AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 18 | IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE 19 | DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE 20 | FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 21 | DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR 22 | SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 23 | CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, 24 | OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 25 | OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. 26 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/MANIFEST.in: -------------------------------------------------------------------------------- 1 | prune datasets 2 | prune README.md 3 | include README.rst 4 | include requirements.txt -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/__init__.py -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DAGMM/.gitignore: -------------------------------------------------------------------------------- 1 | data/* 2 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DAGMM/utils/utils.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | 4 | def weights_init_normal(m): 5 | classname = m.__class__.__name__ 6 | if classname.find("Conv") != -1 and classname != 'Conv': 7 | torch.nn.init.normal_(m.weight.data, 0.0, 0.02) 8 | torch.nn.init.normal_(m.bias.data, 0.0, 0.02) 9 | elif classname.find("Linear") != -1: 10 | torch.nn.init.normal_(m.weight.data, 0.0, 0.02) 11 | torch.nn.init.normal_(m.bias.data, 0.0, 0.02) 12 | elif classname.find('BatchNorm') != -1: 13 | m.weight.data.normal_(1.0, 0.01) 14 | m.bias.data.fill_(0) -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2019 lukasruff 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/ae_results.json: -------------------------------------------------------------------------------- 1 | {"train_time": 49.85617208480835, "test_aucroc": 0.45984687500000004, "test_aucpr": 0.13354349144694128, "test_time": 0.12167739868164062} -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/imgs/fig1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/baseline/DeepSAD/imgs/fig1.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/requirements.txt: -------------------------------------------------------------------------------- 1 | Click==7.0 2 | cvxopt==1.2.3 3 | cycler==0.10.0 4 | joblib==0.13.2 5 | kiwisolver==1.1.0 6 | matplotlib==3.1.0 7 | numpy==1.16.4 8 | pandas==0.24.2 9 | Pillow==6.0.0 10 | pyparsing==2.4.0 11 | python-dateutil==2.8.0 12 | pytz==2019.1 13 | scikit-learn==0.21.2 14 | scipy==1.3.0 15 | seaborn==0.9.0 16 | six==1.12.0 17 | torch==1.1.0 18 | torchvision==0.3.0 19 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/base/__init__.py: -------------------------------------------------------------------------------- 1 | from .base_dataset import * 2 | from .torchvision_dataset import * 3 | from .odds_dataset import * 4 | from .base_net import * 5 | from .base_trainer import * 6 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/base/base_dataset.py: -------------------------------------------------------------------------------- 1 | from abc import ABC, abstractmethod 2 | from torch.utils.data import DataLoader 3 | 4 | 5 | class BaseADDataset(ABC): 6 | """Anomaly detection dataset base class.""" 7 | 8 | def __init__(self, root: str): 9 | super().__init__() 10 | self.root = root # root path to data 11 | 12 | self.n_classes = 2 # 0: normal, 1: outlier 13 | self.normal_classes = None # tuple with original class labels that define the normal class 14 | self.outlier_classes = None # tuple with original class labels that define the outlier class 15 | 16 | self.train_set = None # must be of type torch.utils.data.Dataset 17 | self.test_set = None # must be of type torch.utils.data.Dataset 18 | 19 | @abstractmethod 20 | def loaders(self, batch_size: int, shuffle_train=True, shuffle_test=False, num_workers: int = 0) -> ( 21 | DataLoader, DataLoader): 22 | """Implement data loaders of type torch.utils.data.DataLoader for train_set and test_set.""" 23 | pass 24 | 25 | def __repr__(self): 26 | return self.__class__.__name__ 27 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/base/base_net.py: -------------------------------------------------------------------------------- 1 | import logging 2 | import torch.nn as nn 3 | import numpy as np 4 | 5 | 6 | class BaseNet(nn.Module): 7 | """Base class for all neural networks.""" 8 | 9 | def __init__(self): 10 | super().__init__() 11 | self.logger = logging.getLogger(self.__class__.__name__) 12 | self.rep_dim = None # representation dimensionality, i.e. dim of the code layer or last layer 13 | 14 | def forward(self, *input): 15 | """ 16 | Forward pass logic 17 | :return: Network output 18 | """ 19 | raise NotImplementedError 20 | 21 | def summary(self): 22 | """Network summary.""" 23 | net_parameters = filter(lambda p: p.requires_grad, self.parameters()) 24 | params = sum([np.prod(p.size()) for p in net_parameters]) 25 | self.logger.info('Trainable parameters: {}'.format(params)) 26 | self.logger.info(self) 27 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/base/base_trainer.py: -------------------------------------------------------------------------------- 1 | from abc import ABC, abstractmethod 2 | from .base_dataset import BaseADDataset 3 | from .base_net import BaseNet 4 | 5 | 6 | class BaseTrainer(ABC): 7 | """Trainer base class.""" 8 | 9 | def __init__(self, optimizer_name: str, lr: float, n_epochs: int, lr_milestones: tuple, batch_size: int, 10 | weight_decay: float, device: str, n_jobs_dataloader: int): 11 | super().__init__() 12 | self.optimizer_name = optimizer_name 13 | self.lr = lr 14 | self.n_epochs = n_epochs 15 | self.lr_milestones = lr_milestones 16 | self.batch_size = batch_size 17 | self.weight_decay = weight_decay 18 | self.device = device 19 | self.n_jobs_dataloader = n_jobs_dataloader 20 | 21 | @abstractmethod 22 | def train(self, dataset: BaseADDataset, net: BaseNet) -> BaseNet: 23 | """ 24 | Implement train method that trains the given network using the train_set of dataset. 25 | :return: Trained net 26 | """ 27 | pass 28 | 29 | @abstractmethod 30 | def test(self, dataset: BaseADDataset, net: BaseNet): 31 | """ 32 | Implement test method that evaluates the test_set of dataset on the given network. 33 | """ 34 | pass 35 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/base/torchvision_dataset.py: -------------------------------------------------------------------------------- 1 | from .base_dataset import BaseADDataset 2 | from torch.utils.data import DataLoader 3 | 4 | 5 | class TorchvisionDataset(BaseADDataset): 6 | """TorchvisionDataset class for datasets_cc already implemented in torchvision.datasets_cc.""" 7 | 8 | def __init__(self, root: str): 9 | super().__init__(root) 10 | 11 | def loaders(self, batch_size: int, shuffle_train=True, shuffle_test=False, num_workers: int = 0) -> ( 12 | DataLoader, DataLoader): 13 | train_loader = DataLoader(dataset=self.train_set, batch_size=batch_size, shuffle=shuffle_train, 14 | num_workers=num_workers, drop_last=True) 15 | test_loader = DataLoader(dataset=self.test_set, batch_size=batch_size, shuffle=shuffle_test, 16 | num_workers=num_workers, drop_last=False) 17 | return train_loader, test_loader 18 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/baselines/__init__.py: -------------------------------------------------------------------------------- 1 | from .SemiDGM import SemiDeepGenerativeModel 2 | from .ocsvm import OCSVM 3 | from .kde import KDE 4 | from .isoforest import IsoForest 5 | from .ssad import SSAD 6 | from .shallow_ssad.ssad_convex import ConvexSSAD 7 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/baselines/shallow_ssad/__init__.py: -------------------------------------------------------------------------------- 1 | from .ssad_convex import ConvexSSAD 2 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/datasets/__init__.py: -------------------------------------------------------------------------------- 1 | from .main import load_dataset 2 | # from .mnist import MNIST_Dataset 3 | # from .fmnist import FashionMNIST_Dataset 4 | # from .cifar10 import CIFAR10_Dataset 5 | from .odds import ODDSADDataset 6 | from .preprocessing import * 7 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/datasets/main.py: -------------------------------------------------------------------------------- 1 | # from .mnist import MNIST_Dataset 2 | # from .fmnist import FashionMNIST_Dataset 3 | # from .cifar10 import CIFAR10_Dataset 4 | from .odds import ODDSADDataset 5 | 6 | 7 | def load_dataset(data, train=True): 8 | """Loads the dataset.""" 9 | 10 | # for tabular data 11 | dataset = ODDSADDataset(data=data, train=train) 12 | 13 | return dataset 14 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/datasets/odds.py: -------------------------------------------------------------------------------- 1 | from torch.utils.data import DataLoader, Subset 2 | from ADBench.baseline.DeepSAD.src.base.base_dataset import BaseADDataset 3 | from ADBench.baseline.DeepSAD.src.base.odds_dataset import ODDSDataset 4 | from .preprocessing import create_semisupervised_setting 5 | 6 | import torch 7 | 8 | 9 | class ODDSADDataset(BaseADDataset): 10 | 11 | def __init__(self, data, train): 12 | super().__init__(self) 13 | 14 | # Define normal and outlier classes 15 | self.n_classes = 2 # 0: normal, 1: outlier 16 | self.normal_classes = (0,) 17 | self.outlier_classes = (1,) 18 | 19 | # training or testing dataset 20 | self.train = train 21 | 22 | if self.train: 23 | # Get training set 24 | self.train_set = ODDSDataset(data=data, train=True) 25 | else: 26 | # Get testing set 27 | self.test_set = ODDSDataset(data=data, train=False) 28 | 29 | def loaders(self, batch_size: int, shuffle_train=True, shuffle_test=False, num_workers: int = 0): 30 | 31 | if self.train: 32 | train_loader = DataLoader(dataset=self.train_set, batch_size=batch_size, shuffle=shuffle_train, 33 | num_workers=num_workers, drop_last=True) 34 | return train_loader 35 | else: 36 | test_loader = DataLoader(dataset=self.test_set, batch_size=batch_size, shuffle=shuffle_test, 37 | num_workers=num_workers, drop_last=False) 38 | return test_loader -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/networks/__init__.py: -------------------------------------------------------------------------------- 1 | from .main import build_network, build_autoencoder 2 | # from .mnist_LeNet import MNIST_LeNet, MNIST_LeNet_Decoder, MNIST_LeNet_Autoencoder 3 | # from .fmnist_LeNet import FashionMNIST_LeNet, FashionMNIST_LeNet_Decoder, FashionMNIST_LeNet_Autoencoder 4 | # from .cifar10_LeNet import CIFAR10_LeNet, CIFAR10_LeNet_Decoder, CIFAR10_LeNet_Autoencoder 5 | from .mlp import MLP, MLP_Decoder, MLP_Autoencoder 6 | from .layers.stochastic import GaussianSample 7 | from .layers.standard import Standardize 8 | from .inference.distributions import log_standard_gaussian, log_gaussian, log_standard_categorical 9 | from .vae import VariationalAutoencoder, Encoder, Decoder 10 | from .dgm import DeepGenerativeModel, StackedDeepGenerativeModel 11 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/networks/inference/distributions.py: -------------------------------------------------------------------------------- 1 | import math 2 | import torch 3 | import torch.nn.functional as F 4 | 5 | 6 | # Acknowledgements: https://github.com/wohlert/semi-supervised-pytorch 7 | def log_standard_gaussian(x): 8 | """ 9 | Evaluates the log pdf of a standard normal distribution at x. 10 | 11 | :param x: point to evaluate 12 | :return: log N(x|0,I) 13 | """ 14 | return torch.sum(-0.5 * math.log(2 * math.pi) - x ** 2 / 2, dim=-1) 15 | 16 | 17 | def log_gaussian(x, mu, log_var): 18 | """ 19 | Evaluates the log pdf of a normal distribution parametrized by mu and log_var at x. 20 | 21 | :param x: point to evaluate 22 | :param mu: mean 23 | :param log_var: log variance 24 | :return: log N(x|µ,σI) 25 | """ 26 | log_pdf = -0.5 * math.log(2 * math.pi) - log_var / 2 - (x - mu)**2 / (2 * torch.exp(log_var)) 27 | return torch.sum(log_pdf, dim=-1) 28 | 29 | 30 | def log_standard_categorical(p): 31 | """ 32 | Computes the cross-entropy between a (one-hot) categorical vector and a standard (uniform) categorical distribution. 33 | :param p: one-hot categorical distribution 34 | :return: H(p,u) 35 | """ 36 | eps = 1e-8 37 | prior = F.softmax(torch.ones_like(p), dim=1) # Uniform prior over y 38 | prior.requires_grad = False 39 | cross_entropy = -torch.sum(p * torch.log(prior + eps), dim=1) 40 | 41 | return cross_entropy 42 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/networks/layers/stochastic.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import torch.nn as nn 3 | import torch.nn.functional as F 4 | 5 | from torch.autograd import Variable 6 | 7 | 8 | # Acknowledgements: https://github.com/wohlert/semi-supervised-pytorch 9 | class Stochastic(nn.Module): 10 | """ 11 | Base stochastic layer that uses the reparametrization trick (Kingma and Welling, 2013) to draw a sample from a 12 | distribution parametrized by mu and log_var. 13 | """ 14 | 15 | def __init__(self): 16 | super(Stochastic, self).__init__() 17 | 18 | def reparametrize(self, mu, log_var): 19 | epsilon = Variable(torch.randn(mu.size()), requires_grad=False) 20 | 21 | if mu.is_cuda: 22 | epsilon = epsilon.to(mu.device) 23 | 24 | # log_std = 0.5 * log_var 25 | # std = exp(log_std) 26 | std = log_var.mul(0.5).exp_() 27 | 28 | # z = std * epsilon + mu 29 | z = mu.addcmul(std, epsilon) 30 | 31 | return z 32 | 33 | def forward(self, x): 34 | raise NotImplementedError 35 | 36 | 37 | class GaussianSample(Stochastic): 38 | """ 39 | Layer that represents a sample from a Gaussian distribution. 40 | """ 41 | 42 | def __init__(self, in_features, out_features): 43 | super(GaussianSample, self).__init__() 44 | self.in_features = in_features 45 | self.out_features = out_features 46 | 47 | self.mu = nn.Linear(in_features, out_features) 48 | self.log_var = nn.Linear(in_features, out_features) 49 | 50 | def forward(self, x): 51 | mu = self.mu(x) 52 | log_var = F.softplus(self.log_var(x)) 53 | return self.reparametrize(mu, log_var), mu, log_var 54 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/networks/main.py: -------------------------------------------------------------------------------- 1 | # from .mnist_LeNet import MNIST_LeNet, MNIST_LeNet_Autoencoder 2 | # from .fmnist_LeNet import FashionMNIST_LeNet, FashionMNIST_LeNet_Autoencoder 3 | # from .cifar10_LeNet import CIFAR10_LeNet, CIFAR10_LeNet_Autoencoder 4 | from .mlp import MLP, MLP_Autoencoder 5 | from .vae import VariationalAutoencoder 6 | from .dgm import DeepGenerativeModel, StackedDeepGenerativeModel 7 | 8 | 9 | #注意此处与源码有不同 10 | #源码是不同数据集有不同的网络结构(which is weird) 11 | #注意bias必须要设为0,否则DeepSAD可能出现mode collapse(原论文中也提及) 12 | def build_network(net_name, input_size ,ae_net=None): 13 | """Builds the neural network.""" 14 | net = None 15 | 16 | if net_name == 'mnist_LeNet': 17 | net = MNIST_LeNet() 18 | 19 | elif net_name == 'fmnist_LeNet': 20 | net = FashionMNIST_LeNet() 21 | 22 | elif net_name == 'cifar10_LeNet': 23 | net = CIFAR10_LeNet() 24 | 25 | else: 26 | net = MLP(x_dim=input_size, h_dims=[100, 20], rep_dim=10, bias=False) 27 | 28 | return net 29 | 30 | def build_autoencoder(net_name, input_size): 31 | """Builds the corresponding autoencoder network.""" 32 | ae_net = None 33 | 34 | if net_name == 'mnist_LeNet': 35 | ae_net = MNIST_LeNet_Autoencoder() 36 | 37 | elif net_name == 'fmnist_LeNet': 38 | ae_net = FashionMNIST_LeNet_Autoencoder() 39 | 40 | elif net_name == 'cifar10_LeNet': 41 | ae_net = CIFAR10_LeNet_Autoencoder() 42 | 43 | else: 44 | ae_net = MLP_Autoencoder(x_dim=input_size, h_dims=[100, 20], rep_dim=10, bias=False) 45 | 46 | return ae_net 47 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/optim/__init__.py: -------------------------------------------------------------------------------- 1 | from .DeepSAD_trainer import DeepSADTrainer 2 | from .ae_trainer import AETrainer 3 | from .SemiDGM_trainer import SemiDeepGenerativeTrainer 4 | from .vae_trainer import VAETrainer 5 | from .variational import SVI, ImportanceWeightedSampler 6 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/utils/__init__.py: -------------------------------------------------------------------------------- 1 | from .config import Config 2 | from .visualization.plot_images_grid import plot_images_grid 3 | from .misc import enumerate_discrete, log_sum_exp, binary_cross_entropy 4 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/utils/config.py: -------------------------------------------------------------------------------- 1 | import json 2 | 3 | 4 | class Config(object): 5 | """Base class for experimental setting/configuration.""" 6 | 7 | def __init__(self, settings): 8 | self.settings = settings 9 | 10 | def load_config(self, import_json): 11 | """Load settings dict from import_json (path/filename.json) JSON-file.""" 12 | 13 | with open(import_json, 'r') as fp: 14 | settings = json.load(fp) 15 | 16 | for key, value in settings.items(): 17 | self.settings[key] = value 18 | 19 | def save_config(self, export_json): 20 | """Save settings dict to export_json (path/filename.json) JSON-file.""" 21 | 22 | with open(export_json, 'w') as fp: 23 | json.dump(self.settings, fp) 24 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/utils/misc.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | from torch.autograd import Variable 4 | 5 | 6 | # Acknowledgements: https://github.com/wohlert/semi-supervised-pytorch 7 | def enumerate_discrete(x, y_dim): 8 | """ 9 | Generates a 'torch.Tensor' of size batch_size x n_labels of the given label. 10 | 11 | :param x: tensor with batch size to mimic 12 | :param y_dim: number of total labels 13 | :return variable 14 | """ 15 | 16 | def batch(batch_size, label): 17 | labels = (torch.ones(batch_size, 1) * label).type(torch.LongTensor) 18 | y = torch.zeros((batch_size, y_dim)) 19 | y.scatter_(1, labels, 1) 20 | return y.type(torch.LongTensor) 21 | 22 | batch_size = x.size(0) 23 | generated = torch.cat([batch(batch_size, i) for i in range(y_dim)]) 24 | 25 | if x.is_cuda: 26 | generated = generated.to(x.device) 27 | 28 | return Variable(generated.float()) 29 | 30 | 31 | def log_sum_exp(tensor, dim=-1, sum_op=torch.sum): 32 | """ 33 | Uses the LogSumExp (LSE) as an approximation for the sum in a log-domain. 34 | 35 | :param tensor: Tensor to compute LSE over 36 | :param dim: dimension to perform operation over 37 | :param sum_op: reductive operation to be applied, e.g. torch.sum or torch.mean 38 | :return: LSE 39 | """ 40 | max, _ = torch.max(tensor, dim=dim, keepdim=True) 41 | return torch.log(sum_op(torch.exp(tensor - max), dim=dim, keepdim=True) + 1e-8) + max 42 | 43 | 44 | def binary_cross_entropy(x, y): 45 | eps = 1e-8 46 | return -torch.sum(y * torch.log(x + eps) + (1 - y) * torch.log(1 - x + eps), dim=-1) 47 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/DeepSAD/src/utils/visualization/plot_images_grid.py: -------------------------------------------------------------------------------- 1 | import torch 2 | import matplotlib 3 | matplotlib.use('Agg') # or 'PS', 'PDF', 'SVG' 4 | 5 | import matplotlib.pyplot as plt 6 | import numpy as np 7 | from torchvision.utils import make_grid 8 | 9 | 10 | def plot_images_grid(x: torch.tensor, export_img, title: str = '', nrow=8, padding=2, normalize=False, pad_value=0): 11 | """Plot 4D Tensor of images of shape (B x C x H x W) as a grid.""" 12 | 13 | grid = make_grid(x, nrow=nrow, padding=padding, normalize=normalize, pad_value=pad_value) 14 | npgrid = grid.cpu().numpy() 15 | 16 | plt.imshow(np.transpose(npgrid, (1, 2, 0)), interpolation='nearest') 17 | 18 | ax = plt.gca() 19 | ax.xaxis.set_visible(False) 20 | ax.yaxis.set_visible(False) 21 | 22 | if not (title == ''): 23 | plt.title(title) 24 | 25 | plt.savefig(export_img, bbox_inches='tight', pad_inches=0.1) 26 | plt.clf() 27 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/FEAWAD/toolsdev.py: -------------------------------------------------------------------------------- 1 | #!/usr/bin/env python3 2 | # -*- coding: utf-8 -*- 3 | 4 | import numpy as np 5 | from sklearn.metrics import average_precision_score, roc_auc_score 6 | from sklearn.externals.joblib import Memory 7 | from sklearn.datasets import load_svmlight_file 8 | import csv 9 | mem = Memory("./dataset/") 10 | 11 | @mem.cache 12 | def get_data_from_svmlight_file(path): 13 | data = load_svmlight_file(path) 14 | return data[0], data[1] 15 | 16 | def dataLoading(path, byte_num): 17 | # loading data 18 | x=[] 19 | labels=[] 20 | 21 | with (open(path,'r')) as data_from: 22 | csv_reader=csv.reader(data_from) 23 | for i in csv_reader: 24 | x.append(i[0:byte_num]) 25 | labels.append(i[byte_num]) 26 | 27 | for i in range(len(x)): 28 | for j in range(byte_num): 29 | x[i][j] = float(x[i][j]) 30 | for i in range(len(labels)): 31 | labels[i] = float(labels[i]) 32 | x = np.array(x) 33 | labels = np.array(labels) 34 | 35 | return x, labels; 36 | 37 | 38 | def aucPerformance(mse, labels): 39 | roc_auc = roc_auc_score(labels, mse) 40 | ap = average_precision_score(labels, mse) 41 | print("AUC-ROC: %.4f, AUC-PR: %.4f" % (roc_auc, ap)) 42 | return roc_auc, ap; 43 | 44 | def writeResults(name, n_samples_trn, n_outliers, n_samples_test,test_outliers ,test_inliers, avg_AUC_ROC, avg_AUC_PR, std_AUC_ROC,std_AUC_PR, path): 45 | csv_file = open(path, 'a') 46 | row = name + "," + n_samples_trn + ','+n_outliers + ','+n_samples_test+','+test_outliers+','+test_inliers+','+avg_AUC_ROC+','+avg_AUC_PR+','+std_AUC_ROC+','+std_AUC_PR + "\n" 47 | csv_file.write(row) 48 | 49 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/GANomaly/model.py: -------------------------------------------------------------------------------- 1 | from torch import nn 2 | 3 | class generator(nn.Module): 4 | def __init__(self, input_size, hidden_size, act_fun): 5 | super(generator, self).__init__() 6 | 7 | self.encoder_1 = nn.Sequential( 8 | nn.Linear(input_size, hidden_size), 9 | act_fun, 10 | ) 11 | 12 | self.decoder_1 = nn.Sequential( 13 | nn.Linear(hidden_size, input_size), 14 | ) 15 | 16 | self.encoder_2 = nn.Sequential( 17 | nn.Linear(input_size, hidden_size), 18 | act_fun, 19 | ) 20 | 21 | def forward(self, input): 22 | z = self.encoder_1(input) 23 | X_hat = self.decoder_1(z) 24 | z_hat = self.encoder_2(X_hat) 25 | 26 | return z, X_hat, z_hat 27 | 28 | class discriminator(nn.Module): 29 | def __init__(self, input_size, act_fun): 30 | super(discriminator, self).__init__() 31 | 32 | self.encoder = nn.Sequential( 33 | nn.Linear(input_size, 100), 34 | act_fun, 35 | nn.Linear(100, 20), 36 | act_fun 37 | ) 38 | 39 | self.classifier = nn.Sequential( 40 | nn.Linear(20, 1), 41 | nn.Sigmoid() 42 | ) 43 | 44 | def forward(self, input): 45 | latent_vector = self.encoder(input) 46 | output = self.classifier(latent_vector) 47 | 48 | return latent_vector, output 49 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/PReNet/fit.py: -------------------------------------------------------------------------------- 1 | import torch 2 | from torch.autograd import Variable 3 | from ADBench.baseline.PReNet.utils import sampler_pairs 4 | 5 | def fit(X_train_tensor, y_train, model, optimizer, epochs, batch_num, batch_size, 6 | s_a_a, s_a_u, s_u_u, device=None): 7 | # epochs 8 | for epoch in range(epochs): 9 | # generate the batch samples 10 | X_train_loader, y_train_loader = sampler_pairs(X_train_tensor, y_train, epoch, batch_num, batch_size, 11 | s_a_a=s_a_a, s_a_u=s_a_u, s_u_u=s_u_u) 12 | for i in range(len(X_train_loader)): 13 | X_left, X_right = X_train_loader[i][0], X_train_loader[i][1] 14 | y = y_train_loader[i] 15 | 16 | #to device 17 | X_left = X_left.to(device); X_right = X_right.to(device); y = y.to(device) 18 | # to variable 19 | X_left = Variable(X_left); X_right = Variable(X_right); y = Variable(y) 20 | 21 | # clear gradient 22 | model.zero_grad() 23 | 24 | # loss forward 25 | score = model(X_left, X_right) 26 | loss = torch.mean(torch.abs(y - score)) 27 | 28 | # loss backward 29 | loss.backward() 30 | # update model parameters 31 | optimizer.step() -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/PReNet/model.py: -------------------------------------------------------------------------------- 1 | import torch 2 | from torch import nn 3 | 4 | class prenet(nn.Module): 5 | def __init__(self, input_size, act_fun): 6 | super(prenet, self).__init__() 7 | 8 | self.feature = nn.Sequential( 9 | nn.Linear(input_size, 20), 10 | act_fun 11 | ) 12 | 13 | self.reg = nn.Linear(40, 1) 14 | 15 | #the input vector of prenet should be a pair 16 | def forward(self, X_left, X_right): 17 | feature_left = self.feature(X_left) 18 | feature_right = self.feature(X_right) 19 | 20 | # concat feature 21 | feature = torch.cat((feature_left, feature_right), dim=1) 22 | # generate score based on the concat feature 23 | score = self.reg(feature) 24 | 25 | return score.squeeze() -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/REPEN/run.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | from ADBench.baseline.REPEN.model import repen 3 | from ADBench.myutils import Utils 4 | import os 5 | 6 | 7 | class REPEN(): 8 | def __init__(self, seed, model_name='REPEN', save_suffix='test', 9 | mode:str='supervised', hidden_dim:int=20, batch_size:int=256, nb_batch:int=50, n_epochs:int=30): 10 | self.utils = Utils() 11 | self.device = self.utils.get_device() # get device 12 | self.seed = seed 13 | 14 | self.MAX_INT = np.iinfo(np.int32).max 15 | self.MAX_FLOAT = np.finfo(np.float32).max 16 | 17 | # self.sess = tf.Session() 18 | # K.set_session(self.sess) 19 | 20 | # hyper-parameters 21 | self.mode = mode 22 | self.hidden_dim = hidden_dim 23 | self.batch_size = batch_size 24 | self.nb_batch = nb_batch 25 | self.n_epochs = n_epochs 26 | 27 | self.save_suffix = save_suffix 28 | if not os.path.exists('baseline/REPEN/model'): 29 | os.makedirs('baseline/REPEN/model') 30 | 31 | def fit(self, X_train, y_train, ratio=None): 32 | # initialization the network 33 | self.utils.set_seed(self.seed) 34 | 35 | # change the model type when no label information is available 36 | if sum(y_train) == 0: 37 | self.mode = 'unsupervised' 38 | 39 | # model initialization 40 | self.model = repen(mode=self.mode, hidden_dim=self.hidden_dim, batch_size=self.batch_size, nb_batch=self.nb_batch, 41 | n_epochs=self.n_epochs, known_outliers=1000000, save_suffix=self.save_suffix) 42 | 43 | 44 | # fitting 45 | self.model.fit(X_train, y_train) 46 | 47 | return self 48 | 49 | def predict_score(self, X): 50 | score = self.model.decision_function(X) 51 | return score -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/Supervised.py: -------------------------------------------------------------------------------- 1 | from sklearn.linear_model import LogisticRegression 2 | from sklearn.naive_bayes import GaussianNB 3 | from sklearn.svm import SVC 4 | from sklearn.neural_network import MLPClassifier 5 | from sklearn.ensemble import RandomForestClassifier 6 | import lightgbm as lgb 7 | import xgboost as xgb 8 | from catboost import CatBoostClassifier 9 | 10 | from ADBench.myutils import Utils 11 | 12 | class supervised(): 13 | def __init__(self, seed:int, model_name:str=None): 14 | self.seed = seed 15 | self.utils = Utils() 16 | 17 | self.model_name = model_name 18 | self.model_dict = {'LR':LogisticRegression, 19 | 'NB':GaussianNB, 20 | 'SVM':SVC, 21 | 'MLP':MLPClassifier, 22 | 'RF':RandomForestClassifier, 23 | 'LGB':lgb.LGBMClassifier, 24 | 'XGB':xgb.XGBClassifier, 25 | 'CatB':CatBoostClassifier} 26 | 27 | def fit(self, X_train, y_train, ratio=None): 28 | if self.model_name == 'NB': 29 | self.model = self.model_dict[self.model_name]() 30 | elif self.model_name == 'SVM': 31 | self.model = self.model_dict[self.model_name](probability=True) 32 | else: 33 | self.model = self.model_dict[self.model_name](random_state=self.seed) 34 | 35 | # fitting 36 | self.model.fit(X_train, y_train) 37 | 38 | return self 39 | 40 | def predict_score(self, X): 41 | score = self.model.predict_proba(X)[:, 1] 42 | return score -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/baseline/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/baseline/__init__.py -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/figs/ADBench.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/figs/ADBench.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/figs/ADBenchV2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/figs/ADBenchV2.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/figs/Algorithms.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/figs/Algorithms.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/figs/MNIST-C.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/figs/MNIST-C.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/figs/MVTec-AD(ViT).png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/figs/MVTec-AD(ViT).png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/figs/MVTec-AD.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/figs/MVTec-AD.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/other_utils/gmm/LICENSE.md: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2019 Lucas Deecke 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/other_utils/gmm/README.md: -------------------------------------------------------------------------------- 1 | This repository contains an implementation of a simple **Gaussian mixture model** (GMM) fitted with Expectation-Maximization in [pytorch](http://www.pytorch.org). The interface closely follows that of [sklearn](http://scikit-learn.org). 2 | 3 | ![Example of a fit via a Gaussian Mixture model.](example.png) 4 | 5 | --- 6 | 7 | A new model is instantiated by calling `gmm.GaussianMixture(..)` and providing as arguments the number of components, as well as the tensor dimension. Note that once instantiated, the model expects tensors in a flattened shape `(n, d)`. 8 | 9 | The first step would usually be to fit the model via `model.fit(data)`, then predict with `model.predict(data)`. To reproduce the above figure, just run the provided `example.py`. 10 | 11 | Some sanity checks can be executed by calling `python test.py`. To fit data on GPUs, ensure that you first call `model.cuda()`. -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/other_utils/gmm/example.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/ADBench/other_utils/gmm/example.png -------------------------------------------------------------------------------- /pyoe/OEBench/ADBench/other_utils/gmm/utils.py: -------------------------------------------------------------------------------- 1 | import torch 2 | 3 | def calculate_matmul_n_times(n_components, mat_a, mat_b): 4 | """ 5 | Calculate matrix product of two matrics with mat_a[0] >= mat_b[0]. 6 | Bypasses torch.matmul to reduce memory footprint. 7 | args: 8 | mat_a: torch.Tensor (n, k, 1, d) 9 | mat_b: torch.Tensor (1, k, d, d) 10 | """ 11 | res = torch.zeros(mat_a.shape).to(mat_a.device) 12 | 13 | for i in range(n_components): 14 | mat_a_i = mat_a[:, i, :, :].squeeze(-2) 15 | mat_b_i = mat_b[0, i, :, :].squeeze() 16 | # by bug 17 | if len(mat_b_i.size()) == 0: 18 | mat_b_i = mat_b_i.reshape(1, 1) 19 | res[:, i, :, :] = mat_a_i.mm(mat_b_i).unsqueeze(1) 20 | 21 | return res 22 | 23 | 24 | def calculate_matmul(mat_a, mat_b): 25 | """ 26 | Calculate matrix product of two matrics with mat_a[0] >= mat_b[0]. 27 | Bypasses torch.matmul to reduce memory footprint. 28 | args: 29 | mat_a: torch.Tensor (n, k, 1, d) 30 | mat_b: torch.Tensor (n, k, d, 1) 31 | """ 32 | assert mat_a.shape[-2] == 1 and mat_b.shape[-1] == 1 33 | return torch.sum(mat_a.squeeze(-2) * mat_b.squeeze(-1), dim=2, keepdim=True) 34 | -------------------------------------------------------------------------------- /pyoe/OEBench/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/__init__.py -------------------------------------------------------------------------------- /pyoe/OEBench/dataset/README.md: -------------------------------------------------------------------------------- 1 | ### The dataset folder is too large. If needed, it can be downloaded from https://drive.google.com/file/d/1m7eKbycaEh38OxB7gJibUZ2kNqzVzYMf/view?usp=sharing 2 | -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/beijing/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/FiveCitiePMData/BeijingPM20100101_20151231.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/beijing/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2638888889},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/beijing/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM_Dongsi":{"hdddm":0.375,"kdq":0.0,"cdbd":0.3472222222},"PM_Dongsihuan":{"hdddm":0.375,"kdq":0.0,"cdbd":0.3333333333},"PM_Nongzhanguan":{"hdddm":0.3055555556,"kdq":0.0,"cdbd":0.3194444444},"DEWP":{"hdddm":0.5833333333,"kdq":0.0,"cdbd":0.5694444444},"HUMI":{"hdddm":0.4305555556,"kdq":0.0,"cdbd":0.3472222222},"PRES":{"hdddm":0.5555555556,"kdq":0.0,"cdbd":0.5138888889},"TEMP":{"hdddm":0.5972222222,"kdq":0.0,"cdbd":0.6388888889},"Iws":{"hdddm":0.4027777778,"kdq":0.8333333333,"cdbd":0.3333333333},"precipitation":{"hdddm":0.2361111111,"kdq":0.0,"cdbd":0.25},"Iprec":{"hdddm":0.1666666667,"kdq":0.0,"cdbd":0.1388888889},"cbwd_NE":{"hdddm":0.2638888889,"kdq":0.0,"cdbd":0.2361111111},"cbwd_NW":{"hdddm":0.4027777778,"kdq":0.0,"cdbd":0.3472222222},"cbwd_SE":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.375},"cbwd_cv":{"hdddm":0.2777777778,"kdq":0.0,"cdbd":0.2361111111}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/beijing/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 626, "IForest": 998, "mean": 812.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/beijing/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM_Dongsi","PM_Dongsihuan","PM_Nongzhanguan","PM_US Post","DEWP","HUMI","PRES","TEMP","cbwd","Iws","precipitation","Iprec"],"col_null_dict":{"PM_Dongsi":27532,"PM_Dongsihuan":32076,"PM_Nongzhanguan":27653,"PM_US Post":2197,"DEWP":5,"HUMI":339,"PRES":339,"TEMP":5,"cbwd":5,"Iws":5,"precipitation":484,"Iprec":484},"empty_cells_num":91124,"ave_null_columns":1.732922562}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/beijing/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/beijing/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM_Dongsi", "PM_Dongsihuan", "PM_Nongzhanguan", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "Iws", "precipitation", "Iprec"], 3 | "categorical": ["cbwd"], 4 | "target": ["PM_US Post"], 5 | "timestamp": ["No", "year", "month", "day", "hour", "season"], 6 | "null": ["PM_Dongsi", "PM_Dongsihuan", "PM_Nongzhanguan", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "cbwd", "Iws", "precipitation", "Iprec"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/chengdu/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/FiveCitiePMData/ChengduPM20100101_20151231.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/chengdu/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.25},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/chengdu/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM_Caotangsi":{"hdddm":0.375,"kdq":0.625,"cdbd":0.4027777778},"PM_Shahepu":{"hdddm":0.3611111111,"kdq":0.4166666667,"cdbd":0.3611111111},"DEWP":{"hdddm":0.625,"kdq":0.0,"cdbd":0.6388888889},"HUMI":{"hdddm":0.4861111111,"kdq":0.125,"cdbd":0.4444444444},"PRES":{"hdddm":0.5277777778,"kdq":0.0,"cdbd":0.4722222222},"TEMP":{"hdddm":0.6111111111,"kdq":0.0,"cdbd":0.5833333333},"Iws":{"hdddm":0.2638888889,"kdq":0.0,"cdbd":0.2222222222},"precipitation":{"hdddm":0.2361111111,"kdq":0.0,"cdbd":0.1944444444},"Iprec":{"hdddm":0.2638888889,"kdq":0.0,"cdbd":0.2777777778},"cbwd_NE":{"hdddm":0.3194444444,"kdq":0.0,"cdbd":0.3333333333},"cbwd_NW":{"hdddm":0.25,"kdq":0.0,"cdbd":0.2777777778},"cbwd_SE":{"hdddm":0.1388888889,"kdq":0.0,"cdbd":0.1944444444},"cbwd_SW":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.375},"cbwd_cv":{"hdddm":0.2777777778,"kdq":0.0,"cdbd":0.2638888889}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/chengdu/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 615, "IForest": 519, "mean": 567.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/chengdu/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM_Caotangsi","PM_Shahepu","PM_US Post","DEWP","HUMI","PRES","TEMP","cbwd","Iws","precipitation","Iprec"],"col_null_dict":{"PM_Caotangsi":28164,"PM_Shahepu":27990,"PM_US Post":23684,"DEWP":529,"HUMI":535,"PRES":521,"TEMP":527,"cbwd":521,"Iws":533,"precipitation":2955,"Iprec":2955},"empty_cells_num":88914,"ave_null_columns":1.6908945687}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/chengdu/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/chengdu/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM_Caotangsi", "PM_Shahepu", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "Iws", "precipitation", "Iprec"], 3 | "categorical": ["cbwd"], 4 | "target": ["PM_US Post"], 5 | "timestamp": ["No", "year", "month", "day", "hour", "season"], 6 | "null": ["PM_Caotangsi", "PM_Shahepu", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "cbwd", "Iws", "precipitation", "Iprec"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/guangzhou/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/FiveCitiePMData/GuangzhouPM20100101_20151231.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/guangzhou/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.375},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/guangzhou/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM_City Station":{"hdddm":0.375,"kdq":0.3472222222,"cdbd":0.4027777778},"PM_5th Middle School":{"hdddm":0.4166666667,"kdq":0.2916666667,"cdbd":0.4444444444},"DEWP":{"hdddm":0.3888888889,"kdq":0.0694444444,"cdbd":0.3333333333},"HUMI":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.3611111111},"PRES":{"hdddm":0.6111111111,"kdq":0.0833333333,"cdbd":0.5277777778},"TEMP":{"hdddm":0.4861111111,"kdq":0.8194444444,"cdbd":0.5138888889},"Iws":{"hdddm":0.2638888889,"kdq":0.6805555556,"cdbd":0.1805555556},"precipitation":{"hdddm":0.1805555556,"kdq":0.0,"cdbd":0.1805555556},"Iprec":{"hdddm":0.1944444444,"kdq":0.0,"cdbd":0.1666666667},"cbwd_NE":{"hdddm":0.375,"kdq":0.0,"cdbd":0.375},"cbwd_NW":{"hdddm":0.2916666667,"kdq":0.0,"cdbd":0.375},"cbwd_SE":{"hdddm":0.4166666667,"kdq":0.0,"cdbd":0.2916666667},"cbwd_SW":{"hdddm":0.3333333333,"kdq":0.0,"cdbd":0.3333333333},"cbwd_cv":{"hdddm":0.2777777778,"kdq":0.0,"cdbd":0.2638888889}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/guangzhou/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 538, "IForest": 631, "mean": 584.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/guangzhou/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["season","PM_City Station","PM_5th Middle School","PM_US Post","DEWP","HUMI","PRES","TEMP","cbwd","Iws","precipitation","Iprec"],"col_null_dict":{"season":1,"PM_City Station":20232,"PM_5th Middle School":31489,"PM_US Post":20232,"DEWP":1,"HUMI":1,"PRES":1,"TEMP":1,"cbwd":1,"Iws":1,"precipitation":1,"Iprec":1},"empty_cells_num":71962,"ave_null_columns":1.3685151377}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/guangzhou/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/guangzhou/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM_City Station", "PM_5th Middle School", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "Iws", "precipitation", "Iprec"], 3 | "categorical": ["cbwd"], 4 | "target": ["PM_US Post"], 5 | "timestamp": ["No", "year", "month", "day", "hour", "season"], 6 | "null": ["PM_City Station", "PM_5th Middle School", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "cbwd", "Iws", "precipitation", "Iprec"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shanghai/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/FiveCitiePMData/ShanghaiPM20100101_20151231.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shanghai/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.1527777778},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shanghai/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM_Jingan":{"hdddm":0.2777777778,"kdq":0.0,"cdbd":0.3055555556},"PM_Xuhui":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.3888888889},"DEWP":{"hdddm":0.6388888889,"kdq":0.0,"cdbd":0.6527777778},"HUMI":{"hdddm":0.4305555556,"kdq":0.0555555556,"cdbd":0.4444444444},"PRES":{"hdddm":0.5555555556,"kdq":0.0,"cdbd":0.5138888889},"TEMP":{"hdddm":0.5833333333,"kdq":0.0,"cdbd":0.5694444444},"Iws":{"hdddm":0.2916666667,"kdq":0.5694444444,"cdbd":0.3055555556},"precipitation":{"hdddm":0.2361111111,"kdq":0.0,"cdbd":0.2083333333},"Iprec":{"hdddm":0.2638888889,"kdq":0.0,"cdbd":0.3055555556},"cbwd_NE":{"hdddm":0.4722222222,"kdq":0.0,"cdbd":0.375},"cbwd_NW":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.3472222222},"cbwd_SE":{"hdddm":0.4305555556,"kdq":0.0,"cdbd":0.3888888889},"cbwd_SW":{"hdddm":0.375,"kdq":0.0,"cdbd":0.3472222222},"cbwd_cv":{"hdddm":0.2777777778,"kdq":0.0,"cdbd":0.2916666667}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shanghai/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 516, "IForest": 515, "mean": 515.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shanghai/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM_Jingan","PM_US Post","PM_Xuhui","DEWP","HUMI","PRES","TEMP","cbwd","Iws","precipitation","Iprec"],"col_null_dict":{"PM_Jingan":27884,"PM_US Post":18545,"PM_Xuhui":27395,"DEWP":13,"HUMI":13,"PRES":28,"TEMP":13,"cbwd":12,"Iws":12,"precipitation":4009,"Iprec":4009},"empty_cells_num":81933,"ave_null_columns":1.5581355545}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shanghai/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shanghai/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM_Jingan", "PM_Xuhui", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "Iws", "precipitation", "Iprec"], 3 | "categorical": ["cbwd"], 4 | "target": ["PM_US Post"], 5 | "timestamp": ["No", "year", "month", "day", "hour", "season"], 6 | "null": ["PM_Jingan", "PM_Xuhui", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "cbwd", "Iws", "precipitation", "Iprec"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shenyang/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/FiveCitiePMData/ShenyangPM20100101_20151231.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shenyang/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.3611111111},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shenyang/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM_Taiyuanjie":{"hdddm":0.2638888889,"kdq":0.0,"cdbd":0.2777777778},"PM_Xiaoheyan":{"hdddm":0.2916666667,"kdq":0.0,"cdbd":0.2083333333},"DEWP":{"hdddm":0.5972222222,"kdq":0.0,"cdbd":0.5833333333},"HUMI":{"hdddm":0.4444444444,"kdq":0.0833333333,"cdbd":0.4305555556},"PRES":{"hdddm":0.5416666667,"kdq":0.0,"cdbd":0.5138888889},"TEMP":{"hdddm":0.5694444444,"kdq":0.0,"cdbd":0.5833333333},"Iws":{"hdddm":0.2222222222,"kdq":0.0416666667,"cdbd":0.2916666667},"precipitation":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.3055555556},"Iprec":{"hdddm":0.375,"kdq":0.0,"cdbd":0.2361111111},"cbwd_NE":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.4027777778},"cbwd_NW":{"hdddm":0.4305555556,"kdq":0.0,"cdbd":0.4027777778},"cbwd_SE":{"hdddm":0.3194444444,"kdq":0.0,"cdbd":0.2777777778},"cbwd_SW":{"hdddm":0.3333333333,"kdq":0.0,"cdbd":0.3472222222},"cbwd_cv":{"hdddm":0.3472222222,"kdq":0.0,"cdbd":0.3194444444}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shenyang/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 602, "IForest": 474, "mean": 538.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shenyang/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM_Taiyuanjie","PM_US Post","PM_Xiaoheyan","DEWP","HUMI","PRES","TEMP","cbwd","Iws","precipitation","Iprec"],"col_null_dict":{"PM_Taiyuanjie":28196,"PM_US Post":30904,"PM_Xiaoheyan":27957,"DEWP":692,"HUMI":680,"PRES":692,"TEMP":692,"cbwd":692,"Iws":692,"precipitation":12763,"Iprec":12763},"empty_cells_num":116723,"ave_null_columns":2.2197436483}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shenyang/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/5cities/shenyang/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM_Taiyuanjie", "PM_Xiaoheyan", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "Iws", "precipitation", "Iprec"], 3 | "categorical": ["cbwd"], 4 | "target": ["PM_US Post"], 5 | "timestamp": ["No", "year", "month", "day", "hour", "season"], 6 | "null": ["PM_Taiyuanjie", "PM_Xiaoheyan", "PM_US Post", "DEWP", "HUMI", "PRES", "TEMP", "cbwd", "Iws", "precipitation", "Iprec"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/KDDCUP99/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/kddcup99.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/KDDCUP99/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": ["protocol_type", "service", "flag"], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 499, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airbnb/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/airbnb-recruiting-new-user-bookings/train_users_2.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airbnb/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.25},"kdq":{"0":0.7}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airbnb/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":30,"IForest":5,"mean":17.5},"2":{"ECOD":35,"IForest":13,"mean":24.0},"3":{"ECOD":28,"IForest":7,"mean":17.5},"4":{"ECOD":84,"IForest":4,"mean":44.0},"5":{"ECOD":62,"IForest":1,"mean":31.5},"6":{"ECOD":38,"IForest":0,"mean":19.0},"7":{"ECOD":40,"IForest":2,"mean":21.0},"8":{"ECOD":38,"IForest":1,"mean":19.5},"9":{"ECOD":51,"IForest":1,"mean":26.0},"10":{"ECOD":64,"IForest":3,"mean":33.5},"11":{"ECOD":141,"IForest":13,"mean":77.0},"12":{"ECOD":99,"IForest":16,"mean":57.5},"13":{"ECOD":116,"IForest":16,"mean":66.0},"14":{"ECOD":100,"IForest":15,"mean":57.5},"15":{"ECOD":81,"IForest":11,"mean":46.0},"16":{"ECOD":97,"IForest":9,"mean":53.0},"17":{"ECOD":58,"IForest":2,"mean":30.0},"18":{"ECOD":47,"IForest":2,"mean":24.5},"19":{"ECOD":64,"IForest":3,"mean":33.5},"20":{"ECOD":62,"IForest":6,"mean":34.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airbnb/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 1417, "IForest": 150, "mean": 783.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airbnb/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["date_first_booking","age","first_affiliate_tracked"],"col_null_dict":{"date_first_booking":124543,"age":87990,"first_affiliate_tracked":6065},"empty_cells_num":218598,"ave_null_columns":1.0241132625}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airbnb/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airbnb/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["age"], 3 | "categorical": ["gender","signup_method", "signup_flow", "language", "affiliate_channel", "affiliate_provider", "first_affiliate_tracked", "signup_app", "first_device_type", "first_browser"], 4 | "target": ["country_destination"], 5 | "timestamp": ["date_account_created", "timestamp_first_active", "date_first_booking"], 6 | "null": [], 7 | "window size": 10000, 8 | "unnecessary": ["id"] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/airlines.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/missing_value_by_window_stats.json: -------------------------------------------------------------------------------- 1 | {"columns_with_null":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null},"col_null_dict":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null},"empty_cells_num":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null},"ave_null_columns":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0},"kdq":{"0":0.275862069}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":135,"IForest":107,"mean":121.0},"2":{"ECOD":137,"IForest":106,"mean":121.5},"3":{"ECOD":172,"IForest":121,"mean":146.5},"4":{"ECOD":144,"IForest":107,"mean":125.5},"5":{"ECOD":137,"IForest":111,"mean":124.0},"6":{"ECOD":138,"IForest":107,"mean":122.5},"7":{"ECOD":134,"IForest":110,"mean":122.0},"8":{"ECOD":138,"IForest":109,"mean":123.5},"9":{"ECOD":138,"IForest":108,"mean":123.0},"10":{"ECOD":159,"IForest":120,"mean":139.5},"11":{"ECOD":149,"IForest":106,"mean":127.5},"12":{"ECOD":135,"IForest":110,"mean":122.5},"13":{"ECOD":141,"IForest":110,"mean":125.5},"14":{"ECOD":131,"IForest":112,"mean":121.5},"15":{"ECOD":133,"IForest":109,"mean":121.0},"16":{"ECOD":136,"IForest":105,"mean":120.5},"17":{"ECOD":143,"IForest":115,"mean":129.0},"18":{"ECOD":147,"IForest":112,"mean":129.5},"19":{"ECOD":137,"IForest":110,"mean":123.5},"20":{"ECOD":131,"IForest":107,"mean":119.0},"21":{"ECOD":129,"IForest":107,"mean":118.0},"22":{"ECOD":137,"IForest":108,"mean":122.5},"23":{"ECOD":137,"IForest":121,"mean":129.0},"24":{"ECOD":124,"IForest":118,"mean":121.0},"25":{"ECOD":145,"IForest":105,"mean":125.0},"26":{"ECOD":136,"IForest":111,"mean":123.5},"27":{"ECOD":133,"IForest":106,"mean":119.5},"28":{"ECOD":129,"IForest":106,"mean":117.5},"29":{"ECOD":140,"IForest":109,"mean":124.5}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 4276, "IForest": 3402, "mean": 3839.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/airlines/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["DayOfWeek","Time", "Length"], 3 | "categorical": ["Airline","Flight", "AirportFrom", "AirportTo"], 4 | "target": ["Delay"], 5 | "timestamp": ["DayOfWeek","Time"], 6 | "null": [], 7 | "window size": 17500, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/allstate_claims_severity/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/allstate-claims-severity/train.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/allstate_claims_severity/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0217391304},"kdq":{"0":0.0217391304}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/allstate_claims_severity/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 2220, "IForest": 2098, "mean": 2159.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/allstate_claims_severity/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/allstate_claims_severity/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/allstate_claims_severity/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["count1","count2","count3","count4","count5","count6","count7","count8","count9","count10","count11","count12","count13","count14"], 3 | "categorical": ["cat1","cat2","cat3","cat4","cat5","cat6","cat7","cat8","cat9","cat10","cat11","cat12","cat13","cat14","cat15","cat16","cat17","cat18","cat19","cat20","cat21","cat22","cat23","cat24","cat25","cat26","cat27","cat28","cat29","cat30","cat31","cat32","cat33","cat34","cat35","cat36","cat37","cat38","cat39","cat40","cat41","cat42","cat43","cat44","cat45","cat46","cat47","cat48","cat49","cat50","cat51","cat52","cat53","cat54","cat55","cat56","cat57","cat58","cat59","cat60","cat61","cat62","cat63","cat64","cat65","cat66","cat67","cat68","cat69","cat70","cat71","cat72","cat73","cat74","cat75","cat76","cat77","cat78","cat79","cat80","cat81","cat82","cat83","cat84","cat85","cat86","cat87","cat88","cat89","cat90","cat91","cat92","cat93","cat94","cat95","cat96","cat97","cat98","cat99","cat100","cat101","cat102","cat103","cat104","cat105","cat106","cat107","cat108","cat109","cat110","cat111","cat112","cat113","cat114","cat115","cat116"], 4 | "target": ["loss"], 5 | "timestamp": ["id"], 6 | "null": [], 7 | "window size": 4000, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijingPM2.5/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingPM2.5Data.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijingPM2.5/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["DEWP", "TEMP", "PRES", "Iws", "Is", "Ir"], 3 | "categorical": ["cbwd"], 4 | "target": ["pm2.5"], 5 | "timestamp": ["year","month", "day", "hour"], 6 | "window size": 720, 7 | "unnecessary": ["No"] 8 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Aotizhongxin_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2553191489},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.3191489362,"kdq":0.7659574468,"cdbd":0.3191489362},"SO2":{"hdddm":0.4042553191,"kdq":0.0212765957,"cdbd":0.3829787234},"NO2":{"hdddm":0.4255319149,"kdq":0.5319148936,"cdbd":0.3617021277},"CO":{"hdddm":0.4255319149,"kdq":0.0,"cdbd":0.3404255319},"O3":{"hdddm":0.3404255319,"kdq":0.1489361702,"cdbd":0.3404255319},"TEMP":{"hdddm":0.5957446809,"kdq":0.4468085106,"cdbd":0.5319148936},"PRES":{"hdddm":0.4680851064,"kdq":0.4468085106,"cdbd":0.4255319149},"DEWP":{"hdddm":0.5744680851,"kdq":0.9574468085,"cdbd":0.5957446809},"RAIN":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"WSPM":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.4042553191},"wd_ENE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2978723404},"wd_ESE":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"wd_N":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3191489362},"wd_NE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2553191489},"wd_NNE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_NNW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_NW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3404255319},"wd_S":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_SE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_SSE":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.1914893617},"wd_SSW":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2978723404},"wd_SW":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2978723404},"wd_W":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2127659574},"wd_WNW":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.1914893617},"wd_WSW":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3191489362},"station_Aotizhongxin":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":0,"mean":0.0},"2":{"ECOD":0,"IForest":2,"mean":1.0},"3":{"ECOD":0,"IForest":6,"mean":3.0},"4":{"ECOD":0,"IForest":10,"mean":5.0},"5":{"ECOD":0,"IForest":7,"mean":3.5},"6":{"ECOD":0,"IForest":2,"mean":1.0},"7":{"ECOD":0,"IForest":0,"mean":0.0},"8":{"ECOD":0,"IForest":2,"mean":1.0},"9":{"ECOD":0,"IForest":19,"mean":9.5},"10":{"ECOD":0,"IForest":25,"mean":12.5},"11":{"ECOD":0,"IForest":9,"mean":4.5},"12":{"ECOD":0,"IForest":11,"mean":5.5},"13":{"ECOD":0,"IForest":0,"mean":0.0},"14":{"ECOD":0,"IForest":1,"mean":0.5},"15":{"ECOD":0,"IForest":14,"mean":7.0},"16":{"ECOD":0,"IForest":5,"mean":2.5},"17":{"ECOD":0,"IForest":3,"mean":1.5},"18":{"ECOD":0,"IForest":1,"mean":0.5},"19":{"ECOD":0,"IForest":3,"mean":1.5},"20":{"ECOD":0,"IForest":3,"mean":1.5},"21":{"ECOD":0,"IForest":14,"mean":7.0},"22":{"ECOD":0,"IForest":18,"mean":9.0},"23":{"ECOD":0,"IForest":5,"mean":2.5},"24":{"ECOD":0,"IForest":11,"mean":5.5},"25":{"ECOD":0,"IForest":3,"mean":1.5},"26":{"ECOD":0,"IForest":1,"mean":0.5},"27":{"ECOD":0,"IForest":7,"mean":3.5},"28":{"ECOD":0,"IForest":5,"mean":2.5},"29":{"ECOD":0,"IForest":5,"mean":2.5},"30":{"ECOD":0,"IForest":1,"mean":0.5},"31":{"ECOD":0,"IForest":0,"mean":0.0},"32":{"ECOD":0,"IForest":0,"mean":0.0},"33":{"ECOD":0,"IForest":43,"mean":21.5},"34":{"ECOD":0,"IForest":57,"mean":28.5},"35":{"ECOD":0,"IForest":53,"mean":26.5},"36":{"ECOD":0,"IForest":0,"mean":0.0},"37":{"ECOD":0,"IForest":0,"mean":0.0},"38":{"ECOD":0,"IForest":1,"mean":0.5},"39":{"ECOD":0,"IForest":3,"mean":1.5},"40":{"ECOD":0,"IForest":1,"mean":0.5},"41":{"ECOD":0,"IForest":14,"mean":7.0},"42":{"ECOD":0,"IForest":3,"mean":1.5},"43":{"ECOD":0,"IForest":1,"mean":0.5},"44":{"ECOD":0,"IForest":0,"mean":0.0},"45":{"ECOD":0,"IForest":7,"mean":3.5},"46":{"ECOD":0,"IForest":53,"mean":26.5},"47":{"ECOD":0,"IForest":6,"mean":3.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 450, "mean": 225.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":925,"PM10":718,"SO2":935,"NO2":1023,"CO":1776,"O3":1719,"TEMP":20,"PRES":20,"DEWP":20,"RAIN":20,"wd":81,"WSPM":14},"empty_cells_num":7271,"ave_null_columns":0.2073636778}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/aotizhongxin/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Changping_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.3829787234},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.4255319149,"kdq":0.7446808511,"cdbd":0.4468085106},"SO2":{"hdddm":0.4255319149,"kdq":0.0212765957,"cdbd":0.4680851064},"NO2":{"hdddm":0.4042553191,"kdq":0.0425531915,"cdbd":0.3829787234},"CO":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.3191489362},"O3":{"hdddm":0.4468085106,"kdq":0.1489361702,"cdbd":0.4255319149},"TEMP":{"hdddm":0.5531914894,"kdq":0.4255319149,"cdbd":0.5319148936},"PRES":{"hdddm":0.4255319149,"kdq":0.4468085106,"cdbd":0.4468085106},"DEWP":{"hdddm":0.5531914894,"kdq":0.9787234043,"cdbd":0.5319148936},"RAIN":{"hdddm":0.1276595745,"kdq":0.0,"cdbd":0.1276595745},"WSPM":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2553191489},"wd_ENE":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2340425532},"wd_ESE":{"hdddm":0.3617021277,"kdq":0.0,"cdbd":0.3404255319},"wd_N":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_NE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2765957447},"wd_NNE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_NNW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3617021277},"wd_NW":{"hdddm":0.3829787234,"kdq":0.0,"cdbd":0.3617021277},"wd_S":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_SE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_SSE":{"hdddm":0.4468085106,"kdq":0.0,"cdbd":0.3191489362},"wd_SSW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.2765957447},"wd_SW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_W":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_WNW":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2765957447},"wd_WSW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2553191489},"station_Changping":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":0,"mean":0.0},"2":{"ECOD":0,"IForest":1,"mean":0.5},"3":{"ECOD":0,"IForest":4,"mean":2.0},"4":{"ECOD":0,"IForest":3,"mean":1.5},"5":{"ECOD":0,"IForest":6,"mean":3.0},"6":{"ECOD":0,"IForest":3,"mean":1.5},"7":{"ECOD":0,"IForest":0,"mean":0.0},"8":{"ECOD":0,"IForest":1,"mean":0.5},"9":{"ECOD":0,"IForest":8,"mean":4.0},"10":{"ECOD":0,"IForest":32,"mean":16.0},"11":{"ECOD":0,"IForest":11,"mean":5.5},"12":{"ECOD":0,"IForest":21,"mean":10.5},"13":{"ECOD":0,"IForest":3,"mean":1.5},"14":{"ECOD":0,"IForest":3,"mean":1.5},"15":{"ECOD":0,"IForest":9,"mean":4.5},"16":{"ECOD":0,"IForest":2,"mean":1.0},"17":{"ECOD":0,"IForest":2,"mean":1.0},"18":{"ECOD":0,"IForest":1,"mean":0.5},"19":{"ECOD":0,"IForest":1,"mean":0.5},"20":{"ECOD":0,"IForest":3,"mean":1.5},"21":{"ECOD":0,"IForest":12,"mean":6.0},"22":{"ECOD":0,"IForest":35,"mean":17.5},"23":{"ECOD":0,"IForest":21,"mean":10.5},"24":{"ECOD":0,"IForest":12,"mean":6.0},"25":{"ECOD":0,"IForest":3,"mean":1.5},"26":{"ECOD":0,"IForest":0,"mean":0.0},"27":{"ECOD":0,"IForest":3,"mean":1.5},"28":{"ECOD":0,"IForest":6,"mean":3.0},"29":{"ECOD":0,"IForest":8,"mean":4.0},"30":{"ECOD":0,"IForest":1,"mean":0.5},"31":{"ECOD":0,"IForest":1,"mean":0.5},"32":{"ECOD":0,"IForest":0,"mean":0.0},"33":{"ECOD":0,"IForest":25,"mean":12.5},"34":{"ECOD":0,"IForest":51,"mean":25.5},"35":{"ECOD":0,"IForest":13,"mean":6.5},"36":{"ECOD":0,"IForest":7,"mean":3.5},"37":{"ECOD":0,"IForest":0,"mean":0.0},"38":{"ECOD":0,"IForest":0,"mean":0.0},"39":{"ECOD":0,"IForest":1,"mean":0.5},"40":{"ECOD":0,"IForest":0,"mean":0.0},"41":{"ECOD":0,"IForest":9,"mean":4.5},"42":{"ECOD":0,"IForest":1,"mean":0.5},"43":{"ECOD":0,"IForest":0,"mean":0.0},"44":{"ECOD":0,"IForest":4,"mean":2.0},"45":{"ECOD":0,"IForest":1,"mean":0.5},"46":{"ECOD":0,"IForest":73,"mean":36.5},"47":{"ECOD":0,"IForest":0,"mean":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 418, "mean": 209.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":774,"PM10":582,"SO2":628,"NO2":667,"CO":1521,"O3":604,"TEMP":53,"PRES":50,"DEWP":53,"RAIN":51,"wd":140,"WSPM":43},"empty_cells_num":5166,"ave_null_columns":0.1473305955}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/changping/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Dingling_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.3617021277},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.3404255319,"kdq":0.8510638298,"cdbd":0.3404255319},"SO2":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3617021277},"NO2":{"hdddm":0.4255319149,"kdq":0.0212765957,"cdbd":0.3829787234},"CO":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3404255319},"O3":{"hdddm":0.4042553191,"kdq":0.170212766,"cdbd":0.4255319149},"TEMP":{"hdddm":0.6170212766,"kdq":0.4255319149,"cdbd":0.5319148936},"PRES":{"hdddm":0.4893617021,"kdq":0.4468085106,"cdbd":0.4255319149},"DEWP":{"hdddm":0.5319148936,"kdq":0.9787234043,"cdbd":0.5319148936},"RAIN":{"hdddm":0.1276595745,"kdq":0.0,"cdbd":0.1276595745},"WSPM":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_ENE":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2340425532},"wd_ESE":{"hdddm":0.3617021277,"kdq":0.0,"cdbd":0.3404255319},"wd_N":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_NE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_NNE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_NNW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3191489362},"wd_NW":{"hdddm":0.1489361702,"kdq":0.0,"cdbd":0.1914893617},"wd_S":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2553191489},"wd_SE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_SSE":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3191489362},"wd_SSW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_SW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_W":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_WNW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3404255319},"wd_WSW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"station_Dingling":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":1,"mean":0.5},"2":{"ECOD":0,"IForest":3,"mean":1.5},"3":{"ECOD":0,"IForest":6,"mean":3.0},"4":{"ECOD":0,"IForest":7,"mean":3.5},"5":{"ECOD":0,"IForest":5,"mean":2.5},"6":{"ECOD":0,"IForest":3,"mean":1.5},"7":{"ECOD":0,"IForest":1,"mean":0.5},"8":{"ECOD":0,"IForest":7,"mean":3.5},"9":{"ECOD":0,"IForest":17,"mean":8.5},"10":{"ECOD":0,"IForest":29,"mean":14.5},"11":{"ECOD":0,"IForest":35,"mean":17.5},"12":{"ECOD":0,"IForest":22,"mean":11.0},"13":{"ECOD":0,"IForest":3,"mean":1.5},"14":{"ECOD":0,"IForest":3,"mean":1.5},"15":{"ECOD":0,"IForest":8,"mean":4.0},"16":{"ECOD":0,"IForest":3,"mean":1.5},"17":{"ECOD":0,"IForest":2,"mean":1.0},"18":{"ECOD":0,"IForest":1,"mean":0.5},"19":{"ECOD":0,"IForest":4,"mean":2.0},"20":{"ECOD":0,"IForest":8,"mean":4.0},"21":{"ECOD":0,"IForest":19,"mean":9.5},"22":{"ECOD":0,"IForest":29,"mean":14.5},"23":{"ECOD":0,"IForest":16,"mean":8.0},"24":{"ECOD":0,"IForest":11,"mean":5.5},"25":{"ECOD":0,"IForest":0,"mean":0.0},"26":{"ECOD":0,"IForest":1,"mean":0.5},"27":{"ECOD":0,"IForest":6,"mean":3.0},"28":{"ECOD":0,"IForest":6,"mean":3.0},"29":{"ECOD":0,"IForest":9,"mean":4.5},"30":{"ECOD":0,"IForest":1,"mean":0.5},"31":{"ECOD":0,"IForest":2,"mean":1.0},"32":{"ECOD":0,"IForest":0,"mean":0.0},"33":{"ECOD":0,"IForest":24,"mean":12.0},"34":{"ECOD":0,"IForest":46,"mean":23.0},"35":{"ECOD":0,"IForest":18,"mean":9.0},"36":{"ECOD":0,"IForest":10,"mean":5.0},"37":{"ECOD":0,"IForest":5,"mean":2.5},"38":{"ECOD":0,"IForest":1,"mean":0.5},"39":{"ECOD":0,"IForest":1,"mean":0.5},"40":{"ECOD":0,"IForest":0,"mean":0.0},"41":{"ECOD":0,"IForest":9,"mean":4.5},"42":{"ECOD":0,"IForest":1,"mean":0.5},"43":{"ECOD":0,"IForest":2,"mean":1.0},"44":{"ECOD":0,"IForest":6,"mean":3.0},"45":{"ECOD":0,"IForest":0,"mean":0.0},"46":{"ECOD":0,"IForest":68,"mean":34.0},"47":{"ECOD":0,"IForest":1,"mean":0.5}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 478, "mean": 239.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":779,"PM10":656,"SO2":730,"NO2":1234,"CO":2012,"O3":1214,"TEMP":53,"PRES":50,"DEWP":53,"RAIN":51,"wd":140,"WSPM":43},"empty_cells_num":7015,"ave_null_columns":0.2000627424}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dingling/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Dongsi_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.4468085106},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.3191489362,"kdq":0.8510638298,"cdbd":0.3829787234},"SO2":{"hdddm":0.3617021277,"kdq":0.0212765957,"cdbd":0.3404255319},"NO2":{"hdddm":0.3617021277,"kdq":0.2765957447,"cdbd":0.3404255319},"CO":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3617021277},"O3":{"hdddm":0.3829787234,"kdq":0.1276595745,"cdbd":0.3829787234},"TEMP":{"hdddm":0.5531914894,"kdq":0.4255319149,"cdbd":0.5744680851},"PRES":{"hdddm":0.4468085106,"kdq":0.4468085106,"cdbd":0.4893617021},"DEWP":{"hdddm":0.5319148936,"kdq":0.9574468085,"cdbd":0.5957446809},"RAIN":{"hdddm":0.1063829787,"kdq":0.0,"cdbd":0.2127659574},"WSPM":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2127659574},"wd_ENE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_ESE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_N":{"hdddm":0.4042553191,"kdq":0.0,"cdbd":0.2340425532},"wd_NE":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"wd_NNE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2978723404},"wd_NNW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_NW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_S":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3617021277},"wd_SE":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.2127659574},"wd_SSE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_SSW":{"hdddm":0.4042553191,"kdq":0.0,"cdbd":0.3404255319},"wd_SW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3191489362},"wd_W":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.2553191489},"wd_WNW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_WSW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2127659574},"station_Dongsi":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":1,"mean":0.5},"2":{"ECOD":0,"IForest":7,"mean":3.5},"3":{"ECOD":0,"IForest":3,"mean":1.5},"4":{"ECOD":0,"IForest":10,"mean":5.0},"5":{"ECOD":0,"IForest":11,"mean":5.5},"6":{"ECOD":0,"IForest":2,"mean":1.0},"7":{"ECOD":0,"IForest":3,"mean":1.5},"8":{"ECOD":0,"IForest":3,"mean":1.5},"9":{"ECOD":0,"IForest":27,"mean":13.5},"10":{"ECOD":0,"IForest":24,"mean":12.0},"11":{"ECOD":0,"IForest":12,"mean":6.0},"12":{"ECOD":0,"IForest":23,"mean":11.5},"13":{"ECOD":0,"IForest":1,"mean":0.5},"14":{"ECOD":0,"IForest":7,"mean":3.5},"15":{"ECOD":0,"IForest":15,"mean":7.5},"16":{"ECOD":0,"IForest":3,"mean":1.5},"17":{"ECOD":0,"IForest":1,"mean":0.5},"18":{"ECOD":0,"IForest":6,"mean":3.0},"19":{"ECOD":0,"IForest":1,"mean":0.5},"20":{"ECOD":0,"IForest":3,"mean":1.5},"21":{"ECOD":0,"IForest":24,"mean":12.0},"22":{"ECOD":0,"IForest":21,"mean":10.5},"23":{"ECOD":0,"IForest":4,"mean":2.0},"24":{"ECOD":0,"IForest":7,"mean":3.5},"25":{"ECOD":0,"IForest":6,"mean":3.0},"26":{"ECOD":0,"IForest":2,"mean":1.0},"27":{"ECOD":0,"IForest":5,"mean":2.5},"28":{"ECOD":0,"IForest":5,"mean":2.5},"29":{"ECOD":0,"IForest":4,"mean":2.0},"30":{"ECOD":0,"IForest":1,"mean":0.5},"31":{"ECOD":0,"IForest":1,"mean":0.5},"32":{"ECOD":0,"IForest":0,"mean":0.0},"33":{"ECOD":0,"IForest":38,"mean":19.0},"34":{"ECOD":0,"IForest":62,"mean":31.0},"35":{"ECOD":0,"IForest":20,"mean":10.0},"36":{"ECOD":0,"IForest":0,"mean":0.0},"37":{"ECOD":0,"IForest":0,"mean":0.0},"38":{"ECOD":0,"IForest":1,"mean":0.5},"39":{"ECOD":0,"IForest":2,"mean":1.0},"40":{"ECOD":0,"IForest":1,"mean":0.5},"41":{"ECOD":0,"IForest":14,"mean":7.0},"42":{"ECOD":0,"IForest":3,"mean":1.5},"43":{"ECOD":0,"IForest":1,"mean":0.5},"44":{"ECOD":0,"IForest":0,"mean":0.0},"45":{"ECOD":0,"IForest":10,"mean":5.0},"46":{"ECOD":0,"IForest":112,"mean":56.0},"47":{"ECOD":0,"IForest":8,"mean":4.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 542, "mean": 271.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":750,"PM10":553,"SO2":663,"NO2":1601,"CO":3197,"O3":664,"TEMP":20,"PRES":20,"DEWP":20,"RAIN":20,"wd":78,"WSPM":14},"empty_cells_num":7600,"ave_null_columns":0.2167465206}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/dongsi/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/guanyuan/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Guanyuan_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/guanyuan/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.3617021277},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/guanyuan/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.3404255319,"kdq":0.829787234,"cdbd":0.3404255319},"SO2":{"hdddm":0.3829787234,"kdq":0.0212765957,"cdbd":0.4255319149},"NO2":{"hdddm":0.3617021277,"kdq":0.0638297872,"cdbd":0.3404255319},"CO":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3404255319},"O3":{"hdddm":0.3617021277,"kdq":0.1063829787,"cdbd":0.3404255319},"TEMP":{"hdddm":0.5957446809,"kdq":0.4468085106,"cdbd":0.5531914894},"PRES":{"hdddm":0.4893617021,"kdq":0.4468085106,"cdbd":0.4255319149},"DEWP":{"hdddm":0.6170212766,"kdq":0.9361702128,"cdbd":0.5744680851},"RAIN":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.2340425532},"WSPM":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.3829787234,"kdq":0.0,"cdbd":0.4042553191},"wd_ENE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3404255319},"wd_ESE":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3191489362},"wd_N":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2978723404},"wd_NE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2553191489},"wd_NNE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_NNW":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2340425532},"wd_NW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3404255319},"wd_S":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_SE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_SSE":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.3191489362},"wd_SSW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.2978723404},"wd_SW":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3191489362},"wd_W":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_WNW":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.1914893617},"wd_WSW":{"hdddm":0.4468085106,"kdq":0.0,"cdbd":0.2978723404},"station_Guanyuan":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/guanyuan/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 522, "mean": 261.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/guanyuan/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":616,"PM10":429,"SO2":474,"NO2":659,"CO":1753,"O3":1173,"TEMP":20,"PRES":20,"DEWP":20,"RAIN":20,"wd":81,"WSPM":14},"empty_cells_num":5279,"ave_null_columns":0.150553274}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/guanyuan/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/guanyuan/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Gucheng_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.3404255319},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.2340425532,"kdq":0.8510638298,"cdbd":0.2765957447},"SO2":{"hdddm":0.4468085106,"kdq":0.0212765957,"cdbd":0.4680851064},"NO2":{"hdddm":0.3617021277,"kdq":0.3829787234,"cdbd":0.4042553191},"CO":{"hdddm":0.4255319149,"kdq":0.0,"cdbd":0.3191489362},"O3":{"hdddm":0.3617021277,"kdq":0.2978723404,"cdbd":0.3829787234},"TEMP":{"hdddm":0.6170212766,"kdq":0.4468085106,"cdbd":0.5319148936},"PRES":{"hdddm":0.5106382979,"kdq":0.4468085106,"cdbd":0.4893617021},"DEWP":{"hdddm":0.5106382979,"kdq":1.0,"cdbd":0.4468085106},"RAIN":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2127659574},"WSPM":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.1914893617},"wd_E":{"hdddm":0.1489361702,"kdq":0.0,"cdbd":0.170212766},"wd_ENE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.3191489362},"wd_ESE":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"wd_N":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.1914893617},"wd_NE":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.170212766},"wd_NNE":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"wd_NNW":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3191489362},"wd_NW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3617021277},"wd_S":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_SE":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"wd_SSE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2765957447},"wd_SSW":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2340425532},"wd_SW":{"hdddm":0.3829787234,"kdq":0.0,"cdbd":0.2340425532},"wd_W":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_WNW":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2553191489},"wd_WSW":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"station_Gucheng":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":2,"mean":1.0},"2":{"ECOD":0,"IForest":0,"mean":0.0},"3":{"ECOD":0,"IForest":4,"mean":2.0},"4":{"ECOD":0,"IForest":14,"mean":7.0},"5":{"ECOD":0,"IForest":6,"mean":3.0},"6":{"ECOD":0,"IForest":6,"mean":3.0},"7":{"ECOD":0,"IForest":0,"mean":0.0},"8":{"ECOD":0,"IForest":2,"mean":1.0},"9":{"ECOD":0,"IForest":29,"mean":14.5},"10":{"ECOD":0,"IForest":39,"mean":19.5},"11":{"ECOD":0,"IForest":24,"mean":12.0},"12":{"ECOD":0,"IForest":25,"mean":12.5},"13":{"ECOD":0,"IForest":0,"mean":0.0},"14":{"ECOD":0,"IForest":3,"mean":1.5},"15":{"ECOD":0,"IForest":12,"mean":6.0},"16":{"ECOD":0,"IForest":3,"mean":1.5},"17":{"ECOD":0,"IForest":2,"mean":1.0},"18":{"ECOD":0,"IForest":0,"mean":0.0},"19":{"ECOD":0,"IForest":2,"mean":1.0},"20":{"ECOD":0,"IForest":1,"mean":0.5},"21":{"ECOD":0,"IForest":11,"mean":5.5},"22":{"ECOD":0,"IForest":13,"mean":6.5},"23":{"ECOD":0,"IForest":1,"mean":0.5},"24":{"ECOD":0,"IForest":6,"mean":3.0},"25":{"ECOD":0,"IForest":2,"mean":1.0},"26":{"ECOD":0,"IForest":0,"mean":0.0},"27":{"ECOD":0,"IForest":4,"mean":2.0},"28":{"ECOD":0,"IForest":13,"mean":6.5},"29":{"ECOD":0,"IForest":4,"mean":2.0},"30":{"ECOD":0,"IForest":6,"mean":3.0},"31":{"ECOD":0,"IForest":1,"mean":0.5},"32":{"ECOD":0,"IForest":0,"mean":0.0},"33":{"ECOD":0,"IForest":23,"mean":11.5},"34":{"ECOD":0,"IForest":46,"mean":23.0},"35":{"ECOD":0,"IForest":39,"mean":19.5},"36":{"ECOD":0,"IForest":6,"mean":3.0},"37":{"ECOD":0,"IForest":1,"mean":0.5},"38":{"ECOD":0,"IForest":8,"mean":4.0},"39":{"ECOD":0,"IForest":2,"mean":1.0},"40":{"ECOD":0,"IForest":1,"mean":0.5},"41":{"ECOD":0,"IForest":19,"mean":9.5},"42":{"ECOD":0,"IForest":5,"mean":2.5},"43":{"ECOD":0,"IForest":7,"mean":3.5},"44":{"ECOD":0,"IForest":0,"mean":0.0},"45":{"ECOD":0,"IForest":3,"mean":1.5},"46":{"ECOD":0,"IForest":89,"mean":44.5},"47":{"ECOD":0,"IForest":4,"mean":2.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 505, "mean": 252.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":646,"PM10":381,"SO2":507,"NO2":668,"CO":1401,"O3":729,"TEMP":51,"PRES":50,"DEWP":51,"RAIN":43,"wd":159,"WSPM":42},"empty_cells_num":4728,"ave_null_columns":0.1348391513}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/gucheng/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Huairou_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.3191489362},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.3617021277,"kdq":0.7872340426,"cdbd":0.2340425532},"SO2":{"hdddm":0.3829787234,"kdq":0.0212765957,"cdbd":0.3829787234},"NO2":{"hdddm":0.3404255319,"kdq":0.085106383,"cdbd":0.4042553191},"CO":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.2127659574},"O3":{"hdddm":0.4255319149,"kdq":0.3404255319,"cdbd":0.4042553191},"TEMP":{"hdddm":0.5106382979,"kdq":0.4680851064,"cdbd":0.4468085106},"PRES":{"hdddm":0.5319148936,"kdq":0.4468085106,"cdbd":0.4680851064},"DEWP":{"hdddm":0.5744680851,"kdq":0.9361702128,"cdbd":0.6382978723},"RAIN":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2553191489},"WSPM":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_E":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2765957447},"wd_ENE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_ESE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_N":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.1914893617},"wd_NE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3617021277},"wd_NNE":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3404255319},"wd_NNW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2127659574},"wd_NW":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.2340425532},"wd_S":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2553191489},"wd_SE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_SSE":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3191489362},"wd_SSW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.2553191489},"wd_SW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_W":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3191489362},"wd_WNW":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2340425532},"wd_WSW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"station_Huairou":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":2,"mean":1.0},"2":{"ECOD":0,"IForest":9,"mean":4.5},"3":{"ECOD":0,"IForest":14,"mean":7.0},"4":{"ECOD":0,"IForest":16,"mean":8.0},"5":{"ECOD":0,"IForest":9,"mean":4.5},"6":{"ECOD":0,"IForest":4,"mean":2.0},"7":{"ECOD":0,"IForest":1,"mean":0.5},"8":{"ECOD":0,"IForest":3,"mean":1.5},"9":{"ECOD":0,"IForest":11,"mean":5.5},"10":{"ECOD":0,"IForest":14,"mean":7.0},"11":{"ECOD":0,"IForest":15,"mean":7.5},"12":{"ECOD":0,"IForest":23,"mean":11.5},"13":{"ECOD":0,"IForest":6,"mean":3.0},"14":{"ECOD":0,"IForest":5,"mean":2.5},"15":{"ECOD":0,"IForest":9,"mean":4.5},"16":{"ECOD":0,"IForest":12,"mean":6.0},"17":{"ECOD":0,"IForest":6,"mean":3.0},"18":{"ECOD":0,"IForest":5,"mean":2.5},"19":{"ECOD":0,"IForest":1,"mean":0.5},"20":{"ECOD":0,"IForest":1,"mean":0.5},"21":{"ECOD":0,"IForest":9,"mean":4.5},"22":{"ECOD":0,"IForest":9,"mean":4.5},"23":{"ECOD":0,"IForest":5,"mean":2.5},"24":{"ECOD":0,"IForest":13,"mean":6.5},"25":{"ECOD":0,"IForest":7,"mean":3.5},"26":{"ECOD":0,"IForest":2,"mean":1.0},"27":{"ECOD":0,"IForest":8,"mean":4.0},"28":{"ECOD":0,"IForest":8,"mean":4.0},"29":{"ECOD":0,"IForest":14,"mean":7.0},"30":{"ECOD":0,"IForest":2,"mean":1.0},"31":{"ECOD":0,"IForest":2,"mean":1.0},"32":{"ECOD":0,"IForest":2,"mean":1.0},"33":{"ECOD":0,"IForest":19,"mean":9.5},"34":{"ECOD":0,"IForest":24,"mean":12.0},"35":{"ECOD":0,"IForest":23,"mean":11.5},"36":{"ECOD":0,"IForest":4,"mean":2.0},"37":{"ECOD":0,"IForest":1,"mean":0.5},"38":{"ECOD":0,"IForest":3,"mean":1.5},"39":{"ECOD":0,"IForest":2,"mean":1.0},"40":{"ECOD":0,"IForest":6,"mean":3.0},"41":{"ECOD":0,"IForest":17,"mean":8.5},"42":{"ECOD":0,"IForest":3,"mean":1.5},"43":{"ECOD":0,"IForest":2,"mean":1.0},"44":{"ECOD":0,"IForest":1,"mean":0.5},"45":{"ECOD":0,"IForest":3,"mean":1.5},"46":{"ECOD":0,"IForest":74,"mean":37.0},"47":{"ECOD":0,"IForest":0,"mean":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 455, "mean": 227.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":953,"PM10":777,"SO2":980,"NO2":1639,"CO":1422,"O3":1151,"TEMP":51,"PRES":53,"DEWP":53,"RAIN":55,"wd":302,"WSPM":49},"empty_cells_num":7485,"ave_null_columns":0.2134668036}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/huairou/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/nongzhanguan/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Nongzhanguan_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/nongzhanguan/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.3617021277},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/nongzhanguan/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.3617021277,"kdq":0.8085106383,"cdbd":0.3617021277},"SO2":{"hdddm":0.4255319149,"kdq":0.0212765957,"cdbd":0.4255319149},"NO2":{"hdddm":0.3191489362,"kdq":0.4680851064,"cdbd":0.2340425532},"CO":{"hdddm":0.4042553191,"kdq":0.0,"cdbd":0.2765957447},"O3":{"hdddm":0.3829787234,"kdq":0.1063829787,"cdbd":0.3829787234},"TEMP":{"hdddm":0.5319148936,"kdq":0.4255319149,"cdbd":0.4893617021},"PRES":{"hdddm":0.5106382979,"kdq":0.4468085106,"cdbd":0.4680851064},"DEWP":{"hdddm":0.5106382979,"kdq":0.9574468085,"cdbd":0.6382978723},"RAIN":{"hdddm":0.1063829787,"kdq":0.0,"cdbd":0.1489361702},"WSPM":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2340425532},"wd_ENE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_ESE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2553191489},"wd_N":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3191489362},"wd_NE":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"wd_NNE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2978723404},"wd_NNW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_NW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2553191489},"wd_S":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3404255319},"wd_SE":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.170212766},"wd_SSE":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"wd_SSW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3829787234},"wd_SW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3617021277},"wd_W":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2765957447},"wd_WNW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_WSW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2127659574},"station_Nongzhanguan":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/nongzhanguan/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 576, "mean": 288.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/nongzhanguan/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":628,"PM10":440,"SO2":446,"NO2":692,"CO":1206,"O3":506,"TEMP":20,"PRES":20,"DEWP":20,"RAIN":20,"wd":78,"WSPM":14},"empty_cells_num":4090,"ave_null_columns":0.1166438512}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/nongzhanguan/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/nongzhanguan/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Shunyi_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2765957447},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.2978723404,"kdq":0.7872340426,"cdbd":0.3191489362},"SO2":{"hdddm":0.4468085106,"kdq":0.0212765957,"cdbd":0.4255319149},"NO2":{"hdddm":0.3404255319,"kdq":0.085106383,"cdbd":0.3404255319},"CO":{"hdddm":0.3617021277,"kdq":0.0,"cdbd":0.3404255319},"O3":{"hdddm":0.4468085106,"kdq":0.1063829787,"cdbd":0.3617021277},"TEMP":{"hdddm":0.5106382979,"kdq":0.4468085106,"cdbd":0.5531914894},"PRES":{"hdddm":0.4680851064,"kdq":0.4255319149,"cdbd":0.4680851064},"DEWP":{"hdddm":0.5957446809,"kdq":0.9787234043,"cdbd":0.5531914894},"RAIN":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2340425532},"WSPM":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.170212766},"wd_E":{"hdddm":0.3617021277,"kdq":0.0,"cdbd":0.3617021277},"wd_ENE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_ESE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2978723404},"wd_N":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2553191489},"wd_NE":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2340425532},"wd_NNE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2340425532},"wd_NNW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.1914893617},"wd_NW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3404255319},"wd_S":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2765957447},"wd_SE":{"hdddm":0.3829787234,"kdq":0.0,"cdbd":0.3829787234},"wd_SSE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_SSW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2553191489},"wd_SW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_W":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_WNW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2765957447},"wd_WSW":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.170212766},"station_Shunyi":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":0,"mean":0.0},"2":{"ECOD":0,"IForest":2,"mean":1.0},"3":{"ECOD":0,"IForest":6,"mean":3.0},"4":{"ECOD":0,"IForest":17,"mean":8.5},"5":{"ECOD":0,"IForest":8,"mean":4.0},"6":{"ECOD":0,"IForest":1,"mean":0.5},"7":{"ECOD":0,"IForest":0,"mean":0.0},"8":{"ECOD":0,"IForest":3,"mean":1.5},"9":{"ECOD":0,"IForest":11,"mean":5.5},"10":{"ECOD":0,"IForest":18,"mean":9.0},"11":{"ECOD":0,"IForest":12,"mean":6.0},"12":{"ECOD":0,"IForest":18,"mean":9.0},"13":{"ECOD":0,"IForest":3,"mean":1.5},"14":{"ECOD":0,"IForest":4,"mean":2.0},"15":{"ECOD":0,"IForest":9,"mean":4.5},"16":{"ECOD":0,"IForest":3,"mean":1.5},"17":{"ECOD":0,"IForest":4,"mean":2.0},"18":{"ECOD":0,"IForest":6,"mean":3.0},"19":{"ECOD":0,"IForest":0,"mean":0.0},"20":{"ECOD":0,"IForest":0,"mean":0.0},"21":{"ECOD":0,"IForest":17,"mean":8.5},"22":{"ECOD":0,"IForest":21,"mean":10.5},"23":{"ECOD":0,"IForest":2,"mean":1.0},"24":{"ECOD":0,"IForest":8,"mean":4.0},"25":{"ECOD":0,"IForest":3,"mean":1.5},"26":{"ECOD":0,"IForest":0,"mean":0.0},"27":{"ECOD":0,"IForest":5,"mean":2.5},"28":{"ECOD":0,"IForest":3,"mean":1.5},"29":{"ECOD":0,"IForest":9,"mean":4.5},"30":{"ECOD":0,"IForest":5,"mean":2.5},"31":{"ECOD":0,"IForest":0,"mean":0.0},"32":{"ECOD":0,"IForest":0,"mean":0.0},"33":{"ECOD":0,"IForest":30,"mean":15.0},"34":{"ECOD":0,"IForest":44,"mean":22.0},"35":{"ECOD":0,"IForest":33,"mean":16.5},"36":{"ECOD":0,"IForest":4,"mean":2.0},"37":{"ECOD":0,"IForest":1,"mean":0.5},"38":{"ECOD":0,"IForest":3,"mean":1.5},"39":{"ECOD":0,"IForest":2,"mean":1.0},"40":{"ECOD":0,"IForest":0,"mean":0.0},"41":{"ECOD":0,"IForest":15,"mean":7.5},"42":{"ECOD":0,"IForest":3,"mean":1.5},"43":{"ECOD":0,"IForest":1,"mean":0.5},"44":{"ECOD":0,"IForest":0,"mean":0.0},"45":{"ECOD":0,"IForest":13,"mean":6.5},"46":{"ECOD":0,"IForest":72,"mean":36.0},"47":{"ECOD":0,"IForest":10,"mean":5.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 443, "mean": 221.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":913,"PM10":548,"SO2":1296,"NO2":1365,"CO":2178,"O3":1489,"TEMP":51,"PRES":51,"DEWP":54,"RAIN":51,"wd":483,"WSPM":44},"empty_cells_num":8523,"ave_null_columns":0.2430698152}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/shunyi/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/tiantan/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Tiantan_20130301-20170228.csv", 4 | "task": "regression" 5 | } 6 | -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/tiantan/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2553191489},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/tiantan/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.2978723404,"kdq":0.8085106383,"cdbd":0.3191489362},"SO2":{"hdddm":0.4042553191,"kdq":0.0212765957,"cdbd":0.4255319149},"NO2":{"hdddm":0.2978723404,"kdq":0.0425531915,"cdbd":0.2978723404},"CO":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2765957447},"O3":{"hdddm":0.3617021277,"kdq":0.2765957447,"cdbd":0.3191489362},"TEMP":{"hdddm":0.5531914894,"kdq":0.4255319149,"cdbd":0.5744680851},"PRES":{"hdddm":0.5106382979,"kdq":0.4468085106,"cdbd":0.4680851064},"DEWP":{"hdddm":0.6170212766,"kdq":0.9574468085,"cdbd":0.5957446809},"RAIN":{"hdddm":0.1063829787,"kdq":0.0,"cdbd":0.2127659574},"WSPM":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.2978723404},"wd_ENE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_ESE":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.2553191489},"wd_N":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.3191489362},"wd_NE":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"wd_NNE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3191489362},"wd_NNW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_NW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_S":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2978723404},"wd_SE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.1914893617},"wd_SSE":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"wd_SSW":{"hdddm":0.3829787234,"kdq":0.0,"cdbd":0.3404255319},"wd_SW":{"hdddm":0.3404255319,"kdq":0.0,"cdbd":0.3617021277},"wd_W":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2553191489},"wd_WNW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_WSW":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2127659574},"station_Tiantan":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/tiantan/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 537, "mean": 268.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/tiantan/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":677,"PM10":597,"SO2":1118,"NO2":744,"CO":1126,"O3":843,"TEMP":20,"PRES":20,"DEWP":20,"RAIN":20,"wd":78,"WSPM":14},"empty_cells_num":5277,"ave_null_columns":0.1504962355}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/tiantan/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/tiantan/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Wanliu_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2553191489},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.2765957447,"kdq":0.8085106383,"cdbd":0.3617021277},"SO2":{"hdddm":0.4680851064,"kdq":0.0212765957,"cdbd":0.4042553191},"NO2":{"hdddm":0.3404255319,"kdq":0.4255319149,"cdbd":0.3404255319},"CO":{"hdddm":0.3617021277,"kdq":0.0,"cdbd":0.3404255319},"O3":{"hdddm":0.4042553191,"kdq":0.1914893617,"cdbd":0.4042553191},"TEMP":{"hdddm":0.5106382979,"kdq":0.4468085106,"cdbd":0.5744680851},"PRES":{"hdddm":0.5319148936,"kdq":0.4468085106,"cdbd":0.4893617021},"DEWP":{"hdddm":0.6382978723,"kdq":0.9787234043,"cdbd":0.5531914894},"RAIN":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.1914893617},"WSPM":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.2765957447},"wd_E":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2978723404},"wd_ENE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3191489362},"wd_ESE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_N":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3404255319},"wd_NE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3191489362},"wd_NNE":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"wd_NNW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_NW":{"hdddm":0.3617021277,"kdq":0.0,"cdbd":0.3191489362},"wd_S":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"wd_SE":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"wd_SSE":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_SSW":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2127659574},"wd_SW":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.4042553191},"wd_W":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_WNW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_WSW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"station_Wanliu":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":0,"IForest":0,"mean":0.0},"2":{"ECOD":0,"IForest":3,"mean":1.5},"3":{"ECOD":0,"IForest":1,"mean":0.5},"4":{"ECOD":0,"IForest":5,"mean":2.5},"5":{"ECOD":0,"IForest":7,"mean":3.5},"6":{"ECOD":0,"IForest":2,"mean":1.0},"7":{"ECOD":0,"IForest":0,"mean":0.0},"8":{"ECOD":0,"IForest":1,"mean":0.5},"9":{"ECOD":0,"IForest":8,"mean":4.0},"10":{"ECOD":0,"IForest":49,"mean":24.5},"11":{"ECOD":0,"IForest":15,"mean":7.5},"12":{"ECOD":0,"IForest":31,"mean":15.5},"13":{"ECOD":0,"IForest":1,"mean":0.5},"14":{"ECOD":0,"IForest":0,"mean":0.0},"15":{"ECOD":0,"IForest":17,"mean":8.5},"16":{"ECOD":0,"IForest":4,"mean":2.0},"17":{"ECOD":0,"IForest":4,"mean":2.0},"18":{"ECOD":0,"IForest":6,"mean":3.0},"19":{"ECOD":0,"IForest":2,"mean":1.0},"20":{"ECOD":0,"IForest":5,"mean":2.5},"21":{"ECOD":0,"IForest":15,"mean":7.5},"22":{"ECOD":0,"IForest":20,"mean":10.0},"23":{"ECOD":0,"IForest":8,"mean":4.0},"24":{"ECOD":0,"IForest":9,"mean":4.5},"25":{"ECOD":0,"IForest":6,"mean":3.0},"26":{"ECOD":0,"IForest":1,"mean":0.5},"27":{"ECOD":0,"IForest":2,"mean":1.0},"28":{"ECOD":0,"IForest":6,"mean":3.0},"29":{"ECOD":0,"IForest":7,"mean":3.5},"30":{"ECOD":0,"IForest":3,"mean":1.5},"31":{"ECOD":0,"IForest":0,"mean":0.0},"32":{"ECOD":0,"IForest":0,"mean":0.0},"33":{"ECOD":0,"IForest":25,"mean":12.5},"34":{"ECOD":0,"IForest":33,"mean":16.5},"35":{"ECOD":0,"IForest":25,"mean":12.5},"36":{"ECOD":0,"IForest":5,"mean":2.5},"37":{"ECOD":0,"IForest":2,"mean":1.0},"38":{"ECOD":0,"IForest":2,"mean":1.0},"39":{"ECOD":0,"IForest":2,"mean":1.0},"40":{"ECOD":0,"IForest":0,"mean":0.0},"41":{"ECOD":0,"IForest":6,"mean":3.0},"42":{"ECOD":0,"IForest":1,"mean":0.5},"43":{"ECOD":0,"IForest":1,"mean":0.5},"44":{"ECOD":0,"IForest":0,"mean":0.0},"45":{"ECOD":0,"IForest":0,"mean":0.0},"46":{"ECOD":0,"IForest":60,"mean":30.0},"47":{"ECOD":0,"IForest":3,"mean":1.5}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 418, "mean": 209.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":382,"PM10":284,"SO2":575,"NO2":1070,"CO":1812,"O3":2107,"TEMP":20,"PRES":20,"DEWP":20,"RAIN":20,"wd":123,"WSPM":14},"empty_cells_num":6447,"ave_null_columns":0.1838637919}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanliu/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanshouxingong/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BeijingMulti-SiteAir-QualityData/PRSA_Data_Wanshouxigong_20130301-20170228.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanshouxingong/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.170212766},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanshouxingong/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"PM10":{"hdddm":0.2553191489,"kdq":0.8723404255,"cdbd":0.2340425532},"SO2":{"hdddm":0.4042553191,"kdq":0.0212765957,"cdbd":0.4255319149},"NO2":{"hdddm":0.3829787234,"kdq":0.4680851064,"cdbd":0.3617021277},"CO":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.3404255319},"O3":{"hdddm":0.4042553191,"kdq":0.1063829787,"cdbd":0.4042553191},"TEMP":{"hdddm":0.6382978723,"kdq":0.4468085106,"cdbd":0.6382978723},"PRES":{"hdddm":0.4468085106,"kdq":0.4468085106,"cdbd":0.4468085106},"DEWP":{"hdddm":0.6170212766,"kdq":0.9361702128,"cdbd":0.5744680851},"RAIN":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.2127659574},"WSPM":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3404255319},"wd_E":{"hdddm":0.3617021277,"kdq":0.0,"cdbd":0.3617021277},"wd_ENE":{"hdddm":0.2978723404,"kdq":0.0,"cdbd":0.3191489362},"wd_ESE":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2553191489},"wd_N":{"hdddm":0.2553191489,"kdq":0.0,"cdbd":0.2553191489},"wd_NE":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.2978723404},"wd_NNE":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3191489362},"wd_NNW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_NW":{"hdddm":0.2340425532,"kdq":0.0,"cdbd":0.2340425532},"wd_S":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_SE":{"hdddm":0.170212766,"kdq":0.0,"cdbd":0.170212766},"wd_SSE":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.1914893617},"wd_SSW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.3191489362},"wd_SW":{"hdddm":0.2765957447,"kdq":0.0,"cdbd":0.2765957447},"wd_W":{"hdddm":0.2127659574,"kdq":0.0,"cdbd":0.2340425532},"wd_WNW":{"hdddm":0.3191489362,"kdq":0.0,"cdbd":0.3829787234},"wd_WSW":{"hdddm":0.1914893617,"kdq":0.0,"cdbd":0.3191489362},"station_Wanshouxigong":{"hdddm":0.0,"kdq":0.0,"cdbd":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanshouxingong/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 0, "IForest": 580, "mean": 290.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanshouxingong/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["PM2.5","PM10","SO2","NO2","CO","O3","TEMP","PRES","DEWP","RAIN","wd","WSPM"],"col_null_dict":{"PM2.5":696,"PM10":484,"SO2":669,"NO2":754,"CO":1297,"O3":1078,"TEMP":19,"PRES":19,"DEWP":19,"RAIN":19,"wd":79,"WSPM":13},"empty_cells_num":5146,"ave_null_columns":0.1467602099}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanshouxingong/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/beijing_multisite/wanshouxingong/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM"], 3 | "categorical": ["wd","station"], 4 | "target": ["PM2.5"], 5 | "timestamp": ["No", "year", "month", "day", "hour"], 6 | "null": ["PM2.5", "PM10", "SO2", "NO2", "CO", "O3", "TEMP", "PRES", "DEWP", "RAIN", "WSPM", "wd"], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/bike-sharing-demand/train.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/missing_value_by_window_stats.json: -------------------------------------------------------------------------------- 1 | {"columns_with_null":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null},"col_null_dict":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null},"empty_cells_num":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null},"ave_null_columns":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2857142857},"kdq":{"0":0.0714285714}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"holiday":{"hdddm":0.7857142857,"kdq":0.0,"cdbd":0.5},"workingday":{"hdddm":0.3571428571,"kdq":0.0,"cdbd":0.2857142857},"weather":{"hdddm":0.4285714286,"kdq":0.0,"cdbd":0.4285714286},"temp":{"hdddm":0.6428571429,"kdq":0.0,"cdbd":0.6428571429},"atemp":{"hdddm":0.6428571429,"kdq":0.0,"cdbd":0.5714285714},"humidity":{"hdddm":0.3571428571,"kdq":0.0,"cdbd":0.2142857143},"windspeed":{"hdddm":0.2857142857,"kdq":0.0,"cdbd":0.2857142857},"casual":{"hdddm":0.2857142857,"kdq":0.0,"cdbd":0.2857142857},"registered":{"hdddm":0.1428571429,"kdq":0.4285714286,"cdbd":0.0714285714}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":9,"IForest":2,"mean":5.5},"2":{"ECOD":0,"IForest":2,"mean":1.0},"3":{"ECOD":8,"IForest":15,"mean":11.5},"4":{"ECOD":0,"IForest":1,"mean":0.5},"5":{"ECOD":0,"IForest":17,"mean":8.5},"6":{"ECOD":0,"IForest":7,"mean":3.5},"7":{"ECOD":11,"IForest":8,"mean":9.5},"8":{"ECOD":13,"IForest":10,"mean":11.5},"9":{"ECOD":3,"IForest":11,"mean":7.0},"10":{"ECOD":3,"IForest":0,"mean":1.5},"11":{"ECOD":38,"IForest":20,"mean":29.0},"12":{"ECOD":12,"IForest":18,"mean":15.0},"13":{"ECOD":0,"IForest":5,"mean":2.5},"14":{"ECOD":0,"IForest":1,"mean":0.5}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 116, "IForest": 124, "mean": 120.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bike_sharing_demand/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["holiday","workingday","weather","temp","atemp","humidity","windspeed","casual","registered"], 3 | "categorical": [], 4 | "target": ["count"], 5 | "timestamp": ["datetime","season"], 6 | "window size": 720, 7 | "unnecessary": [] 8 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bitcoin/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/BitcoinHeistData.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/bitcoin/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["length", "weight", "looped", "neighbors", "income"], 3 | "categorical": [], 4 | "target": ["label"], 5 | "timestamp": ["year", "day"], 6 | "null": [], 7 | "window size": 30400, 8 | "unnecessary": ["address"] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/covtype/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/covtype.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/covtype/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 30400, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/election/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/ElectionData.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/election/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": ["territoryName", "Party"], 4 | "target": ["FinalMandates"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 386, 8 | "unnecessary": ["TimeElapsed"] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/electricity_prices/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/elec.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/electricity_prices/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2575757576},"kdq":{"0":0.9393939394}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/electricity_prices/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"nswprice":{"hdddm":0.3636363636,"kdq":0.2121212121,"cdbd":0.4393939394},"nswdemand":{"hdddm":0.4242424242,"kdq":0.7272727273,"cdbd":0.3939393939},"vicprice":{"hdddm":0.196969697,"kdq":0.0,"cdbd":0.1818181818},"vicdemand":{"hdddm":0.2424242424,"kdq":0.0,"cdbd":0.2272727273},"transfer":{"hdddm":0.2575757576,"kdq":0.0,"cdbd":0.2575757576}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/electricity_prices/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 652, "IForest": 518, "mean": 585.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/electricity_prices/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/electricity_prices/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/electricity_prices/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["nswprice","nswdemand","vicprice","vicdemand","transfer"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": ["date","day","period"], 6 | "window size": 672, 7 | "unnecessary": [] 8 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/energy_prediction/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/energydata_complete.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/energy_prediction/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["Appliances"], 5 | "timestamp": ["date"], 6 | "null": [], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/household/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/household_power_consumption.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/household/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":["Sub_metering_3"],"col_null_dict":{"Sub_metering_3":25979},"empty_cells_num":25979,"ave_null_columns":0.0125184375}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/household/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Global_active_power","Global_reactive_power","Voltage","Global_intensity"], 3 | "categorical": [], 4 | "target": ["Sub_metering_3"], 5 | "timestamp": ["Date", "Time"], 6 | "null": [], 7 | "window size": 43200, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_balanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-abrupt_balanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_balanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0891840607},"kdq":{"0":0.0018975332}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_balanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 697, "IForest": 1094, "mean": 895.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_balanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_balanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_balanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_imbalanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-abrupt_imbalanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_imbalanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0881441847},"kdq":{"0":0.0002816108}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_imbalanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 5031, "IForest": 6601, "mean": 5816.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_imbalanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_imbalanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0002815315,"var2":0.0},"var2":{"var1":0.0002815315,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/abrupt_imbalanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_balanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-gradual_balanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_balanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0958333333},"kdq":{"0":0.0041666667}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_balanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 336, "IForest": 393, "mean": 364.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_balanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_balanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_balanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_imbalanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-gradual_imbalanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_imbalanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0879888268},"kdq":{"0":0.000698324}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_imbalanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 2094, "IForest": 2398, "mean": 2246.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_imbalanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_imbalanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0006978367,"var2":0.0},"var2":{"var1":0.0006978367,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/gradual_imbalanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_balanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-incremental-abrupt_balanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_balanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0989974937},"kdq":{"0":0.0012531328}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_balanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 1104, "IForest": 1296, "mean": 1200.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_balanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_balanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0012515645,"var2":0.0},"var2":{"var1":0.0012515645,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_balanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_imbalanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-incremental-abrupt_imbalanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_imbalanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0887364461},"kdq":{"0":0.0002212879}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_imbalanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 6338, "IForest": 9258, "mean": 7798.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_imbalanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_imbalanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0004424779,"var2":0.0},"var2":{"var1":0.0004424779,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_abrupt_imbalanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_balanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-incremental_balanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_balanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0878734622},"kdq":{"0":0.0017574692}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_balanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 769, "IForest": 1098, "mean": 933.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_balanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_balanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.001754386,"var2":0.0},"var2":{"var1":0.001754386,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_balanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 1000, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_imbalanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-incremental_imbalanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_imbalanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0865235672},"kdq":{"0":0.0002212879}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_imbalanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 6338, "IForest": 9443, "mean": 7890.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_imbalanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_imbalanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0002212389,"var2":0.0},"var2":{"var1":0.0002212389,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_imbalanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 1000, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_balanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-incremental-reoccurring_balanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_balanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.1065162907},"kdq":{"0":0.0012531328}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_balanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 1121, "IForest": 1380, "mean": 1250.5} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_balanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_balanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0025031289,"var2":0.0},"var2":{"var1":0.0025031289,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_balanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_imbalanced/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-incremental-reoccurring_imbalanced_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_imbalanced/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0902854614},"kdq":{"0":0.0002212879}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_imbalanced/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 6338, "IForest": 9198, "mean": 7768.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_imbalanced/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_imbalanced/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0006637168,"var2":0.0},"var2":{"var1":0.0006637168,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/incremental_reoccurring_imbalanced/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/out-of-control/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/INSECTS-out-of-control_norm.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/out-of-control/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0942541436},"kdq":{"0":0.0001104972}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/out-of-control/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 10415, "IForest": 12805, "mean": 11610.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/out-of-control/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/out-of-control/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/insects/out-of-control/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Att1","Att2","Att3","Att4","Att5","Att6","Att7","Att8","Att9","Att10","Att11","Att12","Att13","Att14","Att15","Att16","Att17","Att18","Att19","Att20","Att21","Att22","Att23","Att24","Att25","Att26","Att27","Att28","Att29","Att30","Att31", "Att32", "Att33"], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 100, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/AirQualityUCI/AirQualityUCI.xlsx", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/missing_value_by_window_stats.json: -------------------------------------------------------------------------------- 1 | {"columns_with_null":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null},"col_null_dict":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null},"empty_cells_num":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null},"ave_null_columns":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2727272727},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"CO(GT)":{"hdddm":0.5454545455,"kdq":0.0,"cdbd":0.5454545455},"PT08.S1(CO)":{"hdddm":0.2727272727,"kdq":0.9090909091,"cdbd":0.2727272727},"NMHC(GT)":{"hdddm":0.0909090909,"kdq":0.1818181818,"cdbd":0.0909090909},"C6H6(GT)":{"hdddm":0.3636363636,"kdq":1.0,"cdbd":0.3636363636},"PT08.S2(NMHC)":{"hdddm":0.3636363636,"kdq":1.0,"cdbd":0.3636363636},"NOx(GT)":{"hdddm":0.2727272727,"kdq":0.9090909091,"cdbd":0.2727272727},"PT08.S3(NOx)":{"hdddm":0.3636363636,"kdq":0.8181818182,"cdbd":0.4545454545},"PT08.S4(NO2)":{"hdddm":0.3636363636,"kdq":1.0,"cdbd":0.4545454545},"PT08.S5(O3)":{"hdddm":0.3636363636,"kdq":0.8181818182,"cdbd":0.4545454545},"T":{"hdddm":0.5454545455,"kdq":1.0,"cdbd":0.4545454545},"RH":{"hdddm":0.4545454545,"kdq":1.0,"cdbd":0.4545454545},"AH":{"hdddm":0.5454545455,"kdq":1.0,"cdbd":0.3636363636}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":9,"IForest":6,"mean":7.5},"2":{"ECOD":2,"IForest":14,"mean":8.0},"3":{"ECOD":1,"IForest":38,"mean":19.5},"4":{"ECOD":1,"IForest":1,"mean":1.0},"5":{"ECOD":0,"IForest":38,"mean":19.0},"6":{"ECOD":4,"IForest":19,"mean":11.5},"7":{"ECOD":24,"IForest":5,"mean":14.5},"8":{"ECOD":27,"IForest":4,"mean":15.5},"9":{"ECOD":25,"IForest":126,"mean":75.5},"10":{"ECOD":4,"IForest":16,"mean":10.0},"11":{"ECOD":8,"IForest":70,"mean":39.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 121, "IForest": 363, "mean": 242.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/italian_city_airquality/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["CO(GT)", "PT08.S1(CO)", "NMHC(GT)", "C6H6(GT)", "PT08.S2(NMHC)", "NOx(GT)", "PT08.S3(NOx)", "NO2(GT)", "PT08.S4(NO2)", "PT08.S5(O3)", "T", "RH", "AH"], 3 | "target": ["NO2(GT)"], 4 | "categorical": [], 5 | "timestamp": ["Date", "Time" ], 6 | "replace_with_null": [-200], 7 | "window size": 720, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/news_popularity/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/News_Final.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/news_popularity/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["LinkedIn"], 5 | "timestamp": ["PublishDate"], 6 | "null": [-1], 7 | "window size": 2000, 8 | "unnecessary": ["IDLink", "Title","Headline","Source","Topic","GooglePlus","Facebook"] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/noaa/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/NOAA.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/noaa/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0408163265},"kdq":{"0":0.2653061224}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/noaa/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"attribute1":{"hdddm":0.2448979592,"kdq":0.1632653061,"cdbd":0.2857142857},"attribute2":{"hdddm":0.0816326531,"kdq":0.2040816327,"cdbd":0.0612244898},"attribute3":{"hdddm":0.1020408163,"kdq":0.1020408163,"cdbd":0.1020408163},"attribute4":{"hdddm":0.306122449,"kdq":0.0204081633,"cdbd":0.306122449},"attribute5":{"hdddm":0.1632653061,"kdq":0.1836734694,"cdbd":0.1224489796},"attribute6":{"hdddm":0.2244897959,"kdq":0.0,"cdbd":0.3265306122},"attribute7":{"hdddm":0.306122449,"kdq":0.0,"cdbd":0.2448979592},"attribute8":{"hdddm":0.4693877551,"kdq":0.0,"cdbd":0.4489795918}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/noaa/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 279, "IForest": 313, "mean": 296.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/noaa/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/noaa/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/noaa/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 360, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/rialto/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/usp/rialto.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/rialto/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["class"], 5 | "timestamp": [], 6 | "null": [], 7 | "window size": 1500, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/room_occupancy/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Occupancy_Estimation.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/room_occupancy/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["Room_Occupancy_Count"], 5 | "timestamp": ["Date", "Time"], 6 | "null": [], 7 | "window size": 240, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/rssi/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/filtered_rssi.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/rssi/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["rssiOne", "rssiTwo"], 3 | "categorical": [], 4 | "target": ["locationStatus"], 5 | "timestamp": ["timestamp"], 6 | "null": [], 7 | "window size": 499, 8 | "unnecessary": ["name"] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/porto-seguro-safe-driver-prediction/train.csv", 4 | "task": "classification" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/missing_value_by_window_stats.json: -------------------------------------------------------------------------------- 1 | {"columns_with_null":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null,"30":null,"31":null,"32":null,"33":null,"34":null,"35":null,"36":null,"37":null,"38":null},"col_null_dict":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null,"30":null,"31":null,"32":null,"33":null,"34":null,"35":null,"36":null,"37":null,"38":null},"empty_cells_num":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null,"30":null,"31":null,"32":null,"33":null,"34":null,"35":null,"36":null,"37":null,"38":null},"ave_null_columns":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null,"24":null,"25":null,"26":null,"27":null,"28":null,"29":null,"30":null,"31":null,"32":null,"33":null,"34":null,"35":null,"36":null,"37":null,"38":null}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.0263157895},"kdq":{"0":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":124,"IForest":88,"mean":106.0},"2":{"ECOD":134,"IForest":82,"mean":108.0},"3":{"ECOD":158,"IForest":85,"mean":121.5},"4":{"ECOD":136,"IForest":79,"mean":107.5},"5":{"ECOD":123,"IForest":91,"mean":107.0},"6":{"ECOD":140,"IForest":76,"mean":108.0},"7":{"ECOD":136,"IForest":84,"mean":110.0},"8":{"ECOD":119,"IForest":78,"mean":98.5},"9":{"ECOD":124,"IForest":89,"mean":106.5},"10":{"ECOD":132,"IForest":89,"mean":110.5},"11":{"ECOD":138,"IForest":78,"mean":108.0},"12":{"ECOD":144,"IForest":77,"mean":110.5},"13":{"ECOD":155,"IForest":91,"mean":123.0},"14":{"ECOD":129,"IForest":74,"mean":101.5},"15":{"ECOD":122,"IForest":80,"mean":101.0},"16":{"ECOD":143,"IForest":92,"mean":117.5},"17":{"ECOD":144,"IForest":96,"mean":120.0},"18":{"ECOD":135,"IForest":83,"mean":109.0},"19":{"ECOD":128,"IForest":88,"mean":108.0},"20":{"ECOD":128,"IForest":87,"mean":107.5},"21":{"ECOD":126,"IForest":75,"mean":100.5},"22":{"ECOD":120,"IForest":64,"mean":92.0},"23":{"ECOD":154,"IForest":88,"mean":121.0},"24":{"ECOD":135,"IForest":76,"mean":105.5},"25":{"ECOD":143,"IForest":81,"mean":112.0},"26":{"ECOD":138,"IForest":77,"mean":107.5},"27":{"ECOD":138,"IForest":83,"mean":110.5},"28":{"ECOD":124,"IForest":84,"mean":104.0},"29":{"ECOD":137,"IForest":86,"mean":111.5},"30":{"ECOD":142,"IForest":90,"mean":116.0},"31":{"ECOD":138,"IForest":69,"mean":103.5},"32":{"ECOD":132,"IForest":74,"mean":103.0},"33":{"ECOD":158,"IForest":90,"mean":124.0},"34":{"ECOD":132,"IForest":69,"mean":100.5},"35":{"ECOD":142,"IForest":103,"mean":122.5},"36":{"ECOD":142,"IForest":89,"mean":115.5},"37":{"ECOD":123,"IForest":88,"mean":105.5},"38":{"ECOD":129,"IForest":91,"mean":110.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 5364, "IForest": 3294, "mean": 4329.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/safe_driver/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["ps_ind_01", "ps_ind_02_cat", "ps_ind_03", "ps_ind_04_cat", "ps_ind_05_cat", "ps_ind_06_bin", "ps_ind_07_bin", "ps_ind_08_bin", "ps_ind_09_bin", "ps_ind_10_bin", "ps_ind_11_bin", "ps_ind_12_bin", "ps_ind_13_bin", "ps_ind_14", "ps_ind_15", "ps_ind_16_bin", "ps_ind_17_bin", "ps_ind_18_bin", "ps_reg_01", "ps_reg_02", "ps_reg_03", "ps_car_01_cat", "ps_car_02_cat", "ps_car_02_cat", "ps_car_03_cat", "ps_car_04_cat", "ps_car_05_cat", "ps_car_06_cat", "ps_car_07_cat", "ps_car_08_cat", "ps_car_09_cat", "ps_car_10_cat", "ps_car_11_cat", "ps_car_11", "ps_car_12", "ps_car_13", "ps_car_14", "ps_car_15", "ps_calc_01", "ps_calc_02", "ps_calc_03","ps_calc_04","ps_calc_05","ps_calc_06","ps_calc_07","ps_calc_08","ps_calc_09","ps_calc_10","ps_calc_11","ps_calc_12","ps_calc_13","ps_calc_14","ps_calc_15_bin","ps_calc_16_bin","ps_calc_17_bin","ps_calc_18_bin","ps_calc_19_bin","ps_calc_20_bin"], 3 | "categorical": [], 4 | "target": ["target"], 5 | "timestamp": ["id"], 6 | "window size": 15000, 7 | "unnecessary": [] 8 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/taxi_ride_duration/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/taxi_ride_duration.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/taxi_ride_duration/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": ["store_and_fwd_flag"], 4 | "target": ["trip_duration"], 5 | "timestamp": ["pickup_datetime"], 6 | "null": [], 7 | "window size": 20000, 8 | "unnecessary": ["id", "dropoff_datetime"] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Tetuan City power consumption.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/missing_value_by_window_stats.json: -------------------------------------------------------------------------------- 1 | {"columns_with_null":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null},"col_null_dict":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null},"empty_cells_num":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null},"ave_null_columns":{"0":null,"1":null,"2":null,"3":null,"4":null,"5":null,"6":null,"7":null,"8":null,"9":null,"10":null,"11":null,"12":null,"13":null,"14":null,"15":null,"16":null,"17":null,"18":null,"19":null,"20":null,"21":null,"22":null,"23":null}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/multi_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"hdddm":{"0":0.2608695652},"kdq":{"0":1.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"Temperature":{"hdddm":0.6086956522,"kdq":1.0,"cdbd":0.6086956522},"Humidity":{"hdddm":0.5652173913,"kdq":1.0,"cdbd":0.5652173913},"Wind Speed":{"hdddm":0.8260869565,"kdq":0.0,"cdbd":0.6956521739},"general diffuse flows":{"hdddm":0.347826087,"kdq":0.8695652174,"cdbd":0.3913043478},"diffuse flows":{"hdddm":0.2608695652,"kdq":1.0,"cdbd":0.347826087}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/outliers_stats_each_window.json: -------------------------------------------------------------------------------- 1 | {"1":{"ECOD":2,"IForest":6,"mean":4.0},"2":{"ECOD":0,"IForest":38,"mean":19.0},"3":{"ECOD":9,"IForest":56,"mean":32.5},"4":{"ECOD":2,"IForest":2,"mean":2.0},"5":{"ECOD":5,"IForest":27,"mean":16.0},"6":{"ECOD":2,"IForest":5,"mean":3.5},"7":{"ECOD":8,"IForest":6,"mean":7.0},"8":{"ECOD":61,"IForest":36,"mean":48.5},"9":{"ECOD":8,"IForest":26,"mean":17.0},"10":{"ECOD":6,"IForest":12,"mean":9.0},"11":{"ECOD":35,"IForest":1,"mean":18.0},"12":{"ECOD":80,"IForest":1,"mean":40.5},"13":{"ECOD":185,"IForest":29,"mean":107.0},"14":{"ECOD":97,"IForest":0,"mean":48.5},"15":{"ECOD":3,"IForest":0,"mean":1.5},"16":{"ECOD":34,"IForest":0,"mean":17.0},"17":{"ECOD":50,"IForest":0,"mean":25.0},"18":{"ECOD":9,"IForest":0,"mean":4.5},"19":{"ECOD":10,"IForest":0,"mean":5.0},"20":{"ECOD":2,"IForest":7,"mean":4.5},"21":{"ECOD":0,"IForest":0,"mean":0.0},"22":{"ECOD":10,"IForest":0,"mean":5.0},"23":{"ECOD":16,"IForest":0,"mean":8.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/outliers_stats_overall.json: -------------------------------------------------------------------------------- 1 | {"ECOD": 634, "IForest": 252, "mean": 443.0} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/overall_missing_value_stats.json: -------------------------------------------------------------------------------- 1 | {"overall":{"columns_with_null":[],"col_null_dict":{},"empty_cells_num":0,"ave_null_columns":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/pca_one_dimensional_drift_stats.json: -------------------------------------------------------------------------------- 1 | {"var1":{"var1":0.0,"var2":0.0},"var2":{"var1":0.0,"var2":0.0}} -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/tetouan/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": ["Temperature", "Humidity", "Wind Speed", 3 | "general diffuse flows", "diffuse flows"], 4 | "categorical": [], 5 | "target": ["Zone 1 Power Consumption"], 6 | "timestamp": ["DateTime"], 7 | "null": [], 8 | "window size": 2160, 9 | "unnecessary": ["Zone 2 Power Consumption", "Zone 3 Power Consumption"] 10 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/traffic_volumn/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Metro_Interstate_Traffic_Volume.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/traffic_volumn/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": ["weather_description", "weather_main"], 4 | "target": ["traffic_volume"], 5 | "timestamp": ["date_time"], 6 | "null": [], 7 | "window size": 720, 8 | "unnecessary": ["holiday"] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/Bhubhneshwar/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Temperature_And_Precipitation_Cities_IN/Mumbai_1990_2022_Santacruz.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/Bhubhneshwar/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["tavg"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 365, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/Rajasthan/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Temperature_And_Precipitation_Cities_IN/Rajasthan_1990_2022_Jodhpur.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/Rajasthan/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["tavg"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 365, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/bangalore/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Temperature_And_Precipitation_Cities_IN/Bangalore_1990_2022_BangaloreCity.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/bangalore/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["tavg"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 365, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/chennai/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Temperature_And_Precipitation_Cities_IN/Chennai_1990_2022_Madras.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/chennai/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["tavg"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 365, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/delhi/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Temperature_And_Precipitation_Cities_IN/Delhi_NCR_1990_2022_Safdarjung.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/delhi/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["tavg"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 365, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/lucknow/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Temperature_And_Precipitation_Cities_IN/Lucknow_1990_2022.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/lucknow/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["tavg"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 365, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/mumbai/info.json: -------------------------------------------------------------------------------- 1 | { 2 | "schema": "schema.json", 3 | "data": "dataset/Temperature_And_Precipitation_Cities_IN/Mumbai_1990_2022_Santacruz.csv", 4 | "task": "regression" 5 | } -------------------------------------------------------------------------------- /pyoe/OEBench/dataset_experiment_info/weather_indian_cities/mumbai/schema.json: -------------------------------------------------------------------------------- 1 | { 2 | "numerical": [], 3 | "categorical": [], 4 | "target": ["tavg"], 5 | "timestamp": ["time"], 6 | "null": [], 7 | "window size": 365, 8 | "unnecessary": [] 9 | } -------------------------------------------------------------------------------- /pyoe/OEBench/figures/cluster.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/figures/cluster.pdf -------------------------------------------------------------------------------- /pyoe/OEBench/figures/cluster.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/figures/cluster.png -------------------------------------------------------------------------------- /pyoe/OEBench/figures/flowchart.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/figures/flowchart.png -------------------------------------------------------------------------------- /pyoe/OEBench/figures/flowchart2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Xtra-Computing/PyOE/7f66fd6a127312462a87cc1c6dc9b59f608779df/pyoe/OEBench/figures/flowchart2.png -------------------------------------------------------------------------------- /pyoe/OEBench/run.sh: -------------------------------------------------------------------------------- 1 | python experiments.py --model=tree \ 2 | --dataset=selected \ 3 | --alg=naive \ 4 | --epochs=1 \ 5 | --batch_size=64 \ 6 | --lr=0.01 \ 7 | --layers=3 \ 8 | --reg=1 \ 9 | --buffer=100 \ 10 | --ensemble=5 \ 11 | --window_factor=1 \ 12 | --missing_fill=knn2 \ 13 | --device="cpu" 14 | -------------------------------------------------------------------------------- /pyoe/__init__.py: -------------------------------------------------------------------------------- 1 | from .dataloaders import * 2 | from .algorithms import * 3 | from .models import * 4 | from .metrics import * 5 | from .preprocessors import * 6 | -------------------------------------------------------------------------------- /pyoe/__version__.py: -------------------------------------------------------------------------------- 1 | # mmmmmm mmmm mmmmmmmm 2 | # ##""""#m ##""## ##"""""" 3 | # ## ## "## ### ## ## ## 4 | # ######" ##m ## ## ## ####### 5 | # ## ####" ## ## ## 6 | # ## ### ##mm## ##mmmmmm 7 | # "" ## """" """""""" 8 | # ### 9 | 10 | VERSION = (0, 1, 3) 11 | 12 | __version__ = '.'.join(map(str, VERSION)) 13 | -------------------------------------------------------------------------------- /pyoe/algorithms/__init__.py: -------------------------------------------------------------------------------- 1 | from .trainer import * 2 | from .loss import * 3 | -------------------------------------------------------------------------------- /pyoe/dataloaders/__init__.py: -------------------------------------------------------------------------------- 1 | from .base import * 2 | from .pipeline import * 3 | -------------------------------------------------------------------------------- /pyoe/metrics/__init__.py: -------------------------------------------------------------------------------- 1 | from .metrics import * 2 | -------------------------------------------------------------------------------- /pyoe/models/__init__.py: -------------------------------------------------------------------------------- 1 | from .models import * 2 | from .networks import * 3 | -------------------------------------------------------------------------------- /pyoe/utils.py: -------------------------------------------------------------------------------- 1 | import numpy as np 2 | 3 | 4 | def shingle(series: np.array, dim: int) -> np.array: 5 | """ 6 | Takes a one dimensional series and shingles it into dim dimensions. 7 | 8 | Args: 9 | series (np.array): the input series. 10 | dim (int): the dimension of the shingled array. 11 | 12 | Returns: 13 | shingled (np.array): the shingled array. 14 | """ 15 | height = len(series) - dim + 1 16 | shingled = np.zeros((dim, height)) 17 | for i in range(dim): 18 | shingled[i] = series[i : i + height] 19 | return shingled 20 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | autogluon.timeseries[chronos-openvino]==1.1.1 2 | catboost==1.2.5 3 | click==8.1.7 4 | combo==0.1.3 5 | copulas==0.11.0 6 | cvxopt==1.3.2 7 | delu==0.0.25 8 | einops==0.8.0 9 | keras==2.15.0 10 | lightgbm==4.3.0 11 | matplotlib==3.9.2 12 | menelaus==0.2.0 13 | networkx==3.3 14 | numpy==1.23.5 15 | pandas==2.2.2 16 | Pillow==10.4.0 17 | pyod==1.1.3 18 | pytorch_tabnet==4.1.0 19 | river==0.21.2 20 | rtdl==0.0.13 21 | scikit_learn==1.4.0 22 | scikit_multiflow==0.5.3 23 | scipy==1.12.0 24 | seaborn==0.13.2 25 | setuptools==72.1.0 26 | streamad==0.3.1 27 | tensorflow==2.15.0 28 | torch==2.3.1 29 | torchvision==0.18.1 30 | tqdm==4.66.4 31 | wget==3.2 32 | xgboost==2.0.3 33 | --------------------------------------------------------------------------------