python - 如何使用LinearRegression获得重要性F，R平方？

Question

我使用此代码对LinearRegression进行sklearn。

from sklearn.linear_model import LinearRegression
import pandas as pd

def calculate_Intercept_X_Variable():
    list_a=[['2018', '3', 'aa', 'aa', 93,1884.7746222667, 165.36153386251098], ['2018', '3', 'bb', 'bb', 62, 665.6392779848, 125.30386609565328], ['2018', '3', 'cc', 'cc', 89, 580.2259903521, 160.19280253775514]]
    df = pd.DataFrame(list_a)
    X = df.iloc[:, 5]
    y = df.iloc[:, 6]
    X = X.values.reshape(-1, 1)
    y = y.values.reshape(-1, 1)
    clf = LinearRegression()
    clf.fit(X, y)
    para_Intercept = clf.intercept_[0] #133.10871357512195
    para_X_Variable_1 = clf.coef_[0][0] #0.016460552337949654
    para_Significance_F=""
    para_R_Square=""

calculate_Intercept_X_Variable()

如果我使用excel，则对以下数据使用回归分析：

X           Y 
1884.774622 165.3615339
665.639278  125.3038661
580.2259904 160.1928025

Excel将为我生成此类数据：


我想用 LinearRegression来获取 Significance F， R Square这两个参数，就像excel一样，我用绿色标记了。

现在是我的代码吗？

如何获得这两个参数 Significance F， R Square？

Answer 1

现在我知道该怎么做了。
这是代码：

from sklearn.linear_model import LinearRegression
import pandas as pd
import numpy as np
from scipy.stats import linregress

def calculate_Intercept_X_Variable():
    list_a=[['2018', '3', 'aa', 'aa', 93,1884.7746222667, 165.36153386251098], ['2018', '3', 'bb', 'bb', 62, 665.6392779848, 125.30386609565328], ['2018', '3', 'cc', 'cc', 89, 580.2259903521, 160.19280253775514]]
    df = pd.DataFrame(list_a)
    X = df.iloc[:, 5]
    y = df.iloc[:, 6]
    X1 = X.values.reshape(-1, 1)
    y1 = y.values.reshape(-1, 1)
    clf = LinearRegression()
    clf.fit(X1, y1)
    yhat = clf.predict(X1)
    para_Intercept = clf.intercept_[0]
    para_X_Variable_1 = clf.coef_[0][0]
    SS_Residual = sum((y1 - yhat) ** 2)
    SS_Total = sum((y1 - np.mean(y1)) ** 2)
    para_R_Square = 1 - (float(SS_Residual)) / SS_Total
    adjusted_r_squared = 1 - (1 - para_R_Square) * (len(y1) - 1) / (len(y1) - X1.shape[1] - 1)
    #para_a = linregress(X, y)
    para_a = linregress(X.astype(float), y)
    para_Significance_F = para_a[3]
    print("Intercept:"+str(para_Intercept))
    print("X_Variable_1:"+str(para_X_Variable_1))
    print("R_Square:" + str(para_R_Square[0]))
    print("Significance_F:" + str(para_Significance_F))



calculate_Intercept_X_Variable()

输出为：


  拦截：133.10871357512195
  
  X_Variable_1：0.016460552337949654
  
  R_平方：0.3039426453800934
  
  意义_F：0.62825637186​​49847