【数据分析与可视化】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

# 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

# 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

# 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

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

# 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

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