├── .gitignore ├── LICENSE ├── README.md ├── api_anomaly_project ├── .gitignore ├── Dockerfile ├── app │ ├── app.py │ ├── measure_response.py │ └── ping.py ├── assets │ ├── header.png │ ├── roc_pr_curves.png │ ├── shap.png │ └── thresholds.png ├── data │ ├── supervised_clean_data.parquet │ └── supervised_clean_data_w_features.parquet ├── models │ └── hgbt_final.joblib ├── notebooks │ ├── cleaning.ipynb │ ├── eda.ipynb │ ├── feature_engineering.ipynb │ ├── htmls │ │ ├── eda.html │ │ ├── feature_engineering.html │ │ └── modelling.html │ └── modelling.ipynb ├── readme.md ├── requirements.txt └── utils │ ├── __init__.py │ ├── cleaning.py │ ├── feature_engineering.py │ ├── ml.py │ └── visualisations.py ├── deployment ├── fastapi │ ├── Dockerfile │ ├── app.py │ ├── app_test.py │ ├── loan_catboost_model.cbm │ ├── measure_response.py │ └── requirements.txt └── flask │ ├── Dockerfile │ ├── app.py │ ├── app_test.py │ ├── loan_catboost_model.cbm │ ├── measure_response.py │ └── requirements.txt ├── hp_tuning ├── bv_tradeoff.png └── hp_tuning_rf_gbt.ipynb ├── metaflow └── fraud_email │ ├── email_eda.ipynb │ ├── fradulent_emails.txt │ ├── readme.md │ ├── requirements.txt │ └── utils │ ├── __init__.py │ ├── feature_generation.py │ ├── plots.py │ ├── preprocess.py │ └── read_data.py ├── mlflow ├── mlflow_experiment_tracking.ipynb └── old_notebook.ipynb ├── mlflow_models ├── .DS_Store ├── MLProject ├── model_search.ipynb ├── python_env.yaml ├── search_params.py ├── train_hgbt.py ├── train_rf.py └── utils │ ├── __init__.py │ ├── columns.py │ ├── data_utils.py │ └── eval_utils.py ├── mlflow_project ├── MLproject ├── conda_env.yaml ├── main.py └── steps │ ├── __init__.py │ ├── download_data.py │ ├── preprocess_data.py │ ├── train_final_model.py │ └── tune_model.py ├── polars ├── basics.ipynb ├── data_preparation_pipeline.py ├── data_utils │ ├── __init__.py │ ├── feature_engineering.py │ ├── processing.py │ └── transfomation.py ├── model.ipynb ├── pipe_config.yaml └── time_analysis.ipynb ├── pyspark ├── cleaning.py ├── conda_env.yaml ├── config.yaml ├── feature_engineering.py ├── gcs_config.yaml ├── ml_prep.py ├── pipe.py ├── spark_feature_engineering.ipynb ├── spark_hp_tuning.ipynb ├── spark_intro.ipynb └── tuning.py └── tfdf └── notebooks ├── data_preprocessing.ipynb ├── model_training.ipynb └── plot.html /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/README.md -------------------------------------------------------------------------------- /api_anomaly_project/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/.gitignore -------------------------------------------------------------------------------- /api_anomaly_project/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/Dockerfile -------------------------------------------------------------------------------- /api_anomaly_project/app/app.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /api_anomaly_project/app/measure_response.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /api_anomaly_project/app/ping.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /api_anomaly_project/assets/header.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/assets/header.png -------------------------------------------------------------------------------- /api_anomaly_project/assets/roc_pr_curves.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/assets/roc_pr_curves.png -------------------------------------------------------------------------------- /api_anomaly_project/assets/shap.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/assets/shap.png -------------------------------------------------------------------------------- /api_anomaly_project/assets/thresholds.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/assets/thresholds.png -------------------------------------------------------------------------------- /api_anomaly_project/data/supervised_clean_data.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/data/supervised_clean_data.parquet -------------------------------------------------------------------------------- /api_anomaly_project/data/supervised_clean_data_w_features.parquet: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/data/supervised_clean_data_w_features.parquet -------------------------------------------------------------------------------- /api_anomaly_project/models/hgbt_final.joblib: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/models/hgbt_final.joblib -------------------------------------------------------------------------------- /api_anomaly_project/notebooks/cleaning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/notebooks/cleaning.ipynb -------------------------------------------------------------------------------- /api_anomaly_project/notebooks/eda.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/notebooks/eda.ipynb -------------------------------------------------------------------------------- /api_anomaly_project/notebooks/feature_engineering.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/notebooks/feature_engineering.ipynb -------------------------------------------------------------------------------- /api_anomaly_project/notebooks/htmls/eda.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/notebooks/htmls/eda.html -------------------------------------------------------------------------------- /api_anomaly_project/notebooks/htmls/feature_engineering.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/notebooks/htmls/feature_engineering.html -------------------------------------------------------------------------------- /api_anomaly_project/notebooks/htmls/modelling.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/notebooks/htmls/modelling.html -------------------------------------------------------------------------------- /api_anomaly_project/notebooks/modelling.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/notebooks/modelling.ipynb -------------------------------------------------------------------------------- /api_anomaly_project/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/readme.md -------------------------------------------------------------------------------- /api_anomaly_project/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/requirements.txt -------------------------------------------------------------------------------- /api_anomaly_project/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /api_anomaly_project/utils/cleaning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/utils/cleaning.py -------------------------------------------------------------------------------- /api_anomaly_project/utils/feature_engineering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/utils/feature_engineering.py -------------------------------------------------------------------------------- /api_anomaly_project/utils/ml.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/utils/ml.py -------------------------------------------------------------------------------- /api_anomaly_project/utils/visualisations.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/api_anomaly_project/utils/visualisations.py -------------------------------------------------------------------------------- /deployment/fastapi/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/fastapi/Dockerfile -------------------------------------------------------------------------------- /deployment/fastapi/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/fastapi/app.py -------------------------------------------------------------------------------- /deployment/fastapi/app_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/fastapi/app_test.py -------------------------------------------------------------------------------- /deployment/fastapi/loan_catboost_model.cbm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/fastapi/loan_catboost_model.cbm -------------------------------------------------------------------------------- /deployment/fastapi/measure_response.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/fastapi/measure_response.py -------------------------------------------------------------------------------- /deployment/fastapi/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/fastapi/requirements.txt -------------------------------------------------------------------------------- /deployment/flask/Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/flask/Dockerfile -------------------------------------------------------------------------------- /deployment/flask/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/flask/app.py -------------------------------------------------------------------------------- /deployment/flask/app_test.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/flask/app_test.py -------------------------------------------------------------------------------- /deployment/flask/loan_catboost_model.cbm: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/flask/loan_catboost_model.cbm -------------------------------------------------------------------------------- /deployment/flask/measure_response.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/flask/measure_response.py -------------------------------------------------------------------------------- /deployment/flask/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/deployment/flask/requirements.txt -------------------------------------------------------------------------------- /hp_tuning/bv_tradeoff.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/hp_tuning/bv_tradeoff.png -------------------------------------------------------------------------------- /hp_tuning/hp_tuning_rf_gbt.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/hp_tuning/hp_tuning_rf_gbt.ipynb -------------------------------------------------------------------------------- /metaflow/fraud_email/email_eda.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/email_eda.ipynb -------------------------------------------------------------------------------- /metaflow/fraud_email/fradulent_emails.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/fradulent_emails.txt -------------------------------------------------------------------------------- /metaflow/fraud_email/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/readme.md -------------------------------------------------------------------------------- /metaflow/fraud_email/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/requirements.txt -------------------------------------------------------------------------------- /metaflow/fraud_email/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /metaflow/fraud_email/utils/feature_generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/utils/feature_generation.py -------------------------------------------------------------------------------- /metaflow/fraud_email/utils/plots.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/utils/plots.py -------------------------------------------------------------------------------- /metaflow/fraud_email/utils/preprocess.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/utils/preprocess.py -------------------------------------------------------------------------------- /metaflow/fraud_email/utils/read_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/metaflow/fraud_email/utils/read_data.py -------------------------------------------------------------------------------- /mlflow/mlflow_experiment_tracking.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow/mlflow_experiment_tracking.ipynb -------------------------------------------------------------------------------- /mlflow/old_notebook.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow/old_notebook.ipynb -------------------------------------------------------------------------------- /mlflow_models/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/.DS_Store -------------------------------------------------------------------------------- /mlflow_models/MLProject: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/MLProject -------------------------------------------------------------------------------- /mlflow_models/model_search.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/model_search.ipynb -------------------------------------------------------------------------------- /mlflow_models/python_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/python_env.yaml -------------------------------------------------------------------------------- /mlflow_models/search_params.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/search_params.py -------------------------------------------------------------------------------- /mlflow_models/train_hgbt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/train_hgbt.py -------------------------------------------------------------------------------- /mlflow_models/train_rf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/train_rf.py -------------------------------------------------------------------------------- /mlflow_models/utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mlflow_models/utils/columns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/utils/columns.py -------------------------------------------------------------------------------- /mlflow_models/utils/data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/utils/data_utils.py -------------------------------------------------------------------------------- /mlflow_models/utils/eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_models/utils/eval_utils.py -------------------------------------------------------------------------------- /mlflow_project/MLproject: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_project/MLproject -------------------------------------------------------------------------------- /mlflow_project/conda_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_project/conda_env.yaml -------------------------------------------------------------------------------- /mlflow_project/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_project/main.py -------------------------------------------------------------------------------- /mlflow_project/steps/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mlflow_project/steps/download_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_project/steps/download_data.py -------------------------------------------------------------------------------- /mlflow_project/steps/preprocess_data.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_project/steps/preprocess_data.py -------------------------------------------------------------------------------- /mlflow_project/steps/train_final_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_project/steps/train_final_model.py -------------------------------------------------------------------------------- /mlflow_project/steps/tune_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/mlflow_project/steps/tune_model.py -------------------------------------------------------------------------------- /polars/basics.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/basics.ipynb -------------------------------------------------------------------------------- /polars/data_preparation_pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/data_preparation_pipeline.py -------------------------------------------------------------------------------- /polars/data_utils/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /polars/data_utils/feature_engineering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/data_utils/feature_engineering.py -------------------------------------------------------------------------------- /polars/data_utils/processing.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/data_utils/processing.py -------------------------------------------------------------------------------- /polars/data_utils/transfomation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/data_utils/transfomation.py -------------------------------------------------------------------------------- /polars/model.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/model.ipynb -------------------------------------------------------------------------------- /polars/pipe_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/pipe_config.yaml -------------------------------------------------------------------------------- /polars/time_analysis.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/polars/time_analysis.ipynb -------------------------------------------------------------------------------- /pyspark/cleaning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/cleaning.py -------------------------------------------------------------------------------- /pyspark/conda_env.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/conda_env.yaml -------------------------------------------------------------------------------- /pyspark/config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/config.yaml -------------------------------------------------------------------------------- /pyspark/feature_engineering.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/feature_engineering.py -------------------------------------------------------------------------------- /pyspark/gcs_config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/gcs_config.yaml -------------------------------------------------------------------------------- /pyspark/ml_prep.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/ml_prep.py -------------------------------------------------------------------------------- /pyspark/pipe.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/pipe.py -------------------------------------------------------------------------------- /pyspark/spark_feature_engineering.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/spark_feature_engineering.ipynb -------------------------------------------------------------------------------- /pyspark/spark_hp_tuning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/spark_hp_tuning.ipynb -------------------------------------------------------------------------------- /pyspark/spark_intro.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/spark_intro.ipynb -------------------------------------------------------------------------------- /pyspark/tuning.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/pyspark/tuning.py -------------------------------------------------------------------------------- /tfdf/notebooks/data_preprocessing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/tfdf/notebooks/data_preprocessing.ipynb -------------------------------------------------------------------------------- /tfdf/notebooks/model_training.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/tfdf/notebooks/model_training.ipynb -------------------------------------------------------------------------------- /tfdf/notebooks/plot.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aruberts/tutorials/HEAD/tfdf/notebooks/plot.html --------------------------------------------------------------------------------