Pandas实现groupby分组统计方法实例

import pandas as pd
import numpy as np
# 加上这一句，能在jupyter notebook展示matplot图表
#%matplotlib inline
df = pd.DataFrame({'A': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'foo'],
                   'B': ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'],
                   'C': np.random.randn(8),
                   'D': np.random.randn(8)})
df

df.groupby('A').sum()

df.groupby(['A','B']).mean()

df.groupby('A').agg([np.sum, np.mean, np.std])

# 方法1：预过滤，性能更好
df.groupby('A')['C'].agg([np.sum, np.mean, np.std])

# 方法2
df.groupby('A').agg([np.sum, np.mean, np.std])['C']

df.groupby('A').agg({"C":np.sum, "D":np.mean})

g = df.groupby('A')
for name,group in g:
    print(name)
    print(group)
    print()

g.get_group('bar')

g = df.groupby(['A', 'B'])
for name,group in g:
    print(name)
    print(group)
    print()
#可以看到，name是一个2个元素的tuple，代表不同的列

g.get_group(('foo', 'one'))

fpath = "./datas/beijing_tianqi_2018.csv"
df = pd.read_csv(fpath)
# 替换掉温度的后缀℃
df.loc[:, "bWendu"] = df["bWendu"].str.replace("℃", "").astype('int64')
df.loc[:, "yWendu"] = df["yWendu"].str.replace("℃", "").astype('int64')
df.head()

# 新增一列为月份
df['month'] = df['ymd'].str[:7]
df.head()

data = df.groupby('month')['bWendu'].max()
data

pandas.core.series.Series

group_data = df.groupby('month').agg({"bWendu":np.max, "yWendu":np.min, "aqi":np.mean})
group_data