Pandas 计算相关性系数corr()方式

import pandas as pd

data = pd.DataFrame(
    data={
        'age': [2,7,10,16,20],
        'height': [70,90,143,166,178],
        'score': [98,37,103,76,53]
    }
)

# 计算相关性系数的列 必须都是数值型的数据！
corr = data.loc[:, ["age","height"]].corr()        # 会计算两两列之间的相关性系数
print("corr\n", corr)
"""
corr
            age   height
age     1.00000  0.96043
height  0.96043  1.00000
"""

corr = data.loc[:, ["age","height","score"]].corr()
print("corr\n", corr)
"""
corr
             age    height     score
age     1.000000  0.960430 -0.340053
height  0.960430  1.000000 -0.096782
score  -0.340053 -0.096782  1.000000
"""

DataFrame.corr(method='pearson', min_periods=1)

from pandas import DataFrame
import pandas as pd
x=[a for a in range(100)]
#构造一元二次方程，非线性关系
def y_x(x):
    return 2*x**2+4
y=[y_x(i) for i in x]
 
data=DataFrame({'x':x,'y':y})
 
#查看下data的数据结构
data.head()
Out[34]: 
   x   y
0  0   4
1  1   6
2  2  12
3  3  22
4  4  36
 
data.corr()
Out[35]: 
          x         y
x  1.000000  0.967736
y  0.967736  1.000000
 
data.corr(method='spearman')
Out[36]: 
     x    y
x  1.0  1.0
y  1.0  1.0
 
data.corr(method='kendall')
Out[37]: 
     x    y
x  1.0  1.0
y  1.0  1.0