pandas根據dtype選擇columns

pandas根據dtype選擇columns

select_dtypes()方法根據dtype選擇columns中的子集。

import numpy as np
import pandas as pd

df = pd.DataFrame({'string': list('abc'),
                    'int64': list(range(1, 4)),
                    'uint8': np.arange(3, 6).astype('u1'),
                    'float64': np.arange(4.0, 7.0),
                    'bool1': [True, False, True],
                    'bool2': [False, True, False],
                    'dates': pd.date_range('now', periods=3),
                    'category': pd.Series(list("ABC")).astype('category')})

df['tdeltas'] = df.dates.diff()

df['uint64'] = np.arange(3, 6).astype('u8')

 df['other_dates'] = pd.date_range('20130101', periods=3)

 df['tz_aware_dates'] = pd.date_range('20130101', periods=3, tz='US/Eastern')

df

	string	int64	uint8	float64	bool1	bool2	dates	category	tdeltas	uint64	other_dates	tz_aware_dates
0	a	1	3	4.0	True	False	2019-12-01 22:00:58.958571	A	NaT	3	2013-01-01	2013-01-01 00:00:00-05:00
1	b	2	4	5.0	False	True	2019-12-02 22:00:58.958571	B	1 days	4	2013-01-02	2013-01-02 00:00:00-05:00
2	c	3	5	6.0	True	False	2019-12-03 22:00:58.958571	C	1 days	5	2013-01-03	2013-01-03 00:00:00-05:00

 df.dtypes

string                                object
int64                                  int64
uint8                                  uint8
float64                              float64
bool1                                   bool
bool2                                   bool
dates                         datetime64[ns]
category                            category
tdeltas                      timedelta64[ns]
uint64                                uint64
other_dates                   datetime64[ns]
tz_aware_dates    datetime64[ns, US/Eastern]
dtype: object

select_dtypes()有兩個參數include和exclude。

df.select_dtypes(include=[bool])

	bool1	bool2
0	True	False
1	False	True
2	True	False

df.select_dtypes(include=['bool'])

	bool1	bool2
0	True	False
1	False	True
2	True	False

df.select_dtypes(include=['number', 'bool'], exclude=['unsignedinteger'])

	int64	float64	bool1	bool2	tdeltas
0	1	4.0	True	False	NaT
1	2	5.0	False	True	1 days
2	3	6.0	True	False	1 days

要選擇字符串列，你必須使用對象dtype:

df.select_dtypes(include=['object'])

	string
0	a
1	b
2	c

要查看像numpy.number這樣的泛型dtype的所有子dtypes。你可以定義一個返回子類型樹的函數:

def subdtypes(dtype):
    subs = dtype.__subclasses__()
    if not subs:
        return dtype
    return [dtype,[subdtypes(dt) for dt in subs]]

subdtypes(np.generic)

[numpy.generic,
 [[numpy.number,
   [[numpy.integer,
     [[numpy.signedinteger,
       [numpy.int8,
        numpy.int16,
        numpy.int32,
        numpy.int32,
        numpy.int64,
        numpy.timedelta64]],
      [numpy.unsignedinteger,
       [numpy.uint8,
        numpy.uint16,
        numpy.uint32,
        numpy.uint32,
        numpy.uint64]]]],
    [numpy.inexact,
     [[numpy.floating,
       [numpy.float16, numpy.float32, numpy.float64, numpy.float64]],
      [numpy.complexfloating,
       [numpy.complex64, numpy.complex128, numpy.complex128]]]]]],
  [numpy.flexible,
   [[numpy.character, [numpy.bytes_, numpy.str_]],
    [numpy.void, [numpy.record]]]],
  numpy.bool_,
  numpy.datetime64,
  numpy.object_]]

subdtypes(np.number)

[numpy.number,
 [[numpy.integer,
   [[numpy.signedinteger,
     [numpy.int8,
      numpy.int16,
      numpy.int32,
      numpy.int32,
      numpy.int64,
      numpy.timedelta64]],
    [numpy.unsignedinteger,
     [numpy.uint8, numpy.uint16, numpy.uint32, numpy.uint32, numpy.uint64]]]],
  [numpy.inexact,
   [[numpy.floating,
     [numpy.float16, numpy.float32, numpy.float64, numpy.float64]],
    [numpy.complexfloating,
     [numpy.complex64, numpy.complex128, numpy.complex128]]]]]]