Python tushare.get_k_data() Examples

def getSingleStockByTime(symbol, from_date, till_date):
    start = from_date.split('-')
    start_y, start_m, start_d = start[0], start[1], start[2] # starting date

    end = till_date.split('-')
    end_y, end_m, end_d = end[0], end[1], end[2] # until now
    
    repeat_times = 1
    message = ""
    df = pd.DataFrame()

    for _ in range(repeat_times): 
        try:
            data = ts.get_k_data(symbol)#, from_date, till_date)
            data.sort_index(ascending=True, inplace=True)
            return data, ""
        except Exception as e:
            message = symbol + " fetch exception: " + str(e)
            continue   
    return df, message 

def _load_from_api(self, code, start, end, ktype, autype, index):
        d = dict(code=code, ktype=ktype)

        if start:
            d["start"] = start

        if end:
            d["end"] = end

        df = ts.get_k_data(**d)
        df.reset_index(drop=True, inplace=True)
        j = df.to_json()
        data = json.loads(j)

        df_len = len(df)

        return data, df_len 

def jdrs(df, n=20):
    """
    阶段弱势指标	jdrs(20)
    JDRS=（统计N天中个股收盘价<开盘价，且指数收盘价>开盘价的天数）/（统计N天中指数收盘价>开盘价的天数）
    """
    ind = ts.get_k_data("sh000001", start=df.date.iloc[0], end=df.date.iloc[-1])
    sd = df.copy()
    sd.set_index('date', inplace=True)
    ind.set_index('date', inplace=True)
    _jdrs = pd.DataFrame(index=df.date)
    q = ind.close - ind.open
    _jdrs['p'] = sd.close - sd.open
    _jdrs['q'] = q
    _jdrs['m'] = _jdrs.apply(lambda x: 1 if (x.p < 0 and x.q > 0) else np.nan, axis=1)
    q[q < 0] = np.nan
    _jdrs['t'] = q
    _jdrs['jdrs'] = _jdrs.m.rolling(n).count() / _jdrs.t.rolling(n).count()
    _jdrs.drop(columns=['p', 'q', 'm', 't'], inplace=True)
    _jdrs.reset_index(inplace=True)
    return _jdrs 

def jdqs(df, n=20):
    """
    阶段强势指标	jdqs(20)
    JDQS=（统计N天中个股收盘价>开盘价，且指数收盘价<开盘价的天数）/（统计N天中指数收盘价<开盘价的天数）
    """
    ind = ts.get_k_data("sh000001", start=df.date.iloc[0], end=df.date.iloc[-1])
    sd = df.copy()
    sd.set_index('date', inplace=True)   # 可能出现停盘等情况，所以将date设为index
    ind.set_index('date', inplace=True)
    _jdrs = pd.DataFrame(index=df.date)
    q = ind.close - ind.open
    _jdrs['p'] = sd.close - sd.open
    _jdrs['q'] = q
    _jdrs['m'] = _jdrs.apply(lambda x: 1 if (x.p > 0 and x.q < 0) else np.nan, axis=1)
    q[q > 0] = np.nan
    _jdrs['t'] = q
    _jdrs['jdrs'] = _jdrs.m.rolling(n).count() / _jdrs.t.rolling(n).count()
    _jdrs.drop(columns=['p', 'q', 'm', 't'], inplace=True)
    _jdrs.reset_index(inplace=True)
    return _jdrs 

def dptb(df, n=7):
    """
    大盘同步指标	dptb(7)
    DPTB=（统计N天中个股收盘价>开盘价，且指数收盘价>开盘价的天数或者个股收盘价<开盘价，且指数收盘价<开盘价）/N
    """
    ind = ts.get_k_data("sh000001", start=df.date.iloc[0], end=df.date.iloc[-1])
    sd = df.copy()
    sd.set_index('date', inplace=True)  # 可能出现停盘等情况，所以将date设为index
    ind.set_index('date', inplace=True)
    _dptb = pd.DataFrame(index=df.date)
    q = ind.close - ind.open
    _dptb['p'] = sd.close - sd.open
    _dptb['q'] = q
    _dptb['m'] = _dptb.apply(lambda x: 1 if (x.p > 0 and x.q > 0) or (x.p < 0 and x.q < 0) else np.nan, axis=1)
    _dptb['jdrs'] = _dptb.m.rolling(n).count() / n
    _dptb.drop(columns=['p', 'q', 'm'], inplace=True)
    _dptb.reset_index(inplace=True)
    return _dptb 

def getSingleStockByTime(symbol, from_date, till_date):
    start = from_date.split('-')
    start_y, start_m, start_d = start[0], start[1], start[2] # starting date

    end = till_date.split('-')
    end_y, end_m, end_d = end[0], end[1], end[2] # until now
    
    repeat_times = 1
    message = ""
    df = pd.DataFrame()

    for _ in range(repeat_times): 
        try:
            data = ts.get_k_data(symbol, ktype='M')
            data.sort_index(ascending=True, inplace=True)
            return data, ""
        except Exception as e:
            message = symbol + " fetch exception: " + str(e)
            continue   
    return df, message 

def get_single_stock_data_daily(root_path, symbol):
    '''
    All data is from quandl wiki dataset
    Feature set: [Open  High    Low  Close    Volume  Ex-Dividend  Split Ratio Adj. Open  Adj. High  Adj. Low
    Adj. Close  Adj. Volume]
    '''
    #df, lastUpdateTime = queryStock(root_path, "DB_STOCK", "SHEET_CHN", "_DAILY", symbol, "daily_update")
    try:
        df = ts.get_k_data(symbol)
        df.set_index('date', inplace=True)
        df.sort_index(ascending=True, inplace=True)
    except:
        print("stock delisted", symbol)
        return pd.DataFrame()

    if df.empty:
        print("stock delisted", symbol)
        return pd.DataFrame()

    out_path = root_path + "/Data/CSV/symbols/"

    if os.path.exists(out_path) == False:
        os.mkdir(out_path)

    out_file = out_path + symbol + ".csv"
    df.to_csv(out_file)

    return df 

def get_tushare_k_data(instrument, start_dt, end_dt):
        order_book_id = instrument.order_book_id
        code = order_book_id.split(".")[0]

        if instrument.type == 'CS':
            index = False
        elif instrument.type == 'INDX':
            index = True
        else:
            return None

        return ts.get_k_data(code, index=index, start=start_dt.strftime('%Y-%m-%d'), end=end_dt.strftime('%Y-%m-%d')) 

def tapi(df, n=6):
    """ # TODO: 由于get_k_data返回数据中没有amount，可以用get_h_data中amount，算法是正确的
    加权指数成交值	tapi(6)
    TAPI=每日成交总值/当日加权指数=a/PI；A表示每日的成交金额，PI表示当天的股价指数即指收盘价
    """
    _tapi = pd.DataFrame()
    # _tapi['date'] = df.date
    _tapi['tapi'] = df.amount / df.close
    _tapi['matapi'] = _ma(_tapi.tapi, n)
    return _tapi 

def getSingleStock(symbol):
    repeat_times = 1
    message = ""
    df = pd.DataFrame()

    for _ in range(repeat_times): 
        try:
            data = ts.get_k_data(symbol, ktype='W')
            data.sort_index(ascending=True, inplace=True)
            return data, ""
        except Exception as e:
            message = symbol + " fetch exception: " + str(e)
            continue   
    return df, message 

def getSingleStock(symbol):
    repeat_times = 1
    message = ""
    df = pd.DataFrame()

    for _ in range(repeat_times): 
        try:
            data = ts.get_k_data(symbol, ktype='M')
            data.sort_index(ascending=True, inplace=True)
            return data, ""
        except Exception as e:
            message = symbol + " fetch exception: " + str(e)
            continue   
    return df, message 

def test_plot_all(self):
        data = ts.get_k_data("601398", start="2018-01-01", end="2018-05-27")

        data = data.sort_values(by=["date"], ascending=True)

        idx.plot_all(data, is_show=True, output=None) 

def get_tushare_k_data(instrument, start_dt, end_dt):
        order_book_id = instrument.order_book_id
        code = order_book_id.split(".")[0]

        if instrument.type == 'CS':
            index = False
        elif instrument.type == 'INDX':
            index = True
        else:
            return None

        return ts.get_k_data(code, index=index, start=start_dt.strftime('%Y-%m-%d'), end=end_dt.strftime('%Y-%m-%d')) 

def k_data(index,mode='D'):

    if mode == 'D':
        df_to_mysql('anack_d_k_data',ts.get_k_data(index))
    elif mode == 'M':
        df_to_mysql('anack_m_k_data',ts.get_k_data(index,ktype='M'))
        
#------------------------------------------------------------------------------
#create_k_table()
#k_data('600660') 
#k_data('600660','M') 

def k_day(index,mode='D'):

    if mode == 'D':
        return ts.get_k_data(index)
    elif mode == 'M':
        return ts.get_k_data(index,ktype='M') 

def get(self):
        symbol = self.get_argument("symbol")#股票代码
        period = self.get_argument("period")#时间周期,单位-分钟
        period_allow_list = ["5","15","30","60","1440","M","W"]
        if period not in period_allow_list:
            return 
       
        data = None
        if period =="1440":
            data = ts.get_hist_data(symbol)
        else:
            data = ts.get_k_data(symbol,ktype=period)
        print "=========",symbol,":",period
        resultlist = []
        lens = len(data)
        for unit in data.iterrows():
            obj  = {}
            dates = None
            if period =="1440":
                dates = unit[1].name
            else:
                dates = unit[1]['date']
            print "len",len(dates)
#             长度等于10的是%Y-%m-%d格式,16的是%Y-%m-%d %H:%M 格式
            dataformate = "%Y-%m-%d %H:%M"
            date_len = len(dates)
            if date_len == 10 :
                dataformate = "%Y-%m-%d"
            d=datetime.datetime.strptime(dates,dataformate)
            obj["date"]=int(time.mktime(d.timetuple()))
            obj["open"]=unit[1]['open']
            obj["close"]=unit[1]['close']
            obj["high"]=unit[1]['high']
            obj["low"]=unit[1]['low']
            obj["volume"]=unit[1]['volume']
            resultlist.append(obj)
        
        resultlist.sort(key=lambda obj:obj.get('date'), reverse=False) 
        
        s = json.dumps(resultlist)
        self.write(s) 

def download_kline_by_date_range(code, date_start, date_end):
    """
    根据日期范围下载股票行情
    :param code:股票代码，即6位数字代码，或者指数代码（sh=上证指数 sz=深圳成指 hs300=沪深300指数 sz50=上证50 zxb=中小板 cyb=创业板）
    :param date_start:
    :param date_end:
    :return:
    """
    try:
        if len(code)==6:
            df_qfq = ts.get_k_data(str(code), start=date_start, end=date_end, autype='qfq') # 前复权
            df_hfq = ts.get_k_data(str(code), start=date_start, end=date_end, autype='hfq')  # 后复权
        else:
            df_qfq = ts.get_k_data(str(code), start=date_start, end=date_end)
        if len(df_qfq)==0 or (len(code)==6 and len(df_hfq)==0):
            return pd.DataFrame()

        if len(code)==6:
            df_qfq['close_hfq'] = df_hfq['close']
        else:
            df_qfq['close_hfq'] = df_qfq['close']  # 指数后复权=前复权

        print(df_qfq.head())

        return df_qfq
    except Exception as e:
        print(str(e))
        return pd.DataFrame() 

def getSingleStock(symbol):
    repeat_times = 1
    message = ""
    df = pd.DataFrame()

    for _ in range(repeat_times): 
        try:
            data = ts.get_k_data(symbol)
            data.sort_index(ascending=True, inplace=True)
            return data, ""
        except Exception as e:
            message = symbol + " fetch exception: " + str(e)
            continue   
    return df, message 

def _getFundDaysFromTuShare(self, code, startDate, endDate, fields, name=None):
        """
            从tushare获取基金（ETF）日线数据。
            # !!!TuShare没有提供换手率，复权因子和成交额，所以只能假设。
            # 策略针对ETF的，需要注意。
        """
        tuShareCode = code[:-3]

        try:
            # 以无复权方式从腾讯获取OHCLV，成交量是手（整数化过）
            # 此接口支持ETF日线数据
            df = ts.get_k_data(tuShareCode, startDate, endDate, autype=None).sort_index()
        except Exception as ex:
            self._info.print("从TuShare获取{}({})日线数据[{}, {}]失败: {}".format(code, name, startDate, endDate, ex), DyLogData.error)
            return None

        df['volume'] = df['volume']*100

        # !!!TuShare没有提供换手率，复权因子和成交额，所以只能假设。
        # 策略针对ETF的，需要注意。
        df['turnover'] = 0
        df['factor'] = 1
        df['amount'] = 0
        df.index.name = None

        # change to Wind's indicators
        df.rename(columns={'date': 'datetime', 'amount': 'amt', 'turnover': 'turn', 'factor': 'adjfactor'}, inplace=True)

        # 把日期的HH:MM:SS转成 00:00:00
        df['datetime'] = pd.to_datetime(df['datetime'], format='%Y-%m-%d')

        # select according @fields
        df = df[['datetime'] + fields]

        return df 

def _getFundDaysFromTuShare(self, code, startDate, endDate, fields, name=None):
        """
            从tushare获取基金（ETF）日线数据。
            # !!!TuShare没有提供换手率，复权因子和成交额，所以只能假设。
            # 策略针对ETF的，需要注意。
        """
        tuShareCode = code[:-3]

        sleepTime = self.tuShareDaysSleepTimeConst + self.tuShareDaysSleepTime
        try:
            try:
                # 以无复权方式从腾讯获取OHCLV，成交量是手（整数化过）
                # 此接口支持ETF日线数据
                df = ts.get_k_data(tuShareCode, startDate, endDate, autype=None, pause=sleepTime)
                if df is None or df.empty: # If no data, TuShare return None
                    df = pd.DataFrame(columns=['date', 'open', 'high', 'close', 'low', 'volume'])
                else:
                    df = df.sort_index()
            except Exception as ex:
                self._info.print("从TuShare获取{}({})日线数据[{}, {}]失败: {}".format(code, name, startDate, endDate, ex), DyLogData.error)
                return None

            df['volume'] = df['volume']*100

            # !!!TuShare没有提供换手率，复权因子和成交额，所以只能假设。
            # 策略针对ETF的，需要注意。
            df['turnover'] = 0
            df['factor'] = 1
            df['amount'] = 0
            df.index.name = None

            # change to Wind's indicators
            df.rename(columns={'date': 'datetime', 'amount': 'amt', 'turnover': 'turn', 'factor': 'adjfactor'}, inplace=True)

            # 把日期的HH:MM:SS转成 00:00:00
            df['datetime'] = pd.to_datetime(df['datetime'], format='%Y-%m-%d')

            # select according @fields
            df = df[['datetime'] + fields]
        except Exception as ex:
            self._info.print("从TuShare获取{}({})日线数据[{}, {}]失败: {}".format(code, name, startDate, endDate, ex), DyLogData.error)
            return None

        return df 

def init():
    '''
        根据target_id获取历史平均成交量、均线水平等参数，作为后续check的比对依据
        id:
        avg_price_week:周线
        avg_price_month:月线
        avg_price_year:年线
        volume_min:5日内平均每分钟成交量（用于计算量比）
    '''
    global avg_info
    global morning_open_time
    global morning_close_time
    global afternoon_open_time
    global afternoon_close_time
#    input_id = ['000651','600887','600066','600660']
    input_id = target_id
    
    avg_price_week = []    #周均线，5天
    avg_price_month = []   #月均线，22天
    avg_price_year = [] #年线，250天
    avg_volumn_min = []
    for id_name in input_id:
        a = ts.get_k_data(id_name)  #获取基础信息
        temp = a.iloc[-5:]['close']
        avg_price_week.append(temp.sum()/5)
        temp = a.iloc[-22:]['close']
        avg_price_month.append(temp.sum()/22)    
        if len(a) > 250:
            temp = a.iloc[-250:]['close']
            avg_price_year.append(temp.sum()/250)
        else:
            temp = a.iloc[:]['close']
            avg_price_year.append(temp.sum()/len(a))     
        a = a[-5:]  #计算过去5天内的平均成交量
        b = a.iloc[:]['volume']
        c = b.sum() / len(b) / 240
        avg_volumn_min.append(c)
        
    data = {'id':input_id,
            'avg_price_week':avg_price_week,
            'avg_price_month':avg_price_month,
            'avg_price_year':avg_price_year,
            'volume_min':avg_volumn_min
            }
    avg_info = pd.DataFrame(data)
    
    
    now = datetime.now()
    morning_open_time = datetime(now.year,now.month,now.day,9,30)
    morning_close_time = datetime(now.year,now.month,now.day,11,30)
    afternoon_open_time = datetime(now.year,now.month,now.day,13,00)
    afternoon_close_time = datetime(now.year,now.month,now.day,15,00)
#    return pd.DataFrame(data)