def QA_fetch_get_stock_day(name, startDate, endDate, if_fq='01'):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if(QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
if if_fq in ['00', 'bfq']:
data = w.wsd(name, "sec_name,pre_close,open,high,low,close,volume",
startDate, endDate)
elif if_fq in ['01', 'qfq']:
data = w.wsd(name, "sec_name,pre_close,open,high,low,close,volume",
startDate, endDate, "PriceAdj=F")
elif if_fq in ['02', 'hfq']:
data = w.wsd(name, "sec_name,pre_close,open,high,low,close,volume",
startDate, endDate, "PriceAdj=B")
else:
QA_util_log_info('wrong fq factor! using qfq')
data = w.wsd(name, "sec_name,pre_close,open,high,low,close,volume",
startDate, endDate, "PriceAdj=B")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T, columns=data.Fields, index=data.Times)
def func9():
yesterday = (datetime.datetime.now() - datetime.timedelta(days = 1)).strftime("%Y-%m-%d")
df_discount_ratio_M = pd.read_csv('discount_ratio_M.csv')
last_date_discount_ratio_M = time.strftime("%Y-%m-%d",time.strptime(str(int(df_discount_ratio_M.iloc[-1,0])),"%Y%m%d"))
day_gap_discount_ratio_M = w.tdayscount(last_date_discount_ratio_M, yesterday).Data[0][0]-1
w_wsd_data={}
print 9
stock_ls=[]
for stock in universe:
if stock[0]=='1':
stock = stock + '.SZ'
else:
stock = stock + '.SH'
mA_code = w.wsd(stock, 'fund_smfcode', yesterday).Data[0][0]
stock_ls.append(mA_code)
w_wsd_data[mA_code] = w.wsd(mA_code, 'anal_tdiscountratio', (w.tdaysoffset(1,last_date_discount_ratio_M).Data[0][0]).strftime("%Y-%m-%d"),yesterday)
for i in xrange(day_gap_discount_ratio_M):
this_day = w.tdaysoffset(i+1,last_date_discount_ratio_M)
ls = []
this_day_csv = (this_day.Data[0][0]).strftime("%Y%m%d")
for stock in stock_ls:
ls.append(w_wsd_data[stock].Data[0][i])
f=open('discount_ratio_M.csv','a')
f.write(this_day_csv)
for stock_data in ls:
f.write(",")
f.write(str(stock_data))
f.write("\n")
f.close()
print 'finish'
def wsd(tickers, fields, startdate, enddate):
if isinstance(tickers,str):
tickers = tickers.replace(',','').split()
if isinstance(fields,str):
fields = fields.replace(',','').split()
if len(tickers) == 1:
tmp = w.wsd(tickers, fields, startdate, enddate)
return pd.DataFrame(dict(zip(fields, tmp.Data)),index = tmp.Times)
elif len(fields) == 1:
tmp = w.wsd(tickers, fields, startdate, enddate)
return pd.DataFrame(dict(zip(tickers, tmp.Data)),index = tmp.Times)
else:
print 'cannot surrport multiple code with multiple fields'
def func11():
yesterday = (datetime.datetime.now() - datetime.timedelta(days = 1)).strftime("%Y-%m-%d")
df_industry=pd.read_csv('industry.csv')
last_date_industry = time.strftime("%Y-%m-%d",time.strptime(str(int(df_industry.iloc[-1,0])),"%Y%m%d"))
day_gap_industry = w.tdayscount(last_date_industry, yesterday).Data[0][0]-1
print 11
w_wsd_data={}
stock_ls=[]
for stock in list(df_industry.columns.values)[1:] :
stock_ls.append(stock)
w_wsd_data[stock] = w.wsd(stock, 'close', (w.tdaysoffset(1,last_date_industry).Data[0][0]).strftime("%Y-%m-%d"),yesterday)
print w_wsd_data
f=open('industry.csv','a')
for i in xrange(day_gap_industry):
this_day = w.tdaysoffset(i+1,last_date_industry)
ls = []
this_day_csv = (this_day.Data[0][0]).strftime("%Y%m%d")
for stock in stock_ls:
ls.append(w_wsd_data[stock].Data[0][i])
f.write(this_day_csv)
for stock_data in ls:
f.write(",")
f.write(str(stock_data))
f.write("\n")
f.close()
print 'finish'
def vpup():
'提取持仓与价格变动超过一定幅度的期货合作信息'
codes = pw.getCodes()
dic = {}
for code in codes:
data = w.wsd(code, "close,pct_chg,oi,oi_chg", "ED-1TD").Data
if isinstance((data[1][-1]), float):
price = data[0][-1]
price_chg = data[1][-1]
oi = data[2][-1]
oi_chg = data[3][-1]
else:
price = data[0][-2]
price_chg = data[1][-2]
oi = data[2][-2]
oi_chg = data[3][-2]
if oi != 0:
oichg = oi_chg / oi
else:
oichg = 0
if abs(oichg) > 0.05 and abs(price_chg) > 1.5:
dic[code] = ' '.join(['Oichg:%.2f%%' % (100 * oichg), 'Oi:%.0f' % oi,
'Pricechg:%.2f%%' % price_chg, 'Price:%.0f' % price])
else:
pass
return dic
def GetSWexponent(ExponentID=None,BeginTime=None,EndTime=None):
if(ExponentID==None):
print("沒有传入申万之一指数代码，数据将返回所有申万一级指数的数据")
ExponentID = '801010.SI,801020.SI,801030.SI,\
801040.SI,801050.SI,801080.SI,801110.SI,\
801120.SI,801130.SI,801140.SI,801150.SI,\
801160.SI,801170.SI,801180.SI,801200.SI,\
801210.SI,801230.SI,801710.SI,801720.SI,\
801730.SI,801740.SI,801750.SI,801760.SI,\
801770.SI,801780.SI,801790.SI,801880.SI,\
801890.SI'
if(BeginTime==None):
BeginTime = '2010-01-01'
if(EndTime==None):
EndTime=date.today();
tmp = (ExponentID,'close',BeginTime,EndTime,'Fill=Previous')
data = w.wsd(*tmp)
Value = []
for i in range(0,len(data.Codes)):
for j in range(0,len(data.Data[0])):
value = data.Data[i][j];
if isnan(value):
value=0.0
Value.append((str(data.Codes[i]),data.Times[j].strftime("%Y-%m-%d"),str(value)))
for n in Value:
print(n)
return Value
def IndustryConfiguration(fundid=None, industry=None, begintime='2010-01-01', endtime=date.today()):
if(fundid == None):
print("没选择基金，默认为全部基金")
fundid = FundID()
if(industry == None):
print("未选择行业，默认为全部19个新证监会行业指标")
industry = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,15,16, 17, 18, 19]
Value = []
for k in range(0, len(industry)):
param = (fundid, 'prt_stockvalue_industrytoasset2', begintime, endtime,
'industry=' + str(industry[k]), 'Period=Q', 'Fill=Previous')
data = w.wsd(*param)
if(data.ErrorCode != 0):
print("Wind Error")
for i in range(0, len(data.Codes)):
for j in range(0, len(data.Data[0])):
value = data.Data[i][j]
if(value is None or isnan(value)):
value = 0.0
record = (data.Codes[i], data.Times[j].strftime("%Y-%m-%d"), industry[k], value)
Value.append(record)
return Value
def getUpdateCode(self,stockCodeList):
'''得到直接插入和复权的代码'''
reRightCode = [] # 需要復權的股票
# 得到数据库中最新一天的收盘价
closeList = []
for code in stockCodeList:
sql = "select close from stockData_day where stockCode = %s order by date desc limit 1"
self.cur.execute(sql,code)
result = self.cur.fetchone()
if not result:
closeList.append(0.0)
else:
closeList.append(result[0])
# 查找今天的數據
fields = ['pre_close']
today = datetime.date.today().strftime('%Y%m%d') #今天的日期
option = 'showblank=0.0;PriceAdj=F' # 要進行前復權處理
wsd_data = w.wsd(stockCodeList,fields,today,today,option)
if wsd_data.ErrorCode==0: # 返回成功
stockData = wsd_data.Data[0]
ifEqualList = (np.array(stockData) == np.array(closeList))
for i in range(len(ifEqualList)):
if not ifEqualList[i]:
rate = (stockData[i] - closeList[i]) / closeList[i]
reRightCode.append([stockCodeList[i],rate])
print '需要复权的数量为'
print len(reRightCode)
print '需要复权的股票代码为：'
print reRightCode
logging.info('需要复权的股票代码为：%s' % reRightCode)
return reRightCode
def import_data_from_wind(d_start, d_end, file_folder='C:\\dev\\src\\ktlib\\data3\\', freq='d', contracts=[]):
df = load_live_cont(d_start, d_end)
contList = [str(inst) for inst in df.index]
startDates = df.start_date
endDates = df.expiry
fields = 'open,close,high,low,volume,oi'
if len(contracts) !=0:
contList = contracts
#w.start()
for cont in contList:
if cont[1].isalpha(): key = cont[:2]
else: key = cont[:1]
ex = 'SH'
for exch in product_code.keys():
if key in product_code[exch]:
ex = exch
ticker = cont + '.' + ex
mth = int(cont[-2:])
if (key not in contMonth):
continue
if mth not in contMonth[key]:
continue
start_d = max(d_start, startDates.ix[cont])
end_d = min(d_end, endDates.ix[cont])
try:
if freq == 'm':
print "loading min data for ticker = %s" % ticker
raw_data = w.wsi(ticker,fields,start_d,end_d)
if len(raw_data.Data)>1:
outfile = file_folder + cont+'_min.csv'
output={'datetime':raw_data.Times,
'open':raw_data.Data[2],
'close':raw_data.Data[3],
'high':raw_data.Data[4],
'low':raw_data.Data[5],
'volume':raw_data.Data[6],
'openInterest':raw_data.Data[7]}
dump2csvfile(output,outfile)
else:
print "no min data obtained for ticker=%s" % ticker
else:
print "loading daily data for ticker = %s" % ticker
raw_data = w.wsd(ticker,fields,start_d,end_d)
if len(raw_data.Data)>1:
outfile = file_folder + cont+'_daily.csv'
output={'datetime':raw_data.Times,
'open':raw_data.Data[0],
'close':raw_data.Data[1],
'high':raw_data.Data[2],
'low':raw_data.Data[3],
'volume':raw_data.Data[4],
'openInterest':raw_data.Data[5]}
dump2csvfile(output,outfile)
else:
print "no daily data obtained for ticker=%s" % ticker
except ValueError:
pass
w.stop()
return True
def func2():
yesterday = (datetime.datetime.now() - datetime.timedelta(days = 1)).strftime("%Y-%m-%d")
df_openA=pd.read_csv('openA.csv')
last_date_openA = time.strftime("%Y-%m-%d",time.strptime(str(int(df_openA.iloc[-1,0])),"%Y%m%d"))
day_gap_openA = w.tdayscount(last_date_openA, yesterday).Data[0][0]-1
print 2
w_wsd_data={}
stock_ls=[]
for stock in universe:
if stock[0]=='1':
stock = stock + '.SZ'
else:
stock += '.SH'
stock_ls.append(stock)
w_wsd_data[stock] = w.wsd(stock, 'open', (w.tdaysoffset(1,last_date_openA).Data[0][0]).strftime("%Y-%m-%d"),yesterday)
for i in xrange(day_gap_openA):
this_day = w.tdaysoffset(i+1,last_date_openA)
ls = []
this_day_csv = (this_day.Data[0][0]).strftime("%Y%m%d")
for stock in stock_ls:
ls.append(w_wsd_data[stock].Data[0][i])
f=open('openA.csv','a')
f.write(this_day_csv)
for stock_data in ls:
f.write(",")
f.write(str(stock_data))
f.write("\n")
f.close()
print 'finish'
def wsd(self, *args, **kwargs):
try:
raw_data = w.wsd(*args, **kwargs)
if raw_data.ErrorCode < 0:
return json.dumps(raw_data.Codes)
df = pd.DataFrame(raw_data.Data)
df = df.transpose()
df.columns = [f.lower() for f in raw_data.Fields]
df['date'] = raw_data.Times
df.set_index(['date'])
return df.to_json()
except:
return json.dumps({'error': 'something wrong in calculation'})
def run(fund_code):
result = w.wsd(fund_code, "NAV_adj,sec_name,fund_fundmanageroftradedate",
"2010-01-01", today_date, "Fill=Previous;PriceAdj=F")
df = pd.DataFrame(result.Data, columns=result.Times).transpose()
fund_name = df.iloc[0, 1]
manager = df.iloc[-1, 2]
df = df.iloc[:, 0:1]
df.dropna(inplace=True)
df = del_eql(df)
df.columns = [fund_name + '(' + manager + ')']
df.to_csv('D:\\TF\\公募数据\\' + fund_code + ' ' + fund_name + '.csv',
encoding='gbk')
def __init__(self, backtest_start_date, backtest_end_date, index_code, threshold=1.5, hold_L=30, mean_L=5):
self.backtest_start_date = backtest_start_date
# 策略参数设定
self.threshold = threshold
self.hold_L = hold_L
self.mean_L = mean_L
# 提取数据
w.start()
start_date = get_trading_date_from_now(backtest_start_date, -mean_L-3, ql.Days)
data = w.wsd(index_code, "amt, close", start_date, backtest_end_date, "")
self.times = [t.strftime('%Y-%m-%d') for t in data.Times] # 日期序列
self.amt = data.Data[0] # 成交额数据
self.close = data.Data[1] # 价格序列
super().__init__(backtest_start_date, backtest_end_date, index_code)
def get_weights(self):
code_list = list_jq2wind(self.code_list)
w.start()
return_value = np.array(
w.wsd(code_list, "pct_chg", "ED-" + str(self.N - 1) + "TD",
self.date, "").Data)
return_value = return_value.transpose()
return_value = pd.DataFrame(return_value, columns=code_list)
optimizer = HRPOpt(return_value)
hrp_portfolio = optimizer.hrp_portfolio()
hrp_portfolio = dict(
zip(list_wind2jq(list(hrp_portfolio.keys())),
hrp_portfolio.values()))
return hrp_portfolio
def update_recorder(endDate=None, recordFile=None, holdListPath=None):
endDate = dt.datetime.today().strftime(
'%Y%m%d') if endDate is None else endDate
recordFile = r'.\backtest_recorder.csv' if recordFile is None else recordFile
holdListPath = r'.\holdLists' if holdListPath is None else holdListPath
recordDF = pd.read_csv(recordFile)
lastUpdt = recordDF['tradeDate'].values[-1]
w.start()
startDate = w.tdaysoffset(1, str(lastUpdt)).Data[0][0].strftime('%Y%m%d')
if startDate > endDate:
print('no new data to update')
return
betweenDays = w.tdays(startDate, endDate).Data[0]
betweenDays = [int(tdt.strftime('%Y%m%d')) for tdt in betweenDays]
print(betweenDays)
outPut = {
'tradeDate': [],
'buyReturn': [],
'holdReturn': [],
'netReturn': []
}
cols = ['stkcd', 'buyDate', 'ret', 'flag']
for tdt in betweenDays:
retList = pd.read_csv(os.path.join(
holdListPath, 'returns_tradeDate_{}.csv'.format(tdt)),
encoding='gbk')
retList = retList.loc[:, cols]
validBuy = np.all(
[retList['buyDate'] == tdt,
np.isin(retList['flag'], (0, 3, 4))],
axis=0)
validHold = np.all(
[retList['buyDate'] < tdt,
np.isin(retList['flag'], (0, 2, 3, 4))],
axis=0)
outPut['tradeDate'].append(tdt)
outPut['buyReturn'].append(retList.loc[validBuy, 'ret'].mean())
outPut['holdReturn'].append(retList.loc[validHold, 'ret'].mean())
outPut['netReturn'].append(retList.loc[validBuy | validHold,
'ret'].mean())
outPut = pd.DataFrame(
outPut).loc[:, ['tradeDate', 'buyReturn', 'holdReturn', 'netReturn']]
indices = ['000001.SH', '000300.SH', '000905.SH', '000016.SH']
idxRets = pd.DataFrame(w.wsd(','.join(indices), 'pct_chg', startDate,
endDate).Data,
columns=indices)
idxRets = idxRets.loc[:] / 100
outPut = pd.concat([outPut, idxRets], axis=1)
outPut.to_csv(recordFile, mode='a+', index=False, header=False)
print('recorder updated till {}'.format(endDate))
def Expire(self):
today = date.today()
tommorrow = today + timedelta(days=1)
expire = w.wsd(self.atCode, "exe_enddate", "ED0TD", today,
"TradingCalender=DCE").Data[0][0]
if self.position == 'flat':
return False
elif expire == tommorrow:
string = "Option will expire tommorrow!"
print(string + "Please COVER " + str(self.atCode) + 'and' +
str(self.outCode))
return True
else:
return False
def QA_fetch_get_stock_xueqiu(name, startDate, endDate):
with w.start():
if (QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
data = w.wsd(
name,
"xq_accmfocus,xq_accmcomments,xq_accmshares,xq_focusadded,xq_commentsadded,xq_sharesadded,xq_WOW_focus,xq_WOW_comments,xq_WOW_shares",
startDate, endDate, "")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T,
columns=data.Fields,
index=data.Times)
def stocks_infomation():
print('合并股票基础数据')
codes = pd.read_excel(const.STOCKS_CODE_FILE, skiprows=4, index_col=0)
codes.columns = ['股票代码', '股票名称']
hkcodes = pd.read_excel(const.HKSTOCKS_CODE_FILE, skiprows=4, index_col=0)
hkcodes.columns = ['股票代码', '股票名称']
codes = codes.merge(hkcodes, on=['股票名称'], how='outer')
codes['股票代码'] = [
codes.loc[i, '股票代码_y']
if pd.isna(codes.loc[i, '股票代码_x']) else codes.loc[i, '股票代码_x']
for i in codes.index
]
codes = codes[['股票名称', '股票代码']]
stocks = pd.read_excel(const.STOCKS_LIST_FILE,
converters={
'增速(2020)': utils.percent2float,
'增速(2021)': utils.percent2float,
'增速(2022)': utils.percent2float
})
results = stocks.merge(codes, how='left', on=['股票名称'])
# 计算股票动量
data = w.wsd(results['股票代码'].tolist(), 'close', start_date, end_date)
# print(data.Data)
prices = pd.DataFrame(data.Data, index=data.Codes, columns=data.Times)
prices = prices.T
returns = prices.pct_change().mean()
returns.index = np.arange(results.shape[0])
results['动量'] = returns
data = w.wss(','.join(results['股票代码'].dropna().tolist()),
"industry_sw,close",
"industryType=3;tradeDate=%s;priceAdj=U;cycle=D" % (today))
info = pd.DataFrame(data.Data, index=['细分行业', '收盘价'], columns=data.Codes)
info = info.T
info['细分行业'] = info['细分行业'].astype(str).map(lambda x: x.rstrip('Ⅲ'))
info['股票代码'] = info.index
results = results.merge(info, how='left', on=['股票代码'])
results['pe(2020)'] = results['收盘价'] / results['eps(2020)']
results['pe(2021)'] = results['收盘价'] / results['eps(2021)']
results['pe(2022)'] = results['收盘价'] / results['eps(2022)']
results_columns = [
'主题行业', '股票名称', '细分行业', '收盘价', '上次预测时间', '短评', '长评', '动量', '增速(2020)',
'增速(2021)', '增速(2022)', 'pe(2020)', 'pe(2021)', 'pe(2022)', '内部(40%)',
'外部(20%)', '基金重仓(30%)', '外资重仓(10%)', '总分'
]
results = results[results_columns]
results.to_excel(const.STOCKS_LIST_FILE, index=False)
def get_history(date_end, T):
w.start()
print('获取指数历史数据......')
if type(T) == int:
date_start = w.tdaysoffset(-T, date_end,
'').Data[0][0].strftime('%Y-%m-%d')
else:
date_start = T
Data = w.wsd(list(SW1.keys()), "pct_chg", date_start, date_end, "")
return_d = np.array(Data.Data)
date_list = Data.Times
date_list = [d.strftime('%Y-%m-%d') for d in date_list]
print('指数历史数据获取完毕')
return return_d, date_list
def getMultiTimeSeriesDataFrame(codeList,
beginDate,
endDate,
para,
period="",
tradingCalendar="",
priceAdj="",
credibility=0):
"""
para只能是一个参数
get time series from windPy, each code represents one capture
月度合约: trade_hiscode
:param credibility: (int)
:param codeList: (list)
:param beginDate: (date or datetime)
:param endDate: (date or datetime)
:param para: (string)只能是一个字符参数
:param period: (int) 频率
:param tradingCalendar: (string) 交易日历，选择可以选择银行间:NIB,不选择，则默认交易所日历
:param priceAdj: (string) 价格是否调整,F:前复权，B:后复权
:return: (DataFrame)
"""
try:
w.start()
codeListStr = ",".join(codeList)
period = ("Period=" + period) if period == "W" else ""
tradingCalendar = (
"TradingCalendar=" +
tradingCalendar) if tradingCalendar != "" else ""
priceAdj = ("priceAdj=" + priceAdj) if priceAdj != "" else ""
credibility = ("credibility=" +
str(credibility)) if credibility != 0 else ""
windData = w.wsd(codeListStr, para, beginDate.strftime("%Y-%m-%d"),
endDate.strftime("%Y-%m-%d"), period,
tradingCalendar, priceAdj, credibility)
if len(windData.Data) == 0:
raise BaseException
if len(windData.Data[0]) == 0:
raise BaseException
dataDict = {}
for i in range(len(windData.Data)):
dataDict[windData.Codes[i].lower() + "_" +
para] = windData.Data[i]
df = pd.DataFrame(dataDict, index=windData.Times)
df.index = pd.to_datetime(df.index)
df.index.name = "trade_date"
return df
except BaseException as e:
print(format(e))
raise
def get_sw_industry(code_list, date):
"""
:param code_list:
:param date:
:return: sw level one industry
date should be trade date
code_list can not duplicated
"""
if len(set(code_list)) != len(code_list):
raise ValueError("duplicated value in code_list input")
else:
sw_industry_code = w.wsd(code_list, "indexcode_sw", date, date,
"industryType=1").Data[0]
return sw_industry_code
def QA_fetch_get_stock_day_simple(name, startDate, endDate):
from WindPy import w
#w.start
w.start()
w.isconnected()
if(is_valid_date(endDate)==False):
print ("wrong date")
else :
data=w.wsd(name,"sec_name,preclose,open,high,low,close,volume",startDate,endDate, "Fill=Previous;PriceAdj=F")
#data=w.wsd("000002.SZ", "open,high,low,close,volume", "2017-03-03", "2017-04-01", "PriceAdj=B")
print(data.ErrorCode)
if (data.ErrorCode==0):
print ("Connent to Wind successfully")
return data.Data
def data_download(cmt, start_date, end_date):
tmp_cnt_list = w.wset(
"futurecc", "startdate=" + start_date + ";enddate=" + end_date +
";wind_code=" + cmt + ";field=wind_code")
tmp_cnt_list = tmp_cnt_list.Data[0]
tmp_download_cl_list = []
tmp_download_open_list = []
tmp_download_vol_list = []
tmp_download_oi_list = []
tmp_download_high_list = []
tmp_download_low_list = []
for cnt in tmp_cnt_list:
tmp_download_data = w.wsd(cnt, "close,open,volume,oi,high,low",
start_date, end_date, "")
time_index = [
datetime.strptime(str(x), "%Y-%m-%d")
for x in tmp_download_data.Times
]
tmp_cl = pd.Series(tmp_download_data.Data[0],
index=time_index,
name=cnt)
tmp_open = pd.Series(tmp_download_data.Data[1],
index=time_index,
name=cnt)
tmp_vol = pd.Series(tmp_download_data.Data[2],
index=time_index,
name=cnt)
tmp_oi = pd.Series(tmp_download_data.Data[3],
index=time_index,
name=cnt)
tmp_high = pd.Series(tmp_download_data.Data[4],
index=time_index,
name=cnt)
tmp_low = pd.Series(tmp_download_data.Data[5],
index=time_index,
name=cnt)
tmp_download_cl_list.append(tmp_cl)
tmp_download_open_list.append(tmp_open)
tmp_download_vol_list.append(tmp_vol)
tmp_download_oi_list.append(tmp_oi)
tmp_download_high_list.append(tmp_high)
tmp_download_low_list.append(tmp_low)
tmp_update_cl = pd.concat(tmp_download_cl_list, axis=1)
tmp_update_open = pd.concat(tmp_download_open_list, axis=1)
tmp_update_vol = pd.concat(tmp_download_vol_list, axis=1)
tmp_update_oi = pd.concat(tmp_download_oi_list, axis=1)
tmp_update_high = pd.concat(tmp_download_high_list, axis=1)
tmp_update_low = pd.concat(tmp_download_low_list, axis=1)
return tmp_update_cl, tmp_update_open, tmp_update_vol, tmp_update_oi, tmp_update_high, tmp_update_low
def bench_df(trade_days_list):
#筛选出沪深300每个交易日的成分股的代码、名字和权重，已保存csv防止wind quota exceed
#存在一个bug，wind数据中指数调整没有及时体现，函数取得值跟实际不符
bench_df = pd.DataFrame(
columns=['date', 'stock_code', 'stock_name', 'stock_weight'])
for day in trade_days_list:
strday = day[0]
bench_data = w.wset("indexconstituent", "date=" + strday,
"windcode=000300.SH")
temps_df = pd.DataFrame(bench_data.Data).T
temps_df.columns = ['date', 'stock_code', 'stock_name', 'stock_weight']
#保存了当天的样本和权重
bench_df = pd.concat([bench_df, temps_df])
# 将日期格式转化为文本
# 应该可以apply
bench_df['date'] = bench_df['date'].map(
lambda x: datetime.datetime.strftime(x, '%Y-%m-%d'))
#取每个股票的行业信息
bench_stocks = bench_df['stock_code'].drop_duplicates()
stocks_list = list(bench_stocks)
#print(len(stocks_list))
stocks_code = ','.join(stocks_list)
data = w.wss(stocks_code, "industry_sw",
"tradeDate=20170901;cycle=D;industryType=1")
stock_industry = pd.DataFrame([data.Codes, data.Data[0]]).T
stock_industry.columns = ['stock_code', 'stock_industry']
bench_df = pd.merge(bench_df, stock_industry, on='stock_code')
# 取出沪深300成分股每天的涨跌幅
bench_yield_df = pd.DataFrame(
columns=['date', 'stock_code', 'stock_yield'])
for stock in stocks_list:
bench_data = w.wsd(stock, "pct_chg,windcode", "2017-09-01",
"2017-12-31", "")
temps_df = pd.DataFrame(
[bench_data.Times, bench_data.Data[0], bench_data.Data[1]]).T
temps_df.columns = ['date', 'stock_yield', 'stock_code']
bench_yield_df = pd.concat([bench_yield_df, temps_df])
bench_yield_df['date'] = bench_yield_df['date'].map(
lambda x: datetime.datetime.strftime(x, '%Y-%m-%d'))
bench_yield_df.to_csv('data_produce/yield.csv')
bench_df = pd.merge(bench_df, bench_yield_df, on=['date', 'stock_code'])
bench_df = bench_df.sort_values(by=['date', 'stock_code'])
return bench_df
def QA_fetch_get_stock_shape(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if(QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
# history_low近期创历史新低,stage_high近期创阶段新高,history_high近期创历史新高,stage_low近期创阶段新高,up_days连涨天数,down_days连跌天数,breakout_ma向上有效突破均线,breakdown_ma向下有效突破均线,bull_bear_ma均线多空排列看涨看跌
data = w.wsd(name, "history_low,stage_high,history_high,stage_low,up_days,down_days,breakout_ma,breakdown_ma,bull_bear_ma",
startDate, endDate, "n=3;m=60;meanLine=60;N1=5;N2=10;N3=20;N4=30;upOrLow=1")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T, columns=data.Fields, index=data.Times)
def crawl_benchmark(id):
wind.start() # 启动wind
all_id = str(id) + '.OF'
tmp = wind.wsd(all_id, "NAV_date,nav,NAV_acc", "ED0D", now, "") # 万得API用法
df = pd.DataFrame(tmp.Data)
df = df.T
if df[0][0] == None:
pass
else:
df.columns = ["statistic_date_wind", "nav_wind", "added_nav_wind"]
df["statistic_date_wind"] = df["statistic_date_wind"].apply(lambda x: x.strftime('%Y-%m-%d'))
df["fund_id"] = id
df["version"] = now
to_sql("fund_nv", engine5, df, type="update")
print(df)
def get_portfolio_PL(portfolio_dict, start_date, end_date, base_date):
# 从start_date日收盘到end_date日收盘间计算投资组合价格变动
# base_date为复权定点日
w.start()
stock_names = list(portfolio_dict.keys())
data = w.wsd(stock_names, 'close2', start_date, end_date, 'adjDate=' +
''.join(base_date.split('-')) + ';PriceAdj=T').Data
data = np.array(data)
price_start = data[:, 0]
price_end = data[:, -1]
stock_numbers = np.array(list(portfolio_dict.values()))
market_value_start = np.sum(price_start * stock_numbers)
market_value_end = np.sum(price_end * stock_numbers)
print('投资组合的初期市值为：%.2f\n投资组合的到期市值为：%.2f' %
(market_value_start, market_value_end))
def QA_fetch_get_stock_risk(name, startDate, endDate):
with w.start():
if (QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
data = w.wsd(
name,
"annualyeild_100w,annualyeild_24m,annualyeild_60m,annualstdevr_100w,annualstdevr_24m,annualstdevr_60m,beta_100w,beta_24m,beta_60m,avgreturn,avgreturny,stdevry,stdcof,risk_nonsysrisk1,r2,alpha2,beta,sharpe,treynor,jensen,jenseny,betadf",
startDate, endDate,
"period=2;returnType=1;index=000001.SH;yield=1")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T,
columns=data.Fields,
index=data.Times)
def append_data(codes, fileds):
for code in codes:
print(code)
fname = '%s/%s.xlsx' % (INDEX_DIR, code)
if datetime.datetime.now().hour < 15:
end_date = datetime.datetime.today() - datetime.timedelta(1)
else:
end_date = datetime.datetime.today()
if os.path.exists(fname):
old_df = pd.read_excel(fname, index_col=0)
if 'outmessage' in old_df.columns:
del old_df['outmessage']
start_date = old_df.index[-1] + datetime.timedelta(1)
if start_date > end_date:
continue
else:
data = w.wsd(code, fields, start_date, end_date)
df = wind_data.wind2df(data)
df = old_df.append(df)
df.to_excel(fname)
else:
data = w.wsd(code, fields, '2001-01-01', end_date)
df = wind_data.wind2df(data)
df.to_excel(fname)
def QA_fetch_get_stock_xueqiu(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if(QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
data = w.wsd(name, "xq_accmfocus,xq_accmcomments,xq_accmshares,\
xq_focusadded,xq_commentsadded,xq_sharesadded,\
xq_WOW_focus,xq_WOW_comments,xq_WOW_shares", startDate, endDate, "")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T, columns=data.Fields, index=data.Times)
def QA_fetch_get_stock_shape(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if(QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
# history_low近期创历史新低,stage_high近期创阶段新高,history_high近期创历史新高,stage_low近期创阶段新高,up_days连涨天数,down_days连跌天数,breakout_ma向上有效突破均线,breakdown_ma向下有效突破均线,bull_bear_ma均线多空排列看涨看跌
data = w.wsd(name, "history_low,stage_high,history_high,stage_low,up_days,down_days,breakout_ma,breakdown_ma,bull_bear_ma",
startDate, endDate, "n=3;m=60;meanLine=60;N1=5;N2=10;N3=20;N4=30;upOrLow=1")
if (data.ErrorCode == 0):
QA_util_log_info("Connect to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T, columns=data.Fields, index=data.Times)
def __init__(self, backtest_start_date, backtest_end_date, index_code, N, M, S1=0.7, S2=-0.7):
w.start()
RSRS_start_date = get_trading_date_from_now(backtest_start_date, -N-M, ql.Days)
data = w.wsd(index_code, "high,low,close", RSRS_start_date, backtest_end_date, "")
self.RSRS_times = [t.strftime('%Y-%m-%d') for t in data.Times]
self.RSRS_data_high = data.Data[0]
self.RSRS_data_low = data.Data[1]
self.RSRS_data = data.Data[2]
self.backtest_start_date = backtest_start_date
self.RSRS_cal_start_date = get_trading_date_from_now(backtest_start_date, -M, ql.Days)
self.N = N # 计算RSRS指标采样的历史周期长短
self.M = M # 标准化序列的历史周期长短
self.S1 = S1
self.S2 = S2
self.date_list, _, self.signal_list = self._get_data()
def select_hy_contracts(x,y):
n=len(x)
hy_list=[]
date = pd.to_datetime(y)
start_date = date - dt.timedelta(20)
start_date = start_date.strftime('%Y-%m-%d')
d=w.wsd(x,'volume',start_date,y)
for i in range(n): #y means test date
mean_vol = np.nansum(d.Data[i][-5:])/5.0
#print(mean_vol)
if mean_vol > 2e4:
stock=d.Codes[i]
hy_list.append(stock)
return hy_list
def QA_fetch_get_stock_xueqiu(name, startDate, endDate):
from WindPy import w
# w.start()
w.start()
w.isconnected()
if (is_valid_date(endDate) == False):
print("wrong date")
else:
data = w.wsd(
name,
"xq_accmfocus,xq_accmcomments,xq_accmshares,xq_focusadded,xq_commentsadded,xq_sharesadded,xq_WOW_focus,xq_WOW_comments,xq_WOW_shares",
startDate, endDate, "")
if (data.ErrorCode == 0):
print("Connent to Wind successfully")
return data.Data
def QA_fetch_get_stock_risk(name, startDate, endDate):
from WindPy import w
w.start()
w.isconnected()
if (is_valid_date(endDate) == False):
print("wrong date")
else:
data = w.wsd(
name,
"annualyeild_100w,annualyeild_24m,annualyeild_60m,annualstdevr_100w,annualstdevr_24m,annualstdevr_60m,beta_100w,beta_24m,beta_60m,avgreturn,avgreturny,stdevry,stdcof,risk_nonsysrisk1,r2,alpha2,beta,sharpe,treynor,jensen,jenseny,betadf",
startDate, endDate,
"period=2;returnType=1;index=000001.SH;yield=1")
if (data.ErrorCode == 0):
print("Connent to Wind successfully")
return data.Data
def start_market_simulation(self):
error, data = w.wsd(self.ticker,
"open, close, volume",
self.start,
self.end,
"Fill=Previous;PriceAdj=F",
usedf=True)
for time, row in data.iterrows():
self.md.add_last_price(time, self.ticker, row["close"],
row["volume"])
self.md_add_open_price(time, self.ticker, row["open"])
if not self.event_tick is None:
self.event_tick(self.md)
def QA_fetch_get_stock_day(name, startDate, endDate):
with w.start():
if (QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
if w.isconnected() is False:
w.start()
data = w.wsd(name, "sec_name,pre_close,open,high,low,close,volume",
startDate, endDate, "PriceAdj=F")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T,
columns=data.Fields,
index=data.Times)
def __init__(self, backtest_start_date, backtest_end_date, index_code, L=50, N=3, Long=100, Threshold=1.02):
self.backtest_start_date = backtest_start_date
# 策略参数设定
self.L = L
self.N = N
self.Long = Long
self.Threshold = Threshold
# 基本数据获取
w.start()
start_date = get_trading_date_from_now(backtest_start_date, -(max(L+N, Long)+100), ql.Days)
data = w.wsd(index_code, "close,amt", start_date, backtest_end_date, "")
self.times = [t.strftime('%Y-%m-%d') for t in data.Times] # 日期序列
self.close = data.Data[0] # 价格序列
self.amt = data.Data[1] # 成交额序列
self._get_signal('2015-01-27')
super().__init__(backtest_start_date, backtest_end_date, index_code)
def __init__(self, backtest_start_date, backtest_end_date, index_code, threshold=0.0, RPS_history=250, max_vol_diff_history=100):
self.backtest_start_date = backtest_start_date
# 策略参数设定
self.threshold = threshold
self.RPS_history = RPS_history
self.max_vol_diff_history = max_vol_diff_history
# 提取数据
w.start()
start_date = get_trading_date_from_now(backtest_start_date, -RPS_history-max_vol_diff_history-30, ql.Days)
data = w.wsd(index_code, "open, close, high, low", start_date, backtest_end_date, "")
self.times = [t.strftime('%Y-%m-%d') for t in data.Times] # 日期序列
self.open = data.Data[0]
self.close = data.Data[1]
self.high = data.Data[2]
self.low = data.Data[3]
super().__init__(backtest_start_date, backtest_end_date, index_code)
def __init__(self, backtest_start_date, backtest_end_date, index_code, llt_d, llt_cal_history=100, llt_threshold=0.0):
'''
:param llt_d: 上证综指适合参数39
:param llt_cal_history:
:param llt_threshold:
'''
w.start()
llt_start_date = get_trading_date_from_now(backtest_start_date, -llt_cal_history, ql.Days)
data = w.wsd(index_code, "close", llt_start_date, backtest_end_date, "")
self.llt_times = [t.strftime('%Y-%m-%d') for t in data.Times]
self.llt_data = data.Data[0]
self.llt_d = llt_d
self.llt_threshold = llt_threshold
self.llt_cal_history = llt_cal_history # LLT信号计算的历史长度
self.backtest_start_date = backtest_start_date
super().__init__(backtest_start_date, backtest_end_date, index_code)
def column_append(ticker,
fields,
start_date='2015-01-01',
end_date='2017-03-28'):
fname = '%s/%s.xlsx' % (const.STOCK_DIR, ticker)
old_df = pd.read_excel(fname, index_col=0)
for col in fields.split(','):
if col in old_df.columns:
return
print ticker
data = w.wsd(ticker, fields, start_date, end_date, "traderType=1")
df = wind2df(data)
assert (df.shape[0] == old_df.shape[0])
df = old_df.join(df)
df.to_excel(fname)
def alert(chg=3.1):
'定义警示函数，扫描所有品种的涨幅幅，若超过某个限定的阈值，则发送邮件提醒自己注意！'
codes = pw.getActivecodes()
dic = {}
for code in codes:
data = w.wsd(code, "close,pct_chg,oi,oi_chg", "ED-0TD").Data
price = data[0][0]
price_chg = data[1][0]
if price:
if price_chg > chg:
dic[code] = [price, price_chg]
else:
pass
else:
print('没有有效的返回数据!')
return dic
def QA_fetch_get_stock_day_simple(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if(QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
data = w.wsd(name, "sec_name,preclose,open,high,low,close,volume",
startDate, endDate, "Fill=Previous;PriceAdj=F")
#data=w.wsd("000002.SZ", "open,high,low,close,volume", "2017-03-03", "2017-04-01", "PriceAdj=B")
QA_util_log_info(data.ErrorCode)
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return data.Data
def QA_fetch_get_stock_day_simple(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if (QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
data = w.wsd(name, "sec_name,preclose,open,high,low,close,volume",
startDate, endDate, "Fill=Previous;PriceAdj=F")
#data=w.wsd("000002.SZ", "open,high,low,close,volume", "2017-03-03", "2017-04-01", "PriceAdj=B")
QA_util_log_info(data.ErrorCode)
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return data.Data
def get_wind_nev(windid, fre="日"):
"""
获取wind基金数据
"""
date = w.wss(windid, "fund_setupdate,NAV_date").Data
start_date = date[0][0].strftime('%Y-%m-%d')
end_date = date[1][0].strftime('%Y-%m-%d')
fund_name = w.wss(windid, "name_official").Data[0]
if fre == "周":
para = "Period=W;Fill=Previous"
else:
para = "Period=D;Fill=Previous"
data = w.wsd(windid, "NAV_adj", start_date, end_date, para)
df = pd.DataFrame(data.Data[0], index=data.Times, columns=fund_name)
df.index = pd.to_datetime(df.index)
return df
def QA_fetch_get_stock_risk(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if(QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
data = w.wsd(name, "annualyeild_100w,annualyeild_24m,annualyeild_60m,\
annualstdevr_100w,annualstdevr_24m,annualstdevr_60m,beta_100w,\
beta_24m,beta_60m,avgreturn,avgreturny,stdevry,stdcof,\
risk_nonsysrisk1,r2,alpha2,beta,sharpe,treynor,jensen,jenseny,betadf",
startDate, endDate, "period=2;returnType=1;index=000001.SH;yield=1")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T, columns=data.Fields, index=data.Times)
def ExponentScale(fundid=None, begintime='2010-01-01', endtime=date.today()):
if(fundid == None):
fundid = FundID()
param = (fundid, 'prt_totalasset', begintime, endtime, 'Period=Q', 'Fill=Previous')
data = w.wsd(*param)
Value = []
for i in range(0, len(data.Codes)):
for j in range(0, len(data.Data[0])):
stockvalue = data.Data[i][j]
print(stockvalue)
if(stockvalue is None or isnan(stockvalue)):
stockvalue = 0.0
record = (data.Codes[i], data.Times[j].strftime("%Y-%m-%d"), stockvalue)
print(record)
Value.append(record)
return Value
def getDayData(self,stockCodeList,fields,startDate,endDate,option):
'''日数据的具体的获取步骤'''
for stockCode in stockCodeList:
print '添加日数据,代碼%s' % stockCode
wsd_data = w.wsd(stockCode,fields,startDate,endDate,option)
if wsd_data.ErrorCode==0: # 返回成功
stockDate = wsd_data.Times
dateList = [date.strftime("%Y-%m-%d") for date in stockDate]
stockDataDict = {'stockCode':stockCode,'date':dateList}
for i in range(len(fields)):
stockDataDict[fields[i]] = wsd_data.Data[i]
stockData = pd.DataFrame(stockDataDict,columns=['stockCode','date']+fields,index=dateList).dropna() # 只要有缺失的数据就删掉这一行，保证数据最为干净
stockData['pct_chg'] = stockData['pct_chg'] / 100 # 让涨幅变为实际涨幅（查询出来的是百分比数据）
# 插入到數據庫中
sql = "insert ignore into stockdata_day values(" + "%s,"*(len(fields)+1)+"%s)"
self.cur.executemany(sql,tuple(stockData.values.tolist()))
self.con.commit()
else:
logging.info('ERROR-%s-day數據下載失敗，錯誤代碼為：%s' % (stockCode,wsd_data.ErrorCode))
def func6():
yesterday = (datetime.datetime.now() - datetime.timedelta(days = 1)).strftime("%Y-%m-%d")
df_closeB=pd.read_csv('closeB.csv')
last_date_closeB = time.strftime("%Y-%m-%d",time.strptime(str(int(df_closeB.iloc[-1,0])),"%Y%m%d"))
day_gap_closeB = w.tdayscount(last_date_closeB, yesterday).Data[0][0]-1
print 6
w_wsd_data={}
stock_ls=[]
for stock in universe:
if stock =='150073':
stock='150075.SZ'
else:
if stock[0]=='1':
stock = str(int(stock[:6])+1) + '.SZ'
else:
stock = str(int(stock[:6])+1) + '.SH'
stock_ls.append(stock)
w_wsd_data[stock] = w.wsd(stock, 'close', (w.tdaysoffset(1,last_date_closeB).Data[0][0]).strftime("%Y-%m-%d"),yesterday)
# print 1
print stock
#if w_wsd_data[stock].Data[0][0]==None:
for i in xrange(day_gap_closeB):
this_day = w.tdaysoffset(i+1,last_date_closeB)
ls = []
this_day_csv = (this_day.Data[0][0]).strftime("%Y%m%d")
for stock in stock_ls:
ls.append(w_wsd_data[stock].Data[0][i])
f=open('closeB.csv','a')
f.write(this_day_csv)
for stock_data in ls:
f.write(",")
f.write(str(stock_data))
f.write("\n")
f.close()
print 'finish'
def QA_fetch_get_stock_info(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
# get the all stock list on the endDate
# judge the vaild date
if(QA_util_date_valid(endDate) is False):
QA_util_log_info("wrong date")
else:
# tempStr='date='+endDate+";sectorid=a001010100000000"
# data=w.wset("sectorconstituent",tempStr)
data = w.wsd(name, "sec_name,sec_englishname,ipo_date,exch_city,mkt,\
sec_status,delist_date,issuecurrencycode,curr,RO,parvalue,\
lotsize,tunit,exch_eng,country,concept,marginornot,SHSC,\
parallelcode,sec_type,backdoor,backdoordate,windtype",
startDate, endDate)
# QA_util_log_info(data)
if (data.ErrorCode != 0):
QA_util_log_info("Connent to Wind successfully")
return data.Data
def totalAmount(codes, baseDate='20160706', backwardDays=0):
tradeTotal = 0
baseDate = baseDate
backDays = backwardDays
backwardDays = 'ED-' + str(backwardDays) + "TD"
for code in codes:
data = w.wsd(code, "open,high,low,close,volume,oi,pct_chg", backwardDays,
baseDate)
dt = data.Data
for i in range(backDays + 1):
date = data.Times[i]
o = dt[0][i]
h = dt[1][i]
l = dt[2][i]
c = dt[3][i]
v = dt[4][i]
# pchg=data[5][0]
avg = (o + h + l + c) / 4
tradeAmount = v * avg * float(TRADEUNIT[code])
print(str(date.strftime("%Y-%m-%d")) + ":" +
code + "的名义成交金额为:", tradeAmount / 10000)
tradeTotal += tradeAmount
return '名义成交量：' + str(tradeTotal / 10000) + "（万元）"
def QA_fetch_get_stock_indicator(name, startDate, endDate):
try:
from WindPy import w
except:
QA_util_log_info('No WindPY Module!')
w.start()
if(QA_util_date_valid(endDate) == False):
QA_util_log_info("wrong date")
else:
# ADTM动态买卖气指标,ATR真实波幅,BBI多空指数,BBIBOLL多空布林线,BIAS乖离率,BOLL布林带,CCI顺势指标,CDP逆势操作,DMA平均线差,
# DMI趋向标准,DPO区间震荡线,ENV,EXPMA指数平滑移动平均,KDJ随机指标,slowKD慢速kd,MA简单移动平均,MACD指数平滑移动平均,MIKE麦克指数,
# MTM动力指标,PRICEOSC价格震荡指标,PVT量价趋势指标,RC变化率指数,ROC变动速率,RSI相对强弱指标,SAR抛物转向,SI摆动指标,SOBV能量潮,
# SRMI MI修正指标,STD 标准差,TAPI 加权指数成交值,TRIX 三重指数平滑平均,VHF纵横指标,VMA量简单移动平均,VMACD量指数平滑移动平均,
# VOSC成交量震荡,WVAD威廉变异离散量,vol_ratio量比
data = w.wsd(name, "ADTM,ATR,BBI,BBIBOLL,BIAS,BOLL,CCI,CDP,\
DMA,DMI,DPO,ENV,EXPMA,KDJ,slowKD,MA,MACD,\
MIKE,MTM,PRICEOSC,PVT,RC,ROC,RSI,SAR,SI,\
SOBV,SRMI,STD,TAPI,TRIX,VHF,VMA,VMACD,VOSC,\
WVAD,vol_ratio", startDate, endDate,
"ADTM_N1=23;ADTM_N2=8;ADTM_IO=1;ATR_N=14;ATR_IO=1;\
BBI_N1=3;BBI_N2=6;BBI_N3=12;BBI_N4=24;BBIBOLL_N=10;\
BBIBOLL_Width=3;BBIBOLL_IO=1;BIAS_N=12;BOLL_N=26;\
BOLL_Width=2;BOLL_IO=1;CCI_N=14;CDP_IO=1;DMA_S=10;\
DMA_L=50;DMA_N=10;DMA_IO=1;DMI_N=14;DMI_N1=6;\
DMI_IO=1;DPO_N=20;DPO_M=6;DPO_IO=1;ENV_N=14;ENV_IO=1;\
EXPMA_N=12;KDJ_N=9;KDJ_M1=3;KDJ_M2=3;KDJ_IO=1;SlowKD_N1=9;\
SlowKD_N2=3;SlowKD_N3=3;SlowKD_N4=5;SlowKD_IO=1;MA_N=5;\
MACD_L=26;MACD_S=12;MACD_N=9;MACD_IO=1;MIKE_N=12;MIKE_IO=1;\
MTM_interDay=6;MTM_N=6;MTM_IO=1;PRICEOSC_L=26;PRICEOSC_S=12;\
RC_N=50;ROC_interDay=12;ROC_N=6;ROC_IO=1;RSI_N=6;SAR_N=4;\
SAR_SP=2;SAR_MP=20;SRMI_N=9;STD_N=26;TAPI_N=6;TAPI_IO=1;\
TRIX_N1=12;TRIX_N2=20;TRIX_IO=1;VHF_N=28;VMA_N=5;VMACD_S=12;\
VMACD_L=26;VMACD_N=9;VMACD_IO=1;VOSC_S=12;VOSC_L=26;WVAD_N1=24;\
WVAD_N2=6;WVAD_IO=1;VolumeRatio_N=5")
if (data.ErrorCode == 0):
QA_util_log_info("Connent to Wind successfully")
return pd.DataFrame(np.asarray(data.Data).T, columns=data.Fields, index=data.Times)
from WindPy import w
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model
import cPickle
w.start();
wsd_data=w.wsd("000300.SH", "amt,turn,pct_chg,pe_ttm,pb,roe,yoy_tr,yoy_or,yoyprofit,close", "2005-10-01", "2016-07-31", "Period=M;Days=Alldays;PriceAdj=F")
time=wsd_data.Times
amt=wsd_data.Data[0]
turn=wsd_data.Data[1]
pct_chg=wsd_data.Data[2]
pe_ttm=wsd_data.Data[3]
# pb=wsd_data.Data[4]
# roe=wsd_data.Data[5]
# yoy_tr=wsd_data.Data[6]
# yoy_or=wsd_data.Data[7]
# yoyprofit=wsd_data.Data[8]
close=wsd_data.Data[9]
nrows=len(time)
lable=0
# generate train data
train_data=[]
train_lable=[]
for i in range(3,nrows-1):
start=close[i-2]
end=close[i+1]
gain=(float(end)/start)**(float(1)/3)
def printpy(outdata):
if outdata.ErrorCode != 0:
print('error code:' + str(outdata.ErrorCode) + '\n');
return ();
for i in range(0, len(outdata.Data[0])):
strTemp = ''
if len(outdata.Times) > 1:
strTemp = str(outdata.Times[i]) + ' '
for k in range(0, len(outdata.Fields)):
strTemp = strTemp + str(outdata.Data[k][i]) + ' '
print(strTemp)
# 通过wsd来提取时间序列数据，比如取开高低收成交量，成交额数据
print('\n\n' + '-----通过wsd来提取时间序列数据，比如取开高低收成交量，成交额数据-----' + '\n')
wsddata1 = w.wsd("000001.SZ", "open,high,low,close,volume,amt", "2015-11-22", "2015-12-22",
"Fill=Previous")
printpy(wsddata1)
# 通过wsd来提取各个报告期财务数据
print('\n\n' + '-----通过wsd来提取各个报告期财务数据-----' + '\n')
wsddata2 = w.wsd("600000.SH", "tot_oper_rev,tot_oper_cost,opprofit,net_profit_is", "2008-01-01",
"2015-12-22", "rptType=1;Period=Q;Days=Alldays;Fill=Previous")
printpy(wsddata2)
# 通过wss来取截面数据
print('\n\n' + '-----通过wss来取截面数据-----' + '\n')
wssdata = w.wss("600000.SH,600007.SH,600016.SH", "ev,total_shares",
"tradeDate=20151222;industryType=1")
printpy(wssdata)
# 通过wst来取日内成交数据
def get_min_data(filename):
file_folder = 'C:\\dev\\src\\ktlib\\data3\\'
reader = csv.reader(file(filename, 'rb'))
contList = []
fields = 'open,close,high,low,volume,oi'
contStart = []
contEnd = []
for line in reader:
contList.append(line[0])
contStart.append(line[1])
contEnd.append(line[2])
#w.start()
for cont, startD, endD in zip(contList, contStart, contEnd):
if cont[1].isalpha(): key = cont[:2]
else: key = cont[:1]
ex = 'SH'
for exch in product_code.keys():
if key in product_code[exch]:
ex = exch
ticker = cont + '.' + ex
startmin = ""
endMin = ""
if ex == 'CFE':
startMin = " 09:14:00"
endMin = " 15:15:00"
else:
startMin = " 08:59:00"
endMin = " 15:00:00"
if ex == 'CFE':
startMin = " 09:14:00"
endMin = " 15:15:00"
else:
startMin = " 08:59:00"
endMin = " 15:00:00"
try:
sdate = datetime.datetime.strptime(startD, "%Y/%m/%d")
edate = datetime.datetime.strptime(endD, "%Y/%m/%d")
sMin = datetime.datetime.strptime(startD + startMin, "%Y/%m/%d %H:%M:%S")
eMin = datetime.datetime.strptime(endD + endMin, "%Y/%m/%d %H:%M:%S")
print ticker, sMin, eMin
if edate > datetime.date(2009,1,1):
raw_data = w.wsi(ticker,fields,sMin,eMin)
if len(raw_data.Data)>1:
outfile = file_folder + cont+'_min.csv'
output={'datetime':raw_data.Times,
'open':raw_data.Data[0],
'close':raw_data.Data[1],
'high':raw_data.Data[2],
'low':raw_data.Data[3],
'volume':raw_data.Data[4],
'openInterest':raw_data.Data[5]}
dump2csvfile(output,outfile)
else:
print "no min data obtained for ticker=%s" % ticker
raw_data = w.wsd(ticker,fields,sdate,edate)
if len(raw_data.Data)>1:
outfile = file_folder + cont+'_daily.csv'
output={'datetime':raw_data.Times,
'open':raw_data.Data[0],
'close':raw_data.Data[1],
'high':raw_data.Data[2],
'low':raw_data.Data[3],
'volume':raw_data.Data[4],
'openInterest':raw_data.Data[5]}
dump2csvfile(output,outfile)
else:
print "no daily data obtained for ticker=%s" % ticker
except ValueError:
pass
w.stop()
return True
PRIMARY KEY (secid,tradedate)
)
""")
sql = "INSERT OR REPLACE INTO stockprice VALUES (?, ?, ?, ?, ?, ?, ?, ?)"
# 通过wset来取数据集数据
print('\n\n'+'-----通过wset来取数据集数据,获取全部A股代码列表-----'+'\n')
wsetdata=w.wset('SectorConstituent','date=20160625;sectorId=a001010100000000;field=wind_code')
print(wsetdata)
for j in range(0,len(wsetdata.Data[0])):
# 通过wsd来提取时间序列数据，比如取开高低收成交量，成交额数据
print( u"\n\n-----第 %i 次通过wsd来提取 %s 开高低收成交量数据-----\n" %(j,str(wsetdata.Data[0][j])) )
wssdata=w.wss(str(wsetdata.Data[0][j]),'ipo_date')
wsddata1=w.wsd(str(wsetdata.Data[0][j]), "open,high,low,close,volume,amt", wssdata.Data[0][0], dt, "Fill=Previous")
if wsddata1.ErrorCode!=0:
continue
print (wsddata1)
for i in range(0,len(wsddata1.Data[0])):
sqllist=[]
sqltuple=()
sqllist.append(str(wsetdata.Data[0][j]))
if len(wsddata1.Times)>1:
sqllist.append(wsddata1.Times[i].strftime('%Y%m%d'))
for k in range(0, len(wsddata1.Fields)):
sqllist.append(wsddata1.Data[k][i])
sqltuple=tuple(sqllist)
cursor.execute(sql,sqltuple)
conn.commit()
conn.close()
# personal version allows 600000-600120
stockStartIndex=600000
for j in range(0,100):
stockIndex=stockStartIndex+j
print ("j="+str(j))
stock=str(stockIndex)+".sh"
oneday=datetime.timedelta(days=1)
totaldays=datetime.timedelta(days=numdays)
dateEnd=datetime.date.today()
dateStr=dateEnd-totaldays
strdateStr=str(dateStr).replace("-","").split(" ")[0]
strdateEnd=str(dateEnd).replace("-","").split(" ")[0]
d=w.wsd(stock,"sec_englishname,open,high,low,close,volume",strdateStr,strdateEnd,"Priceadj=f;tradingcalendar=nib")
print (d.Data)
stockname=stock
#data of each requested entry between the requested dates
#will be returned into its own array
# in this case i asked for 6 kinds of entries
arrSec_Name=d.Data[0]
arrOpen=d.Data[1]
arrHigh=d.Data[2]
arrLow=d.Data[3]
arrClose=d.Data[4]
arrVolume=d.Data[5]
data = []
if len(outdata.Times) > 1:
data.append(str(outdata.Times[i]))
for k in range(0, len(outdata.Fields)):
data.append(str(outdata.Data[k][i]))
x.add_row(data)
print(x)
if __name__ == '__main__':
stock = '600000.SH' # 浦发银行
now = datetime.now()
w.start()
print('\n' + '获取过去三个季度总股本')
wsddata = w.wsd(stock, "total_shares", "ED-3Q", now, "Period=Q;Fill=Previous")
printinfo(wsddata)
print('\n' + '获取过去三个季度自由流通股本')
wsddata = w.wsd(stock, "free_float_shares", "ED-3Q", now, "Period=Q;Fill=Previous")
printinfo(wsddata)
print('\n' + '获取过去三个季度股东户数')
wsddata = w.wsd(stock, "holder_num", "ED-3Q", now, "Period=Q;Fill=Previous")
printinfo(wsddata)
print('\n' + '获取过去三个季度户均持股数量（流通股本）')
wsddata = w.wsd(stock, "holder_avgnum", "ED-3Q", now, "shareType=1;Period=Q;Fill=Previous")
printinfo(wsddata)
print('\n' + '获取过去三个季度户均持股数量（总股本）')
'''
Created on 2016年4月9日
@author: caiwx
'''
#!/usr/bin/env python3
# -*- coding:utf-8 -*-
from WindPy import w
import datetime
import pandas as pd
w.start();
# 取数据的命令如何写可以用命令生成器来辅助完成
wsd_data=w.wsd("000001.SZ", "open,high,low,close", "2015-12-10", "2015-12-22", "Fill=Previous")
#演示如何将api返回的数据装入Pandas的Series
open=pd.Series(wsd_data.Data[0])
high=pd.Series(wsd_data.Data[1])
low=pd.Series(wsd_data.Data[2])
close=pd.Series(wsd_data.Data[3])
print('open:/n',open)
print('high:/n',high)
print('low:/n',low)
print('close:/n',close)
#演示如何将api返回的数据装入Pandas的DataFrame
fm=pd.DataFrame(wsd_data.Data,index=wsd_data.Fields,columns=wsd_data.Times)
fm=fm.T #将矩阵转置
print('fm:/n',fm)
reload(sys)
sys.setdefaultencoding( "utf-8" )
from WindPy import w
from Utility import str1D
from Utility import str2D
if (w.isconnected() != True):
w.start(); #pwd:607387
stock_code = sys.argv[1]
start_date = sys.argv[2]
end_date = sys.argv[3]
# res= w.wset("TradeSuspend","startdate=20150122;enddate=20150122")
fields = "sec_name,trade_status,susp_reason"
res = w.wsd(stock_code, fields, start_date, end_date, "Fill=Previous")
#1.List getStocks
print "WindStockReuslt:"
print res
print "\n.Codes="+str1D(res.Codes)
print "\n.Fields="+str1D(res.Fields)
print "\n.Times="+str1D([ format(x,'%Y%m%d %H:%M:%S') for x in res.Times])
print "\n.Data="+str2D(res.Data)