# -*- encoding:utf-8 -*-
# Copyright (c) 2015 Shiye Inc.
# All rights reserved.
#
# Author: ldq <liangduanqi@shiyejinrong.com>
# Date: 2019/2/12 10:07
import numpy as np
import pandas as pd
dates = pd.date_range("", periods=5)
'''
DatetimeIndex(['2019-01-01', '2019-01-02', '2019-01-03', '2019-01-04',
'2019-01-05', '2019-01-06'],
dtype='datetime64[ns]', freq='D')
'''
df = pd.DataFrame(np.random.randn(5, 4), index=dates,
columns=["a", "b", "c", "d"])
'''
a b c d
2019-01-01 -0.406321 -0.518128 -0.151546 1.438366
2019-01-02 -0.738235 0.400646 1.337277 1.393154
2019-01-03 1.646115 -0.073540 0.644506 0.987226
2019-01-04 -1.270745 -1.333457 -1.571356 -0.051486
2019-01-05 -0.075171 2.424032 -0.274433 1.205959
'''
df1 = pd.DataFrame(np.arange(12).reshape(3, 4))
'''
0 1 2 3
0 0 1 2 3
1 4 5 6 7
2 8 9 10 11
'''
data2 = {
"a": 1,
"b": pd.Timestamp(""),
"c": pd.Series(1, index=range(4), dtype=np.float64),
"d": np.array([3] * 4, dtype=np.int32),
"e": pd.Categorical(["test", "train", "test", "train"]),
"f": "foo",
"g": pd.date_range("",periods=4),
}
df2 = pd.DataFrame(data2)
'''
a b c d e f g
0 1 2019-01-01 1.0 3 test foo 2002-02-05
1 1 2019-01-01 1.0 3 train foo 2002-02-06
2 1 2019-01-01 1.0 3 test foo 2002-02-07
3 1 2019-01-01 1.0 3 train foo 2002-02-08
'''
columns1 = df2.columns
'''
所有列
Index(['a', 'b', 'c', 'd', 'e', 'f', 'g'], dtype='object')
'''
index1 = df2.index
'''
RangeIndex(start=0, stop=4, step=1)
'''
values1 = df2.values
'''
[[1 Timestamp('2019-01-01 00:00:00') 1.0 3 'test' 'foo'
Timestamp('2002-02-05 00:00:00')]
[1 Timestamp('2019-01-01 00:00:00') 1.0 3 'train' 'foo'
Timestamp('2002-02-06 00:00:00')]
[1 Timestamp('2019-01-01 00:00:00') 1.0 3 'test' 'foo'
Timestamp('2002-02-07 00:00:00')]
[1 Timestamp('2019-01-01 00:00:00') 1.0 3 'train' 'foo'
Timestamp('2002-02-08 00:00:00')]]
'''
describe1 = df2.describe()
'''
数据简单统计
a c d
count 4.0 4.0 4.0
mean 1.0 1.0 3.0
std 0.0 0.0 0.0
min 1.0 1.0 3.0
25% 1.0 1.0 3.0
50% 1.0 1.0 3.0
75% 1.0 1.0 3.0
max 1.0 1.0 3.0
'''
transpose1 = df2.T
'''
数据翻转
0 ... 3
a 1 ... 1
b 2019-01-01 00:00:00 ... 2019-01-01 00:00:00
c 1 ... 1
d 3 ... 3
e test ... train
f foo ... foo
g 2002-02-05 00:00:00 ... 2002-02-08 00:00:00
[7 rows x 4 columns]
'''
df2_sort_index = df2.sort_index(axis=0, ascending=False)
'''
对行和列的索引进行排序
a b c d e f g
3 1 2019-01-01 1.0 3 train foo 2002-02-08
2 1 2019-01-01 1.0 3 test foo 2002-02-07
1 1 2019-01-01 1.0 3 train foo 2002-02-06
0 1 2019-01-01 1.0 3 test foo 2002-02-05
'''
df2_sort_values = df2.sort_values(by='g', ascending=False)
'''
根据值排序
a b c d e f g
3 1 2019-01-01 1.0 3 train foo 2002-02-08
2 1 2019-01-01 1.0 3 test foo 2002-02-07
1 1 2019-01-01 1.0 3 train foo 2002-02-06
0 1 2019-01-01 1.0 3 test foo 2002-02-05
'''