{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.ensemble import RandomForestRegressor","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"a55b5d5e4b874b9c912aed248d86f75a44693bf0"},"cell_type":"code","source":"df_train = pd.read_csv('../input/train.csv')\ntrain_X = df_train.iloc[:,:-1]\ntrain_Y = df_train[['SalePrice']]\ntrain_X\ntrain_Y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1ff7af0fbabb5604dce220bdd443a78be068283d"},"cell_type":"code","source":"df_test =  pd.read_csv('../input/test.csv')\nmissing_cols_fillna = ['PoolQC','MiscFeature','Alley','Fence','MasVnrType','FireplaceQu',\n               'GarageQual','GarageCond','GarageFinish','GarageType', 'Electrical',\n               'KitchenQual', 'SaleType', 'Functional', 'Exterior2nd', 'Exterior1st',\n               'BsmtExposure','BsmtCond','BsmtQual','BsmtFinType1','BsmtFinType2',\n               'MSZoning', 'Utilities']\ndf_train[missing_cols_fillna].dtypes\nfor col in missing_cols_fillna:\n    df_train[col].fillna('None', inplace=True)\n    df_test[col].fillna('None', inplace=True)\n\ndf_train.fillna(df_train.mean(), inplace=True)\ndf_test.fillna(df_train.mean(), inplace=True)\n\ndf_train.isnull().sum().sum()\ndf_test.isnull().sum().sum()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3661b348be8927abed1f14acd76855ba4b6d77ea"},"cell_type":"code","source":"import seaborn as sns\n#sns.distplot(df_train['SalePrice'])\nprint(\"Skewness: %f\" % train_Y.skew())\nprint(\"kurtosis: %f\" % train_Y.kurt())\n#df_train['SalePrice'] = np.log(train_Y)\nsns.distplot(df_train['SalePrice'])\nprint(\"Skewness: %f\" % df_train['SalePrice'].skew())\nprint(\"kurtosis: %f\" % df_train['SalePrice'].kurt())\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"068a56a5c81e30fc1aa516c130b676495f535cc0"},"cell_type":"code","source":"categorical_features = df_data.dtypes[df_data.dtypes ==\"object\"].index\nfrom sklearn.preprocessing import LabelEncoder #, OneHotEncoder\nlabelEncoder = LabelEncoder()\ndf_train[categorical_features]= labelEncoder.fit_transform(categorical_features)\ndf_test[categorical_features]= labelEncoder.fit_transform(categorical_features)\ndf_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2143859375a6581042ab13a03451fb5ac4c3af0e"},"cell_type":"code","source":"train_X = df_train.iloc[:,:-1]\ntrain_Y = df_train[['SalePrice']]\nrfg = RandomForestRegressor()\nrfg.fit(train_X,train_Y)\npredicted_price = rfg.predict(df_test)\nprint(predicted_price)\nmy_submission = pd.DataFrame({'Id': df_test.Id, 'SalePrice': predicted_price})\nmy_submission\nmy_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":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}