pandas学习（一）

pandas学习一

import pandas as pd
import numpy as np

#创建一个列表
s=pd.Series([1,3,6,np.nan,44,1])
s

0     1.0
1     3.0
2     6.0
3     NaN
4    44.0
5     1.0
dtype: float64

#日期列表   （起始日期，个数）
date=pd.date_range('20200224',periods=6)
date

DatetimeIndex(['2020-02-24', '2020-02-25', '2020-02-26', '2020-02-27',
               '2020-02-28', '2020-02-29'],
              dtype='datetime64[ns]', freq='D')

#随机生成一个表   6行4列  行用日期索引，列用abcd索引
df=pd.DataFrame(np.random.randn(6,4),index=date,columns=['a','b','c','d'])
df

	a	b	c	d
2020-02-24	-0.626171	0.246824	0.165425	0.148035
2020-02-25	0.710622	-1.679865	-0.777670	0.968605
2020-02-26	-0.858063	-0.261376	1.132020	-0.158369
2020-02-27	-0.612111	0.081410	-0.034667	1.355139
2020-02-28	-0.631792	-0.891452	0.488653	0.313943
2020-02-29	-0.295801	0.246308	0.231300	0.240889

#df的类型
df.dtypes

a    float64
b    float64
c    float64
d    float64
dtype: object

#df的索引
df.index

DatetimeIndex(['2020-02-24', '2020-02-25', '2020-02-26', '2020-02-27',
               '2020-02-28', '2020-02-29'],
              dtype='datetime64[ns]', freq='D')

#df的列索引
df.columns

Index(['a', 'b', 'c', 'd'], dtype='object')

#df的值
df.values

array([[-0.62617077,  0.24682398,  0.16542528,  0.14803493],
       [ 0.71062227, -1.67986545, -0.77766962,  0.96860532],
       [-0.85806291, -0.26137552,  1.13201976, -0.15836874],
       [-0.61211132,  0.0814105 , -0.03466684,  1.35513929],
       [-0.63179158, -0.89145187,  0.48865349,  0.31394313],
       [-0.29580124,  0.24630751,  0.23130023,  0.24088918]])

#计算方差，平均值等各种数据
df.describe()

	a	b	c	d
count	6.000000	6.000000	6.000000	6.000000
mean	-0.385553	-0.376358	0.200844	0.478041
std	0.566177	0.769843	0.626907	0.566929
min	-0.858063	-1.679865	-0.777670	-0.158369
25%	-0.630386	-0.733933	0.015356	0.171248
50%	-0.619141	-0.089983	0.198363	0.277416
75%	-0.374879	0.205083	0.424315	0.804940
max	0.710622	0.246824	1.132020	1.355139

#转置一下再计算
df.T.describe()

	2020-02-24 00:00:00	2020-02-25 00:00:00	2020-02-26 00:00:00	2020-02-27 00:00:00	2020-02-28 00:00:00	2020-02-29 00:00:00
count	4.000000	4.000000	4.000000	4.000000	4.000000	4.000000
mean	-0.016472	-0.194577	-0.036447	0.197443	-0.180162	0.105674
std	0.408741	1.254121	0.837820	0.829252	0.683461	0.267722
min	-0.626171	-1.679865	-0.858063	-0.612111	-0.891452	-0.295801
25%	-0.045516	-1.003219	-0.410547	-0.179028	-0.696707	0.099525
50%	0.156730	-0.033524	-0.209872	0.023372	-0.158924	0.236095
75%	0.185775	0.775118	0.164228	0.399843	0.357621	0.242244
max	0.246824	0.968605	1.132020	1.355139	0.488653	0.246308

#按索引排序 axis=1对行排序，=0对列排序，ascending=False是逆序
df.sort_index(axis=1,ascending=False)

	d	c	b	a
2020-02-24	0.148035	0.165425	0.246824	-0.626171
2020-02-25	0.968605	-0.777670	-1.679865	0.710622
2020-02-26	-0.158369	1.132020	-0.261376	-0.858063
2020-02-27	1.355139	-0.034667	0.081410	-0.612111
2020-02-28	0.313943	0.488653	-0.891452	-0.631792
2020-02-29	0.240889	0.231300	0.246308	-0.295801

#按值排序   by=列名
df.sort_values(by='d')

	a	b	c	d
2020-02-26	-0.858063	-0.261376	1.132020	-0.158369
2020-02-24	-0.626171	0.246824	0.165425	0.148035
2020-02-29	-0.295801	0.246308	0.231300	0.240889
2020-02-28	-0.631792	-0.891452	0.488653	0.313943
2020-02-25	0.710622	-1.679865	-0.777670	0.968605
2020-02-27	-0.612111	0.081410	-0.034667	1.355139