├── .gitignore ├── .keepsake ├── checkpoints │ ├── 0eab042e90251b4e187c4b05e5fc148ea55210c121f283bf67c330307956e1ae.tar.gz │ ├── 0f3d3e5908573a819f7c7d646cc6e6995443be89fad8b39f26c7e6b47b243d6c.tar.gz │ ├── 16fff240d2cf4b817bc0d38f0983e9ce4277d34a20a7416553715c72bc19c541.tar.gz │ ├── 4327f1777a5617c6e60a6e54be3b9dbc124f255049e6f205b8cf0061ca5cae33.tar.gz │ ├── 55f4a25d700ba8bf06afcaea3724f64630cbdb2ba57c23b15aa055bb1eab5534.tar.gz │ ├── 5f27590d4624cf295e7973cfb5b3e478601126909856baa1771067f4e82d1143.tar.gz │ ├── 727383bfc0a9ff8b4ef65dac72aca33dc4ad7cb90f6f2661b10e831b0d3c3c83.tar.gz │ ├── c84f79ed4cdad74aa1e36f40e23764b2f71c115dd03fd1eae51372b038467134.tar.gz │ ├── cf9d863ccd0cc459a0ff4da7cf33627c64d65e56ea5353c8395474e1f8281762.tar.gz │ ├── d04857d63f58b7c27fb08799c94f578ec505b431198c4353705258ed522c8b11.tar.gz │ ├── e6409a1403d608bcc3d56f81481eb9925e4d824888e03e4a28397499bb55bae6.tar.gz │ └── eafbd060e0cb802891662e6f7861e3864e03cc7567230cb8cd405e553a181674.tar.gz ├── metadata │ ├── experiments │ │ ├── 232d3ae734e4cf165c2e5e787ede74491d617e9aa69dabb5343627ba2fc3472d.json │ │ ├── 263279a8a311a0fbd6505ee942513c3badda392f0efd6b3b6d0cbbe6f06ddbb6.json │ │ ├── 2c811abdcb363d76004c08323e5e2b4b43424c52ddfcdf1b99cf2cece3c1d9fd.json │ │ ├── 30462fd2ace1bf59670a6bedba5e2d73077aa9d2e11be8a465a95b48c0ed0b7b.json │ │ ├── 36284c77af396b5fbb1eae2cd51db3376d4dc0a9bb3d3796670b7122517c8a3d.json │ │ ├── 4edbe66c1a0f4a7e52d61b30dd6c1be1e29b524d53dede3ce92aa74dc6e0fbae.json │ │ ├── 5b65d1f2aeb50b2bd9745a67071a0a620ba9ce2bb02e0aad47e08819966634e3.json │ │ ├── 628e0293596bbb72eacf1ad0545a74eadc3598f3017b049b23f09d8b9591adc1.json │ │ ├── 78ad688d570ae4ea82282ee1aaf4ad22317627d14843f21651f441671a07320f.json │ │ ├── b159d8339c38a842d02649f3de43d701d881cae53f7126a37e1e24abe5c19446.json │ │ ├── d5da9fecf9b5363890afef50d7a7eb131e510c7e49d6d8bcd5e03989bd554964.json │ │ └── f28b45cf9f3fa6f4f99a3324c9a41b5357576dfe468d5f78b489cef1094ecec2.json │ └── heartbeats │ │ ├── 09aca8b7b73f4ad02df085281f2b3e7caf311e26a825d69497ab91a211c0cea1.json │ │ ├── 1aef50134132ec21236e246486e0f00cbbc8124d2ec79206cc4b53b25230cbfe.json │ │ ├── 43081ce4e5a9d0685384e4cf8b010dfedb8c2fc027fdf5c1d2af3494ad805124.json │ │ ├── 4583c25a4e4ea3cb485340ceec106c39595580ab21a3e66b37f4d83fe2f24638.json │ │ ├── 7bc2e3b967292165ed78fe67ca22fceebc6f5b3dea1109415446cb20ad3894a0.json │ │ ├── be9d03b6b85d2d48ae36559508b1a1a982d1b5ae14d7714533cd197f88ba4691.json │ │ └── f86ce50035181f9772c76aa0c89885803c6e046639e68c8a3c10f32ec8d5600d.json └── repository.json ├── 1-eda.ipynb ├── 2-baseline-model.ipynb ├── 3-baseline-model-validation.ipynb ├── 4-inference-time-test.ipynb ├── 5-optimize-models.ipynb ├── 6-optimized-model-validation.ipynb ├── 7-debounce-inference.ipynb ├── README.md ├── backup ├── 1-eda.py ├── 2-baseline-model.py └── 3-baseline-model_validation.py ├── data ├── transformed │ ├── .gitignore │ ├── 20210529_v2_data_all_100hz.csv │ ├── 20210529_v2_data_all_10hz.csv │ ├── 20210529_v2_data_all_20hz.csv │ ├── 20210529_v2_data_all_25hz.csv │ └── 20210529_v2_data_all_50hz.csv └── validation │ ├── .gitignore │ ├── move_circle_20210522_1.csv │ ├── move_x_20210522_1.csv │ └── move_y_20210522_1.csv ├── eda_utils.py ├── keepsake.yaml ├── models ├── baseline │ ├── base │ │ ├── decision_tree │ │ │ ├── decision_tree_100hz.py │ │ │ ├── decision_tree_10hz.py │ │ │ ├── decision_tree_20hz.py │ │ │ ├── decision_tree_25hz.py │ │ │ └── decision_tree_50hz.py │ │ ├── logistic_regression │ │ │ ├── logistic_regression_100hz.py │ │ │ ├── logistic_regression_10hz.py │ │ │ ├── logistic_regression_20hz.py │ │ │ ├── logistic_regression_25hz.py │ │ │ └── logistic_regression_50hz.py │ │ ├── random_forest │ │ │ ├── random_forest_100hz.py │ │ │ ├── random_forest_10hz.py │ │ │ ├── random_forest_20hz.py │ │ │ ├── random_forest_25hz.py │ │ │ └── random_forest_50hz.py │ │ └── svc │ │ │ ├── svc_100hz.py │ │ │ ├── svc_10hz.py │ │ │ ├── svc_20hz.py │ │ │ ├── svc_25hz.py │ │ │ └── svc_50hz.py │ ├── centered │ │ ├── decision_tree │ │ │ ├── decision_tree_100hz.py │ │ │ ├── decision_tree_10hz.py │ │ │ ├── decision_tree_20hz.py │ │ │ ├── decision_tree_25hz.py │ │ │ └── decision_tree_50hz.py │ │ ├── logistic_regression │ │ │ ├── logistic_regression_100hz.py │ │ │ ├── logistic_regression_10hz.py │ │ │ ├── logistic_regression_20hz.py │ │ │ ├── logistic_regression_25hz.py │ │ │ └── logistic_regression_50hz.py │ │ ├── random_forest │ │ │ ├── random_forest_100hz.py │ │ │ ├── random_forest_10hz.py │ │ │ ├── random_forest_20hz.py │ │ │ ├── random_forest_25hz.py │ │ │ └── random_forest_50hz.py │ │ └── svc │ │ │ ├── svc_100hz.py │ │ │ ├── svc_10hz.py │ │ │ ├── svc_20hz.py │ │ │ ├── svc_25hz.py │ │ │ └── svc_50hz.py │ ├── centered_aug │ │ ├── decision_tree │ │ │ ├── decision_tree_100hz.py │ │ │ ├── decision_tree_10hz.py │ │ │ ├── decision_tree_20hz.py │ │ │ ├── decision_tree_25hz.py │ │ │ └── decision_tree_50hz.py │ │ ├── logistic_regression │ │ │ ├── logistic_regression_100hz.py │ │ │ ├── logistic_regression_10hz.py │ │ │ ├── logistic_regression_20hz.py │ │ │ ├── logistic_regression_25hz.py │ │ │ └── logistic_regression_50hz.py │ │ ├── random_forest │ │ │ ├── random_forest_100hz.py │ │ │ ├── random_forest_10hz.py │ │ │ ├── random_forest_20hz.py │ │ │ ├── random_forest_25hz.py │ │ │ └── random_forest_50hz.py │ │ └── svc │ │ │ ├── svc_100hz.py │ │ │ ├── svc_10hz.py │ │ │ ├── svc_20hz.py │ │ │ ├── svc_25hz.py │ │ │ └── svc_50hz.py │ ├── centered_smote │ │ ├── decision_tree │ │ │ ├── decision_tree_100hz.py │ │ │ ├── decision_tree_10hz.py │ │ │ ├── decision_tree_20hz.py │ │ │ ├── decision_tree_25hz.py │ │ │ └── decision_tree_50hz.py │ │ ├── logistic_regression │ │ │ ├── logistic_regression_100hz.py │ │ │ ├── logistic_regression_10hz.py │ │ │ ├── logistic_regression_20hz.py │ │ │ ├── logistic_regression_25hz.py │ │ │ └── logistic_regression_50hz.py │ │ ├── random_forest │ │ │ ├── random_forest_100hz.py │ │ │ ├── random_forest_10hz.py │ │ │ ├── random_forest_20hz.py │ │ │ ├── random_forest_25hz.py │ │ │ └── random_forest_50hz.py │ │ └── svc │ │ │ ├── svc_100hz.py │ │ │ ├── svc_10hz.py │ │ │ ├── svc_20hz.py │ │ │ ├── svc_25hz.py │ │ │ └── svc_50hz.py │ └── end │ │ ├── decision_tree │ │ ├── decision_tree_100hz.py │ │ ├── decision_tree_10hz.py │ │ ├── decision_tree_20hz.py │ │ ├── decision_tree_25hz.py │ │ └── decision_tree_50hz.py │ │ ├── logistic_regression │ │ ├── logistic_regression_100hz.py │ │ ├── logistic_regression_10hz.py │ │ ├── logistic_regression_20hz.py │ │ ├── logistic_regression_25hz.py │ │ └── logistic_regression_50hz.py │ │ ├── random_forest │ │ ├── random_forest_100hz.py │ │ ├── random_forest_10hz.py │ │ ├── random_forest_20hz.py │ │ ├── random_forest_25hz.py │ │ └── random_forest_50hz.py │ │ └── svc │ │ ├── svc_100hz.py │ │ ├── svc_10hz.py │ │ ├── svc_20hz.py │ │ ├── svc_25hz.py │ │ └── svc_50hz.py ├── inf_time_test │ └── random_forest │ │ ├── random_forest_10est_100hz.py │ │ ├── random_forest_10est_25hz.py │ │ ├── random_forest_3est_100hz.py │ │ ├── random_forest_3est_25hz.py │ │ ├── random_forest_4est_100hz.py │ │ ├── random_forest_4est_25hz.py │ │ ├── random_forest_5est_100hz.py │ │ └── random_forest_5est_25hz.py └── optimized │ └── base │ ├── decision_tree │ ├── decision_tree_30462fd.py │ ├── decision_tree_36284c7.py │ └── decision_tree_4edbe66.py │ └── random_forest │ ├── random_forest_232d3ae.py │ ├── random_forest_263279a.py │ ├── random_forest_2c811ab.py │ ├── random_forest_5b65d1f.py │ ├── random_forest_628e029.py │ ├── random_forest_78ad688.py │ ├── random_forest_b159d83.py │ ├── random_forest_d5da9fe.py │ └── random_forest_f28b45c.py ├── output ├── baseline_base_dataset_results.csv ├── baseline_model_accuracy.csv ├── baseline_model_inference_time.csv ├── baseline_results │ ├── baseline_centered_aug_dataset_results.csv │ ├── baseline_centered_dataset_results.csv │ ├── baseline_centered_smote_dataset_results.csv │ ├── baseline_end_dataset_results.csv │ ├── baseline_model_accuracy.csv │ └── baseline_model_inference_time.csv ├── inference_time_rf_estimators_50hz.csv └── validation │ ├── val_res_base_circle.csv │ ├── val_res_base_x.csv │ ├── val_res_base_y.csv │ ├── val_res_centered_aug_circle.csv │ ├── val_res_centered_aug_x.csv │ ├── val_res_centered_aug_y.csv │ ├── val_res_centered_circle.csv │ ├── val_res_centered_smote_circle.csv │ ├── val_res_centered_smote_x.csv │ ├── val_res_centered_smote_y.csv │ ├── val_res_centered_x.csv │ ├── val_res_centered_y.csv │ ├── val_res_end_circle.csv │ ├── val_res_end_x.csv │ └── val_res_end_y.csv ├── requirements.txt └── validation_utils.py /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # macOS 7 | .DS_Store 8 | 9 | # ignore data 10 | 11 | 12 | # C extensions 13 | *.so 14 | 15 | # vscode 16 | .vscode 17 | 18 | # Distribution / packaging 19 | .Python 20 | build/ 21 | develop-eggs/ 22 | dist/ 23 | downloads/ 24 | eggs/ 25 | .eggs/ 26 | lib/ 27 | lib64/ 28 | parts/ 29 | sdist/ 30 | var/ 31 | wheels/ 32 | pip-wheel-metadata/ 33 | share/python-wheels/ 34 | *.egg-info/ 35 | .installed.cfg 36 | *.egg 37 | MANIFEST 38 | 39 | # PyInstaller 40 | # Usually these files are written by a python script from a template 41 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 42 | *.manifest 43 | *.spec 44 | 45 | # Installer logs 46 | pip-log.txt 47 | pip-delete-this-directory.txt 48 | 49 | # Unit test / coverage reports 50 | htmlcov/ 51 | .tox/ 52 | .nox/ 53 | .coverage 54 | .coverage.* 55 | .cache 56 | nosetests.xml 57 | coverage.xml 58 | *.cover 59 | *.py,cover 60 | .hypothesis/ 61 | .pytest_cache/ 62 | 63 | # Translations 64 | *.mo 65 | *.pot 66 | 67 | # Django stuff: 68 | *.log 69 | local_settings.py 70 | db.sqlite3 71 | db.sqlite3-journal 72 | 73 | # Flask stuff: 74 | instance/ 75 | .webassets-cache 76 | 77 | # Scrapy stuff: 78 | .scrapy 79 | 80 | # Sphinx documentation 81 | docs/_build/ 82 | 83 | # PyBuilder 84 | target/ 85 | 86 | # Jupyter Notebook 87 | .ipynb_checkpoints 88 | 89 | # IPython 90 | profile_default/ 91 | ipython_config.py 92 | 93 | # pyenv 94 | .python-version 95 | 96 | # pipenv 97 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 98 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 99 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 100 | # install all needed dependencies. 101 | #Pipfile.lock 102 | 103 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow 104 | __pypackages__/ 105 | 106 | # Celery stuff 107 | celerybeat-schedule 108 | celerybeat.pid 109 | 110 | # SageMath parsed files 111 | *.sage.py 112 | 113 | # Environments 114 | .env 115 | .venv 116 | env/ 117 | venv/ 118 | ENV/ 119 | env.bak/ 120 | venv.bak/ 121 | 122 | # Spyder project settings 123 | .spyderproject 124 | .spyproject 125 | 126 | # Rope project settings 127 | .ropeproject 128 | 129 | # mkdocs documentation 130 | /site 131 | 132 | # mypy 133 | .mypy_cache/ 134 | .dmypy.json 135 | dmypy.json 136 | 137 | # Pyre type checker 138 | .pyre/ 139 | -------------------------------------------------------------------------------- /.keepsake/checkpoints/0eab042e90251b4e187c4b05e5fc148ea55210c121f283bf67c330307956e1ae.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/0eab042e90251b4e187c4b05e5fc148ea55210c121f283bf67c330307956e1ae.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/0f3d3e5908573a819f7c7d646cc6e6995443be89fad8b39f26c7e6b47b243d6c.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/0f3d3e5908573a819f7c7d646cc6e6995443be89fad8b39f26c7e6b47b243d6c.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/16fff240d2cf4b817bc0d38f0983e9ce4277d34a20a7416553715c72bc19c541.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/16fff240d2cf4b817bc0d38f0983e9ce4277d34a20a7416553715c72bc19c541.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/4327f1777a5617c6e60a6e54be3b9dbc124f255049e6f205b8cf0061ca5cae33.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/4327f1777a5617c6e60a6e54be3b9dbc124f255049e6f205b8cf0061ca5cae33.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/55f4a25d700ba8bf06afcaea3724f64630cbdb2ba57c23b15aa055bb1eab5534.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/55f4a25d700ba8bf06afcaea3724f64630cbdb2ba57c23b15aa055bb1eab5534.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/5f27590d4624cf295e7973cfb5b3e478601126909856baa1771067f4e82d1143.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/5f27590d4624cf295e7973cfb5b3e478601126909856baa1771067f4e82d1143.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/727383bfc0a9ff8b4ef65dac72aca33dc4ad7cb90f6f2661b10e831b0d3c3c83.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/727383bfc0a9ff8b4ef65dac72aca33dc4ad7cb90f6f2661b10e831b0d3c3c83.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/c84f79ed4cdad74aa1e36f40e23764b2f71c115dd03fd1eae51372b038467134.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/c84f79ed4cdad74aa1e36f40e23764b2f71c115dd03fd1eae51372b038467134.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/cf9d863ccd0cc459a0ff4da7cf33627c64d65e56ea5353c8395474e1f8281762.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/cf9d863ccd0cc459a0ff4da7cf33627c64d65e56ea5353c8395474e1f8281762.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/d04857d63f58b7c27fb08799c94f578ec505b431198c4353705258ed522c8b11.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/d04857d63f58b7c27fb08799c94f578ec505b431198c4353705258ed522c8b11.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/e6409a1403d608bcc3d56f81481eb9925e4d824888e03e4a28397499bb55bae6.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/e6409a1403d608bcc3d56f81481eb9925e4d824888e03e4a28397499bb55bae6.tar.gz -------------------------------------------------------------------------------- /.keepsake/checkpoints/eafbd060e0cb802891662e6f7861e3864e03cc7567230cb8cd405e553a181674.tar.gz: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/.keepsake/checkpoints/eafbd060e0cb802891662e6f7861e3864e03cc7567230cb8cd405e553a181674.tar.gz -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/232d3ae734e4cf165c2e5e787ede74491d617e9aa69dabb5343627ba2fc3472d.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "232d3ae734e4cf165c2e5e787ede74491d617e9aa69dabb5343627ba2fc3472d", 3 | "created": "2021-06-11T16:36:12.643836021Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 5, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_z" 16 | ], 17 | "hz": 50, 18 | "model": "random_forest", 19 | "n_estimators": 6, 20 | "other_params": "default", 21 | "precision": 1, 22 | "quantization": null, 23 | "recall": 1 24 | }, 25 | "host": "", 26 | "user": "tk", 27 | "config": { 28 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 29 | "storage": "" 30 | }, 31 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 32 | "path": "", 33 | "python_version": "3.8.3", 34 | "python_packages": { 35 | "appnope": "0.1.2", 36 | "backcall": "0.2.0", 37 | "cffi": "1.14.5", 38 | "colorama": "0.4.4", 39 | "cycler": "0.10.0", 40 | "decorator": "4.4.2", 41 | "ipykernel": "5.3.4", 42 | "ipywidgets": "7.6.3", 43 | "jedi": "0.17.0", 44 | "joblib": "1.0.1", 45 | "keepsake": "0.4.2", 46 | "kiwisolver": "1.3.1", 47 | "m2cgen": "0.9.0", 48 | "matplotlib": "3.3.4", 49 | "numpy": "1.20.1", 50 | "pandas": "1.2.3", 51 | "parso": "0.8.1", 52 | "pexpect": "4.8.0", 53 | "pickleshare": "0.7.5", 54 | "psutil": "5.8.0", 55 | "ptyprocess": "0.7.0", 56 | "pygments": "2.8.1", 57 | "pyparsing": "2.4.7", 58 | "pytz": "2021.1", 59 | "scipy": "1.6.1", 60 | "seaborn": "0.10.1", 61 | "six": "1.15.0", 62 | "statsmodels": "0.12.2", 63 | "tornado": "6.1", 64 | "traitlets": "5.0.5", 65 | "wcwidth": "0.2.5" 66 | }, 67 | "checkpoints": [ 68 | { 69 | "id": "0eab042e90251b4e187c4b05e5fc148ea55210c121f283bf67c330307956e1ae", 70 | "created": "2021-06-11T16:36:12.660695076Z", 71 | "metrics": { 72 | "accurracy": 1, 73 | "f1": 1, 74 | "precision": 1, 75 | "recall": 1 76 | }, 77 | "step": 0, 78 | "path": "models/optimized/base/random_forest/random_forest_232d3ae.py", 79 | "primary_metric": { 80 | "name": "recall", 81 | "goal": "maximize" 82 | } 83 | } 84 | ], 85 | "keepsake_version": "0.4.2" 86 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/263279a8a311a0fbd6505ee942513c3badda392f0efd6b3b6d0cbbe6f06ddbb6.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "263279a8a311a0fbd6505ee942513c3badda392f0efd6b3b6d0cbbe6f06ddbb6", 3 | "created": "2021-06-11T16:36:10.254252911Z", 4 | "params": { 5 | "accuracy": 0.9875, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 0.9880893300248139, 9 | "feature_count": 6, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_y", 16 | "gyro_z" 17 | ], 18 | "hz": 25, 19 | "model": "random_forest", 20 | "n_estimators": 6, 21 | "other_params": "default", 22 | "precision": 0.984375, 23 | "quantization": null, 24 | "recall": 0.9924242424242424 25 | }, 26 | "host": "", 27 | "user": "tk", 28 | "config": { 29 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 30 | "storage": "" 31 | }, 32 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 33 | "path": "", 34 | "python_version": "3.8.3", 35 | "python_packages": { 36 | "appnope": "0.1.2", 37 | "backcall": "0.2.0", 38 | "cffi": "1.14.5", 39 | "colorama": "0.4.4", 40 | "cycler": "0.10.0", 41 | "decorator": "4.4.2", 42 | "ipykernel": "5.3.4", 43 | "ipywidgets": "7.6.3", 44 | "jedi": "0.17.0", 45 | "joblib": "1.0.1", 46 | "keepsake": "0.4.2", 47 | "kiwisolver": "1.3.1", 48 | "m2cgen": "0.9.0", 49 | "matplotlib": "3.3.4", 50 | "numpy": "1.20.1", 51 | "pandas": "1.2.3", 52 | "parso": "0.8.1", 53 | "pexpect": "4.8.0", 54 | "pickleshare": "0.7.5", 55 | "psutil": "5.8.0", 56 | "ptyprocess": "0.7.0", 57 | "pygments": "2.8.1", 58 | "pyparsing": "2.4.7", 59 | "pytz": "2021.1", 60 | "scipy": "1.6.1", 61 | "seaborn": "0.10.1", 62 | "six": "1.15.0", 63 | "statsmodels": "0.12.2", 64 | "tornado": "6.1", 65 | "traitlets": "5.0.5", 66 | "wcwidth": "0.2.5" 67 | }, 68 | "checkpoints": [ 69 | { 70 | "id": "0f3d3e5908573a819f7c7d646cc6e6995443be89fad8b39f26c7e6b47b243d6c", 71 | "created": "2021-06-11T16:36:10.270921946Z", 72 | "metrics": { 73 | "accurracy": 0.9875, 74 | "f1": 0.9880893300248139, 75 | "precision": 0.984375, 76 | "recall": 0.9924242424242424 77 | }, 78 | "step": 0, 79 | "path": "models/optimized/base/random_forest/random_forest_263279a.py", 80 | "primary_metric": { 81 | "name": "recall", 82 | "goal": "maximize" 83 | } 84 | } 85 | ], 86 | "keepsake_version": "0.4.2" 87 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/2c811abdcb363d76004c08323e5e2b4b43424c52ddfcdf1b99cf2cece3c1d9fd.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "2c811abdcb363d76004c08323e5e2b4b43424c52ddfcdf1b99cf2cece3c1d9fd", 3 | "created": "2021-06-11T16:36:07.63767004Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 5, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_z" 16 | ], 17 | "hz": 20, 18 | "model": "random_forest", 19 | "n_estimators": 4, 20 | "other_params": "default", 21 | "precision": 1, 22 | "quantization": null, 23 | "recall": 1 24 | }, 25 | "host": "", 26 | "user": "tk", 27 | "config": { 28 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 29 | "storage": "" 30 | }, 31 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 32 | "path": "", 33 | "python_version": "3.8.3", 34 | "python_packages": { 35 | "appnope": "0.1.2", 36 | "backcall": "0.2.0", 37 | "cffi": "1.14.5", 38 | "colorama": "0.4.4", 39 | "cycler": "0.10.0", 40 | "decorator": "4.4.2", 41 | "ipykernel": "5.3.4", 42 | "ipywidgets": "7.6.3", 43 | "jedi": "0.17.0", 44 | "joblib": "1.0.1", 45 | "keepsake": "0.4.2", 46 | "kiwisolver": "1.3.1", 47 | "m2cgen": "0.9.0", 48 | "matplotlib": "3.3.4", 49 | "numpy": "1.20.1", 50 | "pandas": "1.2.3", 51 | "parso": "0.8.1", 52 | "pexpect": "4.8.0", 53 | "pickleshare": "0.7.5", 54 | "psutil": "5.8.0", 55 | "ptyprocess": "0.7.0", 56 | "pygments": "2.8.1", 57 | "pyparsing": "2.4.7", 58 | "pytz": "2021.1", 59 | "scipy": "1.6.1", 60 | "seaborn": "0.10.1", 61 | "six": "1.15.0", 62 | "statsmodels": "0.12.2", 63 | "tornado": "6.1", 64 | "traitlets": "5.0.5", 65 | "wcwidth": "0.2.5" 66 | }, 67 | "checkpoints": [ 68 | { 69 | "id": "c84f79ed4cdad74aa1e36f40e23764b2f71c115dd03fd1eae51372b038467134", 70 | "created": "2021-06-11T16:36:07.654140949Z", 71 | "metrics": { 72 | "accurracy": 1, 73 | "f1": 1, 74 | "precision": 1, 75 | "recall": 1 76 | }, 77 | "step": 0, 78 | "path": "models/optimized/base/random_forest/random_forest_2c811ab.py", 79 | "primary_metric": { 80 | "name": "recall", 81 | "goal": "maximize" 82 | } 83 | } 84 | ], 85 | "keepsake_version": "0.4.2" 86 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/30462fd2ace1bf59670a6bedba5e2d73077aa9d2e11be8a465a95b48c0ed0b7b.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "30462fd2ace1bf59670a6bedba5e2d73077aa9d2e11be8a465a95b48c0ed0b7b", 3 | "created": "2021-06-11T16:36:14.962589025Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 4, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x" 15 | ], 16 | "hz": 25, 17 | "model": "decision_tree", 18 | "n_estimators": null, 19 | "other_params": "default", 20 | "precision": 1, 21 | "quantization": null, 22 | "recall": 1 23 | }, 24 | "host": "", 25 | "user": "tk", 26 | "config": { 27 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 28 | "storage": "" 29 | }, 30 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 31 | "path": "", 32 | "python_version": "3.8.3", 33 | "python_packages": { 34 | "appnope": "0.1.2", 35 | "backcall": "0.2.0", 36 | "cffi": "1.14.5", 37 | "colorama": "0.4.4", 38 | "cycler": "0.10.0", 39 | "decorator": "4.4.2", 40 | "ipykernel": "5.3.4", 41 | "ipywidgets": "7.6.3", 42 | "jedi": "0.17.0", 43 | "joblib": "1.0.1", 44 | "keepsake": "0.4.2", 45 | "kiwisolver": "1.3.1", 46 | "m2cgen": "0.9.0", 47 | "matplotlib": "3.3.4", 48 | "numpy": "1.20.1", 49 | "pandas": "1.2.3", 50 | "parso": "0.8.1", 51 | "pexpect": "4.8.0", 52 | "pickleshare": "0.7.5", 53 | "psutil": "5.8.0", 54 | "ptyprocess": "0.7.0", 55 | "pygments": "2.8.1", 56 | "pyparsing": "2.4.7", 57 | "pytz": "2021.1", 58 | "scipy": "1.6.1", 59 | "seaborn": "0.10.1", 60 | "six": "1.15.0", 61 | "statsmodels": "0.12.2", 62 | "tornado": "6.1", 63 | "traitlets": "5.0.5", 64 | "wcwidth": "0.2.5" 65 | }, 66 | "checkpoints": [ 67 | { 68 | "id": "eafbd060e0cb802891662e6f7861e3864e03cc7567230cb8cd405e553a181674", 69 | "created": "2021-06-11T16:36:14.971193075Z", 70 | "metrics": { 71 | "accurracy": 1, 72 | "f1": 1, 73 | "precision": 1, 74 | "recall": 1 75 | }, 76 | "step": 0, 77 | "path": "models/optimized/base/decision_tree/decision_tree_30462fd.py", 78 | "primary_metric": { 79 | "name": "recall", 80 | "goal": "maximize" 81 | } 82 | } 83 | ], 84 | "keepsake_version": "0.4.2" 85 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/36284c77af396b5fbb1eae2cd51db3376d4dc0a9bb3d3796670b7122517c8a3d.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "36284c77af396b5fbb1eae2cd51db3376d4dc0a9bb3d3796670b7122517c8a3d", 3 | "created": "2021-06-11T16:36:16.018637896Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 4, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_y" 15 | ], 16 | "hz": 25, 17 | "model": "decision_tree", 18 | "n_estimators": null, 19 | "other_params": "default", 20 | "precision": 1, 21 | "quantization": null, 22 | "recall": 1 23 | }, 24 | "host": "", 25 | "user": "tk", 26 | "config": { 27 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 28 | "storage": "" 29 | }, 30 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 31 | "path": "", 32 | "python_version": "3.8.3", 33 | "python_packages": { 34 | "appnope": "0.1.2", 35 | "backcall": "0.2.0", 36 | "cffi": "1.14.5", 37 | "colorama": "0.4.4", 38 | "cycler": "0.10.0", 39 | "decorator": "4.4.2", 40 | "ipykernel": "5.3.4", 41 | "ipywidgets": "7.6.3", 42 | "jedi": "0.17.0", 43 | "joblib": "1.0.1", 44 | "keepsake": "0.4.2", 45 | "kiwisolver": "1.3.1", 46 | "m2cgen": "0.9.0", 47 | "matplotlib": "3.3.4", 48 | "numpy": "1.20.1", 49 | "pandas": "1.2.3", 50 | "parso": "0.8.1", 51 | "pexpect": "4.8.0", 52 | "pickleshare": "0.7.5", 53 | "psutil": "5.8.0", 54 | "ptyprocess": "0.7.0", 55 | "pygments": "2.8.1", 56 | "pyparsing": "2.4.7", 57 | "pytz": "2021.1", 58 | "scipy": "1.6.1", 59 | "seaborn": "0.10.1", 60 | "six": "1.15.0", 61 | "statsmodels": "0.12.2", 62 | "tornado": "6.1", 63 | "traitlets": "5.0.5", 64 | "wcwidth": "0.2.5" 65 | }, 66 | "checkpoints": [ 67 | { 68 | "id": "727383bfc0a9ff8b4ef65dac72aca33dc4ad7cb90f6f2661b10e831b0d3c3c83", 69 | "created": "2021-06-11T16:36:16.026283026Z", 70 | "metrics": { 71 | "accurracy": 1, 72 | "f1": 1, 73 | "precision": 1, 74 | "recall": 1 75 | }, 76 | "step": 0, 77 | "path": "models/optimized/base/decision_tree/decision_tree_36284c7.py", 78 | "primary_metric": { 79 | "name": "recall", 80 | "goal": "maximize" 81 | } 82 | } 83 | ], 84 | "keepsake_version": "0.4.2" 85 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/4edbe66c1a0f4a7e52d61b30dd6c1be1e29b524d53dede3ce92aa74dc6e0fbae.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "4edbe66c1a0f4a7e52d61b30dd6c1be1e29b524d53dede3ce92aa74dc6e0fbae", 3 | "created": "2021-06-11T16:36:17.069444895Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 4, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_z" 15 | ], 16 | "hz": 25, 17 | "model": "decision_tree", 18 | "n_estimators": null, 19 | "other_params": "default", 20 | "precision": 1, 21 | "quantization": null, 22 | "recall": 1 23 | }, 24 | "host": "", 25 | "user": "tk", 26 | "config": { 27 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 28 | "storage": "" 29 | }, 30 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 31 | "path": "", 32 | "python_version": "3.8.3", 33 | "python_packages": { 34 | "appnope": "0.1.2", 35 | "backcall": "0.2.0", 36 | "cffi": "1.14.5", 37 | "colorama": "0.4.4", 38 | "cycler": "0.10.0", 39 | "decorator": "4.4.2", 40 | "ipykernel": "5.3.4", 41 | "ipywidgets": "7.6.3", 42 | "jedi": "0.17.0", 43 | "joblib": "1.0.1", 44 | "keepsake": "0.4.2", 45 | "kiwisolver": "1.3.1", 46 | "m2cgen": "0.9.0", 47 | "matplotlib": "3.3.4", 48 | "numpy": "1.20.1", 49 | "pandas": "1.2.3", 50 | "parso": "0.8.1", 51 | "pexpect": "4.8.0", 52 | "pickleshare": "0.7.5", 53 | "psutil": "5.8.0", 54 | "ptyprocess": "0.7.0", 55 | "pygments": "2.8.1", 56 | "pyparsing": "2.4.7", 57 | "pytz": "2021.1", 58 | "scipy": "1.6.1", 59 | "seaborn": "0.10.1", 60 | "six": "1.15.0", 61 | "statsmodels": "0.12.2", 62 | "tornado": "6.1", 63 | "traitlets": "5.0.5", 64 | "wcwidth": "0.2.5" 65 | }, 66 | "checkpoints": [ 67 | { 68 | "id": "55f4a25d700ba8bf06afcaea3724f64630cbdb2ba57c23b15aa055bb1eab5534", 69 | "created": "2021-06-11T16:36:17.079246998Z", 70 | "metrics": { 71 | "accurracy": 1, 72 | "f1": 1, 73 | "precision": 1, 74 | "recall": 1 75 | }, 76 | "step": 0, 77 | "path": "models/optimized/base/decision_tree/decision_tree_4edbe66.py", 78 | "primary_metric": { 79 | "name": "recall", 80 | "goal": "maximize" 81 | } 82 | } 83 | ], 84 | "keepsake_version": "0.4.2" 85 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/5b65d1f2aeb50b2bd9745a67071a0a620ba9ce2bb02e0aad47e08819966634e3.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "5b65d1f2aeb50b2bd9745a67071a0a620ba9ce2bb02e0aad47e08819966634e3", 3 | "created": "2021-06-11T16:36:06.563545942Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 5, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_y" 16 | ], 17 | "hz": 20, 18 | "model": "random_forest", 19 | "n_estimators": 6, 20 | "other_params": "default", 21 | "precision": 1, 22 | "quantization": null, 23 | "recall": 1 24 | }, 25 | "host": "", 26 | "user": "tk", 27 | "config": { 28 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 29 | "storage": "" 30 | }, 31 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 32 | "path": "", 33 | "python_version": "3.8.3", 34 | "python_packages": { 35 | "appnope": "0.1.2", 36 | "backcall": "0.2.0", 37 | "cffi": "1.14.5", 38 | "colorama": "0.4.4", 39 | "cycler": "0.10.0", 40 | "decorator": "4.4.2", 41 | "ipykernel": "5.3.4", 42 | "ipywidgets": "7.6.3", 43 | "jedi": "0.17.0", 44 | "joblib": "1.0.1", 45 | "keepsake": "0.4.2", 46 | "kiwisolver": "1.3.1", 47 | "m2cgen": "0.9.0", 48 | "matplotlib": "3.3.4", 49 | "numpy": "1.20.1", 50 | "pandas": "1.2.3", 51 | "parso": "0.8.1", 52 | "pexpect": "4.8.0", 53 | "pickleshare": "0.7.5", 54 | "psutil": "5.8.0", 55 | "ptyprocess": "0.7.0", 56 | "pygments": "2.8.1", 57 | "pyparsing": "2.4.7", 58 | "pytz": "2021.1", 59 | "scipy": "1.6.1", 60 | "seaborn": "0.10.1", 61 | "six": "1.15.0", 62 | "statsmodels": "0.12.2", 63 | "tornado": "6.1", 64 | "traitlets": "5.0.5", 65 | "wcwidth": "0.2.5" 66 | }, 67 | "checkpoints": [ 68 | { 69 | "id": "16fff240d2cf4b817bc0d38f0983e9ce4277d34a20a7416553715c72bc19c541", 70 | "created": "2021-06-11T16:36:06.579153061Z", 71 | "metrics": { 72 | "accurracy": 1, 73 | "f1": 1, 74 | "precision": 1, 75 | "recall": 1 76 | }, 77 | "step": 0, 78 | "path": "models/optimized/base/random_forest/random_forest_5b65d1f.py", 79 | "primary_metric": { 80 | "name": "recall", 81 | "goal": "maximize" 82 | } 83 | } 84 | ], 85 | "keepsake_version": "0.4.2" 86 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/628e0293596bbb72eacf1ad0545a74eadc3598f3017b049b23f09d8b9591adc1.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "628e0293596bbb72eacf1ad0545a74eadc3598f3017b049b23f09d8b9591adc1", 3 | "created": "2021-06-11T16:36:11.523511887Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 5, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_y" 16 | ], 17 | "hz": 50, 18 | "model": "random_forest", 19 | "n_estimators": 6, 20 | "other_params": "default", 21 | "precision": 1, 22 | "quantization": null, 23 | "recall": 1 24 | }, 25 | "host": "", 26 | "user": "tk", 27 | "config": { 28 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 29 | "storage": "" 30 | }, 31 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 32 | "path": "", 33 | "python_version": "3.8.3", 34 | "python_packages": { 35 | "appnope": "0.1.2", 36 | "backcall": "0.2.0", 37 | "cffi": "1.14.5", 38 | "colorama": "0.4.4", 39 | "cycler": "0.10.0", 40 | "decorator": "4.4.2", 41 | "ipykernel": "5.3.4", 42 | "ipywidgets": "7.6.3", 43 | "jedi": "0.17.0", 44 | "joblib": "1.0.1", 45 | "keepsake": "0.4.2", 46 | "kiwisolver": "1.3.1", 47 | "m2cgen": "0.9.0", 48 | "matplotlib": "3.3.4", 49 | "numpy": "1.20.1", 50 | "pandas": "1.2.3", 51 | "parso": "0.8.1", 52 | "pexpect": "4.8.0", 53 | "pickleshare": "0.7.5", 54 | "psutil": "5.8.0", 55 | "ptyprocess": "0.7.0", 56 | "pygments": "2.8.1", 57 | "pyparsing": "2.4.7", 58 | "pytz": "2021.1", 59 | "scipy": "1.6.1", 60 | "seaborn": "0.10.1", 61 | "six": "1.15.0", 62 | "statsmodels": "0.12.2", 63 | "tornado": "6.1", 64 | "traitlets": "5.0.5", 65 | "wcwidth": "0.2.5" 66 | }, 67 | "checkpoints": [ 68 | { 69 | "id": "d04857d63f58b7c27fb08799c94f578ec505b431198c4353705258ed522c8b11", 70 | "created": "2021-06-11T16:36:11.538644075Z", 71 | "metrics": { 72 | "accurracy": 1, 73 | "f1": 1, 74 | "precision": 1, 75 | "recall": 1 76 | }, 77 | "step": 0, 78 | "path": "models/optimized/base/random_forest/random_forest_628e029.py", 79 | "primary_metric": { 80 | "name": "recall", 81 | "goal": "maximize" 82 | } 83 | } 84 | ], 85 | "keepsake_version": "0.4.2" 86 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/78ad688d570ae4ea82282ee1aaf4ad22317627d14843f21651f441671a07320f.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "78ad688d570ae4ea82282ee1aaf4ad22317627d14843f21651f441671a07320f", 3 | "created": "2021-06-11T16:36:04.393606901Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 5, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_y" 16 | ], 17 | "hz": 20, 18 | "model": "random_forest", 19 | "n_estimators": 4, 20 | "other_params": "default", 21 | "precision": 1, 22 | "quantization": null, 23 | "recall": 1 24 | }, 25 | "host": "", 26 | "user": "tk", 27 | "config": { 28 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 29 | "storage": "" 30 | }, 31 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 32 | "path": "", 33 | "python_version": "3.8.3", 34 | "python_packages": { 35 | "appnope": "0.1.2", 36 | "backcall": "0.2.0", 37 | "cffi": "1.14.5", 38 | "colorama": "0.4.4", 39 | "cycler": "0.10.0", 40 | "decorator": "4.4.2", 41 | "ipykernel": "5.3.4", 42 | "ipywidgets": "7.6.3", 43 | "jedi": "0.17.0", 44 | "joblib": "1.0.1", 45 | "keepsake": "0.4.2", 46 | "kiwisolver": "1.3.1", 47 | "matplotlib": "3.3.4", 48 | "numpy": "1.20.1", 49 | "pandas": "1.2.3", 50 | "parso": "0.8.1", 51 | "pexpect": "4.8.0", 52 | "pickleshare": "0.7.5", 53 | "psutil": "5.8.0", 54 | "ptyprocess": "0.7.0", 55 | "pygments": "2.8.1", 56 | "pyparsing": "2.4.7", 57 | "pytz": "2021.1", 58 | "scipy": "1.6.1", 59 | "seaborn": "0.10.1", 60 | "six": "1.15.0", 61 | "statsmodels": "0.12.2", 62 | "tornado": "6.1", 63 | "traitlets": "5.0.5", 64 | "wcwidth": "0.2.5" 65 | }, 66 | "checkpoints": [ 67 | { 68 | "id": "cf9d863ccd0cc459a0ff4da7cf33627c64d65e56ea5353c8395474e1f8281762", 69 | "created": "2021-06-11T16:36:04.447483063Z", 70 | "metrics": { 71 | "accurracy": 1, 72 | "f1": 1, 73 | "precision": 1, 74 | "recall": 1 75 | }, 76 | "step": 0, 77 | "path": "models/optimized/base/random_forest/random_forest_78ad688.py", 78 | "primary_metric": { 79 | "name": "recall", 80 | "goal": "maximize" 81 | } 82 | } 83 | ], 84 | "keepsake_version": "0.4.2" 85 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/b159d8339c38a842d02649f3de43d701d881cae53f7126a37e1e24abe5c19446.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "b159d8339c38a842d02649f3de43d701d881cae53f7126a37e1e24abe5c19446", 3 | "created": "2021-06-11T16:36:09.159699917Z", 4 | "params": { 5 | "accuracy": 0.9875, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 0.9880893300248139, 9 | "feature_count": 6, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_y", 16 | "gyro_z" 17 | ], 18 | "hz": 25, 19 | "model": "random_forest", 20 | "n_estimators": 5, 21 | "other_params": "default", 22 | "precision": 0.984375, 23 | "quantization": null, 24 | "recall": 0.9924242424242424 25 | }, 26 | "host": "", 27 | "user": "tk", 28 | "config": { 29 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 30 | "storage": "" 31 | }, 32 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 33 | "path": "", 34 | "python_version": "3.8.3", 35 | "python_packages": { 36 | "appnope": "0.1.2", 37 | "backcall": "0.2.0", 38 | "cffi": "1.14.5", 39 | "colorama": "0.4.4", 40 | "cycler": "0.10.0", 41 | "decorator": "4.4.2", 42 | "ipykernel": "5.3.4", 43 | "ipywidgets": "7.6.3", 44 | "jedi": "0.17.0", 45 | "joblib": "1.0.1", 46 | "keepsake": "0.4.2", 47 | "kiwisolver": "1.3.1", 48 | "m2cgen": "0.9.0", 49 | "matplotlib": "3.3.4", 50 | "numpy": "1.20.1", 51 | "pandas": "1.2.3", 52 | "parso": "0.8.1", 53 | "pexpect": "4.8.0", 54 | "pickleshare": "0.7.5", 55 | "psutil": "5.8.0", 56 | "ptyprocess": "0.7.0", 57 | "pygments": "2.8.1", 58 | "pyparsing": "2.4.7", 59 | "pytz": "2021.1", 60 | "scipy": "1.6.1", 61 | "seaborn": "0.10.1", 62 | "six": "1.15.0", 63 | "statsmodels": "0.12.2", 64 | "tornado": "6.1", 65 | "traitlets": "5.0.5", 66 | "wcwidth": "0.2.5" 67 | }, 68 | "checkpoints": [ 69 | { 70 | "id": "4327f1777a5617c6e60a6e54be3b9dbc124f255049e6f205b8cf0061ca5cae33", 71 | "created": "2021-06-11T16:36:09.176839113Z", 72 | "metrics": { 73 | "accurracy": 0.9875, 74 | "f1": 0.9880893300248139, 75 | "precision": 0.984375, 76 | "recall": 0.9924242424242424 77 | }, 78 | "step": 0, 79 | "path": "models/optimized/base/random_forest/random_forest_b159d83.py", 80 | "primary_metric": { 81 | "name": "recall", 82 | "goal": "maximize" 83 | } 84 | } 85 | ], 86 | "keepsake_version": "0.4.2" 87 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/d5da9fecf9b5363890afef50d7a7eb131e510c7e49d6d8bcd5e03989bd554964.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "d5da9fecf9b5363890afef50d7a7eb131e510c7e49d6d8bcd5e03989bd554964", 3 | "created": "2021-06-11T16:36:05.494630098Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 5, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_y" 16 | ], 17 | "hz": 20, 18 | "model": "random_forest", 19 | "n_estimators": 5, 20 | "other_params": "default", 21 | "precision": 1, 22 | "quantization": null, 23 | "recall": 1 24 | }, 25 | "host": "", 26 | "user": "tk", 27 | "config": { 28 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 29 | "storage": "" 30 | }, 31 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 32 | "path": "", 33 | "python_version": "3.8.3", 34 | "python_packages": { 35 | "appnope": "0.1.2", 36 | "backcall": "0.2.0", 37 | "cffi": "1.14.5", 38 | "colorama": "0.4.4", 39 | "cycler": "0.10.0", 40 | "decorator": "4.4.2", 41 | "ipykernel": "5.3.4", 42 | "ipywidgets": "7.6.3", 43 | "jedi": "0.17.0", 44 | "joblib": "1.0.1", 45 | "keepsake": "0.4.2", 46 | "kiwisolver": "1.3.1", 47 | "m2cgen": "0.9.0", 48 | "matplotlib": "3.3.4", 49 | "numpy": "1.20.1", 50 | "pandas": "1.2.3", 51 | "parso": "0.8.1", 52 | "pexpect": "4.8.0", 53 | "pickleshare": "0.7.5", 54 | "psutil": "5.8.0", 55 | "ptyprocess": "0.7.0", 56 | "pygments": "2.8.1", 57 | "pyparsing": "2.4.7", 58 | "pytz": "2021.1", 59 | "scipy": "1.6.1", 60 | "seaborn": "0.10.1", 61 | "six": "1.15.0", 62 | "statsmodels": "0.12.2", 63 | "tornado": "6.1", 64 | "traitlets": "5.0.5", 65 | "wcwidth": "0.2.5" 66 | }, 67 | "checkpoints": [ 68 | { 69 | "id": "5f27590d4624cf295e7973cfb5b3e478601126909856baa1771067f4e82d1143", 70 | "created": "2021-06-11T16:36:05.511065006Z", 71 | "metrics": { 72 | "accurracy": 1, 73 | "f1": 1, 74 | "precision": 1, 75 | "recall": 1 76 | }, 77 | "step": 0, 78 | "path": "models/optimized/base/random_forest/random_forest_d5da9fe.py", 79 | "primary_metric": { 80 | "name": "recall", 81 | "goal": "maximize" 82 | } 83 | } 84 | ], 85 | "keepsake_version": "0.4.2" 86 | } -------------------------------------------------------------------------------- /.keepsake/metadata/experiments/f28b45cf9f3fa6f4f99a3324c9a41b5357576dfe468d5f78b489cef1094ecec2.json: -------------------------------------------------------------------------------- 1 | { 2 | "id": "f28b45cf9f3fa6f4f99a3324c9a41b5357576dfe468d5f78b489cef1094ecec2", 3 | "created": "2021-06-11T16:36:13.792155027Z", 4 | "params": { 5 | "accuracy": 1, 6 | "data_set": "base", 7 | "dataset_test_size": 0.35, 8 | "f1": 1, 9 | "feature_count": 6, 10 | "features": [ 11 | "acc_x", 12 | "acc_y", 13 | "acc_z", 14 | "gyro_x", 15 | "gyro_y", 16 | "gyro_z" 17 | ], 18 | "hz": 50, 19 | "model": "random_forest", 20 | "n_estimators": 5, 21 | "other_params": "default", 22 | "precision": 1, 23 | "quantization": null, 24 | "recall": 1 25 | }, 26 | "host": "", 27 | "user": "tk", 28 | "config": { 29 | "repository": "file:///Users/tk/projects/tinyml-esp32-data/.keepsake", 30 | "storage": "" 31 | }, 32 | "command": "/Users/tk/opt/miniconda3/envs/tinyml/lib/python3.8/site-packages/ipykernel_launcher.py -f /Users/tk/Library/Jupyter/runtime/kernel-dba4cf8a-dddc-479c-9340-bb00ce08d4cb.json", 33 | "path": "", 34 | "python_version": "3.8.3", 35 | "python_packages": { 36 | "appnope": "0.1.2", 37 | "backcall": "0.2.0", 38 | "cffi": "1.14.5", 39 | "colorama": "0.4.4", 40 | "cycler": "0.10.0", 41 | "decorator": "4.4.2", 42 | "ipykernel": "5.3.4", 43 | "ipywidgets": "7.6.3", 44 | "jedi": "0.17.0", 45 | "joblib": "1.0.1", 46 | "keepsake": "0.4.2", 47 | "kiwisolver": "1.3.1", 48 | "m2cgen": "0.9.0", 49 | "matplotlib": "3.3.4", 50 | "numpy": "1.20.1", 51 | "pandas": "1.2.3", 52 | "parso": "0.8.1", 53 | "pexpect": "4.8.0", 54 | "pickleshare": "0.7.5", 55 | "psutil": "5.8.0", 56 | "ptyprocess": "0.7.0", 57 | "pygments": "2.8.1", 58 | "pyparsing": "2.4.7", 59 | "pytz": "2021.1", 60 | "scipy": "1.6.1", 61 | "seaborn": "0.10.1", 62 | "six": "1.15.0", 63 | "statsmodels": "0.12.2", 64 | "tornado": "6.1", 65 | "traitlets": "5.0.5", 66 | "wcwidth": "0.2.5" 67 | }, 68 | "checkpoints": [ 69 | { 70 | "id": "e6409a1403d608bcc3d56f81481eb9925e4d824888e03e4a28397499bb55bae6", 71 | "created": "2021-06-11T16:36:13.807164907Z", 72 | "metrics": { 73 | "accurracy": 1, 74 | "f1": 1, 75 | "precision": 1, 76 | "recall": 1 77 | }, 78 | "step": 0, 79 | "path": "models/optimized/base/random_forest/random_forest_f28b45c.py", 80 | "primary_metric": { 81 | "name": "recall", 82 | "goal": "maximize" 83 | } 84 | } 85 | ], 86 | "keepsake_version": "0.4.2" 87 | } -------------------------------------------------------------------------------- /.keepsake/metadata/heartbeats/09aca8b7b73f4ad02df085281f2b3e7caf311e26a825d69497ab91a211c0cea1.json: -------------------------------------------------------------------------------- 1 | { 2 | "experiment_id": "09aca8b7b73f4ad02df085281f2b3e7caf311e26a825d69497ab91a211c0cea1", 3 | "last_heartbeat": "2021-06-11T15:45:55.434241Z" 4 | } -------------------------------------------------------------------------------- /.keepsake/metadata/heartbeats/1aef50134132ec21236e246486e0f00cbbc8124d2ec79206cc4b53b25230cbfe.json: -------------------------------------------------------------------------------- 1 | { 2 | "experiment_id": "1aef50134132ec21236e246486e0f00cbbc8124d2ec79206cc4b53b25230cbfe", 3 | "last_heartbeat": "2021-06-11T16:33:40.271895Z" 4 | } -------------------------------------------------------------------------------- /.keepsake/metadata/heartbeats/43081ce4e5a9d0685384e4cf8b010dfedb8c2fc027fdf5c1d2af3494ad805124.json: -------------------------------------------------------------------------------- 1 | { 2 | "experiment_id": "43081ce4e5a9d0685384e4cf8b010dfedb8c2fc027fdf5c1d2af3494ad805124", 3 | "last_heartbeat": "2021-06-11T15:38:44.687552Z" 4 | } -------------------------------------------------------------------------------- /.keepsake/metadata/heartbeats/4583c25a4e4ea3cb485340ceec106c39595580ab21a3e66b37f4d83fe2f24638.json: -------------------------------------------------------------------------------- 1 | { 2 | "experiment_id": "4583c25a4e4ea3cb485340ceec106c39595580ab21a3e66b37f4d83fe2f24638", 3 | "last_heartbeat": "2021-06-11T15:38:49.133326Z" 4 | } -------------------------------------------------------------------------------- /.keepsake/metadata/heartbeats/7bc2e3b967292165ed78fe67ca22fceebc6f5b3dea1109415446cb20ad3894a0.json: -------------------------------------------------------------------------------- 1 | { 2 | "experiment_id": "7bc2e3b967292165ed78fe67ca22fceebc6f5b3dea1109415446cb20ad3894a0", 3 | "last_heartbeat": "2021-06-11T15:38:49.048466Z" 4 | } -------------------------------------------------------------------------------- /.keepsake/metadata/heartbeats/be9d03b6b85d2d48ae36559508b1a1a982d1b5ae14d7714533cd197f88ba4691.json: -------------------------------------------------------------------------------- 1 | { 2 | "experiment_id": "be9d03b6b85d2d48ae36559508b1a1a982d1b5ae14d7714533cd197f88ba4691", 3 | "last_heartbeat": "2021-06-11T15:38:45.006694Z" 4 | } -------------------------------------------------------------------------------- /.keepsake/metadata/heartbeats/f86ce50035181f9772c76aa0c89885803c6e046639e68c8a3c10f32ec8d5600d.json: -------------------------------------------------------------------------------- 1 | { 2 | "experiment_id": "f86ce50035181f9772c76aa0c89885803c6e046639e68c8a3c10f32ec8d5600d", 3 | "last_heartbeat": "2021-06-11T15:38:44.83007Z" 4 | } -------------------------------------------------------------------------------- /.keepsake/repository.json: -------------------------------------------------------------------------------- 1 | {"version":1} -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | ## TinyML Data Exploration & Machine Learning 2 | 3 | Data Exploration of acceleration and gyroscope data from ESP32 with MPU6500 sensor. 4 | 5 | Data collected from the device was used to train an ML model that runs on the ESP32. The ML model and code on ESP32 is implemented in pure(Python). 6 | 7 | A detailed walkthrough in the blog below. 8 | 9 | Blog: [TinyML: Machine Learning on ESP32 with MicroPython](https://dev.to/tkeyo/tinyml-machine-learning-on-esp32-with-micropython-38a6) 10 | 11 | ## Installation 12 | ``` 13 | pip install -r requirements.txt 14 | ``` 15 | -------------------------------------------------------------------------------- /data/transformed/.gitignore: -------------------------------------------------------------------------------- 1 | * 2 | */ 3 | !.gitignore -------------------------------------------------------------------------------- /data/validation/.gitignore: -------------------------------------------------------------------------------- 1 | * 2 | */ 3 | !.gitignore -------------------------------------------------------------------------------- /eda_utils.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import seaborn as sns 3 | import matplotlib.pyplot as plt 4 | 5 | 6 | def filter_dataset_by_label(df: pd.DataFrame, label: int) -> pd.DataFrame: 7 | """ 8 | Filters a dataframe for a given label. 9 | 10 | Args: 11 | df: Input dataframe. 12 | label: Label in dataframe to be filtered. 13 | Returns: 14 | Returns a dataframe with only one label category. 15 | """ 16 | return df[df['label'] == label].drop('label', axis=1) 17 | 18 | 19 | def get_acc_dfs(df: pd.DataFrame) -> (pd.DataFrame, pd.DataFrame, pd.DataFrame): 20 | """ 21 | Outputs 3 dataframes for each of the acceleration signals. 22 | 23 | Args: 24 | df: Signals dataframe. 25 | Returns: 26 | Returns dataframes for each of the 3 acceleration signals. 27 | """ 28 | df_acc_x = pd.DataFrame(df.filter(regex='acc_x')).T.reset_index() 29 | df_acc_y = pd.DataFrame(df.filter(regex='acc_y')).T.reset_index() 30 | df_acc_z = pd.DataFrame(df.filter(regex='acc_z')).T.reset_index() 31 | 32 | return df_acc_x, df_acc_y, df_acc_z 33 | 34 | 35 | def extract_time_ms(df: pd.DataFrame) -> pd.DataFrame: 36 | """ 37 | Extracts milisecond values from the index values of a dataframe. 38 | 39 | Args: 40 | df: Signals dataframe. 41 | 42 | Returns: 43 | Returns a dataframe that includes a `ms` time column. 44 | """ 45 | df['ms'] = df['index'].str.extract(r'(\d{1,4})') 46 | return df 47 | 48 | 49 | def extract_signal(df: pd.DataFrame) -> pd.DataFrame: 50 | """ 51 | Extracts a signal (acceleration, gyroscope) from the index values of 52 | a dataframe. 53 | 54 | Args: 55 | df: Signals dataframe. 56 | 57 | Returns: 58 | Returns a dataframe that includes a `signal` column. 59 | """ 60 | df['signal'] = df['index'].str.extract(r'(.*)_\d{1,4}') 61 | return df 62 | 63 | 64 | def melt_df(df: pd.DataFrame) -> list: 65 | """ 66 | Melts a dataframe for signal plotting. 67 | 68 | Args: 69 | df: Signals dataframe. 70 | 71 | Returns: 72 | Returns a list of signals. 73 | """ 74 | signals = ['acc_x', 'acc_y','acc_z','gyro_x','gyro_y','gyro_z'] 75 | return [pd.melt(df[df['signal'] == s].drop(['signal','ms'], axis=1)).rename(columns={'value':s}).drop('variable',axis=1) for s in signals] 76 | 77 | 78 | def plot_signals( 79 | df_x: pd.DataFrame, 80 | df_y: pd.DataFrame, 81 | df_circle: pd.DataFrame, 82 | signal: str, 83 | title_text: str, 84 | quantity: str): 85 | """ 86 | Plots all signals, their mean and associated correlation matrix. 87 | 88 | Args: 89 | df_x: Dataframe containing x movements. 90 | df_y: Dataframe containing y movements. 91 | df_circle: Dataframe containing circle movements. 92 | signal: Signal - acc_x, acc_y, acc_z, gyro_x, gyro_y, gyro_z 93 | title_text: Text to be used for titles. 94 | quantity: Plotted quantity text - acceleration/angular velocity 95 | """ 96 | fig, ax = plt.subplots(ncols=3, sharey=True, figsize=(30,8)) 97 | 98 | # plotting all signals 99 | ax[0].plot(df_x[df_x['signal'] == signal].drop(['mean','signal'], axis=1), alpha=0.3); 100 | ax[1].plot(df_y[df_y['signal'] == signal].drop(['mean','signal'], axis=1), alpha=0.3); 101 | ax[2].plot(df_circle[df_circle['signal'] == signal].drop(['mean','signal'], axis=1), alpha=0.3); 102 | 103 | # plotting mean of all signals 104 | ax[0].plot(df_x[df_x['signal'] == signal]['mean'], alpha=1, color='red', linewidth=3); 105 | ax[1].plot(df_y[df_y['signal'] == signal]['mean'], alpha=1, color='red', linewidth=3); 106 | ax[2].plot(df_circle[df_circle['signal'] == signal]['mean'], alpha=1, color='red', linewidth=3); 107 | 108 | # set titles 109 | ax[0].set_title(f'{title_text} {quantity} of all `X` movements\n+ their mean\n') 110 | ax[1].set_title(f'{title_text} {quantity} of all `Y` movements\n+ their mean\n') 111 | ax[2].set_title(f'{title_text} {quantity} of all `circle` movements\n+ their mean\n') 112 | 113 | ax[0].set_ylabel('Acceleration [m/s^2] / Angular velocity [deg/s]') 114 | 115 | # sets ticklabels 116 | for x in range(3): 117 | ax[x].set_xlabel('Time [ms]') 118 | 119 | temp = ax[x].xaxis.get_ticklabels() 120 | temp = list(set(temp) - set(temp[::5])) 121 | for label in temp: 122 | label.set_visible(False) 123 | 124 | # adding heatmaps 125 | fig, ax = plt.subplots(ncols=3, figsize=(30,6)) 126 | sns.heatmap(df_x[df_x['signal'] == signal].drop(['signal'], axis=1).corr(), ax=ax[0]) 127 | sns.heatmap(df_y[df_y['signal'] == signal].drop(['signal'], axis=1).corr(), ax=ax[1]) 128 | sns.heatmap(df_circle[df_circle['signal'] == signal].drop(['signal'], axis=1).corr(), ax=ax[2]) 129 | 130 | # set titles 131 | ax[0].set_title(f'Correlation matrix\n{title_text} {quantity} of `X` movements\n'); 132 | ax[1].set_title(f'Correlation matrix\n{title_text} {quantity} of `Y` movements\n'); 133 | ax[2].set_title(f'Correlation matrix\n{title_text} {quantity} of `circle` movements\n'); -------------------------------------------------------------------------------- /keepsake.yaml: -------------------------------------------------------------------------------- 1 | repository: "file://.keepsake" 2 | -------------------------------------------------------------------------------- /models/baseline/base/decision_tree/decision_tree_100hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[223]) <= (-2.349908947944641): 3 | if (input[269]) <= (-48.67556953430176): 4 | var0 = [0.0, 0.0, 0.0, 1.0] 5 | else: 6 | if (input[476]) <= (10.145430088043213): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 1.0, 0.0] 10 | else: 11 | if (input[174]) <= (3.2070329189300537): 12 | if (input[121]) <= (3.3339260816574097): 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | var0 = [0.0, 0.0, 1.0, 0.0] 16 | else: 17 | var0 = [0.0, 1.0, 0.0, 0.0] 18 | return var0 19 | -------------------------------------------------------------------------------- /models/baseline/base/decision_tree/decision_tree_10hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[25]) <= (-1.8878280520439148): 3 | if (input[35]) <= (-47.02289867401123): 4 | var0 = [0.0, 0.0, 0.0, 1.0] 5 | else: 6 | if (input[40]) <= (1.8702290058135986): 7 | var0 = [0.0, 0.0, 1.0, 0.0] 8 | else: 9 | var0 = [1.0, 0.0, 0.0, 0.0] 10 | else: 11 | if (input[24]) <= (-2.5175029635429382): 12 | var0 = [0.0, 1.0, 0.0, 0.0] 13 | else: 14 | if (input[13]) <= (3.3339260816574097): 15 | if (input[24]) <= (6.97071897983551): 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 1.0, 0.0, 0.0] 19 | else: 20 | var0 = [0.0, 0.0, 1.0, 0.0] 21 | return var0 22 | -------------------------------------------------------------------------------- /models/baseline/base/decision_tree/decision_tree_20hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[49]) <= (-1.8878280520439148): 3 | if (input[18]) <= (-3.3387140035629272): 4 | var0 = [0.0, 0.0, 0.0, 1.0] 5 | else: 6 | if (input[60]) <= (3.0980969667434692): 7 | var0 = [0.0, 0.0, 1.0, 0.0] 8 | else: 9 | var0 = [1.0, 0.0, 0.0, 0.0] 10 | else: 11 | if (input[30]) <= (3.371035933494568): 12 | if (input[25]) <= (3.3339260816574097): 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | var0 = [0.0, 0.0, 1.0, 0.0] 16 | else: 17 | var0 = [0.0, 1.0, 0.0, 0.0] 18 | return var0 19 | -------------------------------------------------------------------------------- /models/baseline/base/decision_tree/decision_tree_25hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[25]) <= (1.5837639570236206): 3 | if (input[42]) <= (1.8890249729156494): 4 | var0 = [1.0, 0.0, 0.0, 0.0] 5 | else: 6 | if (input[32]) <= (11.513720035552979): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 0.0, 1.0] 10 | else: 11 | if (input[51]) <= (25.400762915611267): 12 | var0 = [0.0, 0.0, 1.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 0.0, 1.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/base/decision_tree/decision_tree_50hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[49]) <= (1.5837639570236206): 3 | if (input[84]) <= (1.8890249729156494): 4 | var0 = [1.0, 0.0, 0.0, 0.0] 5 | else: 6 | if (input[54]) <= (-0.07182605005800724): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | var0 = [0.0, 1.0, 0.0, 0.0] 10 | else: 11 | if (input[112]) <= (-26.931299448013306): 12 | var0 = [0.0, 0.0, 0.0, 1.0] 13 | else: 14 | var0 = [0.0, 0.0, 1.0, 0.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/base/random_forest/random_forest_100hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[229]) <= (-3.192668080329895): 7 | if (input[305]) <= (-47.02289867401123): 8 | var0 = [0.0, 0.0, 0.0, 1.0] 9 | else: 10 | var0 = [0.0, 0.0, 1.0, 0.0] 11 | else: 12 | if (input[126]) <= (1.410184919834137): 13 | if (input[253]) <= (-2.5151090025901794): 14 | if (input[22]) <= (1.748091459274292): 15 | var0 = [0.0, 0.0, 1.0, 0.0] 16 | else: 17 | var0 = [0.0, 0.0, 0.0, 1.0] 18 | else: 19 | var0 = [1.0, 0.0, 0.0, 0.0] 20 | else: 21 | if (input[64]) <= (0.5610686987638474): 22 | var0 = [0.0, 0.0, 1.0, 0.0] 23 | else: 24 | var0 = [0.0, 1.0, 0.0, 0.0] 25 | if (input[156]) <= (3.671508550643921): 26 | if (input[121]) <= (2.5605984926223755): 27 | if (input[84]) <= (-3.162740468978882): 28 | var1 = [0.0, 0.0, 0.0, 1.0] 29 | else: 30 | var1 = [1.0, 0.0, 0.0, 0.0] 31 | else: 32 | if (input[495]) <= (-1.6717554926872253): 33 | var1 = [0.0, 0.0, 0.0, 1.0] 34 | else: 35 | var1 = [0.0, 0.0, 1.0, 0.0] 36 | else: 37 | if (input[214]) <= (-41.034350633621216): 38 | var1 = [0.0, 0.0, 0.0, 1.0] 39 | else: 40 | if (input[446]) <= (10.21007490158081): 41 | var1 = [0.0, 1.0, 0.0, 0.0] 42 | else: 43 | var1 = [0.0, 0.0, 1.0, 0.0] 44 | if (input[241]) <= (-2.2002710700035095): 45 | if (input[339]) <= (-14.534354269504547): 46 | var2 = [0.0, 0.0, 0.0, 1.0] 47 | else: 48 | var2 = [0.0, 0.0, 1.0, 0.0] 49 | else: 50 | if (input[258]) <= (-3.519476532936096): 51 | var2 = [0.0, 1.0, 0.0, 0.0] 52 | else: 53 | if (input[97]) <= (1.8507174253463745): 54 | if (input[270]) <= (5.012261092662811): 55 | var2 = [1.0, 0.0, 0.0, 0.0] 56 | else: 57 | var2 = [0.0, 1.0, 0.0, 0.0] 58 | else: 59 | var2 = [0.0, 0.0, 1.0, 0.0] 60 | if (input[235]) <= (-1.318008005619049): 61 | if (input[351]) <= (-11.545801520347595): 62 | var3 = [0.0, 0.0, 0.0, 1.0] 63 | else: 64 | if (input[132]) <= (5.67545485496521): 65 | if (input[291]) <= (-0.9694656431674957): 66 | var3 = [1.0, 0.0, 0.0, 0.0] 67 | else: 68 | var3 = [0.0, 0.0, 1.0, 0.0] 69 | else: 70 | var3 = [0.0, 1.0, 0.0, 0.0] 71 | else: 72 | if (input[216]) <= (-1.0678139925003052): 73 | if (input[94]) <= (2.824427545070648): 74 | var3 = [0.0, 1.0, 0.0, 0.0] 75 | else: 76 | var3 = [1.0, 0.0, 0.0, 0.0] 77 | else: 78 | if (input[103]) <= (2.2134395241737366): 79 | if (input[162]) <= (6.357802510261536): 80 | var3 = [1.0, 0.0, 0.0, 0.0] 81 | else: 82 | var3 = [0.0, 1.0, 0.0, 0.0] 83 | else: 84 | var3 = [0.0, 0.0, 1.0, 0.0] 85 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 86 | -------------------------------------------------------------------------------- /models/baseline/base/random_forest/random_forest_10hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[6]) <= (-1.5478515028953552): 7 | if (input[39]) <= (-40.73282432556152): 8 | var0 = [0.0, 0.0, 0.0, 1.0] 9 | else: 10 | var0 = [1.0, 0.0, 0.0, 0.0] 11 | else: 12 | if (input[29]) <= (-7.65648889541626): 13 | if (input[54]) <= (0.015562311746180058): 14 | if (input[30]) <= (-0.46088384091854095): 15 | var0 = [0.0, 1.0, 0.0, 0.0] 16 | else: 17 | if (input[17]) <= (47.4961821436882): 18 | var0 = [1.0, 0.0, 0.0, 0.0] 19 | else: 20 | var0 = [0.0, 0.0, 1.0, 0.0] 21 | else: 22 | if (input[39]) <= (4.244274765253067): 23 | var0 = [0.0, 0.0, 1.0, 0.0] 24 | else: 25 | var0 = [1.0, 0.0, 0.0, 0.0] 26 | else: 27 | if (input[19]) <= (-2.3654714822769165): 28 | if (input[6]) <= (0.6584054529666901): 29 | var0 = [0.0, 0.0, 1.0, 0.0] 30 | else: 31 | var0 = [0.0, 1.0, 0.0, 0.0] 32 | else: 33 | if (input[36]) <= (-2.323572516441345): 34 | var0 = [0.0, 1.0, 0.0, 0.0] 35 | else: 36 | if (input[13]) <= (7.054513692855835): 37 | var0 = [1.0, 0.0, 0.0, 0.0] 38 | else: 39 | var0 = [0.0, 0.0, 1.0, 0.0] 40 | if (input[6]) <= (-1.5478515028953552): 41 | if (input[26]) <= (7.443572998046875): 42 | var1 = [0.0, 0.0, 0.0, 1.0] 43 | else: 44 | var1 = [1.0, 0.0, 0.0, 0.0] 45 | else: 46 | if (input[7]) <= (1.143231451511383): 47 | if (input[18]) <= (1.2042829990386963): 48 | if (input[1]) <= (1.0307040214538574): 49 | if (input[4]) <= (2.080152451992035): 50 | var1 = [1.0, 0.0, 0.0, 0.0] 51 | else: 52 | if (input[14]) <= (10.608705043792725): 53 | var1 = [1.0, 0.0, 0.0, 0.0] 54 | else: 55 | var1 = [0.0, 1.0, 0.0, 0.0] 56 | else: 57 | var1 = [0.0, 0.0, 1.0, 0.0] 58 | else: 59 | if (input[12]) <= (0.639251708984375): 60 | var1 = [0.0, 0.0, 1.0, 0.0] 61 | else: 62 | var1 = [0.0, 1.0, 0.0, 0.0] 63 | else: 64 | if (input[3]) <= (12.225190818309784): 65 | var1 = [0.0, 0.0, 1.0, 0.0] 66 | else: 67 | var1 = [1.0, 0.0, 0.0, 0.0] 68 | if (input[13]) <= (1.0857704877853394): 69 | if (input[19]) <= (-4.005499541759491): 70 | var2 = [0.0, 0.0, 0.0, 1.0] 71 | else: 72 | if (input[41]) <= (-2.2290075421333313): 73 | if (input[6]) <= (0.40342293679714203): 74 | var2 = [1.0, 0.0, 0.0, 0.0] 75 | else: 76 | if (input[45]) <= (-6.270992279052734): 77 | var2 = [1.0, 0.0, 0.0, 0.0] 78 | else: 79 | var2 = [0.0, 1.0, 0.0, 0.0] 80 | else: 81 | if (input[6]) <= (1.978808045387268): 82 | var2 = [1.0, 0.0, 0.0, 0.0] 83 | else: 84 | if (input[19]) <= (0.8511387780308723): 85 | var2 = [1.0, 0.0, 0.0, 0.0] 86 | else: 87 | var2 = [0.0, 1.0, 0.0, 0.0] 88 | else: 89 | if (input[22]) <= (-21.351144790649414): 90 | var2 = [0.0, 0.0, 0.0, 1.0] 91 | else: 92 | if (input[48]) <= (-0.0407014237716794): 93 | if (input[28]) <= (5.68702244758606): 94 | var2 = [0.0, 1.0, 0.0, 0.0] 95 | else: 96 | var2 = [1.0, 0.0, 0.0, 0.0] 97 | else: 98 | var2 = [0.0, 0.0, 1.0, 0.0] 99 | if (input[25]) <= (-1.2042829990386963): 100 | if (input[35]) <= (-54.90457820892334): 101 | var3 = [0.0, 0.0, 0.0, 1.0] 102 | else: 103 | if (input[50]) <= (10.1597900390625): 104 | if (input[37]) <= (0.16998832300305367): 105 | var3 = [0.0, 1.0, 0.0, 0.0] 106 | else: 107 | if (input[18]) <= (1.374271884560585): 108 | var3 = [1.0, 0.0, 0.0, 0.0] 109 | else: 110 | var3 = [0.0, 0.0, 1.0, 0.0] 111 | else: 112 | if (input[27]) <= (56.828233510255814): 113 | var3 = [0.0, 0.0, 1.0, 0.0] 114 | else: 115 | var3 = [1.0, 0.0, 0.0, 0.0] 116 | else: 117 | if (input[61]) <= (0.0574608389288187): 118 | if (input[24]) <= (-3.4284964203834534): 119 | var3 = [0.0, 1.0, 0.0, 0.0] 120 | else: 121 | if (input[12]) <= (1.71903657913208): 122 | var3 = [1.0, 0.0, 0.0, 0.0] 123 | else: 124 | var3 = [0.0, 0.0, 1.0, 0.0] 125 | else: 126 | if (input[30]) <= (-1.0211271047592163): 127 | if (input[14]) <= (10.05923843383789): 128 | var3 = [1.0, 0.0, 0.0, 0.0] 129 | else: 130 | var3 = [0.0, 0.0, 1.0, 0.0] 131 | else: 132 | var3 = [1.0, 0.0, 0.0, 0.0] 133 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 134 | -------------------------------------------------------------------------------- /models/baseline/base/random_forest/random_forest_20hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[75]) <= (-59.87022590637207): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[43]) <= (-2.3175870180130005): 10 | if (input[110]) <= (10.146629810333252): 11 | if (input[36]) <= (17.496829986572266): 12 | var0 = [0.0, 1.0, 0.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 0.0, 1.0] 15 | else: 16 | var0 = [0.0, 0.0, 1.0, 0.0] 17 | else: 18 | if (input[43]) <= (2.610876977443695): 19 | if (input[35]) <= (107.10306549072266): 20 | if (input[60]) <= (-4.144362926483154): 21 | var0 = [0.0, 1.0, 0.0, 0.0] 22 | else: 23 | if (input[41]) <= (63.40076446533203): 24 | var0 = [1.0, 0.0, 0.0, 0.0] 25 | else: 26 | if (input[28]) <= (8.393128633499146): 27 | var0 = [0.0, 1.0, 0.0, 0.0] 28 | else: 29 | var0 = [1.0, 0.0, 0.0, 0.0] 30 | else: 31 | var0 = [0.0, 0.0, 1.0, 0.0] 32 | else: 33 | if (input[45]) <= (-1.6183207631111145): 34 | var0 = [0.0, 1.0, 0.0, 0.0] 35 | else: 36 | var0 = [0.0, 0.0, 1.0, 0.0] 37 | if (input[19]) <= (1.292868971824646): 38 | if (input[68]) <= (10.200500011444092): 39 | if (input[54]) <= (-2.531868129968643): 40 | var1 = [0.0, 1.0, 0.0, 0.0] 41 | else: 42 | if (input[46]) <= (-47.62976932525635): 43 | var1 = [0.0, 0.0, 0.0, 1.0] 44 | else: 45 | if (input[66]) <= (-9.588777959346771): 46 | var1 = [0.0, 1.0, 0.0, 0.0] 47 | else: 48 | var1 = [1.0, 0.0, 0.0, 0.0] 49 | else: 50 | var1 = [1.0, 0.0, 0.0, 0.0] 51 | else: 52 | if (input[69]) <= (-2.534351170063019): 53 | if (input[48]) <= (0.6596025228500366): 54 | var1 = [1.0, 0.0, 0.0, 0.0] 55 | else: 56 | var1 = [0.0, 0.0, 0.0, 1.0] 57 | else: 58 | var1 = [0.0, 0.0, 1.0, 0.0] 59 | if (input[42]) <= (10.803835391998291): 60 | if (input[25]) <= (3.250128984451294): 61 | if (input[36]) <= (1.2593500018119812): 62 | if (input[61]) <= (1.2461819648742676): 63 | var2 = [1.0, 0.0, 0.0, 0.0] 64 | else: 65 | var2 = [0.0, 1.0, 0.0, 0.0] 66 | else: 67 | var2 = [0.0, 1.0, 0.0, 0.0] 68 | else: 69 | var2 = [0.0, 0.0, 1.0, 0.0] 70 | else: 71 | var2 = [0.0, 0.0, 0.0, 1.0] 72 | if (input[42]) <= (10.837355136871338): 73 | if (input[49]) <= (-1.8662805557250977): 74 | if (input[69]) <= (-0.9007633030414581): 75 | var3 = [1.0, 0.0, 0.0, 0.0] 76 | else: 77 | var3 = [0.0, 0.0, 1.0, 0.0] 78 | else: 79 | if (input[42]) <= (-1.574187457561493): 80 | var3 = [0.0, 1.0, 0.0, 0.0] 81 | else: 82 | if (input[36]) <= (2.0326775312423706): 83 | if (input[24]) <= (-0.9672574996948242): 84 | var3 = [0.0, 0.0, 1.0, 0.0] 85 | else: 86 | if (input[61]) <= (-6.842628598213196): 87 | var3 = [0.0, 0.0, 1.0, 0.0] 88 | else: 89 | if (input[38]) <= (10.414774894714355): 90 | var3 = [1.0, 0.0, 0.0, 0.0] 91 | else: 92 | if (input[62]) <= (10.035295009613037): 93 | var3 = [0.0, 0.0, 1.0, 0.0] 94 | else: 95 | var3 = [1.0, 0.0, 0.0, 0.0] 96 | else: 97 | if (input[84]) <= (0.053869519382715225): 98 | var3 = [0.0, 1.0, 0.0, 0.0] 99 | else: 100 | var3 = [0.0, 0.0, 1.0, 0.0] 101 | else: 102 | var3 = [0.0, 0.0, 0.0, 1.0] 103 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 104 | -------------------------------------------------------------------------------- /models/baseline/base/random_forest/random_forest_25hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (5.029020547866821): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[67]) <= (-1.2162545323371887): 10 | if (input[120]) <= (-0.017956499010324478): 11 | if (input[26]) <= (12.087130069732666): 12 | var0 = [0.0, 1.0, 0.0, 0.0] 13 | else: 14 | var0 = [1.0, 0.0, 0.0, 0.0] 15 | else: 16 | var0 = [0.0, 0.0, 1.0, 0.0] 17 | else: 18 | if (input[30]) <= (1.4520830512046814): 19 | if (input[1]) <= (1.7058689594268799): 20 | if (input[55]) <= (-3.9947255849838257): 21 | var0 = [0.0, 0.0, 1.0, 0.0] 22 | else: 23 | var0 = [1.0, 0.0, 0.0, 0.0] 24 | else: 25 | var0 = [0.0, 0.0, 1.0, 0.0] 26 | else: 27 | if (input[35]) <= (7.106872618198395): 28 | var0 = [0.0, 1.0, 0.0, 0.0] 29 | else: 30 | var0 = [0.0, 0.0, 1.0, 0.0] 31 | if (input[62]) <= (6.321889400482178): 32 | var1 = [0.0, 0.0, 0.0, 1.0] 33 | else: 34 | if (input[37]) <= (2.505531907081604): 35 | if (input[24]) <= (2.290053963661194): 36 | if (input[13]) <= (5.725733399391174): 37 | if (input[56]) <= (10.609904766082764): 38 | var1 = [1.0, 0.0, 0.0, 0.0] 39 | else: 40 | if (input[149]) <= (-1.4007635116577148): 41 | var1 = [1.0, 0.0, 0.0, 0.0] 42 | else: 43 | var1 = [0.0, 1.0, 0.0, 0.0] 44 | else: 45 | var1 = [0.0, 0.0, 1.0, 0.0] 46 | else: 47 | if (input[42]) <= (-0.18794512748718262): 48 | var1 = [0.0, 0.0, 1.0, 0.0] 49 | else: 50 | var1 = [0.0, 1.0, 0.0, 0.0] 51 | else: 52 | if (input[126]) <= (-0.03591302502900362): 53 | var1 = [0.0, 1.0, 0.0, 0.0] 54 | else: 55 | var1 = [0.0, 0.0, 1.0, 0.0] 56 | if (input[58]) <= (-46.01144886016846): 57 | var2 = [0.0, 0.0, 0.0, 1.0] 58 | else: 59 | if (input[19]) <= (1.7286134958267212): 60 | if (input[78]) <= (-3.317166566848755): 61 | var2 = [0.0, 1.0, 0.0, 0.0] 62 | else: 63 | if (input[49]) <= (-0.9876083731651306): 64 | if (input[92]) <= (10.189725399017334): 65 | var2 = [0.0, 1.0, 0.0, 0.0] 66 | else: 67 | if (input[40]) <= (3.423664391040802): 68 | var2 = [0.0, 0.0, 1.0, 0.0] 69 | else: 70 | var2 = [1.0, 0.0, 0.0, 0.0] 71 | else: 72 | if (input[55]) <= (3.325546443462372): 73 | if (input[7]) <= (1.3012484908103943): 74 | var2 = [1.0, 0.0, 0.0, 0.0] 75 | else: 76 | if (input[141]) <= (-0.6870228946208954): 77 | var2 = [1.0, 0.0, 0.0, 0.0] 78 | else: 79 | var2 = [0.0, 0.0, 1.0, 0.0] 80 | else: 81 | var2 = [0.0, 0.0, 1.0, 0.0] 82 | else: 83 | var2 = [0.0, 0.0, 1.0, 0.0] 84 | if (input[68]) <= (5.029020547866821): 85 | var3 = [0.0, 0.0, 0.0, 1.0] 86 | else: 87 | if (input[25]) <= (1.5765814781188965): 88 | if (input[24]) <= (1.9800044298171997): 89 | var3 = [1.0, 0.0, 0.0, 0.0] 90 | else: 91 | var3 = [0.0, 1.0, 0.0, 0.0] 92 | else: 93 | var3 = [0.0, 0.0, 1.0, 0.0] 94 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 95 | -------------------------------------------------------------------------------- /models/baseline/base/random_forest/random_forest_50hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (13.075935363769531): 7 | if (input[55]) <= (1.9213470220565796): 8 | if (input[121]) <= (2.1428104639053345): 9 | if (input[96]) <= (2.3618800044059753): 10 | if (input[137]) <= (61.343509674072266): 11 | if (input[124]) <= (3.7213739156723022): 12 | var0 = [1.0, 0.0, 0.0, 0.0] 13 | else: 14 | if (input[133]) <= (-1.05464568734169): 15 | var0 = [0.0, 1.0, 0.0, 0.0] 16 | else: 17 | if (input[147]) <= (-3.622137099504471): 18 | var0 = [1.0, 0.0, 0.0, 0.0] 19 | else: 20 | var0 = [0.0, 1.0, 0.0, 0.0] 21 | else: 22 | if (input[196]) <= (-7.236643433570862): 23 | var0 = [1.0, 0.0, 0.0, 0.0] 24 | else: 25 | var0 = [0.0, 1.0, 0.0, 0.0] 26 | else: 27 | var0 = [0.0, 1.0, 0.0, 0.0] 28 | else: 29 | var0 = [0.0, 1.0, 0.0, 0.0] 30 | else: 31 | var0 = [0.0, 0.0, 1.0, 0.0] 32 | else: 33 | if (input[45]) <= (-0.3511451780796051): 34 | var0 = [0.0, 0.0, 0.0, 1.0] 35 | else: 36 | if (input[222]) <= (0.02513910084962845): 37 | var0 = [1.0, 0.0, 0.0, 0.0] 38 | else: 39 | var0 = [0.0, 0.0, 1.0, 0.0] 40 | if (input[97]) <= (-1.5167269706726074): 41 | if (input[162]) <= (-9.149442911148071): 42 | var1 = [0.0, 0.0, 0.0, 1.0] 43 | else: 44 | if (input[126]) <= (-5.919662117958069): 45 | var1 = [0.0, 1.0, 0.0, 0.0] 46 | else: 47 | var1 = [0.0, 0.0, 1.0, 0.0] 48 | else: 49 | if (input[66]) <= (1.8124110102653503): 50 | if (input[103]) <= (3.087322950363159): 51 | if (input[79]) <= (1.7262195348739624): 52 | var1 = [1.0, 0.0, 0.0, 0.0] 53 | else: 54 | if (input[6]) <= (0.02992752264253795): 55 | var1 = [0.0, 0.0, 1.0, 0.0] 56 | else: 57 | var1 = [0.0, 0.0, 0.0, 1.0] 58 | else: 59 | var1 = [0.0, 0.0, 1.0, 0.0] 60 | else: 61 | var1 = [0.0, 1.0, 0.0, 0.0] 62 | if (input[105]) <= (12.198474884033203): 63 | if (input[31]) <= (1.1611875295639038): 64 | if (input[36]) <= (0.9145849943161011): 65 | if (input[85]) <= (1.1839329600334167): 66 | var2 = [1.0, 0.0, 0.0, 0.0] 67 | else: 68 | if (input[41]) <= (6.587786078453064): 69 | var2 = [0.0, 0.0, 1.0, 0.0] 70 | else: 71 | var2 = [0.0, 1.0, 0.0, 0.0] 72 | else: 73 | if (input[210]) <= (-0.06464343890547752): 74 | var2 = [0.0, 1.0, 0.0, 0.0] 75 | else: 76 | var2 = [1.0, 0.0, 0.0, 0.0] 77 | else: 78 | if (input[127]) <= (0.7948749661445618): 79 | var2 = [0.0, 0.0, 1.0, 0.0] 80 | else: 81 | var2 = [1.0, 0.0, 0.0, 0.0] 82 | else: 83 | var2 = [0.0, 0.0, 0.0, 1.0] 84 | if (input[121]) <= (-1.2042829990386963): 85 | if (input[171]) <= (-22.763360023498535): 86 | var3 = [0.0, 0.0, 0.0, 1.0] 87 | else: 88 | if (input[144]) <= (-1.063025325536728): 89 | var3 = [0.0, 1.0, 0.0, 0.0] 90 | else: 91 | if (input[180]) <= (-0.19871873036026955): 92 | var3 = [1.0, 0.0, 0.0, 0.0] 93 | else: 94 | var3 = [0.0, 0.0, 1.0, 0.0] 95 | else: 96 | if (input[120]) <= (-3.4284964203834534): 97 | var3 = [0.0, 1.0, 0.0, 0.0] 98 | else: 99 | if (input[1]) <= (2.1703439354896545): 100 | if (input[54]) <= (4.157531023025513): 101 | if (input[67]) <= (3.1938644647598267): 102 | var3 = [1.0, 0.0, 0.0, 0.0] 103 | else: 104 | var3 = [0.0, 0.0, 1.0, 0.0] 105 | else: 106 | var3 = [0.0, 0.0, 1.0, 0.0] 107 | else: 108 | var3 = [0.0, 0.0, 1.0, 0.0] 109 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 110 | -------------------------------------------------------------------------------- /models/baseline/centered/decision_tree/decision_tree_100hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[217]) <= (1.8064250349998474): 3 | if (input[216]) <= (2.0925320386886597): 4 | var0 = [1.0, 0.0, 0.0, 0.0] 5 | else: 6 | if (input[119]) <= (23.347328901290894): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 0.0, 1.0] 10 | else: 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | return var0 13 | -------------------------------------------------------------------------------- /models/baseline/centered/decision_tree/decision_tree_10hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[25]) <= (3.250128984451294): 3 | if (input[24]) <= (2.3139960765838623): 4 | var0 = [1.0, 0.0, 0.0, 0.0] 5 | else: 6 | if (input[6]) <= (-0.9911993891000748): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | var0 = [0.0, 1.0, 0.0, 0.0] 10 | else: 11 | if (input[14]) <= (10.085575103759766): 12 | var0 = [0.0, 1.0, 0.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 1.0, 0.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/centered/decision_tree/decision_tree_20hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[49]) <= (3.250128984451294): 3 | if (input[48]) <= (2.3139960765838623): 4 | var0 = [1.0, 0.0, 0.0, 0.0] 5 | else: 6 | if (input[43]) <= (-1.1384429037570953): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | var0 = [0.0, 1.0, 0.0, 0.0] 10 | else: 11 | if (input[77]) <= (33.801530838012695): 12 | var0 = [0.0, 0.0, 1.0, 0.0] 13 | else: 14 | var0 = [0.0, 1.0, 0.0, 0.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/centered/decision_tree/decision_tree_25hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[55]) <= (1.8064250349998474): 3 | if (input[60]) <= (2.3139960765838623): 4 | var0 = [1.0, 0.0, 0.0, 0.0] 5 | else: 6 | if (input[32]) <= (10.6925048828125): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 0.0, 1.0] 10 | else: 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | return var0 13 | -------------------------------------------------------------------------------- /models/baseline/centered/decision_tree/decision_tree_50hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[109]) <= (1.8064250349998474): 3 | if (input[108]) <= (2.0925320386886597): 4 | var0 = [1.0, 0.0, 0.0, 0.0] 5 | else: 6 | if (input[106]) <= (-17.950379014015198): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | var0 = [0.0, 1.0, 0.0, 0.0] 10 | else: 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | return var0 13 | -------------------------------------------------------------------------------- /models/baseline/centered/random_forest/random_forest_100hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[214]) <= (-50.04961967468262): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[276]) <= (1.616085946559906): 10 | if (input[325]) <= (-2.1116859316825867): 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | else: 13 | if (input[253]) <= (4.223371982574463): 14 | var0 = [1.0, 0.0, 0.0, 0.0] 15 | else: 16 | var0 = [0.0, 0.0, 1.0, 0.0] 17 | else: 18 | if (input[571]) <= (0.08020575996488333): 19 | var0 = [0.0, 1.0, 0.0, 0.0] 20 | else: 21 | var0 = [0.0, 0.0, 1.0, 0.0] 22 | if (input[333]) <= (-59.732821464538574): 23 | var1 = [0.0, 0.0, 0.0, 1.0] 24 | else: 25 | if (input[229]) <= (2.970007538795471): 26 | if (input[210]) <= (2.3463175296783447): 27 | var1 = [1.0, 0.0, 0.0, 0.0] 28 | else: 29 | if (input[495]) <= (-15.19465434551239): 30 | var1 = [0.0, 0.0, 0.0, 1.0] 31 | else: 32 | var1 = [0.0, 1.0, 0.0, 0.0] 33 | else: 34 | if (input[103]) <= (0.07302313484251499): 35 | var1 = [0.0, 1.0, 0.0, 0.0] 36 | else: 37 | var1 = [0.0, 0.0, 1.0, 0.0] 38 | if (input[247]) <= (4.3191399574279785): 39 | if (input[216]) <= (1.8267759084701538): 40 | var2 = [1.0, 0.0, 0.0, 0.0] 41 | else: 42 | if (input[125]) <= (26.270992517471313): 43 | var2 = [0.0, 1.0, 0.0, 0.0] 44 | else: 45 | var2 = [0.0, 0.0, 0.0, 1.0] 46 | else: 47 | var2 = [0.0, 0.0, 1.0, 0.0] 48 | if (input[235]) <= (3.8917750120162964): 49 | if (input[226]) <= (-49.1984748840332): 50 | var3 = [0.0, 0.0, 0.0, 1.0] 51 | else: 52 | if (input[210]) <= (2.1368249654769897): 53 | if (input[445]) <= (-6.106411337852478): 54 | var3 = [0.0, 0.0, 1.0, 0.0] 55 | else: 56 | var3 = [1.0, 0.0, 0.0, 0.0] 57 | else: 58 | var3 = [0.0, 1.0, 0.0, 0.0] 59 | else: 60 | if (input[237]) <= (-1.2824426293373108): 61 | var3 = [0.0, 1.0, 0.0, 0.0] 62 | else: 63 | var3 = [0.0, 0.0, 1.0, 0.0] 64 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 65 | -------------------------------------------------------------------------------- /models/baseline/centered/random_forest/random_forest_10hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[6]) <= (-1.5478515028953552): 7 | if (input[39]) <= (-40.73282432556152): 8 | var0 = [0.0, 0.0, 0.0, 1.0] 9 | else: 10 | var0 = [1.0, 0.0, 0.0, 0.0] 11 | else: 12 | if (input[36]) <= (-3.4284969568252563): 13 | var0 = [0.0, 1.0, 0.0, 0.0] 14 | else: 15 | if (input[54]) <= (0.12330140173435211): 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | if (input[37]) <= (-1.0714049935340881): 19 | var0 = [0.0, 0.0, 1.0, 0.0] 20 | else: 21 | if (input[1]) <= (1.188721239566803): 22 | var0 = [1.0, 0.0, 0.0, 0.0] 23 | else: 24 | var0 = [0.0, 0.0, 1.0, 0.0] 25 | if (input[6]) <= (-1.5478515028953552): 26 | if (input[26]) <= (7.443572998046875): 27 | var1 = [0.0, 0.0, 0.0, 1.0] 28 | else: 29 | var1 = [1.0, 0.0, 0.0, 0.0] 30 | else: 31 | if (input[60]) <= (0.09457097947597504): 32 | if (input[18]) <= (0.6332663297653198): 33 | if (input[42]) <= (-3.189077079296112): 34 | if (input[46]) <= (-18.286258697509766): 35 | var1 = [1.0, 0.0, 0.0, 0.0] 36 | else: 37 | var1 = [0.0, 1.0, 0.0, 0.0] 38 | else: 39 | var1 = [1.0, 0.0, 0.0, 0.0] 40 | else: 41 | if (input[7]) <= (-0.14245499670505524): 42 | var1 = [1.0, 0.0, 0.0, 0.0] 43 | else: 44 | var1 = [0.0, 1.0, 0.0, 0.0] 45 | else: 46 | if (input[57]) <= (-1.1488549411296844): 47 | if (input[45]) <= (-3.679388999938965): 48 | var1 = [1.0, 0.0, 0.0, 0.0] 49 | else: 50 | if (input[51]) <= (-1.3969465792179108): 51 | var1 = [1.0, 0.0, 0.0, 0.0] 52 | else: 53 | var1 = [0.0, 1.0, 0.0, 0.0] 54 | else: 55 | if (input[59]) <= (7.538170695304871): 56 | var1 = [0.0, 0.0, 1.0, 0.0] 57 | else: 58 | var1 = [1.0, 0.0, 0.0, 0.0] 59 | if (input[18]) <= (5.124788522720337): 60 | if (input[25]) <= (3.250128984451294): 61 | if (input[58]) <= (1.0458015203475952): 62 | if (input[31]) <= (-0.5793967843055725): 63 | if (input[24]) <= (3.875015437602997): 64 | var2 = [1.0, 0.0, 0.0, 0.0] 65 | else: 66 | var2 = [0.0, 1.0, 0.0, 0.0] 67 | else: 68 | if (input[54]) <= (-0.9756371974945068): 69 | var2 = [0.0, 1.0, 0.0, 0.0] 70 | else: 71 | var2 = [1.0, 0.0, 0.0, 0.0] 72 | else: 73 | if (input[38]) <= (9.836577892303467): 74 | if (input[42]) <= (-4.164713889360428): 75 | var2 = [0.0, 1.0, 0.0, 0.0] 76 | else: 77 | var2 = [1.0, 0.0, 0.0, 0.0] 78 | else: 79 | var2 = [1.0, 0.0, 0.0, 0.0] 80 | else: 81 | if (input[48]) <= (-0.42975914478302): 82 | var2 = [0.0, 1.0, 0.0, 0.0] 83 | else: 84 | var2 = [0.0, 0.0, 1.0, 0.0] 85 | else: 86 | if (input[25]) <= (-0.597353458404541): 87 | var2 = [0.0, 0.0, 0.0, 1.0] 88 | else: 89 | var2 = [0.0, 1.0, 0.0, 0.0] 90 | if (input[25]) <= (2.9879640340805054): 91 | if (input[12]) <= (-2.179920494556427): 92 | var3 = [0.0, 0.0, 0.0, 1.0] 93 | else: 94 | if (input[31]) <= (-0.5793967843055725): 95 | if (input[36]) <= (-1.8830396495759487): 96 | if (input[18]) <= (9.406819343566895): 97 | var3 = [0.0, 1.0, 0.0, 0.0] 98 | else: 99 | var3 = [0.0, 0.0, 0.0, 1.0] 100 | else: 101 | var3 = [1.0, 0.0, 0.0, 0.0] 102 | else: 103 | if (input[18]) <= (0.6332663297653198): 104 | var3 = [1.0, 0.0, 0.0, 0.0] 105 | else: 106 | var3 = [0.0, 1.0, 0.0, 0.0] 107 | else: 108 | if (input[13]) <= (0.08499415474943817): 109 | var3 = [0.0, 1.0, 0.0, 0.0] 110 | else: 111 | var3 = [0.0, 0.0, 1.0, 0.0] 112 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 113 | -------------------------------------------------------------------------------- /models/baseline/centered/random_forest/random_forest_20hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[75]) <= (-59.87022590637207): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[43]) <= (1.5693994760513306): 10 | if (input[109]) <= (0.09816226921975613): 11 | if (input[36]) <= (0.5949591398239136): 12 | if (input[91]) <= (0.780509740114212): 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | if (input[113]) <= (-4.580152690410614): 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 1.0, 0.0, 0.0] 19 | else: 20 | if (input[15]) <= (37.721368715167046): 21 | var0 = [0.0, 1.0, 0.0, 0.0] 22 | else: 23 | var0 = [1.0, 0.0, 0.0, 0.0] 24 | else: 25 | if (input[70]) <= (22.992369651794434): 26 | var0 = [1.0, 0.0, 0.0, 0.0] 27 | else: 28 | var0 = [0.0, 0.0, 0.0, 1.0] 29 | else: 30 | if (input[7]) <= (0.047884028404951096): 31 | var0 = [0.0, 1.0, 0.0, 0.0] 32 | else: 33 | var0 = [0.0, 0.0, 1.0, 0.0] 34 | if (input[18]) <= (-3.7900209426879883): 35 | var1 = [0.0, 0.0, 0.0, 1.0] 36 | else: 37 | if (input[84]) <= (-0.591367781162262): 38 | if (input[54]) <= (3.9061397910118103): 39 | var1 = [1.0, 0.0, 0.0, 0.0] 40 | else: 41 | var1 = [0.0, 1.0, 0.0, 0.0] 42 | else: 43 | if (input[71]) <= (-9.572516441345215): 44 | if (input[43]) <= (2.1188685297966003): 45 | if (input[68]) <= (9.689334392547607): 46 | var1 = [0.0, 1.0, 0.0, 0.0] 47 | else: 48 | var1 = [1.0, 0.0, 0.0, 0.0] 49 | else: 50 | var1 = [0.0, 0.0, 1.0, 0.0] 51 | else: 52 | if (input[67]) <= (-4.940435528755188): 53 | var1 = [0.0, 0.0, 1.0, 0.0] 54 | else: 55 | if (input[79]) <= (-8.565256834030151): 56 | var1 = [0.0, 0.0, 1.0, 0.0] 57 | else: 58 | var1 = [1.0, 0.0, 0.0, 0.0] 59 | if (input[42]) <= (9.537301301956177): 60 | if (input[61]) <= (-3.2273834943771362): 61 | if (input[80]) <= (9.97424602508545): 62 | var2 = [0.0, 1.0, 0.0, 0.0] 63 | else: 64 | var2 = [0.0, 0.0, 1.0, 0.0] 65 | else: 66 | if (input[61]) <= (2.249352514743805): 67 | if (input[36]) <= (0.4321534037590027): 68 | if (input[49]) <= (6.708551645278931): 69 | var2 = [1.0, 0.0, 0.0, 0.0] 70 | else: 71 | var2 = [0.0, 0.0, 1.0, 0.0] 72 | else: 73 | if (input[10]) <= (2.625954031944275): 74 | var2 = [0.0, 1.0, 0.0, 0.0] 75 | else: 76 | var2 = [1.0, 0.0, 0.0, 0.0] 77 | else: 78 | var2 = [0.0, 0.0, 1.0, 0.0] 79 | else: 80 | if (input[29]) <= (21.545801401138306): 81 | var2 = [0.0, 1.0, 0.0, 0.0] 82 | else: 83 | var2 = [0.0, 0.0, 0.0, 1.0] 84 | if (input[18]) <= (-2.8898014426231384): 85 | var3 = [0.0, 0.0, 0.0, 1.0] 86 | else: 87 | if (input[49]) <= (2.9879640340805054): 88 | if (input[61]) <= (-0.5793967843055725): 89 | if (input[42]) <= (1.6723496913909912): 90 | var3 = [1.0, 0.0, 0.0, 0.0] 91 | else: 92 | var3 = [0.0, 1.0, 0.0, 0.0] 93 | else: 94 | if (input[36]) <= (0.6332663297653198): 95 | var3 = [1.0, 0.0, 0.0, 0.0] 96 | else: 97 | var3 = [0.0, 1.0, 0.0, 0.0] 98 | else: 99 | if (input[64]) <= (-4.465649127960205): 100 | var3 = [0.0, 1.0, 0.0, 0.0] 101 | else: 102 | var3 = [0.0, 0.0, 1.0, 0.0] 103 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 104 | -------------------------------------------------------------------------------- /models/baseline/centered/random_forest/random_forest_25hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (5.029020547866821): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[67]) <= (2.2397759556770325): 10 | if (input[85]) <= (2.0566194653511047): 11 | if (input[96]) <= (-2.239775538444519): 12 | var0 = [0.0, 1.0, 0.0, 0.0] 13 | else: 14 | if (input[30]) <= (0.11611879989504814): 15 | if (input[1]) <= (1.2425909638404846): 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | if (input[134]) <= (10.581174850463867): 19 | var0 = [0.0, 0.0, 1.0, 0.0] 20 | else: 21 | var0 = [1.0, 0.0, 0.0, 0.0] 22 | else: 23 | if (input[126]) <= (0.01197100430727005): 24 | var0 = [1.0, 0.0, 0.0, 0.0] 25 | else: 26 | if (input[61]) <= (7.115567207336426): 27 | var0 = [1.0, 0.0, 0.0, 0.0] 28 | else: 29 | var0 = [0.0, 0.0, 1.0, 0.0] 30 | else: 31 | var0 = [0.0, 1.0, 0.0, 0.0] 32 | else: 33 | if (input[138]) <= (0.01915362849831581): 34 | var0 = [0.0, 1.0, 0.0, 0.0] 35 | else: 36 | var0 = [0.0, 0.0, 1.0, 0.0] 37 | if (input[62]) <= (6.321889400482178): 38 | var1 = [0.0, 0.0, 0.0, 1.0] 39 | else: 40 | if (input[71]) <= (17.858779907226562): 41 | if (input[54]) <= (2.2278045415878296): 42 | if (input[85]) <= (-10.508151173591614): 43 | var1 = [0.0, 0.0, 1.0, 0.0] 44 | else: 45 | if (input[32]) <= (10.307040214538574): 46 | var1 = [1.0, 0.0, 0.0, 0.0] 47 | else: 48 | if (input[52]) <= (0.6145037859678268): 49 | var1 = [1.0, 0.0, 0.0, 0.0] 50 | else: 51 | var1 = [0.0, 0.0, 1.0, 0.0] 52 | else: 53 | var1 = [0.0, 1.0, 0.0, 0.0] 54 | else: 55 | if (input[49]) <= (1.2713209390640259): 56 | if (input[125]) <= (12.511448860168457): 57 | var1 = [0.0, 1.0, 0.0, 0.0] 58 | else: 59 | var1 = [1.0, 0.0, 0.0, 0.0] 60 | else: 61 | var1 = [0.0, 0.0, 1.0, 0.0] 62 | if (input[58]) <= (-46.01144886016846): 63 | var2 = [0.0, 0.0, 0.0, 1.0] 64 | else: 65 | if (input[126]) <= (-0.009576809243299067): 66 | if (input[78]) <= (-2.697068512439728): 67 | var2 = [0.0, 1.0, 0.0, 0.0] 68 | else: 69 | if (input[90]) <= (-1.8171991407871246): 70 | var2 = [0.0, 1.0, 0.0, 0.0] 71 | else: 72 | var2 = [1.0, 0.0, 0.0, 0.0] 73 | else: 74 | if (input[75]) <= (-0.12977100163698196): 75 | var2 = [1.0, 0.0, 0.0, 0.0] 76 | else: 77 | if (input[119]) <= (13.183207511901855): 78 | if (input[55]) <= (0.9241619156673551): 79 | var2 = [1.0, 0.0, 0.0, 0.0] 80 | else: 81 | var2 = [0.0, 0.0, 1.0, 0.0] 82 | else: 83 | var2 = [1.0, 0.0, 0.0, 0.0] 84 | if (input[68]) <= (5.029020547866821): 85 | var3 = [0.0, 0.0, 0.0, 1.0] 86 | else: 87 | if (input[85]) <= (-3.9456446170806885): 88 | var3 = [0.0, 0.0, 1.0, 0.0] 89 | else: 90 | if (input[54]) <= (2.221819043159485): 91 | if (input[19]) <= (0.828393816947937): 92 | var3 = [1.0, 0.0, 0.0, 0.0] 93 | else: 94 | if (input[55]) <= (1.827972948551178): 95 | var3 = [1.0, 0.0, 0.0, 0.0] 96 | else: 97 | var3 = [0.0, 0.0, 1.0, 0.0] 98 | else: 99 | var3 = [0.0, 1.0, 0.0, 0.0] 100 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 101 | -------------------------------------------------------------------------------- /models/baseline/centered/random_forest/random_forest_50hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (13.075935363769531): 7 | if (input[151]) <= (-6.582857608795166): 8 | var0 = [0.0, 0.0, 1.0, 0.0] 9 | else: 10 | if (input[193]) <= (-4.569334030151367): 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | else: 13 | if (input[96]) <= (0.6476315557956696): 14 | if (input[137]) <= (70.00000381469727): 15 | var0 = [1.0, 0.0, 0.0, 0.0] 16 | else: 17 | var0 = [0.0, 1.0, 0.0, 0.0] 18 | else: 19 | if (input[233]) <= (-46.69466018676758): 20 | var0 = [1.0, 0.0, 0.0, 0.0] 21 | else: 22 | var0 = [0.0, 1.0, 0.0, 0.0] 23 | else: 24 | if (input[21]) <= (6.206106543540955): 25 | var0 = [0.0, 0.0, 0.0, 1.0] 26 | else: 27 | var0 = [1.0, 0.0, 0.0, 0.0] 28 | if (input[42]) <= (-3.162740468978882): 29 | var1 = [0.0, 0.0, 0.0, 1.0] 30 | else: 31 | if (input[168]) <= (-0.5710170865058899): 32 | if (input[270]) <= (0.023942019790410995): 33 | if (input[261]) <= (-7.057251036167145): 34 | var1 = [1.0, 0.0, 0.0, 0.0] 35 | else: 36 | var1 = [0.0, 1.0, 0.0, 0.0] 37 | else: 38 | var1 = [0.0, 0.0, 1.0, 0.0] 39 | else: 40 | if (input[103]) <= (4.177881479263306): 41 | if (input[234]) <= (-1.6627731025218964): 42 | var1 = [0.0, 1.0, 0.0, 0.0] 43 | else: 44 | if (input[144]) <= (6.847419321537018): 45 | if (input[211]) <= (-4.902127921581268): 46 | var1 = [0.0, 0.0, 1.0, 0.0] 47 | else: 48 | var1 = [1.0, 0.0, 0.0, 0.0] 49 | else: 50 | var1 = [0.0, 1.0, 0.0, 0.0] 51 | else: 52 | var1 = [0.0, 0.0, 1.0, 0.0] 53 | if (input[105]) <= (12.198474884033203): 54 | if (input[97]) <= (1.5143325328826904): 55 | if (input[168]) <= (-4.329913973808289): 56 | var2 = [0.0, 1.0, 0.0, 0.0] 57 | else: 58 | if (input[156]) <= (1.2581530213356018): 59 | if (input[169]) <= (3.4739869236946106): 60 | var2 = [1.0, 0.0, 0.0, 0.0] 61 | else: 62 | var2 = [0.0, 0.0, 1.0, 0.0] 63 | else: 64 | var2 = [0.0, 1.0, 0.0, 0.0] 65 | else: 66 | if (input[210]) <= (-0.13168107345700264): 67 | var2 = [1.0, 0.0, 0.0, 0.0] 68 | else: 69 | var2 = [0.0, 0.0, 1.0, 0.0] 70 | else: 71 | var2 = [0.0, 0.0, 0.0, 1.0] 72 | if (input[121]) <= (2.9879640340805054): 73 | if (input[109]) <= (-1.9740195274353027): 74 | var3 = [0.0, 0.0, 0.0, 1.0] 75 | else: 76 | if (input[198]) <= (-1.3227965235710144): 77 | var3 = [0.0, 1.0, 0.0, 0.0] 78 | else: 79 | if (input[180]) <= (-6.936002254486084): 80 | var3 = [0.0, 1.0, 0.0, 0.0] 81 | else: 82 | var3 = [1.0, 0.0, 0.0, 0.0] 83 | else: 84 | if (input[90]) <= (0.767341673374176): 85 | var3 = [0.0, 0.0, 1.0, 0.0] 86 | else: 87 | var3 = [0.0, 1.0, 0.0, 0.0] 88 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 89 | -------------------------------------------------------------------------------- /models/baseline/centered_aug/decision_tree/decision_tree_100hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[278]) <= (5.0266265869140625): 3 | var0 = [0.0, 0.0, 0.0, 1.0] 4 | else: 5 | if (input[211]) <= (1.829170048236847): 6 | if (input[240]) <= (1.9405004978179932): 7 | if (input[349]) <= (2.5426419973373413): 8 | if (input[354]) <= (1.8674774765968323): 9 | var0 = [1.0, 0.0, 0.0, 0.0] 10 | else: 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | if (input[301]) <= (0.1819593533873558): 14 | var0 = [0.0, 1.0, 0.0, 0.0] 15 | else: 16 | var0 = [0.0, 0.0, 1.0, 0.0] 17 | else: 18 | var0 = [0.0, 1.0, 0.0, 0.0] 19 | else: 20 | if (input[210]) <= (9.396045684814453): 21 | var0 = [0.0, 0.0, 1.0, 0.0] 22 | else: 23 | var0 = [0.0, 1.0, 0.0, 0.0] 24 | return var0 25 | -------------------------------------------------------------------------------- /models/baseline/centered_aug/decision_tree/decision_tree_10hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[21]) <= (34.04580497741699): 3 | if (input[25]) <= (4.357446908950806): 4 | if (input[24]) <= (1.9405004978179932): 5 | if (input[37]) <= (1.8758569955825806): 6 | if (input[36]) <= (2.0386629700660706): 7 | if (input[19]) <= (7.9667075872421265): 8 | if (input[43]) <= (-1.4999675154685974): 9 | var0 = [0.0, 0.0, 1.0, 0.0] 10 | else: 11 | var0 = [1.0, 0.0, 0.0, 0.0] 12 | else: 13 | var0 = [0.0, 0.0, 1.0, 0.0] 14 | else: 15 | var0 = [0.0, 1.0, 0.0, 0.0] 16 | else: 17 | if (input[48]) <= (-5.662286996841431): 18 | var0 = [0.0, 1.0, 0.0, 0.0] 19 | else: 20 | var0 = [0.0, 0.0, 1.0, 0.0] 21 | else: 22 | if (input[7]) <= (0.34835633635520935): 23 | var0 = [0.0, 1.0, 0.0, 0.0] 24 | else: 25 | if (input[42]) <= (-5.4013189524412155): 26 | var0 = [0.0, 0.0, 0.0, 1.0] 27 | else: 28 | var0 = [0.0, 0.0, 1.0, 0.0] 29 | else: 30 | if (input[13]) <= (0.11252747103571892): 31 | var0 = [0.0, 1.0, 0.0, 0.0] 32 | else: 33 | var0 = [0.0, 0.0, 1.0, 0.0] 34 | else: 35 | if (input[4]) <= (21.790077209472656): 36 | var0 = [0.0, 0.0, 0.0, 1.0] 37 | else: 38 | var0 = [1.0, 0.0, 0.0, 0.0] 39 | return var0 40 | -------------------------------------------------------------------------------- /models/baseline/centered_aug/decision_tree/decision_tree_20hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[56]) <= (5.518635034561157): 3 | var0 = [0.0, 0.0, 0.0, 1.0] 4 | else: 5 | if (input[43]) <= (1.829170048236847): 6 | if (input[48]) <= (1.9405004978179932): 7 | if (input[67]) <= (1.9895815253257751): 8 | if (input[72]) <= (2.0386629700660706): 9 | var0 = [1.0, 0.0, 0.0, 0.0] 10 | else: 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | if (input[103]) <= (0.8116343319416046): 14 | var0 = [0.0, 0.0, 1.0, 0.0] 15 | else: 16 | var0 = [0.0, 1.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 1.0, 0.0, 0.0] 19 | else: 20 | if (input[25]) <= (0.13407529890537262): 21 | var0 = [0.0, 1.0, 0.0, 0.0] 22 | else: 23 | var0 = [0.0, 0.0, 1.0, 0.0] 24 | return var0 25 | -------------------------------------------------------------------------------- /models/baseline/centered_aug/decision_tree/decision_tree_25hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[24]) <= (-2.3762454986572266): 3 | var0 = [0.0, 0.0, 0.0, 1.0] 4 | else: 5 | if (input[55]) <= (2.0566189289093018): 6 | if (input[66]) <= (1.787271499633789): 7 | if (input[85]) <= (2.318784475326538): 8 | if (input[90]) <= (2.0386629700660706): 9 | if (input[54]) <= (4.236539959907532): 10 | if (input[90]) <= (-4.114435434341431): 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | else: 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | if (input[65]) <= (100.1565055847168): 16 | var0 = [0.0, 1.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 0.0, 1.0, 0.0] 19 | else: 20 | var0 = [0.0, 1.0, 0.0, 0.0] 21 | else: 22 | if (input[114]) <= (-8.931572437286377): 23 | var0 = [0.0, 1.0, 0.0, 0.0] 24 | else: 25 | var0 = [0.0, 0.0, 1.0, 0.0] 26 | else: 27 | var0 = [0.0, 1.0, 0.0, 0.0] 28 | else: 29 | if (input[84]) <= (-7.767987489700317): 30 | var0 = [0.0, 1.0, 0.0, 0.0] 31 | else: 32 | var0 = [0.0, 0.0, 1.0, 0.0] 33 | return var0 34 | -------------------------------------------------------------------------------- /models/baseline/centered_aug/decision_tree/decision_tree_50hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[140]) <= (5.0266265869140625): 3 | var0 = [0.0, 0.0, 0.0, 1.0] 4 | else: 5 | if (input[103]) <= (1.838746964931488): 6 | if (input[120]) <= (1.9405004978179932): 7 | if (input[163]) <= (1.9009965062141418): 8 | if (input[180]) <= (2.0386629700660706): 9 | var0 = [1.0, 0.0, 0.0, 0.0] 10 | else: 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | if (input[90]) <= (0.4752489924430847): 14 | var0 = [0.0, 0.0, 1.0, 0.0] 15 | else: 16 | var0 = [0.0, 1.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 1.0, 0.0, 0.0] 19 | else: 20 | if (input[177]) <= (-2.0610689520835876): 21 | if (input[158]) <= (9.615113735198975): 22 | var0 = [0.0, 1.0, 0.0, 0.0] 23 | else: 24 | var0 = [1.0, 0.0, 0.0, 0.0] 25 | else: 26 | var0 = [0.0, 0.0, 1.0, 0.0] 27 | return var0 28 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/decision_tree/decision_tree_100hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[220]) <= (-44.62213897705078): 3 | var0 = [0.0, 0.0, 0.0, 1.0] 4 | else: 5 | if (input[217]) <= (1.8064250349998474): 6 | if (input[270]) <= (4.112041413784027): 7 | var0 = [1.0, 0.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 1.0, 0.0, 0.0] 10 | else: 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | return var0 13 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/decision_tree/decision_tree_10hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[21]) <= (35.61069107055664): 3 | if (input[24]) <= (5.415684461593628): 4 | if (input[25]) <= (2.9879640340805054): 5 | var0 = [1.0, 0.0, 0.0, 0.0] 6 | else: 7 | var0 = [0.0, 0.0, 1.0, 0.0] 8 | else: 9 | if (input[2]) <= (10.230424880981445): 10 | var0 = [0.0, 1.0, 0.0, 0.0] 11 | else: 12 | var0 = [0.0, 0.0, 1.0, 0.0] 13 | else: 14 | if (input[0]) <= (1.8207902014255524): 15 | var0 = [0.0, 0.0, 0.0, 1.0] 16 | else: 17 | var0 = [1.0, 0.0, 0.0, 0.0] 18 | return var0 19 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/decision_tree/decision_tree_20hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[32]) <= (15.24507999420166): 3 | if (input[54]) <= (5.695805311203003): 4 | if (input[49]) <= (2.9879640340805054): 5 | var0 = [1.0, 0.0, 0.0, 0.0] 6 | else: 7 | var0 = [0.0, 0.0, 1.0, 0.0] 8 | else: 9 | var0 = [0.0, 1.0, 0.0, 0.0] 10 | else: 11 | var0 = [0.0, 0.0, 0.0, 1.0] 12 | return var0 13 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/decision_tree/decision_tree_25hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[48]) <= (8.039729595184326): 3 | if (input[55]) <= (1.8064250349998474): 4 | if (input[96]) <= (-2.1260514855384827): 5 | var0 = [0.0, 1.0, 0.0, 0.0] 6 | else: 7 | var0 = [1.0, 0.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 1.0, 0.0] 10 | else: 11 | var0 = [0.0, 0.0, 0.0, 1.0] 12 | return var0 13 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/decision_tree/decision_tree_50hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[112]) <= (-44.62213897705078): 3 | var0 = [0.0, 0.0, 0.0, 1.0] 4 | else: 5 | if (input[186]) <= (-3.5901055335998535): 6 | var0 = [0.0, 1.0, 0.0, 0.0] 7 | else: 8 | if (input[115]) <= (2.3546974658966064): 9 | var0 = [1.0, 0.0, 0.0, 0.0] 10 | else: 11 | var0 = [0.0, 0.0, 1.0, 0.0] 12 | return var0 13 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/random_forest/random_forest_100hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[229]) <= (2.3546974658966064): 7 | if (input[149]) <= (86.36641311645508): 8 | if (input[372]) <= (-2.9975410103797913): 9 | var0 = [0.0, 1.0, 0.0, 0.0] 10 | else: 11 | var0 = [1.0, 0.0, 0.0, 0.0] 12 | else: 13 | if (input[240]) <= (0.9732429385185242): 14 | var0 = [1.0, 0.0, 0.0, 0.0] 15 | else: 16 | var0 = [0.0, 0.0, 0.0, 1.0] 17 | else: 18 | if (input[454]) <= (0.7595419883728027): 19 | var0 = [0.0, 1.0, 0.0, 0.0] 20 | else: 21 | var0 = [0.0, 0.0, 1.0, 0.0] 22 | if (input[276]) <= (4.514267683029175): 23 | if (input[229]) <= (2.3546974658966064): 24 | if (input[84]) <= (-3.6667200326919556): 25 | var1 = [0.0, 0.0, 0.0, 1.0] 26 | else: 27 | var1 = [1.0, 0.0, 0.0, 0.0] 28 | else: 29 | var1 = [0.0, 0.0, 1.0, 0.0] 30 | else: 31 | if (input[132]) <= (-0.35194770246744156): 32 | if (input[256]) <= (-22.09923791885376): 33 | var1 = [0.0, 0.0, 0.0, 1.0] 34 | else: 35 | var1 = [0.0, 0.0, 1.0, 0.0] 36 | else: 37 | var1 = [0.0, 1.0, 0.0, 0.0] 38 | if (input[241]) <= (-2.439691483974457): 39 | var2 = [0.0, 0.0, 0.0, 1.0] 40 | else: 41 | if (input[264]) <= (5.963956594467163): 42 | if (input[291]) <= (-0.09923665225505829): 43 | if (input[307]) <= (-7.587225914001465): 44 | var2 = [0.0, 0.0, 1.0, 0.0] 45 | else: 46 | var2 = [1.0, 0.0, 0.0, 0.0] 47 | else: 48 | if (input[15]) <= (-0.20610686764121056): 49 | if (input[291]) <= (20.39694619178772): 50 | var2 = [0.0, 0.0, 1.0, 0.0] 51 | else: 52 | var2 = [1.0, 0.0, 0.0, 0.0] 53 | else: 54 | var2 = [1.0, 0.0, 0.0, 0.0] 55 | else: 56 | var2 = [0.0, 1.0, 0.0, 0.0] 57 | if (input[140]) <= (14.522029876708984): 58 | if (input[402]) <= (-1.5873559713363647): 59 | var3 = [0.0, 1.0, 0.0, 0.0] 60 | else: 61 | if (input[301]) <= (-2.6922794580459595): 62 | var3 = [0.0, 0.0, 1.0, 0.0] 63 | else: 64 | if (input[291]) <= (-0.09541984647512436): 65 | if (input[257]) <= (92.56488990783691): 66 | var3 = [1.0, 0.0, 0.0, 0.0] 67 | else: 68 | var3 = [0.0, 1.0, 0.0, 0.0] 69 | else: 70 | if (input[289]) <= (3.5517985224723816): 71 | if (input[480]) <= (-0.32680854201316833): 72 | var3 = [0.0, 1.0, 0.0, 0.0] 73 | else: 74 | var3 = [1.0, 0.0, 0.0, 0.0] 75 | else: 76 | var3 = [0.0, 0.0, 1.0, 0.0] 77 | else: 78 | var3 = [0.0, 0.0, 0.0, 1.0] 79 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 80 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/random_forest/random_forest_25hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (5.029020547866821): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[132]) <= (0.06344634480774403): 10 | if (input[120]) <= (-0.9289501309394836): 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | if (input[96]) <= (-1.933318018913269): 14 | var0 = [0.0, 1.0, 0.0, 0.0] 15 | else: 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | if (input[31]) <= (0.14844050258398056): 19 | var0 = [1.0, 0.0, 0.0, 0.0] 20 | else: 21 | if (input[85]) <= (-2.94845911860466): 22 | var0 = [0.0, 0.0, 1.0, 0.0] 23 | else: 24 | if (input[55]) <= (10.286387205123901): 25 | var0 = [1.0, 0.0, 0.0, 0.0] 26 | else: 27 | var0 = [0.0, 0.0, 1.0, 0.0] 28 | if (input[62]) <= (7.161057472229004): 29 | if (input[32]) <= (10.105924129486084): 30 | var1 = [1.0, 0.0, 0.0, 0.0] 31 | else: 32 | var1 = [0.0, 0.0, 0.0, 1.0] 33 | else: 34 | if (input[54]) <= (2.0925320386886597): 35 | if (input[85]) <= (-5.602432310581207): 36 | var1 = [0.0, 0.0, 1.0, 0.0] 37 | else: 38 | if (input[49]) <= (10.7748042345047): 39 | if (input[36]) <= (0.23942014575004578): 40 | var1 = [1.0, 0.0, 0.0, 0.0] 41 | else: 42 | if (input[67]) <= (4.6842557191848755): 43 | var1 = [1.0, 0.0, 0.0, 0.0] 44 | else: 45 | var1 = [0.0, 0.0, 1.0, 0.0] 46 | else: 47 | var1 = [0.0, 0.0, 1.0, 0.0] 48 | else: 49 | if (input[126]) <= (0.06344634294509888): 50 | var1 = [0.0, 1.0, 0.0, 0.0] 51 | else: 52 | var1 = [0.0, 0.0, 1.0, 0.0] 53 | if (input[58]) <= (-37.6068696975708): 54 | var2 = [0.0, 0.0, 0.0, 1.0] 55 | else: 56 | if (input[126]) <= (-0.16639699786901474): 57 | if (input[114]) <= (-0.49559973180294037): 58 | if (input[90]) <= (-1.5023615919053555): 59 | var2 = [0.0, 1.0, 0.0, 0.0] 60 | else: 61 | var2 = [1.0, 0.0, 0.0, 0.0] 62 | else: 63 | if (input[54]) <= (1.9680339097976685): 64 | var2 = [1.0, 0.0, 0.0, 0.0] 65 | else: 66 | var2 = [0.0, 1.0, 0.0, 0.0] 67 | else: 68 | if (input[9]) <= (-0.3206106945872307): 69 | if (input[55]) <= (1.8064250349998474): 70 | if (input[7]) <= (-0.003591302433051169): 71 | if (input[141]) <= (2.324427545070648): 72 | var2 = [0.0, 1.0, 0.0, 0.0] 73 | else: 74 | var2 = [1.0, 0.0, 0.0, 0.0] 75 | else: 76 | var2 = [1.0, 0.0, 0.0, 0.0] 77 | else: 78 | var2 = [0.0, 0.0, 1.0, 0.0] 79 | else: 80 | var2 = [1.0, 0.0, 0.0, 0.0] 81 | if (input[68]) <= (5.029020547866821): 82 | var3 = [0.0, 0.0, 0.0, 1.0] 83 | else: 84 | if (input[79]) <= (-5.8418519496917725): 85 | var3 = [0.0, 0.0, 1.0, 0.0] 86 | else: 87 | if (input[54]) <= (2.0925320386886597): 88 | if (input[97]) <= (-5.585672497749329): 89 | var3 = [0.0, 0.0, 1.0, 0.0] 90 | else: 91 | var3 = [1.0, 0.0, 0.0, 0.0] 92 | else: 93 | var3 = [0.0, 1.0, 0.0, 0.0] 94 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 95 | -------------------------------------------------------------------------------- /models/baseline/centered_smote/random_forest/random_forest_50hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[30]) <= (-1.5478515028953552): 7 | if (input[168]) <= (-1.5346833802759647): 8 | var0 = [0.0, 0.0, 0.0, 1.0] 9 | else: 10 | var0 = [1.0, 0.0, 0.0, 0.0] 11 | else: 12 | if (input[121]) <= (2.9113495349884033): 13 | if (input[96]) <= (0.6476315557956696): 14 | if (input[228]) <= (-3.653551459312439): 15 | var0 = [0.0, 1.0, 0.0, 0.0] 16 | else: 17 | var0 = [1.0, 0.0, 0.0, 0.0] 18 | else: 19 | if (input[298]) <= (9.091602563858032): 20 | var0 = [0.0, 1.0, 0.0, 0.0] 21 | else: 22 | var0 = [1.0, 0.0, 0.0, 0.0] 23 | else: 24 | if (input[207]) <= (-0.2748091518878937): 25 | var0 = [0.0, 0.0, 1.0, 0.0] 26 | else: 27 | var0 = [0.0, 1.0, 0.0, 0.0] 28 | if (input[42]) <= (-3.162740468978882): 29 | var1 = [0.0, 0.0, 0.0, 1.0] 30 | else: 31 | if (input[132]) <= (5.540183067321777): 32 | if (input[199]) <= (-1.446097493171692): 33 | if (input[305]) <= (28.732824444770813): 34 | var1 = [0.0, 0.0, 1.0, 0.0] 35 | else: 36 | var1 = [1.0, 0.0, 0.0, 0.0] 37 | else: 38 | if (input[103]) <= (2.5187000036239624): 39 | var1 = [1.0, 0.0, 0.0, 0.0] 40 | else: 41 | var1 = [0.0, 0.0, 1.0, 0.0] 42 | else: 43 | var1 = [0.0, 1.0, 0.0, 0.0] 44 | if (input[86]) <= (11.159375190734863): 45 | if (input[31]) <= (0.0825999528169632): 46 | if (input[234]) <= (-0.36750999093055725): 47 | if (input[237]) <= (-13.809159636497498): 48 | var2 = [1.0, 0.0, 0.0, 0.0] 49 | else: 50 | var2 = [0.0, 1.0, 0.0, 0.0] 51 | else: 52 | if (input[156]) <= (-6.622361719608307): 53 | var2 = [0.0, 1.0, 0.0, 0.0] 54 | else: 55 | if (input[210]) <= (-1.1552023887634277): 56 | var2 = [0.0, 1.0, 0.0, 0.0] 57 | else: 58 | var2 = [1.0, 0.0, 0.0, 0.0] 59 | else: 60 | if (input[127]) <= (3.3602619767189026): 61 | if (input[96]) <= (-2.941276431083679): 62 | var2 = [0.0, 0.0, 1.0, 0.0] 63 | else: 64 | var2 = [1.0, 0.0, 0.0, 0.0] 65 | else: 66 | var2 = [0.0, 0.0, 1.0, 0.0] 67 | else: 68 | if (input[140]) <= (7.3238654136657715): 69 | var2 = [0.0, 0.0, 0.0, 1.0] 70 | else: 71 | var2 = [1.0, 0.0, 0.0, 0.0] 72 | if (input[112]) <= (-42.316795349121094): 73 | var3 = [0.0, 0.0, 0.0, 1.0] 74 | else: 75 | if (input[109]) <= (1.8064250349998474): 76 | if (input[198]) <= (-1.4688425064086914): 77 | var3 = [0.0, 1.0, 0.0, 0.0] 78 | else: 79 | if (input[180]) <= (-6.664260268211365): 80 | var3 = [0.0, 1.0, 0.0, 0.0] 81 | else: 82 | var3 = [1.0, 0.0, 0.0, 0.0] 83 | else: 84 | var3 = [0.0, 0.0, 1.0, 0.0] 85 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 86 | -------------------------------------------------------------------------------- /models/baseline/end/decision_tree/decision_tree_100hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[180]) <= (3.488352060317993): 3 | if (input[343]) <= (3.250128984451294): 4 | if (input[486]) <= (-2.141613483428955): 5 | var0 = [0.0, 1.0, 0.0, 0.0] 6 | else: 7 | var0 = [1.0, 0.0, 0.0, 0.0] 8 | else: 9 | if (input[389]) <= (-44.740455627441406): 10 | var0 = [0.0, 1.0, 0.0, 0.0] 11 | else: 12 | var0 = [0.0, 0.0, 1.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 0.0, 1.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/end/decision_tree/decision_tree_10hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[24]) <= (2.3139960765838623): 3 | if (input[31]) <= (1.8171990513801575): 4 | if (input[36]) <= (4.377797901630402): 5 | if (input[37]) <= (3.5458129048347473): 6 | var0 = [1.0, 0.0, 0.0, 0.0] 7 | else: 8 | var0 = [0.0, 0.0, 1.0, 0.0] 9 | else: 10 | var0 = [0.0, 1.0, 0.0, 0.0] 11 | else: 12 | var0 = [0.0, 0.0, 1.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 0.0, 1.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/end/decision_tree/decision_tree_20hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[48]) <= (2.3139960765838623): 3 | if (input[67]) <= (1.8902224898338318): 4 | if (input[78]) <= (3.666719973087311): 5 | var0 = [1.0, 0.0, 0.0, 0.0] 6 | else: 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | if (input[83]) <= (-53.12976837158203): 10 | var0 = [0.0, 1.0, 0.0, 0.0] 11 | else: 12 | var0 = [0.0, 0.0, 1.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 0.0, 1.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/end/decision_tree/decision_tree_25hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[48]) <= (5.516241073608398): 3 | if (input[85]) <= (2.318784475326538): 4 | if (input[90]) <= (4.377797901630402): 5 | var0 = [1.0, 0.0, 0.0, 0.0] 6 | else: 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | if (input[107]) <= (-75.79389381408691): 10 | var0 = [0.0, 1.0, 0.0, 0.0] 11 | else: 12 | var0 = [0.0, 0.0, 1.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 0.0, 1.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/end/decision_tree/decision_tree_50hz.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[112]) <= (-44.62213897705078): 3 | var0 = [0.0, 0.0, 0.0, 1.0] 4 | else: 5 | if (input[169]) <= (2.318784475326538): 6 | if (input[228]) <= (-1.1396400332450867): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [1.0, 0.0, 0.0, 0.0] 10 | else: 11 | if (input[302]) <= (10.096350193023682): 12 | var0 = [0.0, 1.0, 0.0, 0.0] 13 | else: 14 | var0 = [0.0, 0.0, 1.0, 0.0] 15 | return var0 16 | -------------------------------------------------------------------------------- /models/baseline/end/random_forest/random_forest_100hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[214]) <= (-50.04961967468262): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[456]) <= (-1.1168950200080872): 10 | if (input[325]) <= (1.879448413848877): 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | var0 = [0.0, 0.0, 1.0, 0.0] 14 | else: 15 | if (input[427]) <= (-3.3614595532417297): 16 | var0 = [0.0, 0.0, 1.0, 0.0] 17 | else: 18 | var0 = [1.0, 0.0, 0.0, 0.0] 19 | if (input[367]) <= (1.210269033908844): 20 | if (input[360]) <= (4.7369285225868225): 21 | if (input[397]) <= (-8.547301054000854): 22 | var1 = [0.0, 0.0, 1.0, 0.0] 23 | else: 24 | if (input[132]) <= (-2.8203694820404053): 25 | var1 = [0.0, 0.0, 0.0, 1.0] 26 | else: 27 | var1 = [1.0, 0.0, 0.0, 0.0] 28 | else: 29 | if (input[103]) <= (1.5682018548250198): 30 | var1 = [0.0, 1.0, 0.0, 0.0] 31 | else: 32 | var1 = [0.0, 0.0, 0.0, 1.0] 33 | else: 34 | if (input[175]) <= (0.1759737953543663): 35 | if (input[90]) <= (-2.3989899903535843): 36 | var1 = [0.0, 0.0, 0.0, 1.0] 37 | else: 38 | var1 = [0.0, 1.0, 0.0, 0.0] 39 | else: 40 | var1 = [0.0, 0.0, 1.0, 0.0] 41 | if (input[241]) <= (-2.439691483974457): 42 | var2 = [0.0, 0.0, 0.0, 1.0] 43 | else: 44 | if (input[63]) <= (0.10305344313383102): 45 | if (input[295]) <= (1.4125789999961853): 46 | if (input[343]) <= (0.7984662652015686): 47 | if (input[270]) <= (0.5913678109645844): 48 | var2 = [1.0, 0.0, 0.0, 0.0] 49 | else: 50 | if (input[595]) <= (-0.7410053163766861): 51 | var2 = [1.0, 0.0, 0.0, 0.0] 52 | else: 53 | var2 = [0.0, 1.0, 0.0, 0.0] 54 | else: 55 | if (input[462]) <= (-6.933608055114746): 56 | var2 = [0.0, 1.0, 0.0, 0.0] 57 | else: 58 | var2 = [0.0, 0.0, 1.0, 0.0] 59 | else: 60 | var2 = [0.0, 0.0, 1.0, 0.0] 61 | else: 62 | if (input[420]) <= (2.38821604847908): 63 | var2 = [1.0, 0.0, 0.0, 0.0] 64 | else: 65 | var2 = [0.0, 1.0, 0.0, 0.0] 66 | if (input[319]) <= (1.821987509727478): 67 | if (input[226]) <= (-49.1984748840332): 68 | var3 = [0.0, 0.0, 0.0, 1.0] 69 | else: 70 | if (input[480]) <= (-2.1092916131019592): 71 | var3 = [0.0, 1.0, 0.0, 0.0] 72 | else: 73 | var3 = [1.0, 0.0, 0.0, 0.0] 74 | else: 75 | if (input[333]) <= (-43.88549694418907): 76 | var3 = [0.0, 0.0, 0.0, 1.0] 77 | else: 78 | var3 = [0.0, 0.0, 1.0, 0.0] 79 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 80 | -------------------------------------------------------------------------------- /models/baseline/end/random_forest/random_forest_10hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[6]) <= (-1.5478515028953552): 7 | if (input[39]) <= (-40.73282432556152): 8 | var0 = [0.0, 0.0, 0.0, 1.0] 9 | else: 10 | var0 = [1.0, 0.0, 0.0, 0.0] 11 | else: 12 | if (input[43]) <= (-3.645172119140625): 13 | var0 = [0.0, 0.0, 1.0, 0.0] 14 | else: 15 | if (input[54]) <= (-3.4296940565109253): 16 | var0 = [0.0, 1.0, 0.0, 0.0] 17 | else: 18 | if (input[37]) <= (2.773682415485382): 19 | if (input[53]) <= (14.862594604492188): 20 | var0 = [1.0, 0.0, 0.0, 0.0] 21 | else: 22 | if (input[43]) <= (1.720233976840973): 23 | if (input[42]) <= (-14.955379962921143): 24 | var0 = [0.0, 1.0, 0.0, 0.0] 25 | else: 26 | var0 = [1.0, 0.0, 0.0, 0.0] 27 | else: 28 | var0 = [0.0, 1.0, 0.0, 0.0] 29 | else: 30 | if (input[38]) <= (10.66137981414795): 31 | var0 = [0.0, 0.0, 1.0, 0.0] 32 | else: 33 | var0 = [0.0, 1.0, 0.0, 0.0] 34 | if (input[6]) <= (-1.5478515028953552): 35 | if (input[26]) <= (7.443572998046875): 36 | var1 = [0.0, 0.0, 0.0, 1.0] 37 | else: 38 | var1 = [1.0, 0.0, 0.0, 0.0] 39 | else: 40 | if (input[43]) <= (-3.897760033607483): 41 | var1 = [0.0, 0.0, 1.0, 0.0] 42 | else: 43 | if (input[18]) <= (0.5027822852134705): 44 | if (input[42]) <= (1.5011644959449768): 45 | if (input[45]) <= (-3.3664119243621826): 46 | if (input[48]) <= (-2.5737670063972473): 47 | var1 = [0.0, 1.0, 0.0, 0.0] 48 | else: 49 | var1 = [1.0, 0.0, 0.0, 0.0] 50 | else: 51 | var1 = [1.0, 0.0, 0.0, 0.0] 52 | else: 53 | if (input[7]) <= (0.3040636032819748): 54 | var1 = [0.0, 1.0, 0.0, 0.0] 55 | else: 56 | var1 = [0.0, 0.0, 1.0, 0.0] 57 | else: 58 | if (input[23]) <= (-7.709923028945923): 59 | var1 = [1.0, 0.0, 0.0, 0.0] 60 | else: 61 | if (input[40]) <= (13.503816843032837): 62 | var1 = [0.0, 1.0, 0.0, 0.0] 63 | else: 64 | var1 = [1.0, 0.0, 0.0, 0.0] 65 | if (input[18]) <= (3.1376015543937683): 66 | if (input[31]) <= (1.4820110201835632): 67 | if (input[34]) <= (-0.9274809807538986): 68 | var2 = [1.0, 0.0, 0.0, 0.0] 69 | else: 70 | if (input[3]) <= (-0.6793892979621887): 71 | if (input[9]) <= (1.1221371293067932): 72 | if (input[31]) <= (0.23582889884710312): 73 | var2 = [0.0, 1.0, 0.0, 0.0] 74 | else: 75 | if (input[19]) <= (0.42018238455057144): 76 | if (input[50]) <= (9.4930100440979): 77 | var2 = [0.0, 1.0, 0.0, 0.0] 78 | else: 79 | var2 = [1.0, 0.0, 0.0, 0.0] 80 | else: 81 | var2 = [0.0, 0.0, 1.0, 0.0] 82 | else: 83 | var2 = [1.0, 0.0, 0.0, 0.0] 84 | else: 85 | if (input[48]) <= (-2.7210104167461395): 86 | var2 = [0.0, 1.0, 0.0, 0.0] 87 | else: 88 | var2 = [1.0, 0.0, 0.0, 0.0] 89 | else: 90 | var2 = [0.0, 0.0, 1.0, 0.0] 91 | else: 92 | var2 = [0.0, 0.0, 0.0, 1.0] 93 | if (input[25]) <= (-2.3271644711494446): 94 | if (input[7]) <= (-0.020350754261016846): 95 | var3 = [1.0, 0.0, 0.0, 0.0] 96 | else: 97 | var3 = [0.0, 0.0, 0.0, 1.0] 98 | else: 99 | if (input[31]) <= (1.8171990513801575): 100 | if (input[36]) <= (4.377797901630402): 101 | if (input[44]) <= (10.465054988861084): 102 | var3 = [1.0, 0.0, 0.0, 0.0] 103 | else: 104 | if (input[59]) <= (11.103055000305176): 105 | var3 = [1.0, 0.0, 0.0, 0.0] 106 | else: 107 | if (input[55]) <= (-3.5158849954605103): 108 | var3 = [0.0, 0.0, 1.0, 0.0] 109 | else: 110 | var3 = [1.0, 0.0, 0.0, 0.0] 111 | else: 112 | var3 = [0.0, 1.0, 0.0, 0.0] 113 | else: 114 | var3 = [0.0, 0.0, 1.0, 0.0] 115 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 116 | -------------------------------------------------------------------------------- /models/baseline/end/random_forest/random_forest_20hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[75]) <= (-59.87022590637207): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[72]) <= (5.287594437599182): 10 | if (input[12]) <= (-0.038307225331664085): 11 | if (input[66]) <= (-0.6907271444797516): 12 | if (input[46]) <= (1.358778476715088): 13 | var0 = [0.0, 0.0, 1.0, 0.0] 14 | else: 15 | var0 = [1.0, 0.0, 0.0, 0.0] 16 | else: 17 | var0 = [1.0, 0.0, 0.0, 0.0] 18 | else: 19 | if (input[14]) <= (10.122684955596924): 20 | if (input[61]) <= (5.731718480587006): 21 | var0 = [1.0, 0.0, 0.0, 0.0] 22 | else: 23 | var0 = [0.0, 0.0, 1.0, 0.0] 24 | else: 25 | if (input[122]) <= (10.086774826049805): 26 | var0 = [1.0, 0.0, 0.0, 0.0] 27 | else: 28 | if (input[67]) <= (2.232593387365341): 29 | var0 = [1.0, 0.0, 0.0, 0.0] 30 | else: 31 | var0 = [0.0, 0.0, 1.0, 0.0] 32 | else: 33 | if (input[45]) <= (1.8549616746604443): 34 | var0 = [0.0, 1.0, 0.0, 0.0] 35 | else: 36 | var0 = [0.0, 0.0, 0.0, 1.0] 37 | if (input[18]) <= (-3.7900209426879883): 38 | var1 = [0.0, 0.0, 0.0, 1.0] 39 | else: 40 | if (input[91]) <= (-2.583343505859375): 41 | var1 = [0.0, 0.0, 1.0, 0.0] 42 | else: 43 | if (input[66]) <= (2.050634026527405): 44 | var1 = [1.0, 0.0, 0.0, 0.0] 45 | else: 46 | if (input[46]) <= (0.606870174407959): 47 | var1 = [0.0, 0.0, 1.0, 0.0] 48 | else: 49 | var1 = [0.0, 1.0, 0.0, 0.0] 50 | if (input[42]) <= (6.155491232872009): 51 | if (input[61]) <= (1.4820110201835632): 52 | if (input[54]) <= (0.5626373887062073): 53 | if (input[66]) <= (3.5745434165000916): 54 | if (input[87]) <= (1.90076345205307): 55 | var2 = [1.0, 0.0, 0.0, 0.0] 56 | else: 57 | if (input[49]) <= (1.0295066237449646): 58 | var2 = [1.0, 0.0, 0.0, 0.0] 59 | else: 60 | var2 = [0.0, 0.0, 1.0, 0.0] 61 | else: 62 | var2 = [0.0, 1.0, 0.0, 0.0] 63 | else: 64 | if (input[108]) <= (-0.1280898004770279): 65 | var2 = [0.0, 1.0, 0.0, 0.0] 66 | else: 67 | if (input[78]) <= (6.846220523118973): 68 | var2 = [1.0, 0.0, 0.0, 0.0] 69 | else: 70 | var2 = [0.0, 1.0, 0.0, 0.0] 71 | else: 72 | var2 = [0.0, 0.0, 1.0, 0.0] 73 | else: 74 | var2 = [0.0, 0.0, 0.0, 1.0] 75 | if (input[18]) <= (-2.8898014426231384): 76 | var3 = [0.0, 0.0, 0.0, 1.0] 77 | else: 78 | if (input[91]) <= (-4.071340084075928): 79 | var3 = [0.0, 0.0, 1.0, 0.0] 80 | else: 81 | if (input[31]) <= (0.09217675775289536): 82 | if (input[70]) <= (-1.458014965057373): 83 | var3 = [1.0, 0.0, 0.0, 0.0] 84 | else: 85 | if (input[116]) <= (10.190920352935791): 86 | if (input[56]) <= (10.058039665222168): 87 | var3 = [1.0, 0.0, 0.0, 0.0] 88 | else: 89 | var3 = [0.0, 1.0, 0.0, 0.0] 90 | else: 91 | var3 = [1.0, 0.0, 0.0, 0.0] 92 | else: 93 | if (input[61]) <= (0.9241617918014526): 94 | if (input[96]) <= (-2.1320366263389587): 95 | var3 = [0.0, 0.0, 1.0, 0.0] 96 | else: 97 | var3 = [1.0, 0.0, 0.0, 0.0] 98 | else: 99 | var3 = [0.0, 0.0, 1.0, 0.0] 100 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 101 | -------------------------------------------------------------------------------- /models/baseline/end/random_forest/random_forest_25hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (5.029020547866821): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[67]) <= (1.039083480834961): 10 | if (input[120]) <= (-2.5737670063972473): 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | if (input[96]) <= (-0.6117185354232788): 14 | if (input[153]) <= (0.7137402594089508): 15 | if (input[29]) <= (-56.43512010574341): 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 0.0, 1.0, 0.0] 19 | else: 20 | var0 = [1.0, 0.0, 0.0, 0.0] 21 | else: 22 | if (input[12]) <= (0.008379704784601927): 23 | var0 = [1.0, 0.0, 0.0, 0.0] 24 | else: 25 | if (input[121]) <= (-3.2202008962631226): 26 | var0 = [0.0, 0.0, 1.0, 0.0] 27 | else: 28 | var0 = [1.0, 0.0, 0.0, 0.0] 29 | else: 30 | if (input[33]) <= (-9.805343627929688): 31 | var0 = [1.0, 0.0, 0.0, 0.0] 32 | else: 33 | var0 = [0.0, 0.0, 1.0, 0.0] 34 | if (input[62]) <= (6.321889400482178): 35 | var1 = [0.0, 0.0, 0.0, 1.0] 36 | else: 37 | if (input[78]) <= (1.3407530188560486): 38 | if (input[54]) <= (0.10534487664699554): 39 | if (input[85]) <= (4.841075658798218): 40 | var1 = [1.0, 0.0, 0.0, 0.0] 41 | else: 42 | var1 = [0.0, 0.0, 1.0, 0.0] 43 | else: 44 | if (input[139]) <= (-0.15562312118709087): 45 | var1 = [1.0, 0.0, 0.0, 0.0] 46 | else: 47 | if (input[94]) <= (-1.1984731554985046): 48 | var1 = [1.0, 0.0, 0.0, 0.0] 49 | else: 50 | var1 = [0.0, 0.0, 1.0, 0.0] 51 | else: 52 | if (input[67]) <= (0.8295910060405731): 53 | if (input[17]) <= (-8.236639022827148): 54 | var1 = [1.0, 0.0, 0.0, 0.0] 55 | else: 56 | var1 = [0.0, 1.0, 0.0, 0.0] 57 | else: 58 | var1 = [0.0, 0.0, 1.0, 0.0] 59 | if (input[58]) <= (-46.01144886016846): 60 | var2 = [0.0, 0.0, 0.0, 1.0] 61 | else: 62 | if (input[76]) <= (-0.645038079470396): 63 | var2 = [1.0, 0.0, 0.0, 0.0] 64 | else: 65 | if (input[114]) <= (-5.020640969276428): 66 | if (input[90]) <= (3.6439752876758575): 67 | var2 = [0.0, 0.0, 1.0, 0.0] 68 | else: 69 | var2 = [0.0, 1.0, 0.0, 0.0] 70 | else: 71 | if (input[54]) <= (-0.06224924139678478): 72 | if (input[127]) <= (-2.5318684577941895): 73 | var2 = [0.0, 0.0, 1.0, 0.0] 74 | else: 75 | var2 = [1.0, 0.0, 0.0, 0.0] 76 | else: 77 | if (input[76]) <= (3.5305346250534058): 78 | if (input[89]) <= (-20.465649604797363): 79 | if (input[141]) <= (41.58778864145279): 80 | var2 = [0.0, 1.0, 0.0, 0.0] 81 | else: 82 | var2 = [1.0, 0.0, 0.0, 0.0] 83 | else: 84 | var2 = [0.0, 0.0, 1.0, 0.0] 85 | else: 86 | var2 = [1.0, 0.0, 0.0, 0.0] 87 | if (input[91]) <= (1.539471983909607): 88 | if (input[25]) <= (1.7298104763031006): 89 | if (input[114]) <= (-1.0869677662849426): 90 | if (input[2]) <= (10.245989799499512): 91 | var3 = [0.0, 1.0, 0.0, 0.0] 92 | else: 93 | var3 = [0.0, 0.0, 0.0, 1.0] 94 | else: 95 | var3 = [1.0, 0.0, 0.0, 0.0] 96 | else: 97 | var3 = [0.0, 0.0, 0.0, 1.0] 98 | else: 99 | if (input[55]) <= (0.17956510186195374): 100 | if (input[8]) <= (10.131064891815186): 101 | var3 = [0.0, 0.0, 0.0, 1.0] 102 | else: 103 | var3 = [0.0, 1.0, 0.0, 0.0] 104 | else: 105 | var3 = [0.0, 0.0, 1.0, 0.0] 106 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 107 | -------------------------------------------------------------------------------- /models/baseline/end/random_forest/random_forest_50hz.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (13.075935363769531): 7 | if (input[151]) <= (1.8662800192832947): 8 | if (input[209]) <= (31.10305404663086): 9 | if (input[246]) <= (-3.5769375562667847): 10 | if (input[3]) <= (-0.39694660902023315): 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | var0 = [1.0, 0.0, 0.0, 0.0] 16 | else: 17 | if (input[234]) <= (-3.1471779346466064): 18 | var0 = [0.0, 1.0, 0.0, 0.0] 19 | else: 20 | var0 = [1.0, 0.0, 0.0, 0.0] 21 | else: 22 | var0 = [0.0, 0.0, 1.0, 0.0] 23 | else: 24 | if (input[21]) <= (6.206106543540955): 25 | var0 = [0.0, 0.0, 0.0, 1.0] 26 | else: 27 | var0 = [1.0, 0.0, 0.0, 0.0] 28 | if (input[181]) <= (1.2138599753379822): 29 | if (input[174]) <= (1.9512745141983032): 30 | if (input[174]) <= (-2.346318006515503): 31 | if (input[305]) <= (-14.919846013188362): 32 | var1 = [0.0, 0.0, 0.0, 1.0] 33 | else: 34 | var1 = [0.0, 0.0, 1.0, 0.0] 35 | else: 36 | var1 = [1.0, 0.0, 0.0, 0.0] 37 | else: 38 | if (input[19]) <= (0.0790086630731821): 39 | var1 = [0.0, 1.0, 0.0, 0.0] 40 | else: 41 | if (input[72]) <= (3.30758935585618): 42 | var1 = [0.0, 0.0, 1.0, 0.0] 43 | else: 44 | var1 = [0.0, 0.0, 0.0, 1.0] 45 | else: 46 | if (input[83]) <= (48.32061553001404): 47 | if (input[169]) <= (2.318784475326538): 48 | var1 = [0.0, 1.0, 0.0, 0.0] 49 | else: 50 | var1 = [0.0, 0.0, 1.0, 0.0] 51 | else: 52 | var1 = [0.0, 0.0, 0.0, 1.0] 53 | if (input[120]) <= (2.181117534637451): 54 | if (input[39]) <= (-0.5229008197784424): 55 | if (input[294]) <= (-0.06344635970890522): 56 | if (input[156]) <= (1.0426747351884842): 57 | var2 = [1.0, 0.0, 0.0, 0.0] 58 | else: 59 | var2 = [0.0, 1.0, 0.0, 0.0] 60 | else: 61 | if (input[169]) <= (2.182314932346344): 62 | if (input[210]) <= (2.659958004951477): 63 | var2 = [1.0, 0.0, 0.0, 0.0] 64 | else: 65 | var2 = [0.0, 1.0, 0.0, 0.0] 66 | else: 67 | var2 = [0.0, 0.0, 1.0, 0.0] 68 | else: 69 | if (input[198]) <= (1.4664486944675446): 70 | var2 = [1.0, 0.0, 0.0, 0.0] 71 | else: 72 | if (input[25]) <= (0.3543418552726507): 73 | var2 = [0.0, 1.0, 0.0, 0.0] 74 | else: 75 | var2 = [0.0, 0.0, 1.0, 0.0] 76 | else: 77 | var2 = [0.0, 0.0, 0.0, 1.0] 78 | if (input[112]) <= (-44.62213897705078): 79 | var3 = [0.0, 0.0, 0.0, 1.0] 80 | else: 81 | if (input[181]) <= (4.513070583343506): 82 | if (input[198]) <= (3.9097315073013306): 83 | if (input[180]) <= (8.130707800388336): 84 | var3 = [1.0, 0.0, 0.0, 0.0] 85 | else: 86 | var3 = [0.0, 1.0, 0.0, 0.0] 87 | else: 88 | var3 = [0.0, 1.0, 0.0, 0.0] 89 | else: 90 | var3 = [0.0, 0.0, 1.0, 0.0] 91 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 92 | -------------------------------------------------------------------------------- /models/optimized/base/decision_tree/decision_tree_30462fd.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[37]) <= (-2.163161516189575): 3 | if (input[46]) <= (6.84981107711792): 4 | var0 = [0.0, 0.0, 0.0, 1.0] 5 | else: 6 | if (input[92]) <= (-0.050278233364224434): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 1.0, 0.0] 10 | else: 11 | if (input[24]) <= (3.6942529678344727): 12 | if (input[21]) <= (3.3339260816574097): 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | var0 = [0.0, 0.0, 1.0, 0.0] 16 | else: 17 | var0 = [0.0, 1.0, 0.0, 0.0] 18 | return var0 19 | -------------------------------------------------------------------------------- /models/optimized/base/decision_tree/decision_tree_36284c7.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[37]) <= (-2.163161516189575): 3 | if (input[39]) <= (-27.576337337493896): 4 | var0 = [0.0, 0.0, 0.0, 1.0] 5 | else: 6 | if (input[92]) <= (-0.050278233364224434): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 1.0, 0.0] 10 | else: 11 | if (input[24]) <= (3.6942529678344727): 12 | if (input[21]) <= (3.3339260816574097): 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | var0 = [0.0, 0.0, 1.0, 0.0] 16 | else: 17 | var0 = [0.0, 1.0, 0.0, 0.0] 18 | return var0 19 | -------------------------------------------------------------------------------- /models/optimized/base/decision_tree/decision_tree_4edbe66.py: -------------------------------------------------------------------------------- 1 | def score(input): 2 | if (input[37]) <= (-2.163161516189575): 3 | if (input[51]) <= (-57.030521869659424): 4 | var0 = [0.0, 0.0, 0.0, 1.0] 5 | else: 6 | if (input[92]) <= (-0.050278233364224434): 7 | var0 = [0.0, 1.0, 0.0, 0.0] 8 | else: 9 | var0 = [0.0, 0.0, 1.0, 0.0] 10 | else: 11 | if (input[24]) <= (3.6942529678344727): 12 | if (input[21]) <= (3.3339260816574097): 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | var0 = [0.0, 0.0, 1.0, 0.0] 16 | else: 17 | var0 = [0.0, 1.0, 0.0, 0.0] 18 | return var0 19 | -------------------------------------------------------------------------------- /models/optimized/base/random_forest/random_forest_232d3ae.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[117]) <= (5.019443988800049): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[71]) <= (-5.254075527191162): 10 | var0 = [0.0, 0.0, 1.0, 0.0] 11 | else: 12 | if (input[56]) <= (5.359420537948608): 13 | if (input[55]) <= (1.7609354853630066): 14 | var0 = [1.0, 0.0, 0.0, 0.0] 15 | else: 16 | var0 = [0.0, 1.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 0.0, 1.0, 0.0] 19 | if (input[101]) <= (-1.051054298877716): 20 | if (input[52]) <= (10.952275276184082): 21 | if (input[181]) <= (0.17597384750843048): 22 | if (input[238]) <= (-1.9541983306407928): 23 | var1 = [1.0, 0.0, 0.0, 0.0] 24 | else: 25 | var1 = [0.0, 1.0, 0.0, 0.0] 26 | else: 27 | var1 = [0.0, 0.0, 1.0, 0.0] 28 | else: 29 | var1 = [0.0, 0.0, 0.0, 1.0] 30 | else: 31 | if (input[1]) <= (1.009156048297882): 32 | if (input[81]) <= (-3.7900209426879883): 33 | if (input[42]) <= (10.540474891662598): 34 | var1 = [0.0, 1.0, 0.0, 0.0] 35 | else: 36 | var1 = [0.0, 0.0, 1.0, 0.0] 37 | else: 38 | if (input[80]) <= (1.318008005619049): 39 | var1 = [1.0, 0.0, 0.0, 0.0] 40 | else: 41 | var1 = [0.0, 1.0, 0.0, 0.0] 42 | else: 43 | if (input[83]) <= (-6.637402415275574): 44 | var1 = [1.0, 0.0, 0.0, 0.0] 45 | else: 46 | var1 = [0.0, 0.0, 1.0, 0.0] 47 | if (input[50]) <= (-2.7401634454727173): 48 | var2 = [0.0, 0.0, 0.0, 1.0] 49 | else: 50 | if (input[46]) <= (3.0190885066986084): 51 | if (input[80]) <= (1.318008005619049): 52 | if (input[30]) <= (1.3132195472717285): 53 | var2 = [1.0, 0.0, 0.0, 0.0] 54 | else: 55 | if (input[247]) <= (10.200500011444092): 56 | var2 = [0.0, 1.0, 0.0, 0.0] 57 | else: 58 | var2 = [1.0, 0.0, 0.0, 0.0] 59 | else: 60 | if (input[31]) <= (1.1097125709056854): 61 | var2 = [0.0, 1.0, 0.0, 0.0] 62 | else: 63 | var2 = [0.0, 0.0, 0.0, 1.0] 64 | else: 65 | var2 = [0.0, 0.0, 1.0, 0.0] 66 | if (input[130]) <= (-8.705317497253418): 67 | var3 = [0.0, 0.0, 0.0, 1.0] 68 | else: 69 | if (input[106]) <= (-1.7705124616622925): 70 | if (input[70]) <= (7.439981460571289): 71 | var3 = [0.0, 0.0, 1.0, 0.0] 72 | else: 73 | if (input[107]) <= (5.9519853591918945): 74 | var3 = [0.0, 0.0, 0.0, 1.0] 75 | else: 76 | var3 = [0.0, 1.0, 0.0, 0.0] 77 | else: 78 | if (input[55]) <= (3.0945059657096863): 79 | if (input[66]) <= (-2.7700915336608887): 80 | var3 = [0.0, 0.0, 1.0, 0.0] 81 | else: 82 | var3 = [1.0, 0.0, 0.0, 0.0] 83 | else: 84 | if (input[11]) <= (1.5538367927074432): 85 | var3 = [0.0, 1.0, 0.0, 0.0] 86 | else: 87 | var3 = [0.0, 0.0, 1.0, 0.0] 88 | if (input[83]) <= (44.68702507019043): 89 | if (input[51]) <= (3.872621536254883): 90 | if (input[80]) <= (2.420538008213043): 91 | if (input[70]) <= (5.5030728578567505): 92 | var4 = [1.0, 0.0, 0.0, 0.0] 93 | else: 94 | var4 = [0.0, 1.0, 0.0, 0.0] 95 | else: 96 | var4 = [0.0, 1.0, 0.0, 0.0] 97 | else: 98 | var4 = [0.0, 0.0, 1.0, 0.0] 99 | else: 100 | var4 = [0.0, 0.0, 0.0, 1.0] 101 | if (input[40]) <= (-5.299565553665161): 102 | var5 = [0.0, 0.0, 0.0, 1.0] 103 | else: 104 | if (input[51]) <= (3.3339260816574097): 105 | if (input[75]) <= (2.6803085803985596): 106 | if (input[69]) <= (53.461835861206055): 107 | var5 = [1.0, 0.0, 0.0, 0.0] 108 | else: 109 | if (input[66]) <= (-1.8519150093197823): 110 | var5 = [0.0, 1.0, 0.0, 0.0] 111 | else: 112 | var5 = [1.0, 0.0, 0.0, 0.0] 113 | else: 114 | var5 = [0.0, 1.0, 0.0, 0.0] 115 | else: 116 | var5 = [0.0, 0.0, 1.0, 0.0] 117 | return mul_vector_number(add_vectors(add_vectors(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), var4), var5), 0.16666666666666666) 118 | -------------------------------------------------------------------------------- /models/optimized/base/random_forest/random_forest_263279a.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (5.585672616958618): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[67]) <= (-1.2162545323371887): 10 | if (input[120]) <= (-0.011970996856689453): 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | var0 = [0.0, 0.0, 1.0, 0.0] 14 | else: 15 | if (input[6]) <= (0.06105213798582554): 16 | if (input[30]) <= (3.356670379638672): 17 | var0 = [1.0, 0.0, 0.0, 0.0] 18 | else: 19 | var0 = [0.0, 1.0, 0.0, 0.0] 20 | else: 21 | if (input[6]) <= (0.2932896912097931): 22 | if (input[39]) <= (-0.015267163515090942): 23 | if (input[149]) <= (1.8435115814208984): 24 | var0 = [0.0, 1.0, 0.0, 0.0] 25 | else: 26 | var0 = [1.0, 0.0, 0.0, 0.0] 27 | else: 28 | var0 = [0.0, 0.0, 1.0, 0.0] 29 | else: 30 | var0 = [1.0, 0.0, 0.0, 0.0] 31 | if (input[62]) <= (6.321889400482178): 32 | var1 = [0.0, 0.0, 0.0, 1.0] 33 | else: 34 | if (input[37]) <= (2.505531907081604): 35 | if (input[24]) <= (1.9800044298171997): 36 | if (input[13]) <= (3.4416650533676147): 37 | if (input[94]) <= (30.877860069274902): 38 | if (input[36]) <= (3.6942529678344727): 39 | var1 = [1.0, 0.0, 0.0, 0.0] 40 | else: 41 | var1 = [0.0, 1.0, 0.0, 0.0] 42 | else: 43 | var1 = [0.0, 0.0, 0.0, 1.0] 44 | else: 45 | var1 = [0.0, 0.0, 1.0, 0.0] 46 | else: 47 | if (input[130]) <= (1.0572519898414612): 48 | var1 = [0.0, 0.0, 1.0, 0.0] 49 | else: 50 | var1 = [0.0, 1.0, 0.0, 0.0] 51 | else: 52 | if (input[125]) <= (73.25188946723938): 53 | var1 = [0.0, 0.0, 1.0, 0.0] 54 | else: 55 | var1 = [1.0, 0.0, 0.0, 0.0] 56 | if (input[58]) <= (-44.62213897705078): 57 | var2 = [0.0, 0.0, 0.0, 1.0] 58 | else: 59 | if (input[19]) <= (1.4221559762954712): 60 | if (input[78]) <= (-1.5059527158737183): 61 | var2 = [0.0, 1.0, 0.0, 0.0] 62 | else: 63 | if (input[49]) <= (6.445193648338318): 64 | if (input[54]) <= (-9.222464799880981): 65 | var2 = [0.0, 1.0, 0.0, 0.0] 66 | else: 67 | var2 = [1.0, 0.0, 0.0, 0.0] 68 | else: 69 | var2 = [0.0, 0.0, 1.0, 0.0] 70 | else: 71 | if (input[40]) <= (-32.20228958129883): 72 | var2 = [1.0, 0.0, 0.0, 0.0] 73 | else: 74 | var2 = [0.0, 0.0, 1.0, 0.0] 75 | if (input[68]) <= (4.948814392089844): 76 | var3 = [0.0, 0.0, 0.0, 1.0] 77 | else: 78 | if (input[25]) <= (1.6843204498291016): 79 | if (input[24]) <= (1.9800044298171997): 80 | var3 = [1.0, 0.0, 0.0, 0.0] 81 | else: 82 | var3 = [0.0, 1.0, 0.0, 0.0] 83 | else: 84 | var3 = [0.0, 0.0, 1.0, 0.0] 85 | if (input[74]) <= (4.338293433189392): 86 | var4 = [0.0, 0.0, 0.0, 1.0] 87 | else: 88 | if (input[31]) <= (3.872621536254883): 89 | if (input[36]) <= (3.4680010080337524): 90 | var4 = [1.0, 0.0, 0.0, 0.0] 91 | else: 92 | var4 = [0.0, 1.0, 0.0, 0.0] 93 | else: 94 | var4 = [0.0, 0.0, 1.0, 0.0] 95 | if (input[68]) <= (3.8714239597320557): 96 | var5 = [0.0, 0.0, 0.0, 1.0] 97 | else: 98 | if (input[24]) <= (1.9800044298171997): 99 | if (input[7]) <= (0.7912837266921997): 100 | if (input[133]) <= (0.25258830189704895): 101 | var5 = [1.0, 0.0, 0.0, 0.0] 102 | else: 103 | if (input[31]) <= (2.6240450143814087): 104 | var5 = [1.0, 0.0, 0.0, 0.0] 105 | else: 106 | var5 = [0.0, 0.0, 1.0, 0.0] 107 | else: 108 | if (input[25]) <= (1.509544014930725): 109 | var5 = [1.0, 0.0, 0.0, 0.0] 110 | else: 111 | var5 = [0.0, 0.0, 1.0, 0.0] 112 | else: 113 | if (input[66]) <= (-2.311601847410202): 114 | var5 = [0.0, 1.0, 0.0, 0.0] 115 | else: 116 | var5 = [0.0, 0.0, 1.0, 0.0] 117 | return mul_vector_number(add_vectors(add_vectors(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), var4), var5), 0.16666666666666666) 118 | -------------------------------------------------------------------------------- /models/optimized/base/random_forest/random_forest_2c811ab.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[27]) <= (15.24507999420166): 7 | if (input[26]) <= (2.1942859888076782): 8 | if (input[20]) <= (1.2976571321487427): 9 | if (input[95]) <= (0.1520317941904068): 10 | var0 = [1.0, 0.0, 0.0, 0.0] 11 | else: 12 | if (input[94]) <= (-1.3053435683250427): 13 | if (input[92]) <= (10.202889919281006): 14 | var0 = [1.0, 0.0, 0.0, 0.0] 15 | else: 16 | var0 = [0.0, 0.0, 1.0, 0.0] 17 | else: 18 | var0 = [1.0, 0.0, 0.0, 0.0] 19 | else: 20 | if (input[87]) <= (10.178945064544678): 21 | if (input[29]) <= (-84.52287483215332): 22 | var0 = [1.0, 0.0, 0.0, 0.0] 23 | else: 24 | var0 = [0.0, 1.0, 0.0, 0.0] 25 | else: 26 | var0 = [0.0, 0.0, 1.0, 0.0] 27 | else: 28 | if (input[15]) <= (2.359485924243927): 29 | var0 = [0.0, 0.0, 1.0, 0.0] 30 | else: 31 | var0 = [0.0, 1.0, 0.0, 0.0] 32 | else: 33 | var0 = [0.0, 0.0, 0.0, 1.0] 34 | if (input[63]) <= (-60.37786102294922): 35 | var1 = [0.0, 0.0, 0.0, 1.0] 36 | else: 37 | if (input[21]) <= (3.3339260816574097): 38 | if (input[40]) <= (-2.5175029635429382): 39 | var1 = [0.0, 1.0, 0.0, 0.0] 40 | else: 41 | if (input[15]) <= (-8.748413324356079): 42 | var1 = [0.0, 0.0, 0.0, 1.0] 43 | else: 44 | if (input[60]) <= (-8.350977420806885): 45 | var1 = [0.0, 1.0, 0.0, 0.0] 46 | else: 47 | var1 = [1.0, 0.0, 0.0, 0.0] 48 | else: 49 | if (input[22]) <= (14.543574810028076): 50 | var1 = [0.0, 0.0, 1.0, 0.0] 51 | else: 52 | var1 = [0.0, 0.0, 0.0, 1.0] 53 | if (input[29]) <= (95.8587760925293): 54 | if (input[28]) <= (-0.18320614844560623): 55 | if (input[75]) <= (-0.14844050258398056): 56 | if (input[87]) <= (10.201694965362549): 57 | if (input[104]) <= (28.4618319272995): 58 | var2 = [0.0, 1.0, 0.0, 0.0] 59 | else: 60 | var2 = [1.0, 0.0, 0.0, 0.0] 61 | else: 62 | var2 = [1.0, 0.0, 0.0, 0.0] 63 | else: 64 | if (input[25]) <= (4.320336878299713): 65 | var2 = [1.0, 0.0, 0.0, 0.0] 66 | else: 67 | var2 = [0.0, 1.0, 0.0, 0.0] 68 | else: 69 | if (input[28]) <= (3.664121985435486): 70 | if (input[77]) <= (10.10712480545044): 71 | var2 = [0.0, 1.0, 0.0, 0.0] 72 | else: 73 | if (input[46]) <= (0.7517795264720917): 74 | var2 = [0.0, 0.0, 1.0, 0.0] 75 | else: 76 | var2 = [1.0, 0.0, 0.0, 0.0] 77 | else: 78 | var2 = [1.0, 0.0, 0.0, 0.0] 79 | else: 80 | var2 = [0.0, 0.0, 0.0, 1.0] 81 | if (input[41]) <= (-1.8878280520439148): 82 | if (input[30]) <= (7.596801996231079): 83 | if (input[14]) <= (11.961830377578735): 84 | var3 = [0.0, 0.0, 1.0, 0.0] 85 | else: 86 | var3 = [1.0, 0.0, 0.0, 0.0] 87 | else: 88 | var3 = [0.0, 0.0, 0.0, 1.0] 89 | else: 90 | if (input[35]) <= (-1.947683036327362): 91 | var3 = [0.0, 1.0, 0.0, 0.0] 92 | else: 93 | if (input[45]) <= (-5.023034930229187): 94 | var3 = [0.0, 1.0, 0.0, 0.0] 95 | else: 96 | if (input[11]) <= (2.882619023323059): 97 | if (input[0]) <= (0.4357447028160095): 98 | var3 = [1.0, 0.0, 0.0, 0.0] 99 | else: 100 | if (input[11]) <= (0.2753331884741783): 101 | var3 = [1.0, 0.0, 0.0, 0.0] 102 | else: 103 | var3 = [0.0, 0.0, 1.0, 0.0] 104 | else: 105 | var3 = [0.0, 0.0, 1.0, 0.0] 106 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 107 | -------------------------------------------------------------------------------- /models/optimized/base/random_forest/random_forest_628e029.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[117]) <= (5.019443988800049): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[71]) <= (-5.254075527191162): 10 | var0 = [0.0, 0.0, 1.0, 0.0] 11 | else: 12 | if (input[56]) <= (5.359420537948608): 13 | if (input[55]) <= (1.7609354853630066): 14 | var0 = [1.0, 0.0, 0.0, 0.0] 15 | else: 16 | var0 = [0.0, 1.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 0.0, 1.0, 0.0] 19 | if (input[101]) <= (-1.051054298877716): 20 | if (input[52]) <= (10.952275276184082): 21 | if (input[181]) <= (0.17597384750843048): 22 | if (input[238]) <= (-1.9541983306407928): 23 | var1 = [1.0, 0.0, 0.0, 0.0] 24 | else: 25 | var1 = [0.0, 1.0, 0.0, 0.0] 26 | else: 27 | var1 = [0.0, 0.0, 1.0, 0.0] 28 | else: 29 | var1 = [0.0, 0.0, 0.0, 1.0] 30 | else: 31 | if (input[1]) <= (1.009156048297882): 32 | if (input[81]) <= (-3.7900209426879883): 33 | if (input[42]) <= (10.540474891662598): 34 | var1 = [0.0, 1.0, 0.0, 0.0] 35 | else: 36 | var1 = [0.0, 0.0, 1.0, 0.0] 37 | else: 38 | if (input[80]) <= (1.318008005619049): 39 | var1 = [1.0, 0.0, 0.0, 0.0] 40 | else: 41 | var1 = [0.0, 1.0, 0.0, 0.0] 42 | else: 43 | if (input[83]) <= (-6.637402415275574): 44 | var1 = [1.0, 0.0, 0.0, 0.0] 45 | else: 46 | var1 = [0.0, 0.0, 1.0, 0.0] 47 | if (input[50]) <= (-2.7401634454727173): 48 | var2 = [0.0, 0.0, 0.0, 1.0] 49 | else: 50 | if (input[46]) <= (3.0190885066986084): 51 | if (input[80]) <= (1.318008005619049): 52 | if (input[30]) <= (1.3132195472717285): 53 | var2 = [1.0, 0.0, 0.0, 0.0] 54 | else: 55 | if (input[247]) <= (10.200500011444092): 56 | var2 = [0.0, 1.0, 0.0, 0.0] 57 | else: 58 | var2 = [1.0, 0.0, 0.0, 0.0] 59 | else: 60 | if (input[31]) <= (1.1097125709056854): 61 | var2 = [0.0, 1.0, 0.0, 0.0] 62 | else: 63 | var2 = [0.0, 0.0, 0.0, 1.0] 64 | else: 65 | var2 = [0.0, 0.0, 1.0, 0.0] 66 | if (input[130]) <= (-8.705317497253418): 67 | var3 = [0.0, 0.0, 0.0, 1.0] 68 | else: 69 | if (input[106]) <= (-1.7705124616622925): 70 | if (input[70]) <= (7.439981460571289): 71 | var3 = [0.0, 0.0, 1.0, 0.0] 72 | else: 73 | if (input[107]) <= (5.9519853591918945): 74 | var3 = [0.0, 0.0, 0.0, 1.0] 75 | else: 76 | var3 = [0.0, 1.0, 0.0, 0.0] 77 | else: 78 | if (input[55]) <= (3.0945059657096863): 79 | if (input[66]) <= (-2.7700915336608887): 80 | var3 = [0.0, 0.0, 1.0, 0.0] 81 | else: 82 | var3 = [1.0, 0.0, 0.0, 0.0] 83 | else: 84 | if (input[11]) <= (1.5538367927074432): 85 | var3 = [0.0, 1.0, 0.0, 0.0] 86 | else: 87 | var3 = [0.0, 0.0, 1.0, 0.0] 88 | if (input[83]) <= (44.68702507019043): 89 | if (input[51]) <= (3.872621536254883): 90 | if (input[80]) <= (2.420538008213043): 91 | if (input[70]) <= (5.5030728578567505): 92 | var4 = [1.0, 0.0, 0.0, 0.0] 93 | else: 94 | var4 = [0.0, 1.0, 0.0, 0.0] 95 | else: 96 | var4 = [0.0, 1.0, 0.0, 0.0] 97 | else: 98 | var4 = [0.0, 0.0, 1.0, 0.0] 99 | else: 100 | var4 = [0.0, 0.0, 0.0, 1.0] 101 | if (input[40]) <= (-5.299565553665161): 102 | var5 = [0.0, 0.0, 0.0, 1.0] 103 | else: 104 | if (input[51]) <= (3.3339260816574097): 105 | if (input[75]) <= (2.6803085803985596): 106 | if (input[72]) <= (10.888835430145264): 107 | var5 = [1.0, 0.0, 0.0, 0.0] 108 | else: 109 | if (input[66]) <= (-2.9257144927978516): 110 | var5 = [0.0, 1.0, 0.0, 0.0] 111 | else: 112 | var5 = [1.0, 0.0, 0.0, 0.0] 113 | else: 114 | var5 = [0.0, 1.0, 0.0, 0.0] 115 | else: 116 | var5 = [0.0, 0.0, 1.0, 0.0] 117 | return mul_vector_number(add_vectors(add_vectors(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), var4), var5), 0.16666666666666666) 118 | -------------------------------------------------------------------------------- /models/optimized/base/random_forest/random_forest_78ad688.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[27]) <= (15.24507999420166): 7 | if (input[26]) <= (2.1942859888076782): 8 | if (input[20]) <= (1.2976571321487427): 9 | if (input[95]) <= (0.1520317941904068): 10 | var0 = [1.0, 0.0, 0.0, 0.0] 11 | else: 12 | if (input[29]) <= (1.152671456336975): 13 | var0 = [1.0, 0.0, 0.0, 0.0] 14 | else: 15 | if (input[40]) <= (0.09457094594836235): 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 0.0, 1.0, 0.0] 19 | else: 20 | if (input[87]) <= (10.178945064544678): 21 | if (input[29]) <= (-22.45038080215454): 22 | var0 = [1.0, 0.0, 0.0, 0.0] 23 | else: 24 | var0 = [0.0, 1.0, 0.0, 0.0] 25 | else: 26 | var0 = [0.0, 0.0, 1.0, 0.0] 27 | else: 28 | if (input[15]) <= (2.359485924243927): 29 | var0 = [0.0, 0.0, 1.0, 0.0] 30 | else: 31 | var0 = [0.0, 1.0, 0.0, 0.0] 32 | else: 33 | var0 = [0.0, 0.0, 0.0, 1.0] 34 | if (input[63]) <= (-60.37786102294922): 35 | var1 = [0.0, 0.0, 0.0, 1.0] 36 | else: 37 | if (input[21]) <= (3.3339260816574097): 38 | if (input[40]) <= (-2.5175029635429382): 39 | var1 = [0.0, 1.0, 0.0, 0.0] 40 | else: 41 | if (input[15]) <= (-8.748413324356079): 42 | var1 = [0.0, 0.0, 0.0, 1.0] 43 | else: 44 | if (input[60]) <= (-8.350977420806885): 45 | var1 = [0.0, 1.0, 0.0, 0.0] 46 | else: 47 | var1 = [1.0, 0.0, 0.0, 0.0] 48 | else: 49 | if (input[22]) <= (14.543574810028076): 50 | var1 = [0.0, 0.0, 1.0, 0.0] 51 | else: 52 | var1 = [0.0, 0.0, 0.0, 1.0] 53 | if (input[42]) <= (6.321889400482178): 54 | var2 = [0.0, 0.0, 0.0, 1.0] 55 | else: 56 | if (input[28]) <= (-0.18320614844560623): 57 | if (input[75]) <= (-0.14844050258398056): 58 | if (input[87]) <= (10.201694965362549): 59 | if (input[104]) <= (17.618319869041443): 60 | var2 = [0.0, 1.0, 0.0, 0.0] 61 | else: 62 | var2 = [1.0, 0.0, 0.0, 0.0] 63 | else: 64 | var2 = [1.0, 0.0, 0.0, 0.0] 65 | else: 66 | if (input[25]) <= (4.320336878299713): 67 | if (input[80]) <= (11.717221975326538): 68 | var2 = [1.0, 0.0, 0.0, 0.0] 69 | else: 70 | var2 = [0.0, 0.0, 0.0, 1.0] 71 | else: 72 | var2 = [0.0, 1.0, 0.0, 0.0] 73 | else: 74 | if (input[28]) <= (3.664121985435486): 75 | if (input[90]) <= (-0.05386953242123127): 76 | if (input[76]) <= (0.045489829033613205): 77 | var2 = [0.0, 1.0, 0.0, 0.0] 78 | else: 79 | var2 = [1.0, 0.0, 0.0, 0.0] 80 | else: 81 | var2 = [0.0, 0.0, 1.0, 0.0] 82 | else: 83 | var2 = [1.0, 0.0, 0.0, 0.0] 84 | if (input[41]) <= (-1.8878280520439148): 85 | if (input[30]) <= (7.596801996231079): 86 | if (input[14]) <= (-0.5152671691030264): 87 | var3 = [1.0, 0.0, 0.0, 0.0] 88 | else: 89 | var3 = [0.0, 0.0, 1.0, 0.0] 90 | else: 91 | var3 = [0.0, 0.0, 0.0, 1.0] 92 | else: 93 | if (input[35]) <= (-1.947683036327362): 94 | var3 = [0.0, 1.0, 0.0, 0.0] 95 | else: 96 | if (input[45]) <= (-5.023034930229187): 97 | var3 = [0.0, 1.0, 0.0, 0.0] 98 | else: 99 | if (input[11]) <= (2.882619023323059): 100 | if (input[0]) <= (0.4357447028160095): 101 | var3 = [1.0, 0.0, 0.0, 0.0] 102 | else: 103 | if (input[11]) <= (0.2753331884741783): 104 | var3 = [1.0, 0.0, 0.0, 0.0] 105 | else: 106 | var3 = [0.0, 0.0, 1.0, 0.0] 107 | else: 108 | var3 = [0.0, 0.0, 1.0, 0.0] 109 | return mul_vector_number(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), 0.25) 110 | -------------------------------------------------------------------------------- /models/optimized/base/random_forest/random_forest_b159d83.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (5.585672616958618): 7 | var0 = [0.0, 0.0, 0.0, 1.0] 8 | else: 9 | if (input[67]) <= (-1.2162545323371887): 10 | if (input[120]) <= (-0.011970996856689453): 11 | var0 = [0.0, 1.0, 0.0, 0.0] 12 | else: 13 | var0 = [0.0, 0.0, 1.0, 0.0] 14 | else: 15 | if (input[6]) <= (0.06105213798582554): 16 | if (input[30]) <= (3.356670379638672): 17 | var0 = [1.0, 0.0, 0.0, 0.0] 18 | else: 19 | var0 = [0.0, 1.0, 0.0, 0.0] 20 | else: 21 | if (input[6]) <= (0.2932896912097931): 22 | if (input[39]) <= (-0.015267163515090942): 23 | if (input[149]) <= (1.8435115814208984): 24 | var0 = [0.0, 1.0, 0.0, 0.0] 25 | else: 26 | var0 = [1.0, 0.0, 0.0, 0.0] 27 | else: 28 | var0 = [0.0, 0.0, 1.0, 0.0] 29 | else: 30 | var0 = [1.0, 0.0, 0.0, 0.0] 31 | if (input[62]) <= (6.321889400482178): 32 | var1 = [0.0, 0.0, 0.0, 1.0] 33 | else: 34 | if (input[37]) <= (2.505531907081604): 35 | if (input[24]) <= (1.9800044298171997): 36 | if (input[13]) <= (3.4416650533676147): 37 | if (input[94]) <= (30.877860069274902): 38 | if (input[36]) <= (3.6942529678344727): 39 | var1 = [1.0, 0.0, 0.0, 0.0] 40 | else: 41 | var1 = [0.0, 1.0, 0.0, 0.0] 42 | else: 43 | var1 = [0.0, 0.0, 0.0, 1.0] 44 | else: 45 | var1 = [0.0, 0.0, 1.0, 0.0] 46 | else: 47 | if (input[130]) <= (1.0572519898414612): 48 | var1 = [0.0, 0.0, 1.0, 0.0] 49 | else: 50 | var1 = [0.0, 1.0, 0.0, 0.0] 51 | else: 52 | if (input[125]) <= (73.25188946723938): 53 | var1 = [0.0, 0.0, 1.0, 0.0] 54 | else: 55 | var1 = [1.0, 0.0, 0.0, 0.0] 56 | if (input[58]) <= (-44.62213897705078): 57 | var2 = [0.0, 0.0, 0.0, 1.0] 58 | else: 59 | if (input[19]) <= (1.4221559762954712): 60 | if (input[78]) <= (-1.5059527158737183): 61 | var2 = [0.0, 1.0, 0.0, 0.0] 62 | else: 63 | if (input[49]) <= (6.445193648338318): 64 | if (input[54]) <= (-9.222464799880981): 65 | var2 = [0.0, 1.0, 0.0, 0.0] 66 | else: 67 | var2 = [1.0, 0.0, 0.0, 0.0] 68 | else: 69 | var2 = [0.0, 0.0, 1.0, 0.0] 70 | else: 71 | if (input[40]) <= (-32.20228958129883): 72 | var2 = [1.0, 0.0, 0.0, 0.0] 73 | else: 74 | var2 = [0.0, 0.0, 1.0, 0.0] 75 | if (input[68]) <= (4.948814392089844): 76 | var3 = [0.0, 0.0, 0.0, 1.0] 77 | else: 78 | if (input[25]) <= (1.6843204498291016): 79 | if (input[24]) <= (1.9800044298171997): 80 | var3 = [1.0, 0.0, 0.0, 0.0] 81 | else: 82 | var3 = [0.0, 1.0, 0.0, 0.0] 83 | else: 84 | var3 = [0.0, 0.0, 1.0, 0.0] 85 | if (input[74]) <= (4.338293433189392): 86 | var4 = [0.0, 0.0, 0.0, 1.0] 87 | else: 88 | if (input[31]) <= (3.872621536254883): 89 | if (input[36]) <= (3.4680010080337524): 90 | var4 = [1.0, 0.0, 0.0, 0.0] 91 | else: 92 | var4 = [0.0, 1.0, 0.0, 0.0] 93 | else: 94 | var4 = [0.0, 0.0, 1.0, 0.0] 95 | return mul_vector_number(add_vectors(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), var4), 0.2) 96 | -------------------------------------------------------------------------------- /models/optimized/base/random_forest/random_forest_f28b45c.py: -------------------------------------------------------------------------------- 1 | def add_vectors(v1, v2): 2 | return [sum(i) for i in zip(v1, v2)] 3 | def mul_vector_number(v1, num): 4 | return [i * num for i in v1] 5 | def score(input): 6 | if (input[68]) <= (14.246695041656494): 7 | if (input[55]) <= (3.5063085556030273): 8 | if (input[179]) <= (-2.75190806388855): 9 | if (input[251]) <= (-2.900763511657715): 10 | var0 = [1.0, 0.0, 0.0, 0.0] 11 | else: 12 | if (input[199]) <= (0.27892449498176575): 13 | var0 = [0.0, 1.0, 0.0, 0.0] 14 | else: 15 | if (input[233]) <= (22.958014488220215): 16 | var0 = [1.0, 0.0, 0.0, 0.0] 17 | else: 18 | var0 = [0.0, 0.0, 0.0, 1.0] 19 | else: 20 | var0 = [1.0, 0.0, 0.0, 0.0] 21 | else: 22 | var0 = [0.0, 0.0, 1.0, 0.0] 23 | else: 24 | var0 = [0.0, 0.0, 0.0, 1.0] 25 | if (input[48]) <= (-3.9444470405578613): 26 | var1 = [0.0, 0.0, 0.0, 1.0] 27 | else: 28 | if (input[178]) <= (0.8396946489810944): 29 | if (input[126]) <= (-5.281608819961548): 30 | var1 = [0.0, 1.0, 0.0, 0.0] 31 | else: 32 | if (input[145]) <= (-1.7357965111732483): 33 | var1 = [0.0, 1.0, 0.0, 0.0] 34 | else: 35 | var1 = [1.0, 0.0, 0.0, 0.0] 36 | else: 37 | if (input[103]) <= (-1.8363524675369263): 38 | var1 = [0.0, 0.0, 1.0, 0.0] 39 | else: 40 | if (input[72]) <= (4.34547632932663): 41 | if (input[144]) <= (-0.6907271444797516): 42 | var1 = [0.0, 0.0, 1.0, 0.0] 43 | else: 44 | var1 = [1.0, 0.0, 0.0, 0.0] 45 | else: 46 | var1 = [0.0, 1.0, 0.0, 0.0] 47 | if (input[120]) <= (2.6587610244750977): 48 | if (input[31]) <= (1.1611875295639038): 49 | if (input[36]) <= (0.9959878921508789): 50 | if (input[85]) <= (3.9755719900131226): 51 | var2 = [1.0, 0.0, 0.0, 0.0] 52 | else: 53 | var2 = [0.0, 0.0, 1.0, 0.0] 54 | else: 55 | if (input[290]) <= (10.218454837799072): 56 | var2 = [0.0, 1.0, 0.0, 0.0] 57 | else: 58 | var2 = [1.0, 0.0, 0.0, 0.0] 59 | else: 60 | if (input[210]) <= (-0.03232169896364212): 61 | var2 = [1.0, 0.0, 0.0, 0.0] 62 | else: 63 | var2 = [0.0, 0.0, 1.0, 0.0] 64 | else: 65 | var2 = [0.0, 0.0, 0.0, 1.0] 66 | if (input[62]) <= (14.189235210418701): 67 | if (input[109]) <= (-3.031059503555298): 68 | var3 = [0.0, 0.0, 1.0, 0.0] 69 | else: 70 | if (input[144]) <= (-2.968809962272644): 71 | var3 = [0.0, 1.0, 0.0, 0.0] 72 | else: 73 | if (input[60]) <= (3.1328131556510925): 74 | if (input[133]) <= (-5.585672497749329): 75 | var3 = [0.0, 0.0, 1.0, 0.0] 76 | else: 77 | var3 = [1.0, 0.0, 0.0, 0.0] 78 | else: 79 | if (input[82]) <= (-0.5916030406951904): 80 | var3 = [0.0, 0.0, 1.0, 0.0] 81 | else: 82 | var3 = [0.0, 1.0, 0.0, 0.0] 83 | else: 84 | var3 = [0.0, 0.0, 0.0, 1.0] 85 | if (input[134]) <= (5.585672616958618): 86 | var4 = [0.0, 0.0, 0.0, 1.0] 87 | else: 88 | if (input[263]) <= (5.709923505783081): 89 | if (input[19]) <= (0.490811288356781): 90 | if (input[108]) <= (-1.9021929502487183): 91 | var4 = [0.0, 1.0, 0.0, 0.0] 92 | else: 93 | if (input[158]) <= (10.11071491241455): 94 | if (input[67]) <= (0.21547814458608627): 95 | var4 = [0.0, 1.0, 0.0, 0.0] 96 | else: 97 | if (input[60]) <= (-0.02394205331802368): 98 | var4 = [0.0, 0.0, 1.0, 0.0] 99 | else: 100 | var4 = [1.0, 0.0, 0.0, 0.0] 101 | else: 102 | if (input[216]) <= (0.1496376022696495): 103 | var4 = [1.0, 0.0, 0.0, 0.0] 104 | else: 105 | if (input[87]) <= (-6.225192755460739): 106 | var4 = [1.0, 0.0, 0.0, 0.0] 107 | else: 108 | var4 = [0.0, 0.0, 1.0, 0.0] 109 | else: 110 | if (input[47]) <= (-20.343509674072266): 111 | var4 = [1.0, 0.0, 0.0, 0.0] 112 | else: 113 | var4 = [0.0, 0.0, 1.0, 0.0] 114 | else: 115 | var4 = [1.0, 0.0, 0.0, 0.0] 116 | return mul_vector_number(add_vectors(add_vectors(add_vectors(add_vectors(var0, var1), var2), var3), var4), 0.2) 117 | -------------------------------------------------------------------------------- /output/baseline_base_dataset_results.csv: -------------------------------------------------------------------------------- 1 | 10,20,25,50,100 2 | "{'accuracy': 0.9420289855072463, 'f1': 0.8764069264069264, 'precision': 0.9375, 'recall': 0.8660714285714286, 'time': [6.721081279993086e-05, 6.539114669994887e-05, 6.722447599986481e-05, 6.449106880008912e-05, 6.404692830001295e-05, 6.848955579989706e-05, 6.567747770004643e-05]}","{'accuracy': 0.9420289855072463, 'f1': 0.8764069264069264, 'precision': 0.9375, 'recall': 0.8660714285714286, 'time': [6.86460441998861e-05, 6.93281793001006e-05, 7.377102030004608e-05, 7.024197239989007e-05, 6.937440970013995e-05, 6.489967699999398e-05, 6.591632319996279e-05]}","{'accuracy': 0.927536231884058, 'f1': 0.8789173789173789, 'precision': 0.8713369963369964, 'recall': 0.8898809523809523, 'time': [6.615704220002953e-05, 6.503573339996365e-05, 6.75696924001386e-05, 6.481297800000902e-05, 6.530390759999136e-05, 6.675876360004622e-05, 6.682529230001819e-05]}","{'accuracy': 0.927536231884058, 'f1': 0.8828289992119779, 'precision': 0.8774038461538461, 'recall': 0.8898809523809523, 'time': [6.887246910009708e-05, 6.947141050004575e-05, 6.837523080012033e-05, 6.802474569994957e-05, 6.889255930000218e-05, 6.806686569998419e-05, 7.234195109995199e-05]}","{'accuracy': 0.8840579710144928, 'f1': 0.776697177726926, 'precision': 0.7824951160783244, 'recall': 0.771868530020704, 'time': [6.891266989987344e-05, 6.912272569989e-05, 7.009710580005049e-05, 7.000511219994223e-05, 6.870984699999099e-05, 6.922430159993383e-05, 7.03308707999895e-05]}" 3 | "{'accuracy': 0.8695652173913043, 'f1': 0.7820928959661918, 'precision': 0.8208333333333333, 'recall': 0.7828674948240165, 'time': [0.0005764869509985146, 0.0005874070310001116, 0.0006147953990002862, 0.0006001068639998266, 0.0005892869239996799, 0.0005895075640000868, 0.0005925812189998396]}","{'accuracy': 0.9420289855072463, 'f1': 0.8891304347826088, 'precision': 0.96875, 'recall': 0.8541666666666666, 'time': [0.0005826667159999488, 0.0005709295920005388, 0.0005786525980001898, 0.0006485505559994635, 0.0006087883299987879, 0.0005803564809993986, 0.0005876123289999669]}","{'accuracy': 0.9565217391304348, 'f1': 0.908041958041958, 'precision': 0.9142857142857143, 'recall': 0.9077380952380952, 'time': [0.0005935175519989571, 0.0005926575690009486, 0.0005771507200006454, 0.0005851623670005211, 0.0005890819619999093, 0.0006188148649998766, 0.0005874368230015534]}","{'accuracy': 0.9565217391304348, 'f1': 0.9435578310578311, 'precision': 0.9553571428571429, 'recall': 0.9385351966873705, 'time': [0.0005910167829988495, 0.0005830863280007179, 0.0006031499359996815, 0.0005849078379997081, 0.0006007284150000487, 0.0005941418370002794, 0.0006077220499992108]}","{'accuracy': 0.9855072463768116, 'f1': 0.9854545454545455, 'precision': 0.9807692307692308, 'recall': 0.9910714285714286, 'time': [0.0005829294840004877, 0.0006115933449982549, 0.0006103827740007546, 0.000605703031998928, 0.000626725901998725, 0.0005928388550000818, 0.0006115290170000663]}" 4 | "{'accuracy': 0.9420289855072463, 'f1': 0.903961038961039, 'precision': 0.912912087912088, 'recall': 0.8988095238095238, 'time': [5.7327271999929506e-05, 5.836424570006784e-05, 6.0204516200064974e-05, 6.558418690001417e-05, 6.147908739985723e-05, 6.391938659999141e-05, 5.7770006700047815e-05]}","{'accuracy': 0.9710144927536232, 'f1': 0.9413793103448276, 'precision': 0.9833333333333334, 'recall': 0.9166666666666666, 'time': [6.126881019990833e-05, 5.847306279993063e-05, 5.931126989999029e-05, 6.145228519999363e-05, 6.111204030003137e-05, 5.672774220001884e-05, 6.051806170016789e-05]}","{'accuracy': 0.9420289855072463, 'f1': 0.9119252873563218, 'precision': 0.9541666666666666, 'recall': 0.8869047619047619, 'time': [6.374076119991514e-05, 6.303739079994557e-05, 6.303491589987971e-05, 5.788146830000187e-05, 6.091536950007139e-05, 5.84010632999707e-05, 5.894459420014755e-05]}","{'accuracy': 0.9130434782608695, 'f1': 0.8533045977011494, 'precision': 0.8833333333333333, 'recall': 0.8363095238095238, 'time': [6.5787535599884e-05, 6.121307560006244e-05, 5.917057100014063e-05, 5.891633549999824e-05, 6.0654812900065735e-05, 5.937022470006923e-05, 5.8829953200074666e-05]}","{'accuracy': 0.927536231884058, 'f1': 0.8890550239234449, 'precision': 0.9033045977011495, 'recall': 0.8779761904761905, 'time': [6.340462240004854e-05, 6.258691050006746e-05, 6.343376559998433e-05, 6.397538660003192e-05, 6.193942299996706e-05, 6.214922629987996e-05, 6.254817669996556e-05]}" 5 | "{'accuracy': 0.9420289855072463, 'f1': 0.9129120879120879, 'precision': 0.9464285714285714, 'recall': 0.8988095238095238, 'time': [6.013034210009209e-05, 6.152722220012947e-05, 6.10744818999592e-05, 6.0433357700094346e-05, 6.0436639599902266e-05, 6.12815871998464e-05, 5.968720079999912e-05]}","{'accuracy': 0.927536231884058, 'f1': 0.8792915118351391, 'precision': 0.9573252688172044, 'recall': 0.8452380952380952, 'time': [6.141862460008269e-05, 6.254127150004933e-05, 6.337093389993243e-05, 5.9780116500041913e-05, 6.201618330014753e-05, 5.8695505499963475e-05, 6.18228139999701e-05]}","{'accuracy': 0.8840579710144928, 'f1': 0.824496868379847, 'precision': 0.8330357142857143, 'recall': 0.8184523809523809, 'time': [5.9290504800083e-05, 6.065432429986686e-05, 5.976822880002146e-05, 6.049695959991368e-05, 5.8923065299859444e-05, 6.120602020000661e-05, 5.996180139991338e-05]}","{'accuracy': 0.9130434782608695, 'f1': 0.878879985262964, 'precision': 0.8919642857142858, 'recall': 0.8690476190476191, 'time': [6.168035129994678e-05, 6.112151559991617e-05, 6.186891739998828e-05, 6.226228489995265e-05, 6.095359020000615e-05, 6.106597970010625e-05, 6.0802589200102375e-05]}","{'accuracy': 0.9130434782608695, 'f1': 0.878879985262964, 'precision': 0.8919642857142858, 'recall': 0.8690476190476191, 'time': [6.164058729991667e-05, 6.36433349998697e-05, 6.270782610008609e-05, 6.313819309998508e-05, 6.211894629996095e-05, 6.57791465999253e-05, 6.51091298999745e-05]}" 6 | -------------------------------------------------------------------------------- /output/baseline_model_accuracy.csv: -------------------------------------------------------------------------------- 1 | hz,model,accuracy 2 | 10,decision_tree,0.9420289855072463 3 | 20,decision_tree,0.9420289855072463 4 | 25,decision_tree,0.927536231884058 5 | 50,decision_tree,0.927536231884058 6 | 100,decision_tree,0.8840579710144928 7 | 10,random_forest,0.8695652173913043 8 | 20,random_forest,0.9420289855072463 9 | 25,random_forest,0.9565217391304348 10 | 50,random_forest,0.9565217391304348 11 | 100,random_forest,0.9855072463768116 12 | 10,svc,0.9420289855072463 13 | 20,svc,0.9710144927536232 14 | 25,svc,0.9420289855072463 15 | 50,svc,0.9130434782608695 16 | 100,svc,0.927536231884058 17 | 10,logistic_regression,0.9420289855072463 18 | 20,logistic_regression,0.927536231884058 19 | 25,logistic_regression,0.8840579710144928 20 | 50,logistic_regression,0.9130434782608695 21 | 100,logistic_regression,0.9130434782608695 22 | -------------------------------------------------------------------------------- /output/baseline_model_inference_time.csv: -------------------------------------------------------------------------------- 1 | hz,decision_tree,random_forest,svc,logistic_regression,framework 2 | 10,6.476392955714476e-06,2.9903756571431065e-05,0.0004566013789999488,0.00044149468014289335,pure-python 3 | 20,4.891754035714452e-06,3.171041088571006e-05,0.0008524694742856938,0.00085029639857141,pure-python 4 | 25,4.767515031428177e-06,2.798141825714343e-05,0.0010412989151428258,0.0010352276855714341,pure-python 5 | 50,4.787116261428699e-06,3.2101178099998965e-05,0.0020880516314280484,0.0020653362985714402,pure-python 6 | 100,3.2441731014283246e-06,2.6581260757143354e-05,0.00404855613142932,0.004039201875714948,pure-python 7 | 10,6.757382127143013e-05,0.0005959751842857161,5.734799451428541e-05,5.776320132857141e-05,scikit 8 | 20,6.4752782814287e-05,0.0005896995755713955,5.833396732857312e-05,5.86191244142859e-05,scikit 9 | 25,6.495781007142795e-05,0.0005909722012857271,5.8597721128567825e-05,6.011740677142825e-05,scikit 10 | 50,6.780121535714443e-05,0.0005969696755714234,5.982605045714503e-05,6.022152945714165e-05,scikit 11 | 100,6.90361892714301e-05,0.0005944872574286169,6.179261225713942e-05,6.168365317143655e-05,scikit 12 | -------------------------------------------------------------------------------- /output/baseline_results/baseline_centered_aug_dataset_results.csv: -------------------------------------------------------------------------------- 1 | 10,20,25,50,100 2 | "{'accuracy': 0.9970059880239521, 'f1': 0.9974269005847953, 'precision': 0.997787610619469, 'recall': 0.997093023255814}","{'accuracy': 0.9910179640718563, 'f1': 0.989183775040438, 'precision': 0.9895272852127106, 'recall': 0.9888668975754576}","{'accuracy': 0.9880239520958084, 'f1': 0.9836472298183597, 'precision': 0.9836798839458414, 'recall': 0.9837437245995697}","{'accuracy': 0.9940119760479041, 'f1': 0.9916916541729135, 'precision': 0.9943181818181819, 'recall': 0.9893617021276596}","{'accuracy': 0.9940119760479041, 'f1': 0.9933161334709323, 'precision': 0.9925792772861357, 'recall': 0.9941860465116279}" 3 | "{'accuracy': 0.9940119760479041, 'f1': 0.9946028930927775, 'precision': 0.9949140474010782, 'recall': 0.9943820224719101}","{'accuracy': 1.0, 'f1': 1.0, 'precision': 1.0, 'recall': 1.0}","{'accuracy': 0.9880239520958084, 'f1': 0.9838029362899671, 'precision': 0.989932216905901, 'recall': 0.9787234042553191}","{'accuracy': 0.9940119760479041, 'f1': 0.9923528280107734, 'precision': 0.9956140350877193, 'recall': 0.9893617021276596}","{'accuracy': 1.0, 'f1': 1.0, 'precision': 1.0, 'recall': 1.0}" 4 | "{'accuracy': 0.9940119760479041, 'f1': 0.9925394144144144, 'precision': 0.9897959183673469, 'recall': 0.9955357142857143}","{'accuracy': 1.0, 'f1': 1.0, 'precision': 1.0, 'recall': 1.0}","{'accuracy': 0.9970059880239521, 'f1': 0.9962007168458782, 'precision': 0.997787610619469, 'recall': 0.9946808510638298}","{'accuracy': 1.0, 'f1': 1.0, 'precision': 1.0, 'recall': 1.0}","{'accuracy': 0.9970059880239521, 'f1': 0.9962007168458782, 'precision': 0.997787610619469, 'recall': 0.9946808510638298}" 5 | "{'accuracy': 1.0, 'f1': 1.0, 'precision': 1.0, 'recall': 1.0}","{'accuracy': 0.9940119760479041, 'f1': 0.9923528280107734, 'precision': 0.9956140350877193, 'recall': 0.9893617021276596}","{'accuracy': 0.9970059880239521, 'f1': 0.9962007168458782, 'precision': 0.997787610619469, 'recall': 0.9946808510638298}","{'accuracy': 0.9970059880239521, 'f1': 0.9962007168458782, 'precision': 0.997787610619469, 'recall': 0.9946808510638298}","{'accuracy': 0.9910179640718563, 'f1': 0.9884542770005325, 'precision': 0.9934782608695653, 'recall': 0.9840425531914894}" 6 | -------------------------------------------------------------------------------- /output/baseline_results/baseline_centered_dataset_results.csv: -------------------------------------------------------------------------------- 1 | 10,20,25,50,100 2 | "{'accuracy': 0.9710144927536232, 'f1': 0.9483918128654971, 'precision': 0.9497126436781609, 'recall': 0.9474637681159421}","{'accuracy': 0.9710144927536232, 'f1': 0.9402948861515491, 'precision': 0.980962643678161, 'recall': 0.9166666666666666}","{'accuracy': 0.8985507246376812, 'f1': 0.8632724252491694, 'precision': 0.8499313186813187, 'recall': 0.8870341614906831}","{'accuracy': 0.927536231884058, 'f1': 0.9056060606060605, 'precision': 0.9013532763532763, 'recall': 0.9107142857142857}","{'accuracy': 0.927536231884058, 'f1': 0.9056060606060605, 'precision': 0.9013532763532763, 'recall': 0.9107142857142857}" 3 | "{'accuracy': 0.9565217391304348, 'f1': 0.903954802259887, 'precision': 0.9758064516129032, 'recall': 0.875}","{'accuracy': 0.9565217391304348, 'f1': 0.9186602870813397, 'precision': 0.9327586206896552, 'recall': 0.9077380952380952}","{'accuracy': 0.9710144927536232, 'f1': 0.9413793103448276, 'precision': 0.9833333333333334, 'recall': 0.9166666666666666}","{'accuracy': 1.0, 'f1': 1.0, 'precision': 1.0, 'recall': 1.0}","{'accuracy': 0.9420289855072463, 'f1': 0.9037072372904457, 'precision': 0.925, 'recall': 0.8869047619047619}" 4 | "{'accuracy': 0.9565217391304348, 'f1': 0.9230484330484331, 'precision': 0.9093406593406594, 'recall': 0.9404761904761905}","{'accuracy': 0.9855072463768116, 'f1': 0.9762237762237762, 'precision': 0.9642857142857143, 'recall': 0.9910714285714286}","{'accuracy': 0.9855072463768116, 'f1': 0.9901353965183752, 'precision': 0.9895833333333334, 'recall': 0.9910714285714286}","{'accuracy': 0.9420289855072463, 'f1': 0.9254500818330605, 'precision': 0.90625, 'recall': 0.9642857142857143}","{'accuracy': 0.9710144927536232, 'f1': 0.9661908225738013, 'precision': 0.9538690476190477, 'recall': 0.9821428571428572}" 5 | "{'accuracy': 0.927536231884058, 'f1': 0.9019607843137255, 'precision': 0.8863636363636364, 'recall': 0.9553571428571428}","{'accuracy': 0.9565217391304348, 'f1': 0.9401347708894879, 'precision': 0.9182692307692308, 'recall': 0.9732142857142857}","{'accuracy': 0.9130434782608695, 'f1': 0.8660683760683761, 'precision': 0.8543956043956045, 'recall': 0.8809523809523809}","{'accuracy': 0.9130434782608695, 'f1': 0.8778205128205129, 'precision': 0.8592414529914529, 'recall': 0.9136904761904762}","{'accuracy': 0.8985507246376812, 'f1': 0.8498382749326145, 'precision': 0.8357692307692308, 'recall': 0.8720238095238095}" 6 | -------------------------------------------------------------------------------- /output/baseline_results/baseline_centered_smote_dataset_results.csv: -------------------------------------------------------------------------------- 1 | 10,20,25,50,100 2 | "{'accuracy': 0.9420289855072463, 'f1': 0.8583333333333334, 'precision': 0.96875, 'recall': 0.8333333333333333}","{'accuracy': 0.9855072463768116, 'f1': 0.9728867623604466, 'precision': 0.9913793103448276, 'recall': 0.9583333333333334}","{'accuracy': 0.9420289855072463, 'f1': 0.9294155844155844, 'precision': 0.9436813186813187, 'recall': 0.9196428571428571}","{'accuracy': 0.9565217391304348, 'f1': 0.9332160477512004, 'precision': 0.9389880952380952, 'recall': 0.9285714285714286}","{'accuracy': 0.9420289855072463, 'f1': 0.9461623325453112, 'precision': 0.9415064102564104, 'recall': 0.9523809523809523}" 3 | "{'accuracy': 0.9710144927536232, 'f1': 0.9430778032036613, 'precision': 0.9497126436781609, 'recall': 0.9375}","{'accuracy': 0.9420289855072463, 'f1': 0.9106060606060606, 'precision': 0.96875, 'recall': 0.875}","{'accuracy': 0.927536231884058, 'f1': 0.8976505950190161, 'precision': 0.9027093596059114, 'recall': 0.8988095238095238}","{'accuracy': 0.9710144927536232, 'f1': 0.9630250069079856, 'precision': 0.980654761904762, 'recall': 0.9494047619047619}","{'accuracy': 0.9855072463768116, 'f1': 0.9728867623604466, 'precision': 0.9913793103448276, 'recall': 0.9583333333333334}" 4 | "{'accuracy': 0.9565217391304348, 'f1': 0.9230484330484331, 'precision': 0.9093406593406594, 'recall': 0.9404761904761905}","{'accuracy': 0.9710144927536232, 'f1': 0.9661908225738013, 'precision': 0.9538690476190477, 'recall': 0.9821428571428572}","{'accuracy': 0.9565217391304348, 'f1': 0.9315229563269877, 'precision': 0.9723419540229885, 'recall': 0.9077380952380952}","{'accuracy': 0.9420289855072463, 'f1': 0.9244956658786446, 'precision': 0.9190705128205129, 'recall': 0.9315476190476191}","{'accuracy': 0.9710144927536232, 'f1': 0.9630250069079856, 'precision': 0.980654761904762, 'recall': 0.9494047619047619}" 5 | "{'accuracy': 0.9420289855072463, 'f1': 0.9182692307692307, 'precision': 0.9, 'recall': 0.9642857142857143}","{'accuracy': 0.9565217391304348, 'f1': 0.9346969696969697, 'precision': 0.9298433048433048, 'recall': 0.9404761904761905}","{'accuracy': 0.8985507246376812, 'f1': 0.8498382749326145, 'precision': 0.8357692307692308, 'recall': 0.8720238095238095}","{'accuracy': 0.9130434782608695, 'f1': 0.8778205128205129, 'precision': 0.8592414529914529, 'recall': 0.9136904761904762}","{'accuracy': 0.927536231884058, 'f1': 0.8994920174165456, 'precision': 0.8828571428571429, 'recall': 0.9226190476190477}" 6 | -------------------------------------------------------------------------------- /output/baseline_results/baseline_end_dataset_results.csv: -------------------------------------------------------------------------------- 1 | 10,20,25,50,100 2 | "{'accuracy': 0.9710144927536232, 'f1': 0.9583441558441559, 'precision': 0.9718406593406594, 'recall': 0.9494047619047619}","{'accuracy': 0.9855072463768116, 'f1': 0.9728867623604466, 'precision': 0.9913793103448276, 'recall': 0.9583333333333334}","{'accuracy': 0.9855072463768116, 'f1': 0.9728867623604466, 'precision': 0.9913793103448276, 'recall': 0.9583333333333334}","{'accuracy': 0.9565217391304348, 'f1': 0.9393778207607995, 'precision': 0.9386574074074074, 'recall': 0.9404761904761905}","{'accuracy': 0.9855072463768116, 'f1': 0.9728867623604466, 'precision': 0.9913793103448276, 'recall': 0.9583333333333334}" 3 | "{'accuracy': 0.9420289855072463, 'f1': 0.9026811966384554, 'precision': 0.9258064516129032, 'recall': 0.8849637681159419}","{'accuracy': 0.9855072463768116, 'f1': 0.9728867623604466, 'precision': 0.9913793103448276, 'recall': 0.9583333333333334}","{'accuracy': 0.9710144927536232, 'f1': 0.9577824724001636, 'precision': 0.9833333333333334, 'recall': 0.9375}","{'accuracy': 0.9710144927536232, 'f1': 0.9577824724001636, 'precision': 0.9833333333333334, 'recall': 0.9375}","{'accuracy': 0.9565217391304348, 'f1': 0.9483172147001934, 'precision': 0.9610933048433049, 'recall': 0.9404761904761905}" 4 | "{'accuracy': 0.8985507246376812, 'f1': 0.8722796811032105, 'precision': 0.8552018633540373, 'recall': 0.9047619047619048}","{'accuracy': 0.9420289855072463, 'f1': 0.9086418900248687, 'precision': 0.9217261904761905, 'recall': 0.8988095238095238}","{'accuracy': 0.927536231884058, 'f1': 0.9044956658786446, 'precision': 0.8998397435897436, 'recall': 0.9107142857142857}","{'accuracy': 0.9565217391304348, 'f1': 0.9483172147001934, 'precision': 0.9610933048433049, 'recall': 0.9404761904761905}","{'accuracy': 0.9565217391304348, 'f1': 0.9257522796352583, 'precision': 0.9614239926739928, 'recall': 0.9077380952380952}" 5 | "{'accuracy': 0.8695652173913043, 'f1': 0.8446186166774401, 'precision': 0.8287072981366459, 'recall': 0.875}","{'accuracy': 0.9420289855072463, 'f1': 0.9184700248530036, 'precision': 0.9085393772893774, 'recall': 0.9315476190476191}","{'accuracy': 0.9420289855072463, 'f1': 0.9184700248530036, 'precision': 0.9085393772893774, 'recall': 0.9315476190476191}","{'accuracy': 0.9565217391304348, 'f1': 0.9393778207607995, 'precision': 0.9386574074074074, 'recall': 0.9404761904761905}","{'accuracy': 0.9420289855072463, 'f1': 0.9086418900248687, 'precision': 0.9217261904761905, 'recall': 0.8988095238095238}" 6 | -------------------------------------------------------------------------------- /output/baseline_results/baseline_model_accuracy.csv: -------------------------------------------------------------------------------- 1 | hz,model,accuracy 2 | 10,decision_tree,0.9420289855072463 3 | 20,decision_tree,0.9420289855072463 4 | 25,decision_tree,0.927536231884058 5 | 50,decision_tree,0.927536231884058 6 | 100,decision_tree,0.8840579710144928 7 | 10,random_forest,0.8695652173913043 8 | 20,random_forest,0.9420289855072463 9 | 25,random_forest,0.9565217391304348 10 | 50,random_forest,0.9565217391304348 11 | 100,random_forest,0.9855072463768116 12 | 10,svc,0.9420289855072463 13 | 20,svc,0.9710144927536232 14 | 25,svc,0.9420289855072463 15 | 50,svc,0.9130434782608695 16 | 100,svc,0.927536231884058 17 | 10,logistic_regression,0.9420289855072463 18 | 20,logistic_regression,0.927536231884058 19 | 25,logistic_regression,0.8840579710144928 20 | 50,logistic_regression,0.9130434782608695 21 | 100,logistic_regression,0.9130434782608695 22 | -------------------------------------------------------------------------------- /output/baseline_results/baseline_model_inference_time.csv: -------------------------------------------------------------------------------- 1 | hz,decision_tree,random_forest,svc,logistic_regression,framework 2 | 10,6.557890500002291e-06,3.0208239728589044e-05,0.000434073265429106,0.0004398261211429469,pure-python 3 | 20,4.96649174857209e-06,3.281497310001994e-05,0.0008403637582853532,0.0008513739021428981,pure-python 4 | 25,4.875737425708004e-06,2.745845507145402e-05,0.001041573633571326,0.0010471011678572333,pure-python 5 | 50,4.833258169996302e-06,2.9651879714297788e-05,0.0020378926599992804,0.002051195611428349,pure-python 6 | 100,3.326386654282812e-06,2.5566647342878112e-05,0.004211835975719233,0.004121980348572834,pure-python 7 | 10,6.607592372854145e-05,0.0005928817074283351,6.066410021428185e-05,6.06529759285747e-05,scikit 8 | 20,6.888251801428851e-05,0.0005939366574283278,5.9837610328577286e-05,6.13779213285982e-05,scikit 9 | 25,6.606620135717094e-05,0.0005919745511432016,6.085079474284742e-05,6.0042986342809205e-05,scikit 10 | 50,6.914931888573586e-05,0.0005949647409997851,6.056321550004213e-05,6.139360404285981e-05,scikit 11 | 100,6.948609042852435e-05,0.0006059574869996141,6.286250158570641e-05,6.344816632853118e-05,scikit 12 | -------------------------------------------------------------------------------- /output/inference_time_rf_estimators_50hz.csv: -------------------------------------------------------------------------------- 1 | hz,estimators,time,device 2 | 25,3,0.03890949081428577,local 3 | 25,4,0.059462678442857304,local 4 | 25,5,0.07424258258571419,local 5 | 25,10,0.1362965625857144,local 6 | 100,3,0.042696274585714324,local 7 | 100,4,0.051811314657142914,local 8 | 100,5,0.06638631727142845,local 9 | 100,10,0.1205431235857148,local 10 | -------------------------------------------------------------------------------- /output/validation/val_res_base_circle.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,base,52.29007633587786,"0 984 3 | 3 125 4 | 1 92 5 | 2 45 6 | Name: result, dtype: int64" 7 | decision_tree,50,base,67.27272727272727,"0 513 8 | 2 40 9 | 3 36 10 | 1 34 11 | Name: result, dtype: int64" 12 | decision_tree,25,base,37.03703703703704,"0 258 13 | 3 34 14 | 1 11 15 | 2 9 16 | Name: result, dtype: int64" 17 | decision_tree,20,base,64.15094339622641,"0 197 18 | 3 19 19 | 2 18 20 | 1 16 21 | Name: result, dtype: int64" 22 | decision_tree,10,base,65.85365853658537,"0 84 23 | 1 17 24 | 3 14 25 | 2 10 26 | Name: result, dtype: int64" 27 | random_forest,100,base,48.97959183673469,"0 952 28 | 3 150 29 | 1 77 30 | 2 67 31 | Name: result, dtype: int64" 32 | random_forest,50,base,53.179190751445084,"0 450 33 | 3 81 34 | 1 65 35 | 2 27 36 | Name: result, dtype: int64" 37 | random_forest,25,base,61.29032258064516,"0 219 38 | 1 42 39 | 3 36 40 | 2 15 41 | Name: result, dtype: int64" 42 | random_forest,20,base,36.11111111111111,"0 214 43 | 3 23 44 | 1 12 45 | 2 1 46 | Name: result, dtype: int64" 47 | random_forest,10,base,50.0,"0 109 48 | 3 8 49 | 1 5 50 | 2 3 51 | Name: result, dtype: int64" 52 | -------------------------------------------------------------------------------- /output/validation/val_res_base_x.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,base,13.186813186813188,"0 1659 3 | 1 79 4 | 2 9 5 | 3 3 6 | Name: result, dtype: int64" 7 | decision_tree,50,base,33.82352941176471,"0 807 8 | 1 45 9 | 2 13 10 | 3 10 11 | Name: result, dtype: int64" 12 | decision_tree,25,base,9.67741935483871,"0 407 13 | 1 28 14 | 2 3 15 | Name: result, dtype: int64" 16 | decision_tree,20,base,5.263157894736842,"0 331 17 | 1 18 18 | 2 1 19 | Name: result, dtype: int64" 20 | decision_tree,10,base,0.0,"0 163 21 | 1 12 22 | Name: result, dtype: int64" 23 | random_forest,100,base,19.101123595505616,"0 1661 24 | 1 72 25 | 2 17 26 | Name: result, dtype: int64" 27 | random_forest,50,base,13.88888888888889,"0 839 28 | 1 31 29 | 2 5 30 | Name: result, dtype: int64" 31 | random_forest,25,base,40.909090909090914,"0 416 32 | 1 13 33 | 2 9 34 | Name: result, dtype: int64" 35 | random_forest,20,base,28.57142857142857,"0 336 36 | 1 10 37 | 3 4 38 | Name: result, dtype: int64" 39 | random_forest,10,base,0.0,"0 173 40 | 1 2 41 | Name: result, dtype: int64" 42 | -------------------------------------------------------------------------------- /output/validation/val_res_base_y.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,base,3.571428571428571,"0 1739 3 | 2 81 4 | 1 3 5 | Name: result, dtype: int64" 6 | decision_tree,50,base,0.0,"0 862 7 | 2 50 8 | Name: result, dtype: int64" 9 | decision_tree,25,base,0.0,"0 431 10 | 2 25 11 | Name: result, dtype: int64" 12 | decision_tree,20,base,5.0,"0 345 13 | 2 19 14 | 1 1 15 | Name: result, dtype: int64" 16 | decision_tree,10,base,10.0,"0 173 17 | 2 9 18 | 1 1 19 | Name: result, dtype: int64" 20 | random_forest,100,base,0.9803921568627451,"0 1721 21 | 2 101 22 | 1 1 23 | Name: result, dtype: int64" 24 | random_forest,50,base,4.761904761904762,"0 849 25 | 2 60 26 | 1 3 27 | Name: result, dtype: int64" 28 | random_forest,25,base,26.47058823529412,"0 422 29 | 2 25 30 | 1 9 31 | Name: result, dtype: int64" 32 | random_forest,20,base,0.0,"0 348 33 | 2 17 34 | Name: result, dtype: int64" 35 | random_forest,10,base,16.666666666666664,"0 177 36 | 2 5 37 | 1 1 38 | Name: result, dtype: int64" 39 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_aug_circle.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered_aug,72.19917012448133,"0 764 3 | 1 254 4 | 3 134 5 | 2 94 6 | Name: result, dtype: int64" 7 | decision_tree,50,centered_aug,69.86899563318777,"0 394 8 | 1 119 9 | 3 69 10 | 2 41 11 | Name: result, dtype: int64" 12 | decision_tree,25,centered_aug,63.63636363636363,"0 158 13 | 3 56 14 | 2 53 15 | 1 45 16 | Name: result, dtype: int64" 17 | decision_tree,20,centered_aug,72.91666666666666,"0 154 18 | 1 61 19 | 3 26 20 | 2 9 21 | Name: result, dtype: int64" 22 | decision_tree,10,centered_aug,77.77777777777779,"0 71 23 | 1 33 24 | 3 12 25 | 2 9 26 | Name: result, dtype: int64" 27 | random_forest,100,centered_aug,74.93857493857494,"0 839 28 | 1 188 29 | 2 117 30 | 3 102 31 | Name: result, dtype: int64" 32 | random_forest,50,centered_aug,57.02479338842975,"0 381 33 | 3 104 34 | 1 91 35 | 2 47 36 | Name: result, dtype: int64" 37 | random_forest,25,centered_aug,61.206896551724135,"0 196 38 | 3 45 39 | 1 37 40 | 2 34 41 | Name: result, dtype: int64" 42 | random_forest,20,centered_aug,55.42168674698795,"0 167 43 | 1 38 44 | 3 37 45 | 2 8 46 | Name: result, dtype: int64" 47 | random_forest,10,centered_aug,45.714285714285715,"0 90 48 | 3 19 49 | 2 11 50 | 1 5 51 | Name: result, dtype: int64" 52 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_aug_x.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered_aug,6.607929515418502,"0 1523 3 | 1 212 4 | 2 15 5 | Name: result, dtype: int64" 6 | decision_tree,50,centered_aug,13.91304347826087,"0 760 7 | 1 99 8 | 2 16 9 | Name: result, dtype: int64" 10 | decision_tree,25,centered_aug,25.0,"0 362 11 | 1 57 12 | 3 15 13 | 2 4 14 | Name: result, dtype: int64" 15 | decision_tree,20,centered_aug,12.195121951219512,"0 309 16 | 1 36 17 | 2 5 18 | Name: result, dtype: int64" 19 | decision_tree,10,centered_aug,5.0,"0 155 20 | 1 19 21 | 2 1 22 | Name: result, dtype: int64" 23 | random_forest,100,centered_aug,1.7543859649122806,"0 1579 24 | 1 168 25 | 2 3 26 | Name: result, dtype: int64" 27 | random_forest,50,centered_aug,12.037037037037036,"0 767 28 | 1 95 29 | 2 13 30 | Name: result, dtype: int64" 31 | random_forest,25,centered_aug,26.190476190476193,"0 396 32 | 1 31 33 | 2 11 34 | Name: result, dtype: int64" 35 | random_forest,20,centered_aug,13.636363636363635,"0 306 36 | 1 38 37 | 2 6 38 | Name: result, dtype: int64" 39 | random_forest,10,centered_aug,13.333333333333334,"0 160 40 | 1 13 41 | 2 2 42 | Name: result, dtype: int64" 43 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_aug_y.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered_aug,2.3529411764705883,"0 1653 3 | 2 166 4 | 1 4 5 | Name: result, dtype: int64" 6 | decision_tree,50,centered_aug,0.0,"0 825 7 | 2 87 8 | Name: result, dtype: int64" 9 | decision_tree,25,centered_aug,20.754716981132077,"0 403 10 | 2 42 11 | 3 10 12 | 1 1 13 | Name: result, dtype: int64" 14 | decision_tree,20,centered_aug,12.5,"0 333 15 | 2 28 16 | 1 4 17 | Name: result, dtype: int64" 18 | decision_tree,10,centered_aug,0.0,"0 160 19 | 2 23 20 | Name: result, dtype: int64" 21 | random_forest,100,centered_aug,7.216494845360824,"0 1629 22 | 2 180 23 | 1 14 24 | Name: result, dtype: int64" 25 | random_forest,50,centered_aug,5.426356589147287,"0 783 26 | 2 122 27 | 1 7 28 | Name: result, dtype: int64" 29 | random_forest,25,centered_aug,25.53191489361702,"0 409 30 | 2 35 31 | 1 12 32 | Name: result, dtype: int64" 33 | random_forest,20,centered_aug,6.896551724137931,"0 336 34 | 2 27 35 | 1 2 36 | Name: result, dtype: int64" 37 | random_forest,10,centered_aug,0.0,"0 166 38 | 2 17 39 | Name: result, dtype: int64" 40 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_circle.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered,69.12751677852349,"0 948 3 | 1 104 4 | 2 102 5 | 3 92 6 | Name: result, dtype: int64" 7 | decision_tree,50,centered,56.666666666666664,"0 473 8 | 3 65 9 | 2 51 10 | 1 34 11 | Name: result, dtype: int64" 12 | decision_tree,25,centered,69.6969696969697,"0 246 13 | 1 23 14 | 2 23 15 | 3 20 16 | Name: result, dtype: int64" 17 | decision_tree,20,centered,62.06896551724138,"0 192 18 | 3 22 19 | 1 20 20 | 2 16 21 | Name: result, dtype: int64" 22 | decision_tree,10,centered,70.37037037037037,"0 98 23 | 1 19 24 | 3 8 25 | Name: result, dtype: int64" 26 | random_forest,100,centered,57.35294117647059,"0 974 27 | 1 145 28 | 3 116 29 | 2 11 30 | Name: result, dtype: int64" 31 | random_forest,50,centered,56.09756097560976,"0 459 32 | 3 72 33 | 1 71 34 | 2 21 35 | Name: result, dtype: int64" 36 | random_forest,25,centered,32.075471698113205,"0 259 37 | 3 36 38 | 2 9 39 | 1 8 40 | Name: result, dtype: int64" 41 | random_forest,20,centered,48.07692307692308,"0 198 42 | 3 27 43 | 1 22 44 | 2 3 45 | Name: result, dtype: int64" 46 | random_forest,10,centered,35.294117647058826,"0 108 47 | 3 11 48 | 1 5 49 | 2 1 50 | Name: result, dtype: int64" 51 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_smote_circle.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered_smote,41.832669322709165,"0 995 3 | 3 146 4 | 2 80 5 | 1 25 6 | Name: result, dtype: int64" 7 | decision_tree,50,centered_smote,52.94117647058824,"0 470 8 | 3 72 9 | 1 44 10 | 2 37 11 | Name: result, dtype: int64" 12 | decision_tree,25,centered_smote,64.04494382022472,"0 223 13 | 1 34 14 | 3 32 15 | 2 23 16 | Name: result, dtype: int64" 17 | decision_tree,20,centered_smote,52.307692307692314,"0 185 18 | 3 31 19 | 1 23 20 | 2 11 21 | Name: result, dtype: int64" 22 | decision_tree,10,centered_smote,65.51724137931035,"0 96 23 | 2 12 24 | 3 10 25 | 1 7 26 | Name: result, dtype: int64" 27 | random_forest,100,centered_smote,56.97211155378486,"0 995 28 | 1 123 29 | 3 108 30 | 2 20 31 | Name: result, dtype: int64" 32 | random_forest,50,centered_smote,67.21311475409836,"0 501 33 | 1 57 34 | 3 40 35 | 2 25 36 | Name: result, dtype: int64" 37 | random_forest,25,centered_smote,40.74074074074074,"0 258 38 | 3 32 39 | 2 16 40 | 1 6 41 | Name: result, dtype: int64" 42 | random_forest,20,centered_smote,28.57142857142857,"0 194 43 | 3 40 44 | 1 11 45 | 2 5 46 | Name: result, dtype: int64" 47 | random_forest,10,centered_smote,54.54545454545454,"0 103 48 | 3 10 49 | 1 9 50 | 2 3 51 | Name: result, dtype: int64" 52 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_smote_x.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered_smote,23.58490566037736,"0 1644 3 | 1 81 4 | 2 25 5 | Name: result, dtype: int64" 6 | decision_tree,50,centered_smote,19.444444444444446,"0 839 7 | 1 29 8 | 2 7 9 | Name: result, dtype: int64" 10 | decision_tree,25,centered_smote,52.94117647058824,"0 404 11 | 3 17 12 | 1 16 13 | 2 1 14 | Name: result, dtype: int64" 15 | decision_tree,20,centered_smote,0.0,"0 334 16 | 1 16 17 | Name: result, dtype: int64" 18 | decision_tree,10,centered_smote,62.5,"0 167 19 | 2 5 20 | 1 3 21 | Name: result, dtype: int64" 22 | random_forest,100,centered_smote,4.545454545454546,"0 1684 23 | 1 63 24 | 2 3 25 | Name: result, dtype: int64" 26 | random_forest,50,centered_smote,6.25,"0 859 27 | 1 15 28 | 2 1 29 | Name: result, dtype: int64" 30 | random_forest,25,centered_smote,33.33333333333333,"0 432 31 | 1 4 32 | 2 2 33 | Name: result, dtype: int64" 34 | random_forest,20,centered_smote,15.789473684210526,"0 331 35 | 1 16 36 | 3 3 37 | Name: result, dtype: int64" 38 | random_forest,10,centered_smote,0.0,"0 170 39 | 1 5 40 | Name: result, dtype: int64" 41 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_smote_y.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered_smote,0.0,"0 1733 3 | 2 90 4 | Name: result, dtype: int64" 5 | decision_tree,50,centered_smote,20.0,"0 867 6 | 2 36 7 | 1 9 8 | Name: result, dtype: int64" 9 | decision_tree,25,centered_smote,30.303030303030305,"0 423 10 | 2 23 11 | 1 10 12 | Name: result, dtype: int64" 13 | decision_tree,20,centered_smote,0.0,"0 350 14 | 2 15 15 | Name: result, dtype: int64" 16 | decision_tree,10,centered_smote,11.11111111111111,"0 174 17 | 2 8 18 | 1 1 19 | Name: result, dtype: int64" 20 | random_forest,100,centered_smote,7.865168539325842,"0 1734 21 | 2 82 22 | 1 7 23 | Name: result, dtype: int64" 24 | random_forest,50,centered_smote,4.878048780487805,"0 871 25 | 2 39 26 | 1 2 27 | Name: result, dtype: int64" 28 | random_forest,25,centered_smote,18.75,"0 440 29 | 2 13 30 | 1 3 31 | Name: result, dtype: int64" 32 | random_forest,20,centered_smote,19.047619047619047,"0 344 33 | 2 17 34 | 1 2 35 | 3 2 36 | Name: result, dtype: int64" 37 | random_forest,10,centered_smote,20.0,"0 173 38 | 2 8 39 | 1 1 40 | 3 1 41 | Name: result, dtype: int64" 42 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_x.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered,22.52252252252252,"0 1639 3 | 1 86 4 | 2 25 5 | Name: result, dtype: int64" 6 | decision_tree,50,centered,21.818181818181817,"0 820 7 | 1 43 8 | 2 12 9 | Name: result, dtype: int64" 10 | decision_tree,25,centered,12.5,"0 414 11 | 1 21 12 | 2 3 13 | Name: result, dtype: int64" 14 | decision_tree,20,centered,0.0,"0 330 15 | 1 20 16 | Name: result, dtype: int64" 17 | decision_tree,10,centered,0.0,"0 165 18 | 1 10 19 | Name: result, dtype: int64" 20 | random_forest,100,centered,0.0,"0 1659 21 | 1 91 22 | Name: result, dtype: int64" 23 | random_forest,50,centered,0.0,"0 825 24 | 1 50 25 | Name: result, dtype: int64" 26 | random_forest,25,centered,0.0,"0 424 27 | 1 14 28 | Name: result, dtype: int64" 29 | random_forest,20,centered,6.666666666666667,"0 335 30 | 1 14 31 | 3 1 32 | Name: result, dtype: int64" 33 | random_forest,10,centered,0.0,"0 165 34 | 1 10 35 | Name: result, dtype: int64" 36 | -------------------------------------------------------------------------------- /output/validation/val_res_centered_y.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,centered,8.16326530612245,"0 1725 3 | 2 90 4 | 1 8 5 | Name: result, dtype: int64" 6 | decision_tree,50,centered,8.333333333333332,"0 864 7 | 2 44 8 | 1 4 9 | Name: result, dtype: int64" 10 | decision_tree,25,centered,0.0,"0 433 11 | 2 23 12 | Name: result, dtype: int64" 13 | decision_tree,20,centered,12.5,"0 349 14 | 2 14 15 | 1 2 16 | Name: result, dtype: int64" 17 | decision_tree,10,centered,11.11111111111111,"0 174 18 | 2 8 19 | 1 1 20 | Name: result, dtype: int64" 21 | random_forest,100,centered,17.647058823529413,"0 1738 22 | 2 70 23 | 1 15 24 | Name: result, dtype: int64" 25 | random_forest,50,centered,26.31578947368421,"0 855 26 | 2 42 27 | 1 15 28 | Name: result, dtype: int64" 29 | random_forest,25,centered,62.5,"0 440 30 | 1 10 31 | 2 6 32 | Name: result, dtype: int64" 33 | random_forest,20,centered,0.0,"0 349 34 | 2 16 35 | Name: result, dtype: int64" 36 | random_forest,10,centered,33.33333333333333,"0 180 37 | 2 2 38 | 1 1 39 | Name: result, dtype: int64" 40 | -------------------------------------------------------------------------------- /output/validation/val_res_end_circle.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,end,55.582524271844655,"0 834 3 | 1 208 4 | 3 183 5 | 2 21 6 | Name: result, dtype: int64" 7 | decision_tree,50,end,64.17910447761194,"0 422 8 | 1 98 9 | 3 72 10 | 2 31 11 | Name: result, dtype: int64" 12 | decision_tree,25,end,51.94805194805194,"0 235 13 | 3 37 14 | 1 34 15 | 2 6 16 | Name: result, dtype: int64" 17 | decision_tree,20,end,46.25,"0 170 18 | 3 43 19 | 1 21 20 | 2 16 21 | Name: result, dtype: int64" 22 | decision_tree,10,end,50.0,"0 85 23 | 3 20 24 | 1 10 25 | 2 10 26 | Name: result, dtype: int64" 27 | random_forest,100,end,47.81144781144781,"0 949 28 | 3 155 29 | 1 99 30 | 2 43 31 | Name: result, dtype: int64" 32 | random_forest,50,end,49.6,"0 498 33 | 3 63 34 | 1 41 35 | 2 21 36 | Name: result, dtype: int64" 37 | random_forest,25,end,61.72839506172839,"0 231 38 | 3 31 39 | 1 27 40 | 2 23 41 | Name: result, dtype: int64" 42 | random_forest,20,end,52.112676056338024,"0 179 43 | 3 34 44 | 2 20 45 | 1 17 46 | Name: result, dtype: int64" 47 | random_forest,10,end,66.66666666666666,"0 101 48 | 2 14 49 | 3 8 50 | 1 2 51 | Name: result, dtype: int64" 52 | -------------------------------------------------------------------------------- /output/validation/val_res_end_x.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,end,58.82352941176471,"0 1597 3 | 3 87 4 | 1 63 5 | 2 3 6 | Name: result, dtype: int64" 7 | decision_tree,50,end,13.043478260869565,"0 829 8 | 1 40 9 | 2 6 10 | Name: result, dtype: int64" 11 | decision_tree,25,end,55.00000000000001,"0 398 12 | 3 19 13 | 1 18 14 | 2 3 15 | Name: result, dtype: int64" 16 | decision_tree,20,end,56.41025641025641,"0 311 17 | 3 20 18 | 1 17 19 | 2 2 20 | Name: result, dtype: int64" 21 | decision_tree,10,end,55.55555555555556,"0 157 22 | 3 10 23 | 1 8 24 | Name: result, dtype: int64" 25 | random_forest,100,end,10.144927536231885,"0 1681 26 | 1 62 27 | 2 7 28 | Name: result, dtype: int64" 29 | random_forest,50,end,23.404255319148938,"0 828 30 | 1 36 31 | 2 11 32 | Name: result, dtype: int64" 33 | random_forest,25,end,44.44444444444444,"0 411 34 | 1 15 35 | 2 12 36 | Name: result, dtype: int64" 37 | random_forest,20,end,42.857142857142854,"0 329 38 | 1 12 39 | 2 9 40 | Name: result, dtype: int64" 41 | random_forest,10,end,16.666666666666664,"0 169 42 | 1 5 43 | 2 1 44 | Name: result, dtype: int64" 45 | -------------------------------------------------------------------------------- /output/validation/val_res_end_y.csv: -------------------------------------------------------------------------------- 1 | model,hz,dataset,error_percentage,value_counts 2 | decision_tree,100,end,37.391304347826086,"0 1708 3 | 2 72 4 | 1 31 5 | 3 12 6 | Name: result, dtype: int64" 7 | decision_tree,50,end,29.629629629629626,"0 858 8 | 2 38 9 | 1 16 10 | Name: result, dtype: int64" 11 | decision_tree,25,end,4.761904761904762,"0 435 12 | 2 20 13 | 3 1 14 | Name: result, dtype: int64" 15 | decision_tree,20,end,20.0,"0 345 16 | 2 16 17 | 3 4 18 | Name: result, dtype: int64" 19 | decision_tree,10,end,12.5,"0 167 20 | 2 14 21 | 3 2 22 | Name: result, dtype: int64" 23 | random_forest,100,end,6.730769230769231,"0 1719 24 | 2 97 25 | 1 7 26 | Name: result, dtype: int64" 27 | random_forest,50,end,0.0,"0 884 28 | 2 28 29 | Name: result, dtype: int64" 30 | random_forest,25,end,5.555555555555555,"0 438 31 | 2 17 32 | 1 1 33 | Name: result, dtype: int64" 34 | random_forest,20,end,0.0,"0 348 35 | 2 17 36 | Name: result, dtype: int64" 37 | random_forest,10,end,16.666666666666664,"0 177 38 | 2 5 39 | 3 1 40 | Name: result, dtype: int64" 41 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tkeyo/tinyml-esp-data/ec5e2fc3111ea711e87086fb3624d610a1525826/requirements.txt -------------------------------------------------------------------------------- /validation_utils.py: -------------------------------------------------------------------------------- 1 | import pandas as pd 2 | import numpy as np 3 | 4 | import seaborn as sns 5 | import matplotlib.pyplot as plt 6 | import matplotlib.patches as mpatches 7 | 8 | def transform_data_for_inference(df): 9 | ''' 10 | Transoforms dataset for inference. 11 | ms,acc,gyro -> acc_x_0, gyro_x_0, acc_x_10, gyro_x_10, .... acc_x_n, gyro_x_n 12 | ''' 13 | 14 | df_list=[] 15 | 16 | for time in df.index: 17 | _df = pd.DataFrame(df.loc[time]).T 18 | df_list.append(_df.add_suffix(f'_{str(int(time))}').reset_index(drop=True)) 19 | 20 | return pd.concat(df_list, axis=1) 21 | 22 | 23 | def get_filter_string(start, step): 24 | ''' 25 | Creates a string to filter dataset for defined timetimestamps. 26 | To be used with df.filter(regex='') 27 | Example: 0|50|100 28 | ''' 29 | 30 | keep = np.arange(start, start+1+1000, step=int(step)) 31 | return '|'.join(map(str, keep.astype(int))) 32 | 33 | 34 | def line_color(inf_result): 35 | '''Returns color associated with inference result.''' 36 | colors = { 37 | 1:'blue', 38 | 2:'red', 39 | 3:'green' 40 | } 41 | return colors[inf_result] 42 | 43 | 44 | def downsample_df(df, period): 45 | '''Downsamples dataset.''' 46 | 47 | last_index_ms = df.index[-1] 48 | keep = np.arange(last_index_ms, step=period) 49 | 50 | return df.loc[keep] 51 | 52 | 53 | def filter_df_by_signals(df, signals): 54 | '''Filter dataset byt signal''' 55 | return df.filter(regex=f'({"|".join(signals)})') 56 | 57 | 58 | def run_inference(df, model, start, step): 59 | '''Runs inference.''' 60 | regex_filter = get_filter_string(start=start, step=step) 61 | data = list(df.filter(regex=f'_({regex_filter})$').loc[0]) 62 | return model.score(data) 63 | 64 | 65 | def calculate_error(res, move_type): 66 | '''Calculates inference error rate in validation data.''' 67 | 68 | error_setup = { 69 | 'circle': {'err_1':1,'err_2':2}, 70 | 'x':{'err_1':2, 'err_2':3}, 71 | 'y':{'err_1':1,'err_2':3} 72 | } 73 | 74 | err_1 = error_setup[move_type]['err_1'] 75 | err_2 = error_setup[move_type]['err_2'] 76 | 77 | val_counts = res['result'].value_counts().drop(0) # dropping `no movement` 78 | val_counts_keys = val_counts.keys() 79 | 80 | total_wrong = 0 81 | 82 | if err_1 in val_counts_keys: 83 | total_wrong += val_counts[err_1] 84 | if err_2 in val_counts_keys: 85 | total_wrong += val_counts[err_2] 86 | 87 | return (total_wrong / val_counts.sum()) * 100 88 | 89 | 90 | def get_move_from_path(s): 91 | '''Gets movement type from string path.''' 92 | import re 93 | return re.findall(r'_(x|circle|y)_', s)[0] 94 | 95 | 96 | def run_validation(model_setup, dataset_path, dataset, is_plot=False, is_save_results=True): 97 | '''Plots validation results.''' 98 | validation_results = [] 99 | 100 | if is_plot: 101 | fig, ax = plt.subplots(ncols=2, nrows=5, sharey=True, sharex=True, figsize=(30,25)) 102 | 103 | # Create Legend 104 | blue_patch = mpatches.Patch(color='blue', label='X Movement') 105 | red_patch = mpatches.Patch(color='red', label='Y Movement') 106 | green_patch = mpatches.Patch(color='green', label='Circle Movement') 107 | fig.legend(handles=[blue_patch, red_patch, green_patch]) 108 | 109 | fig.tight_layout() 110 | 111 | for setup in model_setup: 112 | # parse settings 113 | MODEL = setup[0] 114 | FREQ = setup[1] 115 | STEP = (1000 / FREQ) 116 | COL = setup[2][0] 117 | ROW = setup[2][1] 118 | 119 | df_val = pd.read_csv(dataset_path).set_index('ms') 120 | 121 | # initialize empty dataset to collect results 122 | inf_results = pd.DataFrame([],columns=['start','end','result']) 123 | 124 | # treat dataset 125 | df_downsampled = downsample_df(df_val, STEP) # downsample dataset 126 | df_inference = transform_data_for_inference(df_downsampled) # converts dataset to inference format 127 | 128 | # generate a list of steps 129 | inference_step = list(np.arange(0, df_val.index[-1] + 1 - 1010, step=STEP)) 130 | 131 | results_for_plot = [] 132 | 133 | for st in inference_step: 134 | res = np.argmax(run_inference(df_inference, MODEL, st, STEP)) 135 | inf_results = pd.concat([inf_results, pd.DataFrame([{'start':st,'end':st+1000,'result':res}])], axis=0) 136 | 137 | if res in [1,2,3]: 138 | color = line_color(res) 139 | results_for_plot.append((color, st)) 140 | 141 | 142 | # Plot signals 143 | if is_plot: 144 | ax[ROW][COL].plot(df_downsampled) 145 | 146 | for r in results_for_plot: 147 | color_plot = r[0] 148 | st_plot = r[1] 149 | 150 | ax[ROW][COL].axvline(x=st_plot+500, ymin=0, ymax=0.4, color=color_plot, alpha=0.4) 151 | 152 | # get error rate 153 | move = get_move_from_path(dataset_path) 154 | 155 | error_percentage = calculate_error(inf_results, move) 156 | validation_results.append({'model':setup[-1], 'hz':setup[1], 'dataset':dataset,'error_percentage': error_percentage, 'value_counts': inf_results['result'].value_counts()}) 157 | 158 | if is_save_results: 159 | pd.DataFrame(validation_results).to_csv(f'output/validation/val_res_{dataset}_{move}.csv', index=False) 160 | 161 | return validation_results --------------------------------------------------------------------------------