{"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":"import pandas as pd\nimport matplotlib.pyplot as plt\npd.options.display.max_columns = None\nimport seaborn as sns\nimport matplotlib.pyplot as plot\nfrom sklearn.model_selection import train_test_split\nfrom xgboost import XGBRegressor","metadata":{"_uuid":"d7579875-43c6-4c2a-bf23-109977cbdffd","_cell_guid":"91c60c72-5ebb-4c64-ad34-04d86be35ef8","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = pd.read_csv('../input/home-data-for-ml-course/train.csv')\ntrain = train_data.drop('Id',axis=1)","metadata":{"_uuid":"5c3abaa4-67f6-4543-982b-5b0b1a64aa8e","_cell_guid":"ba71ebe5-a1cd-460c-bccd-3fceabbcb96c","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Correlation Matrix [Numerical Variables]","metadata":{"_uuid":"29b8a965-8942-444c-83fa-fc8a56d4af28","_cell_guid":"a23c56cf-9405-4568-9ba3-fc37ed24618d","trusted":true}},{"cell_type":"code","source":"cor_matrix = train.corr()\nplt.figure(figsize=(20, 20))\n\nsns.heatmap(cor_matrix[cor_matrix>=0.7],\n            annot=True,\n            fmt='.1f',\n            cmap='coolwarm',\n            square=True,\n            linewidths=1,\n            cbar=False)\nplt.show()","metadata":{"_uuid":"8e41cf69-556d-4f0c-b3a6-f60817f1e64c","_cell_guid":"cd27cfd5-303a-494f-8385-b417ba04ebf1","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Box Plots [Categorical Varaibles Relation Check]","metadata":{"_uuid":"fb7bfc87-6943-43cb-99a0-f77fd1dc9b30","_cell_guid":"505a1996-9d8c-4713-b42b-6416b392fa86","trusted":true}},{"cell_type":"code","source":"import numpy as np\ntrain_data_category = train.select_dtypes(include=['object'])\ntrain_data_category['SalePrice'] = train.loc[:,'SalePrice']","metadata":{"_uuid":"53d6e879-d78a-4d48-bd68-590b0ed96e23","_cell_guid":"13cad1ba-e70d-4236-ada9-0d088dde8f00","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"col_names = train_data_category.columns\nfor i in col_names[0:-1]:\n    plt.figure(figsize=(10, 10))\n    plt.xticks(rotation=60)\n    sns.boxplot(train[i],train['SalePrice'])","metadata":{"_uuid":"b57c593c-4f49-40f7-b997-5dcab5c9b33a","_cell_guid":"4b16b770-0666-4b40-8714-57c01de5f1f3","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Test Data Upload","metadata":{"_uuid":"426e9dce-8adf-46c6-9153-311eadfc3d0b","_cell_guid":"a4c49e0d-434a-46aa-ae87-ea57c26ba196","trusted":true}},{"cell_type":"code","source":"test_data = pd.read_csv(\"../input/home-data-for-ml-course/test.csv\")","metadata":{"_uuid":"b8d322fc-abcd-4c8e-889b-2de59885732d","_cell_guid":"ca4da888-569b-461a-b3cd-980e1ee9189f","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train = train.select_dtypes(include=np.number)\ncol_num = train.columns","metadata":{"_uuid":"3d68161d-178e-44eb-b85c-41da28640ae2","_cell_guid":"ea3e6912-5985-4fea-b3e6-b874628faa5a","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# [Outlier Removal Optional]","metadata":{"_uuid":"9e9f0aae-ff15-4cc0-b5e7-6777a7388b24","_cell_guid":"9ca1a7cc-cb70-406f-897b-10cdb39d9134","trusted":true}},{"cell_type":"code","source":"train = train[(train['LotFrontage']<=200)]\ntrain = train[(train['LotArea']<=60000)]\ntrain = train[(train['MasVnrArea']<=1200)]\ntrain = train[(train['BsmtFinSF1']<=2500)]\ntrain = train[(train['BsmtFinSF2']<=1200)]\ntrain = train[(train['BsmtUnfSF']<=2000)]\ntrain = train[(train['TotalBsmtSF']<=3000)]\ntrain = train[(train['1stFlrSF']<=3000)]\ntrain = train[(train['2ndFlrSF']<=1500)]\ntrain = train[(train['GrLivArea']<=3000)]\ntrain = train[(train['LowQualFinSF']<=600)]\ntrain = train[(train['GarageArea']<=1200)]\ntrain = train[(train['WoodDeckSF']<=800)]\ntrain = train[(train['OpenPorchSF']<=400)]\ntrain = train[(train['EnclosedPorch']<=400)]\ntrain = train[(train['ScreenPorch']<=300)]","metadata":{"_uuid":"50928f0c-a9f2-4f71-a66a-4de7c212c5e4","_cell_guid":"26435340-133e-4b7d-8955-e68bbe46ab51","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = train\ntest_data = test_data.drop(['Id'],axis=1)\ntrain = train.drop(['SalePrice'],axis=1)","metadata":{"_uuid":"46a4730a-0220-4def-a3ca-0a21c7f68ab0","_cell_guid":"4d8b1de7-2b88-4c36-871f-708f525db0e9","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Check if all the columns are same ###\nprint([TC for TC in train.columns if TC not in test_data.columns])\nTest_Train_Data = train.append(test_data, sort=False)","metadata":{"_uuid":"2fbc52ec-0c0c-438c-ab40-c5d1f78be851","_cell_guid":"2045df15-4c05-4017-8473-018cfd88088e","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Missing Value Treatment","metadata":{"_uuid":"3b2efaa8-abda-4fa8-b4db-3a6ed23c56d1","_cell_guid":"d740e3d9-ecba-4320-ab69-0394fa207703","trusted":true}},{"cell_type":"code","source":"Missing_Data = pd.DataFrame(Test_Train_Data.count(axis=0),columns=['count']).reset_index()\nMissing_Data = Missing_Data[Missing_Data['count']<Test_Train_Data.shape[0]]\nplt.figure(figsize=(20,20))\nplt.xticks(rotation=90)\nax = sns.barplot(y=Missing_Data['index'],x=Missing_Data['count'],orient=\"h\",)\nax.bar_label(ax.containers[0])","metadata":{"_uuid":"1960f957-f006-496e-b439-e2e5655a4f0f","_cell_guid":"014d04f8-01df-4c07-a757-136c308f78ac","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"##List of different NAs\n\nNA_Original_Data = ['Alley','BsmtQual','BsmtCond','BsmtExposure','BsmtFinType1','BsmtFinType2','FireplaceQu','GarageType','GarageFinish','GarageQual','GarageCond','PoolQC','Fence','MiscFeature','MasVnrType']\nNA_Equal_Zero = ['GarageArea','GarageYrBlt','MasVnrArea','GarageCars','BsmtFinSF1','BsmtFinSF2','BsmtUnfSF','TotalBsmtSF','BsmtFullBath','BsmtHalfBath']\nNA_Zoning_Lot_Frontage = ['MSZoning','LotFrontage']\nNA_MVT_Required = [TC for TC in Missing_Data['index'] if TC not in NA_Equal_Zero+NA_Original_Data+NA_Zoning_Lot_Frontage]","metadata":{"_uuid":"1d1899e8-f45d-4b88-b36b-6bae928306d6","_cell_guid":"cde46044-886b-4841-8733-c3f33cbbe845","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for col in NA_Original_Data:\n    Test_Train_Data[col].replace(np.nan,'None',inplace=True)    \nfor col in NA_Equal_Zero:\n    Test_Train_Data[col].replace(np.nan,0,inplace=True)    \nfor col in NA_MVT_Required:\n    Test_Train_Data[col].replace(np.nan,'None',inplace=True)\n#for col in NA_Zoning_Lot_Frontage:\n #   Test_Train_Data[col].replace(np.nan,Test_Train_Data[col].mode()[0],inplace=True)","metadata":{"_uuid":"709e705a-e08b-4a31-a2a6-9d938ecffae4","_cell_guid":"a57551b8-30cd-4efc-a665-a10443ed4b89","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Test_Train_Data = Test_Train_Data.reset_index()\nTest_Train_Data['MSZoning'] = Test_Train_Data.groupby('MSSubClass')['MSZoning'].apply(lambda x: x.fillna(x.mode()[0]))\nTest_Train_Data['LotFrontage'] = Test_Train_Data.groupby('Neighborhood')['LotFrontage'].apply(lambda x: x.fillna(x.median()))","metadata":{"_uuid":"8dd28b86-5837-48de-a431-abad92c11497","_cell_guid":"b8741cda-a46e-419b-9d29-f1b260c7a4c6","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Test_Train_Data['MSSubClass'] = Test_Train_Data['MSSubClass'].astype(str)\nTest_Train_Data['YrSold'] = Test_Train_Data['YrSold'].astype(str)\nTest_Train_Data['MoSold'] = Test_Train_Data['MoSold'].astype(str)","metadata":{"_uuid":"c628e24e-71c3-4051-9bd3-3a3af8609a28","_cell_guid":"b6479f9f-7acd-4703-97cb-f06f5118fcb2","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Missing_Data = pd.DataFrame(Test_Train_Data.count(axis=0),columns=['count']).reset_index()\nplt.figure(figsize=(20,20))\nplt.xticks(rotation=90)\nax = sns.barplot(y=Missing_Data['index'],x=Missing_Data['count'],orient=\"h\",)\nax.bar_label(ax.containers[0])","metadata":{"_uuid":"1c5adc8a-783f-4ed2-92d0-3c92723a42cf","_cell_guid":"3120dc29-9621-4ef0-a39a-3443f2d304d6","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Feature Engineering ##","metadata":{"_uuid":"32aa5d49-3bb2-4fba-ba3d-20044b4d608e","_cell_guid":"11426bd3-b3ed-4be3-be19-95a9ebfb79f8","trusted":true}},{"cell_type":"code","source":"Test_Train_Data_Features = Test_Train_Data.select_dtypes(include=['object'])","metadata":{"_uuid":"69a68323-71a4-4618-8202-ef7db798bc88","_cell_guid":"3fea7e29-989f-4641-bef2-b97ebb6052f0","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Test_Train_Data_Features.columns","metadata":{"_uuid":"cb850028-7ffb-4820-876f-f071694952d9","_cell_guid":"8f11e186-6efc-42ae-ae8a-f85bb145bcd0","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Test_Train_Data_Features = Test_Train_Data_Features.drop(['MSSubClass','YrSold','MoSold'],axis=1)\nfor col in Test_Train_Data_Features:\n    mask = Test_Train_Data[col].isin(Test_Train_Data[col].value_counts()[Test_Train_Data[col].value_counts() < 10].index)\n    Test_Train_Data[col][mask] = \"Other\"","metadata":{"_uuid":"040984db-aca4-443a-a259-bc66596139c5","_cell_guid":"371a6f70-a32e-4776-90c0-16feabd5458a","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Test_Train_Data['Bathroom'] = Test_Train_Data['BsmtFullBath']+0.5*Test_Train_Data['BsmtHalfBath']+Test_Train_Data['FullBath']+0.5*Test_Train_Data['HalfBath']\nTest_Train_Data['Total SF'] = Test_Train_Data['1stFlrSF'] + Test_Train_Data['2ndFlrSF']+Test_Train_Data['TotalBsmtSF']+Test_Train_Data['MasVnrArea']+Test_Train_Data['OpenPorchSF']+Test_Train_Data['WoodDeckSF']\nTest_Train_Data['Bsmt_Fin_SF'] = Test_Train_Data['BsmtFinSF1']+Test_Train_Data['BsmtFinSF2']\nTest_Train_Data['Area/Car'] = Test_Train_Data['GarageArea']*Test_Train_Data['GarageCars']\n#Test_Train_Data['OverallQual/Cond'] = Test_Train_Data['OverallCond']+Test_Train_Data['OverallQual']\nTest_Train_Data['TotalRooms'] = Test_Train_Data['KitchenAbvGr']+Test_Train_Data['TotRmsAbvGrd']+Test_Train_Data['Bathroom']\nTest_Train_Data['House_Age'] = np.max(Test_Train_Data['YearBuilt']) - Test_Train_Data['YearBuilt']","metadata":{"_uuid":"4198f933-9de3-4593-bef3-ec34f1bd4ff9","_cell_guid":"1471ddbd-d202-4c7d-b1ae-400562685c8d","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Rxternal Condition \nExterCond_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['ExterCond'] = Test_Train_Data['ExterCond'].map(ExterCond_Rank).astype(int)\n\n## Rxternal Quality \nExterQual_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['ExterQual'] = Test_Train_Data['ExterQual'].map(ExterQual_Rank).astype(int)\n\n## Bsmt Quality \nBsmtQual_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['BsmtQual'] = Test_Train_Data['BsmtQual'].map(BsmtQual_Rank).astype(int)\n\n## Bsmt Cond \nBsmtCond_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['BsmtCond'] = Test_Train_Data['BsmtCond'].map(BsmtCond_Rank).astype(int)\n\n## HeatingQC \nHeatingQC_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['HeatingQC'] = Test_Train_Data['HeatingQC'].map(HeatingQC_Rank).astype(int)\n\n## KitchenQual \nKitchenQual_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['KitchenQual'] = Test_Train_Data['KitchenQual'].map(KitchenQual_Rank).astype(int)\n\n## FireplaceQu \nFireplaceQu_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2,'Po':2}\nTest_Train_Data['FireplaceQu'] = Test_Train_Data['FireplaceQu'].map(FireplaceQu_Rank).astype(int)\n\n## GarageQual \nGarageQual_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['GarageQual'] = Test_Train_Data['GarageQual'].map(GarageQual_Rank).astype(int)\n\n## GarageCond \nGarageCond_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2,'Po':2}\nTest_Train_Data['GarageCond'] = Test_Train_Data['GarageCond'].map(GarageCond_Rank).astype(int)\n\n## PoolQC \nPoolQC_Rank = {'TA':3,'Fa':4,'Gd':5,'Ex':6,'None':1,'Other':2}\nTest_Train_Data['PoolQC'] = Test_Train_Data['PoolQC'].map(PoolQC_Rank).astype(int)","metadata":{"_uuid":"385dc550-90d3-43cc-977c-fdaf1925c7d3","_cell_guid":"623346e2-d200-4d33-83b7-216ed275f9f9","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## New Features\nTest_Train_Data['External_Total_Quality'] = Test_Train_Data['ExterCond']+Test_Train_Data['ExterQual']\nTest_Train_Data['Basement_Total_Quality'] = Test_Train_Data['BsmtQual']+Test_Train_Data['BsmtCond']\nTest_Train_Data['Garage_Total_Quality'] = Test_Train_Data['GarageCond']+Test_Train_Data['GarageQual']\nTest_Train_Data['Overall_Quality'] = Test_Train_Data['External_Total_Quality']+Test_Train_Data['Basement_Total_Quality']+Test_Train_Data['Garage_Total_Quality']","metadata":{"_uuid":"41014816-dc6f-4fd6-9785-ac5977de3e98","_cell_guid":"a0ae806c-3073-4b19-bf71-71b730200958","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import math\nTest_Train_Data_Final =Test_Train_Data.drop(['BsmtFullBath','BsmtHalfBath','FullBath','HalfBath','TotalBsmtSF','2ndFlrSF','1stFlrSF','BsmtFinSF1','BsmtFinSF2','GarageArea','KitchenAbvGr','TotRmsAbvGrd','YearBuilt','ExterCond','ExterQual','BsmtQual','BsmtCond','GarageCond','GarageQual','GarageYrBlt'],axis=1)","metadata":{"_uuid":"d2044210-4a4d-41c7-9c30-7350cd08e6e8","_cell_guid":"48c1d733-1443-47cc-918e-c6780fc681bc","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Transform Data","metadata":{"_uuid":"4ceb3cd0-7e38-49a7-9b39-61e1588ce654","_cell_guid":"54a026cf-8fd8-4971-9f39-ecd521b353d2","trusted":true}},{"cell_type":"code","source":"from scipy.stats import skew, boxcox_normmax, norm\nfrom scipy.special import boxcox1p\nTest_Train_Data_Numerical = Test_Train_Data_Final.select_dtypes(include = np.number)\nTest_Train_Data_Numerical = Test_Train_Data_Numerical.drop(['index'],axis=1)","metadata":{"_uuid":"1110edc9-de99-47c7-9831-4e9176fdccf1","_cell_guid":"aaad40c5-198b-45a0-a1ee-e70f1a7a3634","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Column_Names = Test_Train_Data_Numerical.columns","metadata":{"_uuid":"c21374fe-5d33-406a-bdad-fa4b9619d97d","_cell_guid":"6b4f019f-85a5-405e-b904-0c9f99712f8a","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for col in Column_Names:\n    if(skew(Test_Train_Data_Numerical[col])>0.3):\n        Test_Train_Data_Final[col] = boxcox1p(Test_Train_Data_Final[col], boxcox_normmax(Test_Train_Data_Final[col] + 1))","metadata":{"_uuid":"1a89dfe9-1dca-4009-ae3e-d4bf9beae1bf","_cell_guid":"14ce2392-0c44-44a1-95e0-1bc1612e34f3","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Test_Train_Data_Final.shape","metadata":{"_uuid":"54c21d0f-3e22-4105-bd36-dd3167b7fb55","_cell_guid":"8e7e5aaa-2efa-42b3-bedc-713bf42e305c","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# One hot Encoding ##","metadata":{"_uuid":"fef8fc17-9250-4a64-bdf0-31cc368bcef6","_cell_guid":"bbfc21d3-cbf8-4aac-bad6-d069878d4069","trusted":true}},{"cell_type":"code","source":"Test_Train_Data_Final = pd.get_dummies(Test_Train_Data_Final)\ntrain_data['SalePrice'] = np.log1p(train_data['SalePrice'])","metadata":{"_uuid":"00a33395-26d4-44b8-ba93-9ec5768ae195","_cell_guid":"6b6592e7-b07c-4dba-8b13-d80942096538","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.boxplot(x=np.log1p(train_data['SalePrice']))","metadata":{"_uuid":"dd5b989b-f1da-41ec-992d-a27435d243ec","_cell_guid":"e013056f-8a99-427c-bed7-709daa33e768","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Test_Train_Data_Final=Test_Train_Data_Final.drop(['index'],axis=1)","metadata":{"_uuid":"debe8185-55a7-4976-8d61-bf6e07f39755","_cell_guid":"7f5192bb-352b-47a7-97c9-089698e3bf46","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Seperate Test & Train Data","metadata":{"_uuid":"31f705dc-243d-4bdb-bd34-9db287af2279","_cell_guid":"229b56cd-b040-4364-8959-47d7f4eb9225","trusted":true}},{"cell_type":"code","source":"##Test_Train_Data_Final=Test_Train_Data_Final.drop('index',axis=1)\nTrain_Data = Test_Train_Data_Final.iloc[:len(train),:]\nTest_Data = Test_Train_Data_Final.iloc[len(train):len(Test_Train_Data),:]","metadata":{"_uuid":"484ffecf-ab8e-423d-87f8-b1a763615c6b","_cell_guid":"23b1c490-d3e1-4a13-941a-62bef56a42a1","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Ridge Rigression","metadata":{"_uuid":"583a1552-3a0e-469e-b391-bd049ca9c89d","_cell_guid":"e938bf94-16af-47ce-93d0-3536f0e4d71d","trusted":true}},{"cell_type":"code","source":"from sklearn.linear_model import Ridge,RidgeCV,Lasso\nfrom sklearn.preprocessing import RobustScaler\nfrom sklearn.model_selection import cross_val_score, KFold, cross_validate\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.feature_selection import RFE\nmodel = Ridge(alpha=1.0)\nmodel.fit(Train_Data, train_data['SalePrice'])","metadata":{"_uuid":"0437b79c-8dda-441a-864a-920643d4d798","_cell_guid":"d6c6c732-6638-4adc-b5bc-4e7bee0f0669","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"rfe = RFE(estimator=model, n_features_to_select=50, step=1)\nrfe = rfe.fit(Train_Data,train_data['SalePrice'] )","metadata":{"_uuid":"8ade6bf6-654c-4516-8e8c-32ec9ed6080a","_cell_guid":"b1a900ae-a0f6-4bb9-98f3-96dad6fb0bde","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction = np.expm1(pd.DataFrame(rfe.predict(Test_Data),columns=['SalePrice']))","metadata":{"_uuid":"42fb88a6-163c-4121-b543-068eb4d916f8","_cell_guid":"7b4437f4-cc71-455b-a74d-beed76cc6db8","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"index_data=[]\nfor i in range(len(train)+307,len(Test_Train_Data)+307):\n    index_data.append({'Id':i+1})\nindex_data = pd.DataFrame(index_data)","metadata":{"_uuid":"770d425b-bdb4-4a2e-8fa8-a153f3d8d4d6","_cell_guid":"766d25be-df5d-4de9-a691-02eba6b42174","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#index_data.join(prediction).to_csv('Results.csv',index=False)\nindex_data.join(prediction)","metadata":{"_uuid":"72aa85a0-0fd2-4ed8-a9b9-6509699c6d91","_cell_guid":"71c5b118-9f7b-48ef-be61-87178eb892dd","collapsed":false,"jupyter":{"outputs_hidden":false},"trusted":true},"execution_count":null,"outputs":[]}]}