pandas练习

最新推荐文章于 2025-05-22 23:21:00 发布

Marvin_Kai

最新推荐文章于 2025-05-22 23:21:00 发布

阅读量648

点赞数

CC 4.0 BY-SA版权

分类专栏：数据分析

本文链接：https://blog.youkuaiyun.com/Marvin_Wind/article/details/86709487

数据分析专栏收录该内容

2 篇文章

订阅专栏

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt

df = pd.read_csv('/Users/PycharmProjects/newwork/BeijingPM20100101_20151231.csv')

df.head(3)

	No	year	month	day	hour	season	PM_Dongsi	PM_Dongsihuan	PM_Nongzhanguan	PM_US Post	DEWP	HUMI	PRES	TEMP	cbwd	Iws
0	1	2010	1	1	0	4	NaN	NaN	NaN	NaN	-21.0	43.0	1021.0	-11.0	NW	1.79
1	2	2010	1	1	1	4	NaN	NaN	NaN	NaN	-21.0	47.0	1020.0	-12.0	NW	4.92
2	3	2010	1	1	2	4	NaN	NaN	NaN	NaN	-21.0	43.0	1019.0	-11.0	NW	6.71

#将分散的时间合并到一起
period=pd.PeriodIndex(year=df['year'],month=df['month'],day=df['day'],hour=df['hour'],freq='H')

type(period)

pandas.core.indexes.period.PeriodIndex

print(period)

PeriodIndex(['2010-01-01 00:00', '2010-01-01 01:00', '2010-01-01 02:00',
             '2010-01-01 03:00', '2010-01-01 04:00', '2010-01-01 05:00',
             '2010-01-01 06:00', '2010-01-01 07:00', '2010-01-01 08:00',
             '2010-01-01 09:00',
             ...
             '2015-12-31 14:00', '2015-12-31 15:00', '2015-12-31 16:00',
             '2015-12-31 17:00', '2015-12-31 18:00', '2015-12-31 19:00',
             '2015-12-31 20:00', '2015-12-31 21:00', '2015-12-31 22:00',
             '2015-12-31 23:00'],
            dtype='period[H]', length=52584, freq='H')

#设置统一的时间索引
df['datatime'] = period

df.head(5)

	No	year	month	day	hour	season	PM_Dongsi	PM_Dongsihuan	PM_Nongzhanguan	PM_US Post	DEWP	HUMI	PRES	TEMP	cbwd	Iws	datatime
0	1	2010	1	1	0	4	NaN	NaN	NaN	NaN	-21.0	43.0	1021.0	-11.0	NW	1.79	2010-01-01 00:00
1	2	2010	1	1	1	4	NaN	NaN	NaN	NaN	-21.0	47.0	1020.0	-12.0	NW	4.92	2010-01-01 01:00
2	3	2010	1	1	2	4	NaN	NaN	NaN	NaN	-21.0	43.0	1019.0	-11.0	NW	6.71	2010-01-01 02:00
3	4	2010	1	1	3	4	NaN	NaN	NaN	NaN	-21.0	55.0	1019.0	-14.0	NW	9.84	2010-01-01 03:00
4	5	2010	1	1	4	4	NaN	NaN	NaN	NaN	-20.0	51.0	1018.0	-12.0	NW	12.97	2010-01-01 04:00

df.set_index('datatime',inplace=True)    #重设行索引

df.head(5)

	No	year	month	day	hour	season	PM_Dongsi	PM_Dongsihuan	PM_Nongzhanguan	PM_US Post	DEWP	HUMI	PRES	TEMP	cbwd	Iws	precipitation	Iprec
datatime
2010-01-01 00:00	1	2010	1	1	0	4	NaN	NaN	NaN	NaN	-21.0	43.0	1021.0	-11.0	NW	1.79	0.0	0.0
2010-01-01 01:00	2	2010	1	1	1	4	NaN	NaN	NaN	NaN	-21.0	47.0	1020.0	-12.0	NW	4.92	0.0	0.0
2010-01-01 02:00	3	2010	1	1	2	4	NaN	NaN	NaN	NaN	-21.0	43.0	1019.0	-11.0	NW	6.71	0.0	0.0
2010-01-01 03:00	4	2010	1	1	3	4	NaN	NaN	NaN	NaN	-21.0	55.0	1019.0	-14.0	NW	9.84	0.0	0.0
2010-01-01 04:00	5	2010	1	1	4	4	NaN	NaN	NaN	NaN	-20.0	51.0	1018.0	-12.0	NW	12.97	0.0	0.0

data = df['PM_US Post'].dropna()

plt.figure(figsize=(20,8),dpi=80)

_x = data.index
_y = data.values

plt.plot(range(len(_x)),_y)
#数据过长，不方便分析使用，所以下一步降采样

df = df.resample('7D').mean()    #忽略na

df.head(5)

	No	year	month	day	hour	season	PM_Dongsi	PM_Dongsihuan	PM_Nongzhanguan	PM_US Post	DEWP	HUMI	PRES	TEMP	Iws	precipitation	Iprec
datatime
2010-01-01	372.5	2010.0	1.0	16.0	11.5	4.0	NaN	NaN	NaN	90.40367	-17.013441	46.449597	1028.009409	-6.162634	41.227325	0.015054	0.177688
2010-01-08	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2010-01-15	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2010-01-22	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN
2010-01-29	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN	NaN

data = df['PM_US Post'].dropna()

_x = data.index
_y = data.values

plt.figure(figsize=(20,8),dpi=80)

<Figure size 1600x640 with 0 Axes>




<Figure size 1600x640 with 0 Axes>

plt.plot(range(len(_x)),_y)
plt.xticks(range(0,len(_x),10),list(_x)[::10],rotation=45)
plt.show()

png

两组数据对比：

df = pd.read_csv('/Users/marvinking/PycharmProjects/newwork/BeijingPM20100101_20151231.csv')

period=pd.PeriodIndex(year=df['year'],month=df['month'],day=df['day'],hour=df['hour'],freq='H')

df['datatime'] = period
df.set_index('datatime',inplace=True)

df = df.resample('7D').mean()
data = df['PM_US Post']
data_cn = df['PM_Nongzhanguan']
_x = data.index
_x = [i.strftime("%Y%m%d") for i in _x]
_x_china = [i.strftime("%Y%m%d") for i in data_cn.index]
_y = data.values
_y_china = data_cn.values

plt.figure(figsize=(20,8),dpi=80)


plt.plot(range(len(_x)),_y,label="US_POST",alpha=0.7)
plt.plot(range(len(_x_china)),_y_china,label="CN_POST",alpha=0.7)

plt.xticks(range(0,len(_x_china),10),list(_x_china)[::10],rotation=45)

plt.legend(loc="best")

plt.show()

在这里插入图片描述