{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"!apt-get remove swig \n!apt-get install swig3.0 build-essential -y\n!ln -s /usr/bin/swig3.0 /usr/bin/swig\n!apt-get install build-essential\n!pip install --upgrade setuptools\n!pip install auto-sklearn\ntry:\n    import autosklearn.classification\nexcept:\n    pass","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!apt-get remove swig \n!apt-get install swig3.0 build-essential -y\n!ln -s /usr/bin/swig3.0 /usr/bin/swig\n!apt-get install build-essential\n!pip install --upgrade setuptools\n!pip install auto-sklearn\nimport autosklearn.classification","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport scipy as sc\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport gc\nimport warnings\nwarnings.filterwarnings(\"ignore\")\nwarnings.simplefilter(action='ignore', category=FutureWarning)\nfrom tqdm import tqdm_notebook\nimport datetime\nimport time\nimport random\nfrom joblib import Parallel, delayed\n\n\nimport lightgbm as lgb\nfrom tensorflow import keras\nfrom gplearn.genetic import SymbolicRegressor\nfrom catboost import Pool, CatBoostRegressor\n\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.metrics import mean_absolute_error\nfrom sklearn.model_selection import GridSearchCV, KFold, RandomizedSearchCV\nfrom sklearn.feature_selection import RFECV, SelectFromModel\n\nfrom sklearn.linear_model import LinearRegression, Ridge\nfrom sklearn.tree import DecisionTreeRegressor\nfrom sklearn.svm import NuSVR, SVR\nfrom sklearn.kernel_ridge import KernelRidge\nfrom sklearn.ensemble import AdaBoostRegressor\nfrom sklearn.ensemble import RandomForestRegressor, ExtraTreesRegressor","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"train_X_0 = pd.read_csv(\"../input/lanl-master-s-features-creating-0/train_X_features_865.csv\")\ntrain_X_1 = pd.read_csv(\"../input/lanl-master-s-features-creating-1/train_X_features_865.csv\")\ny_0 = pd.read_csv(\"../input/lanl-master-s-features-creating-0/train_y.csv\", index_col=False,  header=None)\ny_1 = pd.read_csv(\"../input/lanl-master-s-features-creating-1/train_y.csv\", index_col=False,  header=None)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_X = pd.concat([train_X_0, train_X_1], axis=0)\ntrain_X = train_X.reset_index(drop=True)\nprint(train_X.shape)\ntrain_X.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_y = pd.concat([y_0, y_1], axis=0)\ntrain_y = train_y.reset_index(drop=True)\ntrain_y.columns = ['time_to_failure']\ntrain_y['time_to_failure'].shape","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"test_X = pd.read_csv(\"../input/lanl-master-s-features-creating-0/test_X_features_10.csv\")\ntest_X.drop('seg_id',inplace=True,axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"scaler = StandardScaler()\ntrain_columns = train_X.columns\n\ntrain_X[train_columns] = scaler.fit_transform(train_X[train_columns])\ntest_X[train_columns] = scaler.transform(test_X[train_columns])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Auto-SKlearn"},{"metadata":{"trusted":true},"cell_type":"code","source":"import autosklearn.regression\ncls = autosklearn.regression.AutoSklearnRegressor(ensemble_memory_limit=5000,ml_memory_limit=10000,time_left_for_this_task=10000,per_run_time_limit=1000,seed=123,resampling_strategy='cv',resampling_strategy_arguments={\"folds\": 5})\ncls.fit(train_X, train_y,metric=autosklearn.metrics.mean_absolute_error,dataset_name='LANL')\ncls.refit(train_X, train_y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cls.sprint_statistics()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cls.show_models()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = cls.predict(test_X)\n\nsample_submission = pd.read_csv('../input/LANL-Earthquake-Prediction/sample_submission.csv')\nsample_submission['time_to_failure'] = preds.flatten()\nsample_submission.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}