13-numpy笔记-莫烦pandas-1
代码
import pandas as pd
import numpy as np
s = pd.Series([1,3,6,np.nan, 44,1])
print('-1-')
print(s)
dates = pd.date_range('20160101', periods=6)
print('-2-')
print(dates)
# index 是行的key; 默认就是数字
df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=['a','b','c','d'])
print('-3-')
print(df)
df1 = pd.DataFrame(np.arange(12).reshape((3,4)))
print('-4-')
print(df1)
df2 = pd.DataFrame({'A':1.,
'B':pd.Timestamp('20130102'),
'C':pd.Series(1,index=list(range(4)), dtype = 'float32'),
'D':np.array([3]*4,dtype='int32'),
'E':pd.Categorical(["test","train","test","train"]),
'F':'foo'})
print('-5-')
print(df2)
print('-6-')
print(df2.dtypes)
print('-7-')
print(df2.index)
print('-8-')
print(df2.columns)
print('-9-')
print(df2.values)
print('-10-')
#只会计算数字串
print(df2.describe())
print('-11-')
print(df2.T)
print('-12-')
# 对 ABCD排序
print(df2.sort_index(axis=1, ascending=False))
print('-13-')
# 对123排序
print(df2.sort_index(axis=0, ascending=False))
print('-14-')
print(df2.sort_values(by='E'))
输出
-1-
0 1.0
1 3.0
2 6.0
3 NaN
4 44.0
5 1.0
dtype: float64
-2-
DatetimeIndex(['2016-01-01', '2016-01-02', '2016-01-03', '2016-01-04',
'2016-01-05', '2016-01-06'],
dtype='datetime64[ns]', freq='D')
-3-
a b c d
2016-01-01 -0.636080 -0.411646 1.167693 -0.085643
2016-01-02 -0.931738 -0.656105 0.833493 0.866367
2016-01-03 -0.495047 -0.131291 -0.757423 -0.783154
2016-01-04 -0.207423 0.261732 0.300315 -0.674217
2016-01-05 0.241664 0.560630 -0.057852 -0.411710
2016-01-06 -0.964392 0.990477 0.926594 0.388210
-4-
0 1 2 3
0 0 1 2 3
1 4 5 6 7
2 8 9 10 11
-5-
A B C D E F
0 1.0 2013-01-02 1.0 3 test foo
1 1.0 2013-01-02 1.0 3 train foo
2 1.0 2013-01-02 1.0 3 test foo
3 1.0 2013-01-02 1.0 3 train foo
-6-
A float64
B datetime64[ns]
C float32
D int32
E category
F object
dtype: object
-7-
Int64Index([0, 1, 2, 3], dtype='int64')
-8-
Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')
-9-
[[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']
[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']]
-10-
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
-11-
0 ... 3
A 1 ... 1
B 2013-01-02 00:00:00 ... 2013-01-02 00:00:00
C 1 ... 1
D 3 ... 3
E test ... train
F foo ... foo
[6 rows x 4 columns]
-12-
F E D C B A
0 foo test 3 1.0 2013-01-02 1.0
1 foo train 3 1.0 2013-01-02 1.0
2 foo test 3 1.0 2013-01-02 1.0
3 foo train 3 1.0 2013-01-02 1.0
-13-
A B C D E F
3 1.0 2013-01-02 1.0 3 train foo
2 1.0 2013-01-02 1.0 3 test foo
1 1.0 2013-01-02 1.0 3 train foo
0 1.0 2013-01-02 1.0 3 test foo
-14-
A B C D E F
0 1.0 2013-01-02 1.0 3 test foo
2 1.0 2013-01-02 1.0 3 test foo
1 1.0 2013-01-02 1.0 3 train foo
3 1.0 2013-01-02 1.0 3 train foo
