1、加载数据
import pandas as pd
data = pd.read_csv('dataanalysis.csv')
data.head()
2、groupby
data.groupby(by='city')
# <pandas.core.groupby.generic.DataFrameGroupBy object at 0x000001E48722CA08>
data.groupby(by='city').max()
data.groupby(by='city').avg.max()
data.groupby(by='city').avg.describe()
data.groupby(['city', 'workYear']).mean()
for k,v in data.groupby(by='city'):
# print(k, max(v.avg), min(v.avg), max(v.avg)-min(v.avg))
print(k, max(v.avg)-min(v.avg))