Python读取并解析通达信数据文件

通达信的数据文件格式比较简单，网络上能找到的Python 解析代码大多使用struct 来解析，性能不高。 其实numpy 也能直接读取二进制文件，而且结合pandas，功能更强大。

import numpy as np
import pandas as pd
def 读取日线数据(文件路径):
    dt = np.dtype([
        ('Date', 'u4'),
        ('Open', 'u4'),
        ('High', 'u4'),
        ('Low', 'u4'),
        ('Close', 'u4'),
        ('Amount', 'f'),
        ('Volume', 'u4'),
        ('Reserve','u4')])
    data = np.fromfile(文件路径, dtype=dt)
    #df = pd.DataFrame(data)
    # Or if you want to explicitly set the column names
    df = pd.DataFrame(data, columns=data.dtype.names)
    df.eval('''
        year=floor(Date/10000)
        month=floor((Date%10000)/100)
        day=floor(Date%10000%100)
        Open=Open/100
        High=High/100
        Low=Low/100
        Close=Close/100
    ''',inplace=True)
    df.index=pd.to_datetime(df.loc[:,['year','month','day']])
    return df.drop(['Date','year','month','day'],1)

def 读取分钟数据(文件路径):
    '''
    year=floor(m_date/2048)+2004; %提取年信息
    mon=floor(mod(m_date,2048)/100); %提取月信息
    day=mod(mod(m_date,2048),100); %提取日信息*/
    m_time/60 输出小时
    m_time%60 输出分钟
    '''
    dt = np.dtype([
        ('m_date', 'u2'),
        ('m_time', 'u2'),
        ('Open', 'f4'),
        ('High', 'f4'),
        ('Low', 'f4'),
        ('Close', 'f4'),
        ('Amount', 'f4'),
        ('Volume', 'u4'),
        ('Reserve','u4')])
    data = np.fromfile(文件路径, dtype=dt)
    #df = pd.DataFrame(data)
    # Or if you want to explicitly set the column names
    df = pd.DataFrame(data, columns=data.dtype.names)
    df.eval('''
        year=floor(m_date/2048)+2004
        month=floor((m_date%2048)/100)
        day=floor(m_date%2048%100)
        hour = floor(m_time/60)
        minute = m_time%60
    ''',inplace=True)
    df.index=pd.to_datetime(df.loc[:,['year','month','day','hour','minute']])
    return df.drop(['m_date','m_time','year','month','day','hour','minute'],1)

日线文件路径 = r'C:\vipdoc\sh\lday\sh600025.day'
五分文件路径 = r'C:\vipdoc\sh\fzline\sh600025.lc5'
一分文件路径 = r'C:\vipdoc\sh\minline\sh600025.lc1'
日线数据 = 读取日线数据(日线文件路径)
五分数据 = 读取分钟数据(五分文件路径)
一分数据 = 读取分钟数据(一分文件路径)
print(日线数据.tail(10))
print(五分数据.tail(10))
print(一分数据.tail(10))
print(一分数据.head(10))
    

            Open  High   Low  Close       Amount    Volume  Reserve
2020-02-28  3.74  3.77  3.67   3.69  222089056.0  59854355    65536
2020-03-02  3.71  3.79  3.71   3.76  134752352.0  35872664    65536
2020-03-03  3.79  3.82  3.77   3.79  119396688.0  31502027    65536
2020-03-04  3.76  3.88  3.76   3.86  167259584.0  43594328    65536
2020-03-05  3.89  3.95  3.87   3.94  192437232.0  49077518    65536
2020-03-06  3.91  3.93  3.88   3.90  121692808.0  31218072    65536
2020-03-09  3.85  3.86  3.76   3.78  184477168.0  48633066    65536
2020-03-10  3.74  3.88  3.74   3.87  173113808.0  45416429    65536
2020-03-11  3.86  3.87  3.81   3.81  105091608.0  27373594    65536
2020-03-12  3.80  3.81  3.73   3.75   96933592.0  25786021        0
                     Open  High   Low  Close     Amount   Volume  Reserve
2020-03-12 14:15:00  3.75  3.75  3.74   3.74  1437680.0   384000        0
2020-03-12 14:20:00  3.74  3.75  3.74   3.75  1298536.0   347000        0
2020-03-12 14:25:00  3.75  3.75  3.74   3.74   608440.0   162600        0
2020-03-12 14:30:00  3.74  3.75  3.74   3.75  1224136.0   327200        0
2020-03-12 14:35:00  3.75  3.76  3.74   3.76  4984256.0  1329200        0
2020-03-12 14:40:00  3.75  3.76  3.75   3.75  2114376.0   563500        0
2020-03-12 14:45:00  3.76  3.78  3.75   3.75  3283496.0   872300        0
2020-03-12 14:50:00  3.75  3.77  3.75   3.76  1384568.0   368400        0
2020-03-12 14:55:00  3.76  3.77  3.75   3.75  2265616.0   602600        0
2020-03-12 15:00:00  3.75  3.76  3.75   3.75   568992.0   151500        0
                     Open  High   Low  Close        Amount  Volume  Reserve
2020-03-12 14:51:00  3.76  3.77  3.76   3.76  4.428390e+05  117700        0
2020-03-12 14:52:00  3.76  3.77  3.76   3.77  2.189030e+05   58200        0
2020-03-12 14:53:00  3.76  3.77  3.75   3.75  1.140250e+06  303300        0
2020-03-12 14:54:00  3.75  3.76  3.75   3.76  2.192300e+05   58400        0
2020-03-12 14:55:00  3.75  3.76  3.75   3.75  2.441970e+05   65000        0
2020-03-12 14:56:00  3.75  3.76  3.75   3.76  1.799150e+05   47900        0
2020-03-12 14:57:00  3.75  3.76  3.75   3.76  2.011590e+05   53500        0
2020-03-12 14:58:00  3.76  3.76  3.76   3.76  0.000000e+00       0        0
2020-03-12 14:59:00  3.76  3.76  3.76   3.76  0.000000e+00       0        0
2020-03-12 15:00:00  3.75  3.75  3.75   3.75  1.878750e+05   50100        0
                     Open  High   Low  Close        Amount  Volume  Reserve
2019-11-14 09:31:00  4.36  4.36  4.35   4.35  7.074900e+05  162300        0
2019-11-14 09:32:00  4.36  4.36  4.35   4.36  4.887820e+05  112200        0
2019-11-14 09:33:00  4.36  4.36  4.35   4.36  2.453460e+05   56300        0
2019-11-14 09:34:00  4.36  4.36  4.35   4.36  2.981950e+05   68400        0
2019-11-14 09:35:00  4.36  4.36  4.35   4.36  2.192820e+05   50300        0
2019-11-14 09:36:00  4.35  4.36  4.35   4.36  5.482161e+05  125900        0
2019-11-14 09:37:00  4.36  4.36  4.35   4.35  1.130302e+06  259800        0
2019-11-14 09:38:00  4.35  4.35  4.34   4.34  5.735700e+05  131900        0
2019-11-14 09:39:00  4.34  4.35  4.34   4.35  4.512571e+05  103800        0
2019-11-14 09:40:00  4.34  4.34  4.33   4.33  1.674892e+06  386000        0