Pandas实现groupby分组统计的实践

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.groupby('A').sum()

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

df.groupby(['A','B'], as_index=False).mean() #这会使得A、B两列不会成为二级索引

df.groupby('A').agg([np.sum, np.mean, np.std])#列变成了多级索引

# 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)

g.get_group('bar')

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

g.get_group(('foo', 'one'))#可以获取单个分组的数据

g['C']

for name, group in g['C']:
    print(name)
    print(group)
    print(type(group))
    print()

fpath = "./datas/beijing_tianqi/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('int32')
df.loc[:, "yWendu"] = df["yWendu"].str.replace("℃", "").astype('int32')
df.head()
# 新增一列为月份
df['month'] = df['ymd'].str[:7]
df.head()

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

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