本文转载我自己写的文章,我个人网站DataAnswer:http://www.dataanswer.top(大数据博客和大数据问答的网站)上的文章。主要利用python获取股票数据,利用R来作图分析。
由股票代码列表获取历年股票数据
import pandas as pd
from pandas import Series,DataFrame
stock_data=pd.read_csv('/home/hadoop/mywork/stock.txt',sep=' ')
stock_data.columns=Series(['code','name','class'])
stock_data['url']=''
for i in range(len(stock_data)):
if(str(stock_data.code[i]).find('sh')<0):
stock_data['url'][i]=str(stock_data.code[i])[2:8]+".sz"
else:
stock_data['url'][i]=str(stock_data.code[i])[2:8]+".ss"
stock_data1=stock_data[0:18]
stock_data2=stock_data[19:len(stock_data)]
stock_data=pd.concat([stock_data1,stock_data2])
stock_data.index=range(len(stock_data))
for i in range(len(stock_data)):
stock_url='http://table.finance.yahoo.com/table.csv?s='+stock_data.url[i]+'&d=11&e=05&f=2015&g=d&a=00&b=00&c=2015&ignore=.csv'
stock_df=pd.read_csv(stock_url)
path='/home/hadoop/mywork/stock/'+stock_data.url[i]+".txt"
stock_df.to_csv(path)
#对不同行业的公司分层索引
import pandas as pd
from pandas import Series,DataFrame
stock_data=pd.read_csv('/home/hadoop/mywork/stock.txt',sep=' ')
stock_data.columns=Series(['code','name','class'])
key=range(len(stock_data))
stock_data['key']=1
s=stock_data.set_index(['class','key'])
s
获取各行业的公司代码,求出各行业的公司总数
import pandas as pd
from pandas import Series,DataFrame
stock_data=pd.read_csv('/home/hadoop/mywork/stock.txt',sep=' ',encoding='utf-8')
stock_data.columns=Series(['code','name','class'])
stock_total=DataFrame()
stock_total['name']=(['金融','军工','