向后选择法

import numpy as np
import pandas as pd 
import seaborn as sns 
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split

import statsmodels.api as sm

def backwardElimination(x_train,flo):
    tmp=np.zeros((17290,17))
    for i in range(0,17):
        regressor_OLS=sm.OLS(endog=y_train,exog=x_train).fit()
        maxn=max(regressor_OLS.pvalues)
        adj_b=regressor_OLS.rsquared_adj
        if maxn>flo:
            for j in range(0,17-i):
                if regressor_OLS.pvalues[i]==maxn:
                    tmp[:,j]=x_train[:,j]
                    x_train=np.delete(x_train,j,axis=1)
                    regressor_OLS=sm.OLS(endog=y_train,exog=x_train).fit()
                    adj_a=regressor_OLS.rsquared_adj
                    if adj_a<=adj_b:
                        print(regressor_OLS.summary())
                        return np.delete(np.hstack((x_train,tmp[:,[0,j]])),j,1)
                    else :
                        continue
    print(regressor_OLS.summary())
    return x_train
data=pd.read_csv(‘house_data.csv‘)
print(data.shape)
x_data=data.iloc[:,2:].values
print(x_data.shape)
y_data=data[‘price‘].values
class_names=np.array([‘sqft_living‘,‘grade‘,‘sqft_above‘])
x_train,x_test,y_train,y_test=train_test_split(x_data,y_data,test_size=0.2)

clf=LinearRegression()
clf.fit(x_train,y_train)
print(x_train.shape)

x_train=backwardElimination(x_train,0.05)
print(x_train.shape)
y_pred=clf.predict(x_test)
print(y_pred)
print(y_test)
print(clf.score(x_test,y_test))