python 用corr()求解变量相关系数

求变量的相关系数; 用 data[[‘变量1’,‘变量2’,‘变量3’]].corr(method = ‘pearson’)
得出的结果是以: 系数矩阵的形式输出

import os
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib

"""
两连续变量的相关系数 不需要假设检验

"""

os.chdir(r'D:\pycharm程序文件\练习1')
data = pd.read_csv('creditcard_exp.csv',skipinitialspace=True) # skipinitialspace=True 用于方差分析

matplotlib.rcParams['axes.unicode_minus']=False#解决保存图像时负号'-'显示为方块的问题
plt.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体


# 两连续变量: avg_exp(y) ~ avg_exp_ln(x)
data_two = data[['Income','avg_exp_ln']].copy()

def scatter_fig():
    x = data_two['avg_exp_ln']
    y = data_two['Income']
    plt.scatter(x, y)
    plt.xticks(rotation=45)
    plt.show()

# scatter_fig()
# 求解两变量的相关系数; 用 .data[['变量1','变量2']].corr(method = 'pearson')

coefficient = data_two.corr(method = 'pearson')
print(coefficient)

# 多变量之间的相关系数, 以系数矩阵的形式输出
coefficient1 = data[['avg_exp','Income','avg_exp_ln']].corr(method = 'pearson')
print(coefficient1)


输出结果:

            Income  avg_exp_ln
Income      1.00000     0.63489
avg_exp_ln  0.63489     1.00000
             avg_exp    Income  avg_exp_ln
avg_exp     1.000000  0.674011    0.941926
Income      0.674011  1.000000    0.634890
avg_exp_ln  0.941926  0.634890    1.000000