{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\nDIR = \"../input/\"\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv(DIR+'train.csv', nrows=5000000, dtype={'acoustic_data': np.int16, 'time_to_failure': np.float64})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import StandardScaler\nsc = StandardScaler()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = train.iloc[:,0].values\ny = train.iloc[:,1].values\nfrom sklearn.model_selection import train_test_split\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)\n\nX_train= X_train.reshape(-1, 1)\nX_test = X_test.reshape(-1, 1)\n\n# Feature Scaling\nfrom sklearn.preprocessing import StandardScaler\nsc_X = StandardScaler()\nX_train = sc_X.fit_transform(X_train)\nX_test = sc_X.transform(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.svm import SVR\nfrom sklearn.model_selection import GridSearchCV","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"parameters = [{'gamma': [0.001, 0.005, 0.01, 0.02, 0.05, 0.1],\n               'C': [0.1, 0.2, 0.25, 0.5, 1, 1.5, 2]}]\n\nreg1 = GridSearchCV(SVR(kernel='rbf', tol=0.01), parameters, cv=5, scoring='neg_mean_absolute_error')\nreg1.fit(X_train, y_train)\ny_pred1 = reg1.predict(X_test)\n\nprint(\"Best CV score: {:.4f}\".format(reg1.best_score_))\nprint(reg1.best_params_)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}