import numpy as np
import pandas as pd
#pandas的Series
s = pd.Series([1,2,'花朵',98,1,20,0])
print(s)
datas = pd.date_range('20200721',periods=6)
#通過numpy生成的數組,傳遞給pandas
df = pd.DataFrame(np.random.randn(6,4),index=datas,columns=['a','b','c','d'])
print(df)
df1 = pd.DataFrame(np.random.randn(6,4))
#直接生成pandas數組
df2 = pd.DataFrame({
'小明列':22,
'B':pd.Timestamp('20200620'),
'C':pd.Series(1,index=list(range(4)),dtype='float32'),
'D':np.array([3]*4,dtype='int32'),
'E':pd.Categorical(['hello','mike','momo','train']),
'F':'foolie'
})
s
Out[9]:
0 1
1 2
2 花朵
3 98
4 1
5 20
6 0
dtype: object
df
Out[8]:
a b c d
2020-07-21 -1.334143 -0.418217 0.399811 1.286937
2020-07-22 0.122256 1.625069 0.064293 -0.485579
2020-07-23 1.356831 -0.575917 0.326547 -1.440079
2020-07-24 -1.075300 0.248529 1.921025 -0.503600
2020-07-25 -0.965514 0.175607 -0.180204 -2.009705
2020-07-26 -0.036789 -0.266677 0.091262 0.823388
df1
Out[5]:
0 1 2 3
0 -0.221695 0.469178 -1.385129 -0.579727
1 -0.388149 -1.804306 -0.811451 1.867572
2 1.400014 -0.386663 0.935390 0.062821
3 1.000829 0.279782 -0.326873 -0.530542
4 0.862546 0.776912 -0.349843 -0.773228
5 -0.215625 -1.157521 -0.855164 0.265402
df2
Out[7]:
小明列 B C D E F
0 22 2020-06-20 1.0 3 hello foolie
1 22 2020-06-20 1.0 3 mike foolie
2 22 2020-06-20 1.0 3 momo foolie
3 22 2020-06-20 1.0 3 train foolie