python散点图及相关系数矩阵计算
# -*- coding:utf-8 -*-
# __author__ = "LQ"
import matplotlib.pyplot as plt
import pandas as pd
import scipy.stats as stats
#自定义方法调用,上一篇有该方法
from DataAnalysis.TeachingModel.dbc import dbcConnect
def main(sql):
df = dbcConnect.selectDf(sql)
print(df)
# pearson相关系数矩阵
corr = df.corr()
print(corr)
#计算某一个元素相关
print(df.corr()[u'avg_getscore'])
# 输出结果第一个值为pearsonr相关系数,
# 第二个为p-value,所以这里Guba列和Value值是显著相关的
pearsonr = stats.pearsonr(df['avg_total_afterrequire_num'], df['avg_getscore'])
print(pearsonr)
# 散点图矩阵
pd.plotting.scatter_matrix(df, figsize=(8, 8),
c='k',
marker='+',
diagonal='hist',
alpha=0.8,