【Data Analysis and Visualization】 Pandas Dataframe

import numpy as np
import pandas as pd
from pandas import Series, DataFrame

 # 引入网页
import webbrowser
link = 'https://www.tiobe.com/tiobe-index/'

webbrowser.open(link)

True

# 获取剪贴板数据
df = pd.read_clipboard()
df

	Year	Winner
2019	medal	C
2018	medal	Python
2017	medal	C
2016	medal	Go
2015	medal	Java
2014	medal	JavaScript
2013	medal	Transact-SQL
2012	medal	Objective-C
2011	medal	Objective-C
2010	medal	Python
2009	medal	Go
2008	medal	C
2007	medal	Python
2006	medal	Ruby
2005	medal	Java
2004	medal	PHP
2003	medal	C++

# 查看类型-DataFrame
type(df)

pandas.core.frame.DataFrame

# 返回列
df.columns

Index(['Year', 'Winner'], dtype='object')

# 获取某列的value
df.Winner

2019               C
2018          Python
2017               C
2016              Go
2015            Java
2014      JavaScript
2013    Transact-SQL
2012     Objective-C
2011     Objective-C
2010          Python
2009              Go
2008               C
2007          Python
2006            Ruby
2005            Java
2004             PHP
2003             C++
Name: Winner, dtype: object

# 提取数据生成新 过滤DataFrame
df_new = DataFrame(df, columns=['Year'])
df_new

	Year
2019	medal
2018	medal
2017	medal
2016	medal
2015	medal
2014	medal
2013	medal
2012	medal
2011	medal
2010	medal
2009	medal
2008	medal
2007	medal
2006	medal
2005	medal
2004	medal
2003	medal

# 假如列名有空格，用此方法读取
df_new['Year']

2019    medal
2018    medal
2017    medal
2016    medal
2015    medal
2014    medal
2013    medal
2012    medal
2011    medal
2010    medal
2009    medal
2008    medal
2007    medal
2006    medal
2005    medal
2004    medal
2003    medal
Name: Year, dtype: object

# 其中某列的类型 Series
type(df_new['Year'])

pandas.core.series.Series

# 提取数据生成新 过滤DataFrame
# 如果列名根本不存在 值默认为NaN
df_new = DataFrame(df, columns=['Year','Age'])
df_new

	Year	Age
2019	medal	NaN
2018	medal	NaN
2017	medal	NaN
2016	medal	NaN
2015	medal	NaN
2014	medal	NaN
2013	medal	NaN
2012	medal	NaN
2011	medal	NaN
2010	medal	NaN
2009	medal	NaN
2008	medal	NaN
2007	medal	NaN
2006	medal	NaN
2005	medal	NaN
2004	medal	NaN
2003	medal	NaN

# 通过字典方式给空值赋值(必须全部写满列)
df_new['Age'] = range(0,17)
df_new

	Year	Age
2019	medal	0
2018	medal	1
2017	medal	2
2016	medal	3
2015	medal	4
2014	medal	5
2013	medal	6
2012	medal	7
2011	medal	8
2010	medal	9
2009	medal	10
2008	medal	11
2007	medal	12
2006	medal	13
2005	medal	14
2004	medal	15
2003	medal	16

df_new['Age'] = np.arange(0,17)
df_new

	Year	Age
2019	medal	0
2018	medal	1
2017	medal	2
2016	medal	3
2015	medal	4
2014	medal	5
2013	medal	6
2012	medal	7
2011	medal	8
2010	medal	9
2009	medal	10
2008	medal	11
2007	medal	12
2006	medal	13
2005	medal	14
2004	medal	15
2003	medal	16

# 利用DataFrame某列返回值是Series类型的特点
df_new['Age'] = pd.Series(np.arange(0,17))
df_new

	Year	Age
2019	NaN	NaN
2018	NaN	NaN
2017	NaN	NaN
2016	NaN	NaN
2015	NaN	NaN
2014	NaN	NaN
2013	NaN	NaN
2012	NaN	NaN
2011	NaN	NaN
2010	NaN	NaN
2009	NaN	NaN
2008	NaN	NaN
2007	NaN	NaN
2006	NaN	NaN
2005	NaN	NaN
2004	NaN	NaN
2003	NaN	NaN

# 修改部分值
df_new['Age'] = pd.Series([18, 17], index=[2019, 2018])
df_new

	Year	Age
2019	NaN	18.0
2018	NaN	17.0
2017	NaN	NaN
2016	NaN	NaN
2015	NaN	NaN
2014	NaN	NaN
2013	NaN	NaN
2012	NaN	NaN
2011	NaN	NaN
2010	NaN	NaN
2009	NaN	NaN
2008	NaN	NaN
2007	NaN	NaN
2006	NaN	NaN
2005	NaN	NaN
2004	NaN	NaN
2003	NaN	NaN