Use Random Forest to Predict House Price

import pandas as pd train_file_path = '/work/train.csv' train_file = pd.read_csv(train_file_path)

# find out the columns without null value col_complete_value = [col for col in train_file.columns if train_file[col].notnull().all()] print(col_complete_value) print(len(col_complete_value))

# limite the trainig data to those with complete valus train_data = train_file [col_complete_value]

y = train_data['SalePrice']

x = train_data [['MSSubClass', 'MSZoning', 'LotArea', 'Street', 'LotShape', 'LandContour', 'Utilities', 'LotConfig', 'LandSlope', 'Neighborhood', 'Condition1', 'Condition2', 'BldgType', 'HouseStyle', 'OverallQual', 'OverallCond', 'YearBuilt', 'YearRemodAdd', 'RoofStyle', 'RoofMatl', 'Exterior1st', 'Exterior2nd', 'ExterQual', 'ExterCond', 'Foundation', 'BsmtFinSF1', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF', 'Heating', 'HeatingQC', 'CentralAir', '1stFlrSF', '2ndFlrSF', 'LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath', 'HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'KitchenQual', 'TotRmsAbvGrd', 'Functional', 'Fireplaces', 'GarageCars', 'GarageArea', 'PavedDrive', 'WoodDeckSF', 'OpenPorchSF', 'EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'MiscVal', 'MoSold', 'YrSold', 'SaleType', 'SaleCondition']]

x.info()

feature_int = ['MSSubClass','LotArea','OverallQual','OverallCond','YearBuilt','YearRemodAdd'] x_int = train_data [feature_int]

from sklearn.ensemble import RandomForestRegressor forest_model = RandomForestRegressor(random_state=1) forest_model.fit(x_int,y)

test_file_path = '/work/test.csv' test_file = pd.read_csv(test_file_path)

val_x = test_file [feature_int]

predictions = forest_model.predict(val_x)

predictions