数据分析之分组拆分

1.代码

import pandas as pd;
import numpy as np;
data = {"data1":np.random.randn(1000),"data2":np.random.randn(1000)};
df1 = pd.DataFrame(data);
factor = pd.cut(df1.data1,4);#get equal length 
factor1 = pd.qcut(df1.data1,5, labels=False);
def get_stats(group):
    return {"min":group.min(),"max":group.max(),"count":group.count()};
grouped = df1.data2.groupby(factor1);

print grouped.apply(get_stats).unstack().dropna();

2.结果

       count       max       min
data1                           
0      200.0  3.111853 -3.556149
1      200.0  2.726763 -3.015856
2      200.0  2.265047 -3.439436
3      200.0  2.709829 -4.088341
4      200.0  2.978180 -2.819611