{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":102335,"databundleVersionId":12518947,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import pandas as pd\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.preprocessing import LabelEncoder\n\n# Загрузка обучающих данных\ntrain = pd.read_csv('/kaggle/input/cmi-detect-behavior-with-sensor-data/train.csv')\nX = train[['acc_x', 'acc_y', 'acc_z', 'sequence_counter']]\ny = train['behavior']\n\n# Кодирование целевой переменной\nle = LabelEncoder()\ny_encoded = le.fit_transform(y)\n\n# Обучение модели\nmodel = RandomForestClassifier(n_estimators=10, random_state=42)\nmodel.fit(X, y_encoded)\n\n# ОБЯЗАТЕЛЬНАЯ функция\ndef predict(test_df):\n    X_test = test_df[['acc_x', 'acc_y', 'acc_z', 'sequence_counter']]\n    preds = model.predict(X_test)\n    labels = le.inverse_transform(preds)\n    return pd.Series(labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-06-13T07:49:06.187222Z","iopub.execute_input":"2025-06-13T07:49:06.187875Z","iopub.status.idle":"2025-06-13T07:49:53.632284Z","shell.execute_reply.started":"2025-06-13T07:49:06.187832Z","shell.execute_reply":"2025-06-13T07:49:53.629788Z"}},"outputs":[],"execution_count":null}]}