def SampleCNN(ticker: str):
#Print sample CNN graphs of ticker, CNN will treat price data as picture and anticipate the next picture
plot = PlotHelper()
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory():
prices.NormalizePrices()
window_size = 80
target_size = 10
daysInTraining = 800
sampleData = prices.GetPriceHistory()
endDate = sampleData.index.max()
cuttoffDate = endDate - BDay(window_size)
startDate = cuttoffDate - BDay(daysInTraining)
print(dataFolder + 'samples\CNNsampleLearning', startDate, cuttoffDate,
endDate)
for i in range(0, 10):
ii = i * window_size
d1 = startDate + BDay(ii)
d2 = d1 + BDay(target_size)
print(d1, d2, window_size, target_size)
plot.PlotDataFrameDateRange(
sampleData[['Average']], d1, window_size,
'Sample image ' + str(i), 'Date', 'Price',
dataFolder + 'samples/CNN' + str(i) + 'Sample')
plot.PlotDataFrameDateRange(
sampleData[['Average']], d2, target_size,
'Target image ' + str(i), 'Date', 'Price',
dataFolder + 'samples/CNN' + str(i) + 'Target')
def DownloadAndGraphStocks(tickerList: list):
for ticker in tickerList:
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory(True):
print('Calcualting stats ' + ticker)
prices.NormalizePrices()
prices.CalculateStats()
prices.PredictPrices(2, 15)
prices.NormalizePrices()
prices.SaveStatsToFile(True)
psnap = prices.GetCurrentPriceSnapshot()
titleStatistics = ' 5/15 dev: ' + str(
round(psnap.fiveDayDeviation * 100, 2)) + '/' + str(
round(psnap.fifteenDayDeviation * 100, 2)) + '% ' + str(
psnap.low) + '/' + str(
psnap.nextDayTarget) + '/' + str(
psnap.high) + ' ' + str(
psnap.snapshotDate)[:10]
print('Graphing ' + ticker + ' ' + str(psnap.snapshotDate)[:10])
for days in [90, 180, 365, 2190, 4380]:
prices.GraphData(None,
days,
ticker + '_days' + str(days) + ' ' +
titleStatistics, (days < 1000),
True,
str(days).rjust(4, '0') + 'd',
trimHistoricalPredictions=False)
def DownloadAndSaveStocksWithStats(tickerList: list):
for ticker in tickerList:
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory(requestedEndDate=GetTodaysDate()):
print('Calcualting stats ' + ticker)
prices.CalculateStats()
prices.SaveStatsToFile(includePredictions=False, verbose=True)
def RunPredictions(ticker: str = '^SPX', numberOfLearningPasses: int = 750):
prices = PricingData(ticker)
CreateFolder(dataFolder)
print('Loading ' + ticker)
if prices.LoadHistory():
prices.TrimToDateRange('1/1/1950', '3/1/2018')
prices.NormalizePrices()
for ii in [4, 20, 60]:
for i in range(0, 3):
PredictPrices(prices, i, ii, numberOfLearningPasses)
def RunPredictions(ticker: str = '^SPX', numberOfLearningPasses: int = 750):
#Runs three prediction models (Linear, LSTM, CCN) predicting a target price 4, 20, and 60 days in the future.
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory():
prices.TrimToDateRange('1/1/1950', '3/1/2018')
prices.NormalizePrices()
for ii in [4, 20, 60]:
for i in range(0, 3):
PredictPrices(prices, i, ii, numberOfLearningPasses)
def DownloadAndGraphStocks(tickerList: list):
for ticker in tickerList:
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory(requestedEndDate=GetTodaysDate()):
print('Calcualting stats ' + ticker)
prices.NormalizePrices()
prices.CalculateStats()
prices.PredictPrices(2, 15)
prices.NormalizePrices()
#prices.SaveStatsToFile(includePredictions=True, verbose=True)
psnap = prices.GetCurrentPriceSnapshot()
titleStatistics = ' 5/15 dev: ' + str(
round(psnap.fiveDayDeviation * 100, 2)) + '/' + str(
round(psnap.fifteenDayDeviation * 100, 2)) + '% ' + str(
psnap.low) + '/' + str(
psnap.nextDayTarget) + '/' + str(
psnap.high) + ' ' + str(
psnap.snapShotDate)[:10]
print('Graphing ' + ticker + ' ' + str(psnap.snapShotDate)[:10])
for days in [90, 180, 365, 2190, 4380]:
prices.GraphData(endDate=None,
daysToGraph=days,
graphTitle=ticker + '_days' + str(days) +
' ' + titleStatistics,
includePredictions=(days < 1000),
saveToFile=True,
fileNameSuffix=str(days).rjust(4, '0') + 'd',
trimHistoricalPredictions=False)
def SampleGraphs(ticker:str, daysInGraph:int):
plot = PlotHelper()
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory(True):
prices.NormalizePrices()
sampleData = prices.GetPriceHistory()
d = sampleData.index[-1]
for i in range(0,200, 10): #Add new days to the end for crystal ball predictions
sampleDate = d - BDay(i) #pick business day to plot
plot.PlotDataFrameDateRange(sampleData[['Open','High', 'Low','Close']], sampleDate, daysInGraph, 'Sample window ' + str(daysInGraph), 'Date', 'Price', dataFolder + 'samples/sample' + str(i) + '_' + str(daysInGraph))
def GraphTimePeriod(ticker: str, endDate: str, days: int):
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory():
prices.GraphData(endDate=endDate,
daysToGraph=days,
graphTitle=None,
includePredictions=False,
saveToFile=True,
fileNameSuffix=None)
print('Chart saved to \data\charts')
def SampleLSTM(ticker:str):
plot = PlotHelper()
prices = PricingData(ticker)
print('Loading ' + ticker)
CreateFolder(dataFolder + 'samples')
if prices.LoadHistory(True):
prices.NormalizePrices()
daysInTarget = 15
daysInTraining = 200
sampleData = prices.GetPriceHistory()
endDate = sampleData.index.max()
cuttoffDate = endDate - BDay(daysInTarget)
startDate = cuttoffDate - BDay(daysInTraining)
print(dataFolder + 'samples/LSTMsampleLearning', startDate, cuttoffDate, endDate)
plot.PlotDataFrameDateRange(sampleData[['Average']], cuttoffDate, daysInTraining, 'Learn from this series of days', 'Date', 'Price', dataFolder + 'samples/LSTMLearning')
plot.PlotDataFrameDateRange(sampleData[['Average']], endDate, daysInTarget, 'Predict what happens after this series of days', 'Date', 'Price', dataFolder + 'samples/LSTMTarget')
def PlotAnnualPerformance(ticker: str = '^SPX'):
print('Annual performance rate for ' + ticker)
prices = PricingData(ticker)
if prices.LoadHistory(True):
x = prices.GetPriceHistory(['Average'])
yearly = x.groupby([(x.index.year)]).first()
yearlyChange = yearly.pct_change(1)
monthly = x.groupby([(x.index.year), (x.index.month)]).first()
plot = PlotHelper()
plot.PlotDataFrame(yearly, title='Yearly', adjustScale=False)
plot.PlotDataFrame(monthly, title='Monthly', adjustScale=False)
plot.PlotDataFrame(yearlyChange,
title='Yearly Percentage Change',
adjustScale=False)
print('Average annual change from ', prices.historyStartDate, ' to ',
prices.historyEndDate, ': ',
yearlyChange.mean().values * 100, '%')
def CalculatePriceCorrelation(tickerList: list):
datafileName = 'data/_priceCorrelations.csv'
summaryfileName = 'data/_priceCorrelationTop10.txt'
result = pandas.DataFrame()
startDate = str(datetime.datetime.now().date() +
datetime.timedelta(days=-365))
endDate = str(datetime.datetime.now().date())
for ticker in tickerList:
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory(True):
prices.TrimToDateRange(startDate, endDate)
prices.NormalizePrices()
result[ticker] = prices.GetPriceHistory(['Average'])
result = result.corr()
result.to_csv(datafileName)
f = open(summaryfileName, 'w')
for ticker in tickerList:
topTen = result.nsmallest(10, ticker)
print(topTen[ticker])
f.write(ticker + '\n')
f.write(topTen[ticker].to_string(header=True, index=True) + '\n')
f.write('\n')
f.close()
def CalculatePriceCorrelation(tickerList: list):
datafileName = 'data/_priceCorrelations.csv'
summaryfileName = 'data/_priceCorrelationTop10.txt'
result = None
startDate = str(datetime.datetime.now().date() +
datetime.timedelta(days=-365))
endDate = str(datetime.datetime.now().date())
for ticker in tickerList:
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory():
prices.TrimToDateRange(startDate, endDate)
prices.NormalizePrices()
x = prices.GetPriceHistory(['Average'])
x.rename(index=str, columns={"Average": ticker}, inplace=True)
if result is None:
result = x
else:
result = result.join(x, how='outer')
result = result.corr()
result.to_csv(datafileName)
f = open(summaryfileName, 'w')
for ticker in tickerList:
topTen = result.nsmallest(10, ticker)
print(topTen[ticker])
f.write(ticker + '\n')
f.write(topTen[ticker].to_string(header=True, index=True) + '\n')
f.write('\n')
f.close()
def CalculatePriceCorrelation(tickerList: list):
datafileName = 'data/_priceCorrelations.csv'
summaryfileName = 'data/_priceCorrelationTop10.txt'
result = None
startDate = str(AddDays(GetTodaysDate(), -365))
endDate = str(GetTodaysDate())
for ticker in tickerList:
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory(requestedEndDate=GetTodaysDate()):
prices.TrimToDateRange(startDate, endDate)
prices.NormalizePrices()
x = prices.GetPriceHistory(['Average'])
x.rename(index=str, columns={"Average": ticker}, inplace=True)
if result is None:
result = x
else:
result = result.join(x, how='outer')
result = result.corr()
result.to_csv(datafileName)
f = open(summaryfileName, 'w')
for ticker in tickerList:
topTen = result.nsmallest(10, ticker)
print(topTen[ticker])
f.write(ticker + '\n')
f.write(topTen[ticker].to_string(header=True, index=True) + '\n')
f.write('\n')
f.close()
print(
'Intended to create stability, in practice, this is a great way to pair well performing stocks with poor performing or volatile stocks.'
)
def PlotPrediction(ticker: str = '^SPX',
predictionMethod: int = 0,
daysToGraph: int = 60,
daysForward: int = 5,
learnhingEpochs: int = 500):
print('Plotting predictions for ' + ticker)
prices = PricingData(ticker)
if prices.LoadHistory(True):
prices.NormalizePrices()
prices.PredictPrices(predictionMethod, daysForward, learnhingEpochs)
prices.NormalizePrices()
prices.GraphData(None, daysToGraph,
ticker + ' ' + str(daysToGraph) + 'days', True, True,
str(daysToGraph) + 'days')
prices.SaveStatsToFile(True)
def PredictPrices(prices:PricingData, predictionMethod:int=0, daysForward:int = 4, numberOfLearningPasses:int = 500):
#Simple procedure to test different prediction methods
assert(0 <= predictionMethod <= 2)
plot = PlotHelper()
if predictionMethod ==0: #Linear projection
print('Running Linear Projection model predicting ' + str(daysForward) + ' days...')
modelDescription = prices.stockTicker + '_Linear_daysforward' + str(daysForward)
predDF = prices.GetPriceHistory()
predDF['Average'] = (predDF['Open'] + predDF['High'] + predDF['Low'] + predDF['Close'])/4
d = predDF.index[-1]
for i in range(0,daysForward): #Add new days to the end for crystal ball predictions
predDF.loc[d + BDay(i+1), 'Average_Predicted'] = 0
predDF['PastSlope'] = predDF['Average'].shift(daysForward) / predDF['Average'].shift(daysForward*2)
predDF['Average_Predicted'] = predDF['Average'].shift(daysForward) * predDF['PastSlope']
predDF['PercentageDeviation'] = abs((predDF['Average']-predDF['Average_Predicted'])/predDF['Average'])
else:
learningModule = StockPredictionNN()
SourceFieldList = ['High','Low','Open','Close']
if predictionMethod ==1: #LSTM learning
print('Running LSTM model predicting ' + str(daysForward) + ' days...')
window_size = 1
modelDescription = prices.stockTicker + '_LSTM' + '_epochs' + str(numberOfLearningPasses) + '_histwin' + str(window_size) + '_daysforward' + str(daysForward)
learningModule.LoadData(prices.GetPriceHistory(), window_size=window_size, prediction_target_days=daysForward, UseLSTM=True, SourceFieldList=SourceFieldList, batch_size=10, train_test_split=.93)
learningModule.TrainLSTM(epochs=numberOfLearningPasses, learning_rate=2e-5, dropout_rate=0.8, gradient_clip_margin=4)
elif predictionMethod ==2: #CNN Learning
print('Running CNN model predicting ' + str(daysForward) + ' days...')
window_size = 16 * daysForward
modelDescription = prices.stockTicker + '_CNN' + '_epochs' + str(numberOfLearningPasses) + '_histwin' + str(window_size) + '_daysforward' + str(daysForward)
learningModule.LoadData(prices.GetPriceHistory(), window_size=window_size, prediction_target_days=daysForward, UseLSTM=False, SourceFieldList=SourceFieldList, batch_size=32, train_test_split=.93)
learningModule.TrainCNN(epochs=numberOfLearningPasses)
predDF = learningModule.GetTrainingResults(True, True)
averageDeviation = predDF['PercentageDeviation'].tail(round(predDF.shape[0]/4)).mean() #Average of the last 25% to account for training.
print('Average deviation: ', averageDeviation * 100, '%')
predDF = predDF.reindex(sorted(predDF.columns), axis=1) #Sort columns alphabetical
predDF.to_csv(dataFolder + modelDescription + '.csv')
plot.PlotDataFrame(predDF[['Average','Average_Predicted']], modelDescription, 'Date', 'Price', True, 'experiment/' + modelDescription)
plot.PlotDataFrameDateRange(predDF[['Average','Average_Predicted']], None, 160, modelDescription + '_last160ays', 'Date', 'Price', dataFolder + modelDescription + '_last160Days')
plot.PlotDataFrameDateRange(predDF[['Average','Average_Predicted']], None, 1000, modelDescription + '_last1000ays', 'Date', 'Price', dataFolder + modelDescription + '_last1000Days')
def OpportunityFinder(tickerList: list):
outputFolder = 'data/dailypicks/'
summaryFile = '_summary.txt'
overBoughtList = []
oversoldList = []
highDeviationList = []
for root, dirs, files in os.walk(outputFolder):
for f in files:
if f.endswith('.txt') or f.endswith('.png'):
os.unlink(os.path.join(root, f))
for ticker in tickerList:
prices = PricingData(ticker)
print('Checking ' + ticker)
if prices.LoadHistory(True):
prices.CalculateStats()
psnap = prices.GetCurrentPriceSnapshot()
titleStatistics = ' 5/15 dev: ' + str(
round(psnap.fiveDayDeviation * 100, 2)) + '/' + str(
round(psnap.fifteenDayDeviation * 100, 2)) + '% ' + str(
psnap.low) + '/' + str(
psnap.nextDayTarget) + '/' + str(
psnap.high) + str(snapshotDate)
if psnap.low > psnap.channelHigh:
overBoughtList.append(ticker)
if psnap.high < psnap.channelLow:
oversoldList.append(ticker)
prices.GraphData(None, 60, ticker + ' 60d ' + titleStatistics,
False, True, '60d', outputFolder)
if psnap.fiveDayDeviation > .0275:
highDeviationList.append(ticker)
prices.GraphData(None, 60, ticker + ' 60d ' + titleStatistics,
False, True, '60d', outputFolder)
print('Over bought:')
print(overBoughtList)
print('Over sold:')
print(oversoldList)
print('High deviation:')
print(highDeviationList)
f = open(outputFolder + summaryFile, 'w')
f.write('Over bought:\n')
for t in overBoughtList:
f.write(t + '\n')
f.write('\nOver sold:\n')
for t in oversoldList:
f.write(t + '\n')
f.write('\nHigh deviation:\n')
for t in highDeviationList:
f.write(t + '\n')
f.close()
def TestPredictionModels(ticker: str = '^SPX',
numberOfLearningPasses: int = 300):
#Simple procedure to test different prediction methods 4,20,60 days in the future
plot = PlotHelper()
prices = PricingData(ticker)
if prices.LoadHistory():
prices.TrimToDateRange('1/1/2000', '3/1/2018')
print('Loading ' + ticker)
for daysForward in [4, 20, 60]:
for predictionMethod in range(0, 5):
modelDescription = ticker + '_method' + str(
predictionMethod) + '_epochs' + str(
numberOfLearningPasses) + '_daysforward' + str(
daysForward)
print('Predicting ' + str(daysForward) +
' days using method ' + modelDescription)
prices.PredictPrices(predictionMethod, daysForward,
numberOfLearningPasses)
predDF = prices.pricePredictions.copy()
predDF = predDF.join(prices.GetPriceHistory())
predDF['PercentageDeviation'] = abs(
(predDF['Average'] - predDF['estAverage']) /
predDF['Average'])
averageDeviation = predDF['PercentageDeviation'].tail(
round(predDF.shape[0] / 4)).mean(
) #Average of the last 25% to account for training.
print('Average deviation: ', averageDeviation * 100, '%')
predDF.to_csv(dataFolder + modelDescription + '.csv')
plot.PlotDataFrame(predDF[['estAverage', 'Average']],
modelDescription, 'Date', 'Price', True,
dataFolder + modelDescription)
plot.PlotDataFrameDateRange(
predDF[['Average', 'estAverage']], None, 160,
modelDescription + '_last160ays', 'Date', 'Price',
dataFolder + modelDescription + '_last160Days')
plot.PlotDataFrameDateRange(
predDF[['Average', 'estAverage']], None, 500,
modelDescription + '_last500Days', 'Date', 'Price',
dataFolder + modelDescription + '_last500Days')
def PredictPrices(prices: PricingData,
predictionMethod: int = 0,
daysForward: int = 5,
numberOfLearningPasses: int = 500):
#Procedure to execute a given prediction method: linear projection, LSTM, CNN
#Results are exported to the "experiment" sub folder, including a CSV file containing actual and predicted data, and graphs
assert (0 <= predictionMethod <= 2)
plot = PlotHelper()
if predictionMethod == 0: #Linear projection
print('Running Linear Projection model predicting ' +
str(daysForward) + ' days...')
modelDescription = prices.stockTicker + '_Linear_daysforward' + str(
daysForward)
predDF = prices.GetPriceHistory()
predDF['Average'] = (predDF['Open'] + predDF['High'] + predDF['Low'] +
predDF['Close']) / 4
d = predDF.index[-1]
for i in range(
0, daysForward
): #Add new days to the end for crystal ball predictions
predDF.loc[d + BDay(i + 1), 'Average_Predicted'] = 0
predDF['PastSlope'] = predDF['Average'].shift(
daysForward) / predDF['Average'].shift(daysForward * 2)
predDF['Average_Predicted'] = predDF['Average'].shift(
daysForward) * predDF['PastSlope']
predDF['PercentageDeviation'] = abs(
(predDF['Average'] - predDF['Average_Predicted']) /
predDF['Average'])
else:
SourceFieldList = ['High', 'Low', 'Open', 'Close']
if predictionMethod == 1: #LSTM learning
print('Running LSTM model predicting ' + str(daysForward) +
' days...')
SourceFieldList = None
UseLSTM = True
window_size = 10
modelDescription = prices.stockTicker + '_LSTM' + '_epochs' + str(
numberOfLearningPasses) + '_histwin' + str(
window_size) + '_daysforward' + str(daysForward)
elif predictionMethod == 2: #CNN Learning
print('Running CNN model predicting ' + str(daysForward) +
' days...')
UseLSTM = False
window_size = 16 * daysForward
modelDescription = prices.stockTicker + '_CNN' + '_epochs' + str(
numberOfLearningPasses) + '_histwin' + str(
window_size) + '_daysforward' + str(daysForward)
learningModule = StockPredictionNN(baseModelName=prices.stockTicker,
UseLSTM=UseLSTM)
learningModule.LoadSource(prices.GetPriceHistory(),
FieldList=SourceFieldList,
window_size=window_size)
learningModule.LoadTarget(targetDF=None,
prediction_target_days=daysForward)
learningModule.MakeBatches(batch_size=32, train_test_split=.93)
learningModule.Train(epochs=numberOfLearningPasses)
learningModule.Predict(True)
predDF = learningModule.GetTrainingResults(True, True)
predDF['PercentageDeviation'] = abs(
(predDF['Average'] - predDF['Average_Predicted']) /
predDF['Average'])
averageDeviation = predDF['PercentageDeviation'].tail(
round(predDF.shape[0] /
4)).mean() #Average of the last 25% to account for training.
print('Average deviation: ', averageDeviation * 100, '%')
predDF = predDF.reindex(sorted(predDF.columns),
axis=1) #Sort columns alphabetical
predDF.to_csv(dataFolder + modelDescription + '.csv')
plot.PlotDataFrame(predDF[['Average',
'Average_Predicted']], modelDescription, 'Date',
'Price', True, 'experiment/' + modelDescription)
plot.PlotDataFrameDateRange(predDF[['Average', 'Average_Predicted']], None,
160, modelDescription + '_last160ays', 'Date',
'Price',
dataFolder + modelDescription + '_last160Days')
plot.PlotDataFrameDateRange(
predDF[['Average', 'Average_Predicted']], None, 1000,
modelDescription + '_last1000ays', 'Date', 'Price',
dataFolder + modelDescription + '_last1000Days')
def GraphTimePeriod(ticker: str, endDate: datetime, days: int):
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory():
prices.GraphData(endDate, days, None, False, True, None)
def OpportunityFinder(tickerList: list):
outputFolder = 'data/dailypicks/'
summaryFile = '_DailyPicks.csv'
candidates = pd.DataFrame(columns=list([
'Ticker', 'hp2Year', 'hp1Year', 'hp6mo', 'hp3mo', 'hp2mo', 'hp1mo',
'currentPrice', 'channelHigh', 'channelLow', 'shortEMA', 'longEMA',
'2yearPriceChange', '1yearPriceChange', '6moPriceChange',
'3moPriceChange', '2moPriceChange', '1moPriceChange', 'dailyGain',
'monthlyGain', 'monthlyLossStd', 'Comments'
]))
candidates.set_index(['Ticker'], inplace=True)
for root, dirs, files in os.walk(outputFolder):
for f in files:
if f.endswith('.png'): os.unlink(os.path.join(root, f))
for ticker in tickerList:
prices = PricingData(ticker)
currentDate = GetTodaysDate()
print('Checking ' + ticker)
if prices.LoadHistory(requestedEndDate=currentDate):
prices.CalculateStats()
psnap = prices.GetPriceSnapshot(AddDays(currentDate, -730))
hp2Year = psnap.fiveDayAverage
psnap = prices.GetPriceSnapshot(AddDays(currentDate, -365))
hp1Year = psnap.fiveDayAverage
psnap = prices.GetPriceSnapshot(AddDays(currentDate, -180))
hp6mo = psnap.fiveDayAverage
psnap = prices.GetPriceSnapshot(AddDays(currentDate, -90))
hp3mo = psnap.fiveDayAverage
psnap = prices.GetPriceSnapshot(AddDays(currentDate, -60))
hp2mo = psnap.fiveDayAverage
psnap = prices.GetPriceSnapshot(AddDays(currentDate, -30))
hp1mo = psnap.fiveDayAverage
psnap = prices.GetCurrentPriceSnapshot()
currentPrice = psnap.twoDayAverage
Comments = ''
if psnap.low > psnap.channelHigh:
Comments += 'OverBought; '
if psnap.high < psnap.channelLow:
Comments += 'OverSold; '
if psnap.fiveDayDeviation > .0275:
Comments += 'HighDeviation; '
if Comments != '':
titleStatistics = ' 5/15 dev: ' + str(
round(psnap.fiveDayDeviation * 100, 2)) + '/' + str(
round(psnap.fifteenDayDeviation * 100,
2)) + '% ' + str(psnap.low) + '/' + str(
psnap.nextDayTarget) + '/' + str(
psnap.high) + str(psnap.snapShotDate)
prices.GraphData(None, 60, ticker + ' 60d ' + titleStatistics,
False, True, '60d', outputFolder)
if (currentPrice > 0 and hp2Year > 0 and hp1Year > 0
and hp6mo > 0 and hp2mo > 0
and hp1mo > 0): #values were loaded
candidates.loc[ticker] = [
hp2Year, hp1Year, hp6mo, hp3mo, hp2mo, hp1mo,
currentPrice, psnap.channelHigh,
psnap.channelLow, psnap.shortEMA, psnap.longEMA,
(currentPrice / hp2Year) - 1,
(currentPrice / hp1Year) - 1,
(currentPrice / hp6mo) - 1, (currentPrice / hp3mo) - 1,
(currentPrice / hp2mo) - 1, (currentPrice / hp1mo) - 1,
psnap.dailyGain, psnap.monthlyGain,
psnap.monthlyLossStd, Comments
]
else:
print(ticker, currentPrice, hp2Year, hp1Year, hp6mo, hp2mo,
hp1mo)
print(candidates)
candidates.to_csv(outputFolder + summaryFile)
def TrainTickerRaw(ticker: str = '^SPX',
UseLSTM: bool = True,
prediction_target_days: int = 5,
epochs: int = 500,
usePercentages: bool = False,
hidden_layer_size: int = 512,
dropout: bool = True,
dropout_rate: float = 0.01,
learning_rate: float = 2e-5):
plot = PlotHelper()
prices = PricingData(ticker)
print('Loading ' + ticker)
if prices.LoadHistory(True):
prices.TrimToDateRange('1/1/2000', '3/1/2018')
if usePercentages:
prices.ConvertToPercentages(
) #Percentages don't work well I suspect because small errors have a huge impact when you revert back to the original prices and they roll forward
else:
prices.NormalizePrices()
prices.CalculateStats()
model = StockPredictionNN(baseModelName=ticker, UseLSTM=UseLSTM)
if UseLSTM:
window_size = 1
modelDescription = ticker + '_LSTM'
modelDescription += '_epochs' + str(epochs) + '_histwin' + str(
window_size) + '_daysforward' + str(prediction_target_days)
if usePercentages: modelDescription += '_percentages'
FieldList = ['Average']
model.LoadSource(sourceDF=prices.GetPriceHistory(),
FieldList=FieldList,
window_size=window_size)
model.LoadTarget(targetDF=None,
prediction_target_days=prediction_target_days)
model.MakeBatches(batch_size=128, train_test_split=.93)
model.BuildModel(layer_count=1,
hidden_layer_size=hidden_layer_size,
dropout=dropout,
dropout_rate=dropout_rate,
learning_rate=learning_rate)
model.DisplayModel()
model.Train(epochs=epochs)
model.Predict(True)
model.Save()
#model.DisplayDataSample()
else: #CNN
window_size = 16 * prediction_target_days
modelDescription = ticker + '_CNN'
modelDescription += '_epochs' + str(epochs) + '_histwin' + str(
window_size) + '_daysforward' + str(prediction_target_days)
if usePercentages: modelDescription += '_percentages'
#FieldList = None
FieldList = ['High', 'Low', 'Open', 'Close']
model.LoadSource(sourceDF=prices.GetPriceHistory(),
FieldList=FieldList,
window_size=window_size)
model.LoadTarget(targetDF=None,
prediction_target_days=prediction_target_days)
model.MakeBatches(batch_size=64, train_test_split=.93)
model.BuildModel(layer_count=1,
hidden_layer_size=hidden_layer_size,
dropout=dropout,
dropout_rate=dropout_rate,
learning_rate=learning_rate)
model.DisplayModel()
model.Train(epochs=epochs)
model.Predict(True)
model.Save()
if usePercentages:
predDF = model.GetTrainingResults(True, True)
predDF = predDF.loc[:, ['Average', 'Average_Predicted']]
print('Unraveling percentages..')
predDF['Average_Predicted'].fillna(0, inplace=True)
predDF.iloc[0] = prices.CTPFactor['Average']
for i in range(1, predDF.shape[0]):
predDF.iloc[i] = (1 + predDF.iloc[i]) * predDF.iloc[i - 1]
print(predDF)
predDF['PercentageDeviation'] = abs(
(predDF['Average'] - predDF['Average_Predicted']) /
predDF['Average'])
predDF.to_csv(dataFolder + modelDescription + '.csv')
plot.PlotDataFrame(predDF[['Average', 'Average_Predicted']],
modelDescription, 'Date', 'Price', True,
dataFolder + modelDescription)
plot.PlotDataFrameDateRange(
predDF[['Average', 'Average_Predicted']], None, 160,
modelDescription + '_last160ays', 'Date', 'Price',
dataFolder + modelDescription + '_last160Days')
plot.PlotDataFrameDateRange(
predDF[['Average', 'Average_Predicted']], None, 500,
modelDescription + '_last500Days', 'Date', 'Price',
dataFolder + modelDescription + '_last500Days')
else:
model.PredictionResultsSave(modelDescription, True, True)
model.PredictionResultsPlot(modelDescription, True, False)