Pandas的分组聚合groupby

import pandas as pd
import numpy as np
%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','B'], as_index=False).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')
g

<pandas.core.groupby.generic.DataFrameGroupBy object at 0x00000123B250E548>

for name,group in g:
    print(name)
    print(group)
    print()

bar
     A      B         C         D
1  bar    one -0.375789 -0.345869
3  bar  three -1.564748  0.081163
5  bar    two -0.202403  0.701301

foo
     A      B         C         D
0  foo    one  0.542903  0.788896
2  foo    two -0.903407  0.428031
4  foo    two -1.093602  0.837348
6  foo    one -0.665189 -1.505290
7  foo  three -0.498339  0.534438

g.get_group('bar')

g = df.groupby(['A', 'B'])

for name,group in g:
    print(name)
    print(group)
    print()

('bar', 'one')
     A    B         C         D
1  bar  one -0.375789 -0.345869

('bar', 'three')
     A      B         C         D
3  bar  three -1.564748  0.081163

('bar', 'two')
     A    B         C         D
5  bar  two -0.202403  0.701301

('foo', 'one')
     A    B         C         D
0  foo  one  0.542903  0.788896
6  foo  one -0.665189 -1.505290

('foo', 'three')
     A      B         C         D
7  foo  three -0.498339  0.534438

('foo', 'two')
     A    B         C         D
2  foo  two -0.903407  0.428031
4  foo  two -1.093602  0.837348

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

g['C']

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

('bar', 'one')
1   -0.375789
Name: C, dtype: float64
<class 'pandas.core.series.Series'>

('bar', 'three')
3   -1.564748
Name: C, dtype: float64
<class 'pandas.core.series.Series'>

('bar', 'two')
5   -0.202403
Name: C, dtype: float64
<class 'pandas.core.series.Series'>

('foo', 'one')
0    0.542903
6   -0.665189
Name: C, dtype: float64
<class 'pandas.core.series.Series'>

('foo', 'three')
7   -0.498339
Name: C, dtype: float64
<class 'pandas.core.series.Series'>

('foo', 'two')
2   -0.903407
4   -1.093602
Name: C, dtype: float64
<class 'pandas.core.series.Series'>

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

month
2018-01     7
2018-02    12
2018-03    27
2018-04    30
2018-05    35
2018-06    38
2018-07    37
2018-08    36
2018-09    31
2018-10    25
2018-11    18
2018-12    10
Name: bWendu, dtype: int32

type(data)

pandas.core.series.Series

data.plot()

<matplotlib.axes._subplots.AxesSubplot at 0x123c344b308>

df.head()

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

group_data.plot()