House price test one

import numpy as np
import pandas as pd

train_data = pd.read_csv("C:/Users/Liubotao/Desktop/House_price/input/train.csv", index_col=0)
test_data = pd.read_csv("C:/Users/Liubotao/Desktop/House_price/input/test.csv", index_col=0)

prices = pd.DataFrame({"price":train_data["SalePrice"],"log(prine+1)":np.log1p(train_data["SalePrice"])})
prices.hist()

y_train = np.log1p(train_data.pop(‘SalePrice‘))

all_data = pd.concat((train_data, test_data), axis=0)

all_data[‘MSSubClass‘] = all_data[‘MSSubClass‘].astype(str)

all_dummy_data = pd.get_dummies(all_data)

mean_col = all_dummy_data.mean()

all_dummy_data = all_dummy_data.fillna(mean_col)

numeric_col = all_data.columns[all_data.dtypes != ‘object‘]

numeric_col_means = all_dummy_data.loc[:,numeric_col].mean()
numeric_col_std = all_dummy_data.loc[:,numeric_col].std()
all_dummy_data.loc[:, numeric_col] = (all_dummy_data.loc[:, numeric_col] - 
                                                                                 numeric_col_means) / numeric_col_std


dummy_train_data = all_dummy_data.loc[train_data.index]
dummy_test_data = all_dummy_data.loc[test_data.index]


from sklearn.linear_model import Ridge
from sklearn.model_selection import cross_val_score

X_train = dummy_train_data.values
X_test = dummy_test_data.values

ridge = Ridge(alpha=15)
rf = RandomForestRegressor(n_estimators=500, max_features=.3)
ridge.fit(X_train, y_train)
rf.fit(X_train, y_train)


y_ridge = np.expm1(ridge.predict(X_test))
y_rf = np.expm1(rf.predict(X_test))
y_final = (y_ridge + y_rf) / 2

submission_df = pd.DataFrame(data= {‘Id‘ : test_data.index, ‘SalePrice‘: y_final})