def analysicQuantDataOnly(start: datetime, end: datetime):
souces = ZZ500DataSource(start, end)
model = KDJMovementEngineModel()
create = False
engine = None
if create:
engine = CoreEngine.create(dirName,
model,
souces,
build_quant_data_only=True,
min_size=200)
else:
engine = CoreEngine.load(dirName, model)
engine.buildPredictModel(useSVM=False)
pass
def generatePredictOrder(self, engine: CoreEngine, predict: PredictData,debugPrams:{}=None) -> PredictOrder:
if debugPrams is None:
debugPrams = {}
quantData = engine.queryQuantData(predict.dimen)
code = predict.collectData.occurBars[-1].symbol
name = self.sw.getSw2Name(code)
order = PredictOrder(dimen=predict.dimen, code=code, name=name)
start_price = engine.getEngineModel().getYBasePrice(predict.collectData)
_min, _max = quantData.getSellFloatEncoder().parseEncode(quantData.sellRange[0].encode)
order.suggestSellPrice = start_price * (1 + (_min + _max) / 2 / 100)
_min, _max = quantData.getBuyFloatEncoder().parseEncode(quantData.buyRange[0].encode)
order.suggestBuyPrice = start_price * (1 + (_min + _max) / 2 / 100)
order.power_rate = quantData.getPowerRate();
##for backTest
self.checkIfBuyPrice(order,predict.collectData.occurBars[-1].close_price,debugPrams)
return order
def generatePredictOrder(self, engine: CoreEngine, predict: PredictData,debugPrams:{}=None) -> PredictOrder:
if debugPrams is None:
debugPrams = {}
code = predict.collectData.occurBars[-1].symbol
name = self.sw.getSw2Name(code)
order = PredictOrder(dimen=predict.dimen, code=code, name=name)
predict_sell_pct = predict.getPredictSellPct(engine.getEngineModel())
predict_buy_pct = predict.getPredictBuyPct(engine.getEngineModel())
start_price = engine.getEngineModel().getYBasePrice(predict.collectData)
order.suggestSellPrice = start_price * (1 + predict_sell_pct / 100)
order.suggestBuyPrice = start_price * (1 + predict_buy_pct / 100)
order.power_rate = engine.queryQuantData(predict.dimen).getPowerRate()
##for backTest
occurBar: BarData = predict.collectData.occurBars[-2]
skipBar: BarData = predict.collectData.occurBars[-1]
buy_price = skipBar.close_price
predict_sell_pct = 100 * (order.suggestSellPrice - start_price) / start_price
predict_buy_pct = 100 * (order.suggestBuyPrice - start_price) / start_price
buy_point_pct = 100 * (buy_price - occurBar.close_price) / occurBar.close_price ##买入的价格
abilityData = engine.queryPredictAbilityData(predict.dimen)
quantData = engine.queryQuantData(predict.dimen)
delta = abs(quantData.sellCenterPct) - abs(quantData.buyCenterPct)
if abs(delta) < 0.05:
# 多空力量差不多
power = 0
if delta > 0:
# 适合做多
power= (quantData.sellCenterPct + quantData.buyCenterPct) / quantData.sellCenterPct
else:
power = - (quantData.sellCenterPct + quantData.buyCenterPct) / quantData.buyCenterPct
extraCondition = True
quant_power = debugPrams.get("quant_power")
if not quant_power is None:
extraCondition = extraCondition and predict.quantData.getPowerRate() >= quant_power
predict_buy_pct_param = debugPrams.get("predict_buy_pct")
if not predict_buy_pct_param is None:
extraCondition = extraCondition and predict_buy_pct >= predict_buy_pct_param
if extraCondition and predict_sell_pct - buy_point_pct > 1 \
and abilityData.trainData.biasSellLoss < 10:
order.status = PredictOrderStatus.HOLD
order.buyPrice = buy_price
else:
order.status = PredictOrderStatus.STOP
return order
def build(self, engine: CoreEngine, sampleData: Sequence['CollectData'],
quantData: QuantData):
start = timeit.default_timer()
self.quantData = quantData
trainDataList = engine.getEngineModel().generateSampleData(
engine, sampleData)
size = len(trainDataList)
engine.printLog(
f"build PredictModel:dime={self.dimen}, sample size:{size} use SVM ={self.useSVM}",
True)
engine.printLog(f" history quantdata: {self.quantData}")
##建立特征值
x, y_sell_1, y_buy_1, y_sell_2, y_buy_2 = self.__generateFeature(
trainDataList)
self.labelListSell1 = np.sort(np.unique(y_sell_1))
self.labelListSell2 = np.sort(np.unique(y_sell_2))
self.labelListBuy1 = np.sort(np.unique(y_buy_1))
self.labelListBuy2 = np.sort(np.unique(y_buy_2))
engine.printLog(f" labelListSell1: {self.labelListSell1}")
engine.printLog(f" labelListSell2: {self.labelListSell2}")
engine.printLog(f" labelListBuy1: {self.labelListBuy1}")
engine.printLog(f" labelListBuy2: {self.labelListBuy2}")
self.classifierSell_1 = self.__createClassifier(x, y_sell_1)
self.classifierSell_2 = self.__createClassifier(x, y_sell_2)
self.classifierBuy_1 = self.__createClassifier(x, y_buy_1)
self.classifierBuy_2 = self.__createClassifier(x, y_buy_2)
elapsed = (timeit.default_timer() - start)
engine.printLog(
f"build PredictModel finished! elapsed = %.3fs" % (elapsed), True)
pass
return x
def percent_to_one(x):
return int(x * 100) / 1000.0
data = []
data.append(percent_to_one(buy_pct))
data.append(percent_to_one(sell_pct))
data.append(set_0_between_100(kdj[0]) / 100)
data.append(set_0_between_100(kdj[2]) / 100)
return data
if __name__ == "__main__":
dirName = "models/sw_sample_model_analysis"
trainDataSouce = SWDataSource(start=datetime(2014, 2, 1),
end=datetime(2019, 9, 1))
testDataSouce = SWDataSource(datetime(2019, 9, 1), datetime(2020, 9, 1))
model = EngineModel2KAlgo2()
#engine = CoreEngine.create(dirName,model,trainDataSouce,limit_dimen_size=99999999)
engine = CoreEngine.load(dirName, model)
runner = CoreEngineRunner(engine)
strategy = MyStrategy()
pdData = runner.backtest(testDataSouce, strategy, min_deal_count=15)
writer = pd.ExcelWriter('models\output.xlsx')
pdData.to_excel(writer, sheet_name="data", index=False)
writer.save()
writer.close()