使用Python的statsmodels模块进行多元线性回归分析

from pandas import DataFrame
import statsmodels.api as sm
#import statsmodels.regression.linear_model as sm
import pandas as pd

'''
# 测试集
Stock_Market = {'Year': [2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2017,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016,2016],
                'Month': [12, 11,10,9,8,7,6,5,4,3,2,1,12,11,10,9,8,7,6,5,4,3,2,1],
                'Interest_Rate': [2.75,2.5,2.5,2.5,2.5,2.5,2.5,2.25,2.25,2.25,2,2,2,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75,1.75],
                'Unemployment_Rate': [5.3,5.3,5.3,5.3,5.4,5.6,5.5,5.5,5.5,5.6,5.7,5.9,6,5.9,5.8,6.1,6.2,6.1,6.1,6.1,5.9,6.2,6.2,6.1],
                'Stock_Index_Price': [1464,1394,1357,1293,1256,1254,1234,1195,1159,1167,1130,1075,1047,965,943,958,971,949,884,866,876,822,704,719]        
                }

df = DataFrame(Stock_Market,columns=['Year','Month','Interest_Rate','Unemployment_Rate','Stock_Index_Price']) 

X = df[['Interest_Rate','Unemployment_Rate']] # here we have 2 variables for multiple regression. If you just want to use one variable for simple linear regression, then use X = df['Interest_Rate'] for example.Alternatively, you may add additional variables within the brackets
Y = df['Stock_Index_Price']

X = sm.add_constant(X) # adding a constant

model = sm.OLS(Y, X).fit()
predictions = model.predict(X) 

print_model = model.summary()
print(print_model)
'''


#读取文件
datafile = u'cig_data.xlsx'#文件所在位置，u为防止路径中有中文名称，此处没有，可以省略
data = pd.read_excel(datafile)#datafile是excel文件，所以用read_excel,如果是csv文件则用read_csv
examDf = DataFrame(data)
print("GOOD")
new_examDf = examDf.ix[1:, 1:]
X = new_examDf.ix[:,:4]
Y = new_examDf.ix[:,4]


X = sm.add_constant(X) # adding a constant

model = sm.OLS(Y, X).fit()
predictions = model.predict(X) 

print_model = model.summary()
print(print_model)

                  OLS Regression Results
==============================================================================
Dep. Variable:                Day_abs   R-squared:                       0.056
Model:                            OLS   Adj. R-squared:                  0.039
Method:                 Least Squares   F-statistic:                     3.238
Date:                Mon, 15 Jun 2020   Prob (F-statistic):             0.0132
Time:                        00:54:57   Log-Likelihood:                -1392.7
No. Observations:                 223   AIC:                             2795.
Df Residuals:                     218   BIC:                             2812.
Df Model:                           4
Covariance Type:            nonrobust
==============================================================================
                 coef    std err          t      P>|t|      [0.025      0.975]
------------------------------------------------------------------------------
const         62.1170     85.299      0.728      0.467    -105.999     230.233
Age            0.1967      0.692      0.284      0.777      -1.168       1.561
Cig_Day        1.3202      0.705      1.873      0.062      -0.069       2.710
CO            -0.2645      0.103     -2.566      0.011      -0.468      -0.061
LogCOadj       0.0313      0.069      0.458      0.648      -0.104       0.166
==============================================================================
Omnibus:                       54.065   Durbin-Watson:                   1.813
Prob(Omnibus):                  0.000   Jarque-Bera (JB):               86.116
Skew:                           1.475   Prob(JB):                     2.00e-19
Kurtosis:                       3.756   Cond. No.                     1.45e+04
==============================================================================