财务大数据比赛代码例子

Myth丶恋晨 2022-04-04 04:25 256阅读 0赞

pip安装国内源

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple gevent

判分关键字

tushare,import,savefig,figure,get_k_data,figsize,plot,index

排序

import tushare as ts                          #财经数据接口
    stock1 = ts.get_hist_data('002508','2016-01-01','2017-12-31',ktype='M')
    print(stock1.sort_values(axis = 0,ascending = True,by=['date'])) #axis=0表示按列排序
    print(stock1['close'])#获得某一列

loc iloc 提取数据  
详细：[https://blog.csdn.net/w\_weiying/article/details/81411257][https_blog.csdn.net_w_weiying_article_details_81411257]

import tushare as ts
    data=ts.get_k_data('000425',start='2016-01-01',end='2017-12-31',ktype='M')
    print(data)
    print(data.loc[2:4,'open':'high'])
    print(data.iloc[[4,5,6,7],[2,3,4]])

get\_profit\_statement无乱码存储

data=ts.get_profit_statement('000425')
    print(data)
    data.to_csv('1.csv',encoding='utf_8_sig')

画图例子

import tushare as ts
    import matplotlib.pyplot as plt
    
    plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
    plt.rcParams['axes.unicode_minus']=False #用来正常显示负号
    
    fhdata=ts.get_hist_data('600498',start='2017-01-01',end='2017-12-31',ktype='M')
    szdata=ts.get_hist_data('sh',start='2017-01-01',end='2017-12-31',ktype='M')
    
    #print(fhdata,szdata)
    
    fhsort = fhdata.sort_index(axis=0, ascending=True)
    szsort = szdata.sort_index(axis=0, ascending=True)
    
    print(fhsort,szsort)
    
    #fhsort.to_csv('D:\BigData\烽火通信2017年1-12月的指数涨跌幅度数据.csv')
    #szsort.to_csv('D:\BigData\上证指数2017年1-12月的指数涨跌幅度数据.csv')
    
    fhzdf=fhsort['p_change']
    szzdf=szdata['p_change']
    
    print(fhzdf,szzdf)
    
    #fhzdf.to_csv('D:\BigData\烽火通信2017年1-12月的指数涨跌幅度数据（已清洗）.csv',header=1)
    #szzdf.to_csv('D:\BigData\上证指数2017年1-12月的指数涨跌幅度数据（已清洗）.csv',header=1)
    
    fg1=plt.figure(figsize=(10,7))
    
    plt.title('开盘价收盘价最高价折线图')
    fhsort['open'].plot(label='烽火通信开盘价')
    fhsort['close'].plot(label='烽火通信收盘价')
    fhsort['high'].plot(label='烽火通信最高价')
    szsort['open'].plot(label='上证指数开盘价')
    szsort['close'].plot(label='上证指数收盘价')
    szsort['high'].plot(label='上证指数最高价')
    plt.legend()
    fg1.show()
    #fg1.savefig(r'D:\BigData\开盘价收盘价最高价折线图.png',format='png')
    
    fg2=plt.figure(figsize=(10,7))
    plt.title('5日均价10日均价20日均价折线图')
    fhsort['ma5'].plot(label='烽火通信5日均价')
    fhsort['ma10'].plot(label='烽火通信10日均价')
    fhsort['ma20'].plot(label='烽火通信20日均价')
    szsort['ma5'].plot(label='上证指数5日均价')
    szsort['ma10'].plot(label='上证指数10日均价')
    szsort['ma20'].plot(label='上证指数20日均价')
    plt.legend()
    fg2.show()
    #fg2.savefig(r'D:\BigData\5日均价10日均价20日均价折线图.png',format='png')

横坐标设置为日期格式

import tushare as ts
    import pandas as pd
    import matplotlib.pyplot as plt
    import matplotlib.dates as mdate
    import numpy as np
    plt.rcParams['font.sans-serif']=['SimHei'] #用来正常显示中文标签
    plt.rcParams['axes.unicode_minus']=False #用来正常显示负号
    
    data=ts.get_k_data('002193',start='2018-06-01',end='2018-06-31',autype=None)
    print(data)
    data.to_csv('如意集团2018年6月公司股价变动日收盘价.csv')
    
    #print(data['date'])
    #print(data['close'])
    
    result=pd.concat([data['date'], data['close']], axis=1)
    
    print(result)
    result.to_csv('如意集团2018年6月公司股价变动日收盘价（已清洗）.csv')
    
    x_ticks=data['date']
    print(x_ticks)
    
    fg1=plt.figure(figsize=(9,6))
    
    plt.title('开盘价收盘价最高价折线图')
    data['open'].plot(label='开盘价')
    data['close'].plot(label='收盘价')
    data['high'].plot(label='最高价')
    
    plt.xticks(np.arange(99,118),x_ticks,rotation = 60)
    plt.legend()
    fg1.show()
    fg1.savefig(r'D:\bigdata\开盘价收盘价最高价折线图.png',format='png')

获得某一季度数据画图

import matplotlib.pyplot as plt                  #绘图
    import seaborn as sns                       #基于matplotlib的数据可视化库
    import tushare as ts                          #财经数据接口
    import pandas as pd
    import csv
    from datetime import datetime
    
    # get_hist_data函数，获取某只股票的历史交易数据，参数与get_k_data相同
    stock1 = ts.get_profit_statement('600498')
    
    stock1.to_csv('d:/bigdata/利润表.csv',encoding='utf_8_sig')
    
    filename='d:/bigdata/利润表.csv'
    with open(filename,encoding='utf_8_sig') as  f:
        r=csv.DictReader(f)
        d={ }
        for row in r:
            if row['报表日期'] == '减：所得税费用':
                d['第一季度'] = float(row['20170331'])
                d['第二季度'] = float(row['20170630'])
                d['第三季度'] = float(row['20170930'])
                d['第四季度'] = float(row['20171231'])
    
                #print(d)
                sns.set_style("whitegrid")
                plt.rcParams['font.sans-serif'] = ['SimHei']  # 中文字体设置-黑体
                plt.rcParams['axes.unicode_minus'] = False  # 解决保存图像是负号'-'显示为方块的问题
                sns.set(font='SimHei')  # 解决Seaborn中文显示问题
    
                sns.barplot(x=list(d.keys()),y=list(d.values()))
                plt.title('各季度所得税')
                plt.xlabel('季度')
                plt.ylabel('所得税')
                plt.savefig('d:/bigdata/所得税柱状图.png')
                break

追加数据

import tushare as ts
    import pandas as pd
    import os
    pd.set_option('display.max_columns', None)#打印输出显示所有数据
    pd.set_option('display.max_rows', None)
    
    #追加数据到csv
    file='adddatas.csv'
    for code in ['000981','000425','000875']:
        tempdata=ts.get_hist_data(code,start='2017-10-10',end='2018-10-10',ktype='M')
        if os.path.exists(file):
            tempdata.to_csv(file,mode='a')
        else:
            tempdata.to_csv(file)

获得某几列concat

data=ts.get_k_data('002193',start='2018-06-01',end='2018-06-31',autype=None)
    print(data)
    
    #print(data['date'])
    #print(data['close'])
    result=pd.concat([data['date'], data['close']], axis=1)

柱状图饼状图  
[https://blog.csdn.net/hohaizx/article/details/79101322][https_blog.csdn.net_hohaizx_article_details_79101322]  
[https://www.cnblogs.com/Detector/p/8850280.html（柱状图参考）][https_www.cnblogs.com_Detector_p_8850280.html]

表格

Sub a()
    For Each s In Sheet1.OLEObjects
    s.TopLeftCell = s.Object.Value
    s.Delete
    Next
    End Sub

[https_blog.csdn.net_w_weiying_article_details_81411257]: https://blog.csdn.net/w_weiying/article/details/81411257
[https_blog.csdn.net_hohaizx_article_details_79101322]: https://blog.csdn.net/hohaizx/article/details/79101322
[https_www.cnblogs.com_Detector_p_8850280.html]: https://www.cnblogs.com/Detector/p/8850280.html%EF%BC%88%E6%9F%B1%E7%8A%B6%E5%9B%BE%E5%8F%82%E8%80%83%EF%BC%89