{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import warnings\nwarnings.filterwarnings('ignore')\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nsns.set(style=\"white\")\n%matplotlib inline\nfrom sklearn.preprocessing import StandardScaler, OneHotEncoder\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LinearRegression\nfrom sklearn.metrics import mean_absolute_error\nfrom sklearn.neighbors import KNeighborsRegressor\nfrom sklearn.ensemble import ExtraTreesRegressor\nfrom sklearn.model_selection import cross_val_score, GridSearchCV\nfrom scipy.sparse import csr_matrix, hstack\nfrom sklearn.tree import DecisionTreeRegressor\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"test_df = pd.read_csv('../input/departure-delay/x_test.csv')\ntrain_df = pd.read_csv('../input/departure-delay/x_train.csv')\ntarget = pd.read_csv('../input/departure-delay/y_train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = train_df.drop(['Unnamed: 0','UniqueCarrier', 'TailNum', 'Origin', 'Dest', 'CancellationCode'], axis=1)\nx_test = test_df.drop(['Unnamed: 0','UniqueCarrier', 'TailNum', 'Origin', 'Dest', 'CancellationCode'], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.fillna(0, inplace=True)\nx_test.fillna(0, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train.shape, target.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dt = DecisionTreeRegressor(max_depth=10, min_samples_leaf=10000, min_samples_split=10000)\ndt.fit(x_train, target)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction = dt.predict(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.Series(prediction, name='DelayTime').to_csv('prediction.csv', \n                                           index_label='id', header=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}