{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_kg_hide-input":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_parquet('/kaggle/input/icecube-neutrinos-in-deep-ice/test_meta.parquet')\ntrain=pd.read_parquet(\"/kaggle/input/icecube-neutrinos-in-deep-ice/train_meta.parquet\")\nsample=pd.read_parquet('/kaggle/input/icecube-neutrinos-in-deep-ice/sample_submission.parquet')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"features=['batch_id','event_id','first_pulse_index','last_pulse_index']\ntarget=['azimuth','zenith']","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import StratifiedKFold\nimport lightgbm as lgbm\nfrom sklearn.metrics import roc_auc_score\nimport optuna\nfrom optuna.samplers import TPESampler\npd.options.display.max_columns=50","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X=train[features]\ny=train[target]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nX_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.20,random_state=0)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.ensemble import RandomForestRegressor","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"regr = RandomForestRegressor(max_depth=2,n_estimators = 30, random_state=0)\nmodel=regr.fit(X_train, y_train)\npredict=model.predict(X_test)\nRandomForestRegressor(...)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_predict=model.predict(test)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sample['azimuth'] = train['azimuth'].mean()\nsample['zenith'] = train['zenith'].mean()\nsample.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}