用Python实现数据的描述性统计分析

python代码：

import numpy as np
from scipy import stats
import pandas as pd
df=pd.DataFrame(np.random.randn(5,6),index=[1,2,3,4,5],columns=["a","b","c","d","e","f"])

print("最大值:",np.max(df))
print("最小值:",np.min(df))

#集中趋势相关指标
print("平均值:",np.mean(df))
print("中位数:",np.median(df))
print("众数:",stats.mode(df))
print("第一四分位数:",np.percentile(df,25))
print("第二四分位数:",np.percentile(df,50))
print("第三四分位数:",np.percentile(df,75))

#离散趋势相关指标
print("极差:",np.max(df)-np.min(df))
print("四分位差:",np.percentile(df,75)-np.percentile(df,25))
print("标准差:",np.std(df))
print("方差:",np.var(df))
print("离散系数:",np.std(df)/np.mean(df))

#偏度系数和峰度系数
print("偏度:",stats.skew(df))
print("峰度:",stats.kurtosis(df))

输出结果：

最大值: a    1.008610
b    1.403977
c    1.522318
d    1.166711
e