Installing packages

When installing the version of Pandas needed for this exercise, please ignore the incompatibility ERROR that may appear for the packages visions and pandas-profiling. These are not needed.


In [8]:
%pip install pandas==0.24.1 --user
%pip install plotly
%pip install tensorboardX --user
%pip install bs4 --user
%pip install -U auquan_toolbox --user


Collecting pandas==0.24.1
  Using cached pandas-0.24.1-cp37-cp37m-manylinux1_x86_64.whl (10.1 MB)
Requirement already satisfied: python-dateutil>=2.5.0 in /home/jupyter/.local/lib/python3.7/site-packages (from pandas==0.24.1) (2.8.1)
Requirement already satisfied: numpy>=1.12.0 in /home/jupyter/.local/lib/python3.7/site-packages (from pandas==0.24.1) (1.18.4)
Requirement already satisfied: pytz>=2011k in /home/jupyter/.local/lib/python3.7/site-packages (from pandas==0.24.1) (2020.1)
Requirement already satisfied: six>=1.5 in /home/jupyter/.local/lib/python3.7/site-packages (from python-dateutil>=2.5.0->pandas==0.24.1) (1.15.0)
ERROR: visions 0.4.4 has requirement pandas>=0.25.3, but you'll have pandas 0.24.1 which is incompatible.
ERROR: pandas-profiling 2.6.0 has requirement pandas>=0.25.3, but you'll have pandas 0.24.1 which is incompatible.
Installing collected packages: pandas
Successfully installed pandas-0.24.1
Note: you may need to restart the kernel to use updated packages.

This notebook shows how Auquan Toolbox can be used to trade on momentum and mean reversion

Documentation on how to use the toolbox can be found here.

Note: When running the cell below, if you get a module not found error for the backtester library, please restart the Kernel for the package update to be detected.


In [10]:
from backtester.trading_system_parameters import TradingSystemParameters
from backtester.features.feature import Feature
from backtester.dataSource.yahoo_data_source import YahooStockDataSource
from backtester.timeRule.custom_time_rule import CustomTimeRule
from backtester.executionSystem.simple_execution_system import SimpleExecutionSystem
from backtester.orderPlacer.backtesting_order_placer import BacktestingOrderPlacer
from backtester.trading_system import TradingSystem
from backtester.constants import *

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import datetime
from datetime import timedelta

This is the static part of an experiment

It is similar to writing a data loader and trainer for a deep learning project. Once written for a particular experiment we hardly need to change it.


In [11]:
class MyTradingParams(TradingSystemParameters):

    def __init__(self, tradingFunctions):
        self.__tradingFunctions = tradingFunctions
        super(MyTradingParams, self).__init__()
        self.__dataSetId = 'equity_data'
        self.__instrumentIds = self.__tradingFunctions.getSymbolsToTrade()
        self.__startDate = '2015/01/02'
        self.__endDate = '2017/08/31'

    def getDataParser(self):
        '''
        Returns an instance of class DataParser. Source of data for instruments
        '''
        instrumentIds = self.__tradingFunctions.getSymbolsToTrade()
        return YahooStockDataSource(
            cachedFolderName = 'historicalData/',
            dataSetId = self.__dataSetId,
            instrumentIds = instrumentIds,
            startDateStr = self.__startDate,
            endDateStr = self.__endDate,
        )
        
    def getTimeRuleForUpdates(self):
        return CustomTimeRule(
            startDate = self.__startDate, 
            endDate = self.__endDate, 
            frequency = 'D', 
            sample = '30'
        )

    def getFrequencyOfFeatureUpdates(self):
        return timedelta(days = 1)

    def getStartingCapital(self):
        if len(self.__tradingFunctions.getSymbolsToTrade()) > 0:
            return 1000*len(self.__tradingFunctions.getSymbolsToTrade())
        else:
            return 30000

    def getCustomFeatures(self):
        '''
        This is a way to use any custom features you might have made.
        Returns a dictionary where:
        
        key: featureId to access this feature (Make sure this doesnt conflict with any of the pre defined feature Ids)
        value: Your custom Class which computes this feature. The class should be an instance of Feature
        
        Eg. if your custom class is MyCustomFeature, and you want to access this via featureId='my_custom_feature',
        you will import that class, and return this function as {'my_custom_feature': MyCustomFeature}
        '''
        return {
            'my_custom_feature': MyCustomFeature,
            'prediction': TrainingPredictionFeature,
            'zero_fees': FeesCalculator,
            'benchmark_PnL': BuyHoldPnL,
            'score': ScoreFeature
        }

    def getInstrumentFeatureConfigDicts(self):
        '''
        Returns an array of instrument feature config dictionaries instrument feature config Dictionary has the 
        following keys:
        
        featureId: a string representing the type of feature you want to use
        featureKey: a string representing the key you will use to access the value of this feature
        params: A dictionary with which contains other optional params if needed by the feature
        '''

        predictionDict = {
            'featureKey': 'prediction',
            'featureId': 'prediction',
            'params': {}
        }
        feesConfigDict = {
            'featureKey': 'fees',
            'featureId': 'zero_fees',
            'params': {}
        }
        profitlossConfigDict = {
            'featureKey': 'pnl',
            'featureId': 'pnl',
            'params': {
                'price': self.getPriceFeatureKey(),
                'fees': 'fees'
            }
        }
        capitalConfigDict = {
            'featureKey': 'capital',
            'featureId': 'capital',
            'params': {
                'price': 'adjClose',
                'fees': 'fees',
                'capitalReqPercent': 0.95
            }
        }
        benchmarkDict = {
            'featureKey': 'benchmark',
            'featureId': 'benchmark_PnL',
            'params': {'pnlKey': 'pnl'}
        }
        scoreDict = {
            'featureKey': 'score',
            'featureId': 'score',
            'params': {
                'featureName1': 'pnl',
                'featureName2':'benchmark'
            }
        }

        stockFeatureConfigs = self.__tradingFunctions.getInstrumentFeatureConfigDicts()

        return {
            INSTRUMENT_TYPE_STOCK: stockFeatureConfigs + [
                predictionDict,
                feesConfigDict,
                profitlossConfigDict,
                capitalConfigDict,
                benchmarkDict, 
                scoreDict
            ]
        }

    def getMarketFeatureConfigDicts(self):
        '''
        Returns an array of market feature config dictionaries having the following keys:
        
        featureId: a string representing the type of feature you want to use
        featureKey: a string representing the key you will use to access the value of this feature
        params: A dictionary with which contains other optional params if needed by the feature
        '''
        scoreDict = {
            'featureKey': 'score',
            'featureId': 'score_ll',
            'params': {
                'featureName': self.getPriceFeatureKey(),
                'instrument_score_feature': 'score'
            }
        }
        
        return [scoreDict]

    def getPrediction(self, time, updateNum, instrumentManager):
        predictions = pd.Series(index = self.__instrumentIds)
        predictions = self.__tradingFunctions.getPrediction(time, updateNum, instrumentManager, predictions)
        
        return predictions

    def getExecutionSystem(self):
        '''
        Returns the type of execution system we want to use. Its an implementation of the class ExecutionSystem
        It converts prediction to intended positions for different instruments.
        '''
        
        return SimpleExecutionSystem(
            enter_threshold = 0.7,
            exit_threshold = 0.55,
            longLimit = 1,
            shortLimit = 1,
            capitalUsageLimit = 0.10*self.getStartingCapital(),
            enterlotSize = 1, 
            exitlotSize = 1,
            limitType = 'L', 
            price = 'adjClose'
        )

    def getOrderPlacer(self):
        '''
        Returns the type of order placer we want to use. It's an implementation of the class OrderPlacer.
        It helps place an order, and also read confirmations of orders being placed.
        For Backtesting, you can just use the BacktestingOrderPlacer, which places the order which you want, and 
        automatically confirms it too.
        '''
        
        return BacktestingOrderPlacer()

    def getLookbackSize(self):
        '''
        Returns the amount of lookback data you want for your calculations. The historical market features and instrument features are only
        stored upto this amount.
        This number is the number of times we have updated our features.
        '''
        
        return 120

    def getPriceFeatureKey(self):
        '''
        The name of column containing the instrument price
        '''
        
        return 'adjClose'

    def getInstrumentsIds(self):
        '''
        Get all instrument ids
        '''
        
        return self.__instrumentIds

Let's define some of our own features


In [12]:
class TrainingPredictionFeature(Feature):
    
    @classmethod
    def computeForInstrument(cls, updateNum, time, featureParams, featureKey, instrumentManager):
        tf = MyTradingFunctions()
        t = MyTradingParams(tf)
        
        return t.getPrediction(time, updateNum, instrumentManager)

class FeesCalculator(Feature):
    @classmethod
    def computeForInstrument(cls, updateNum, time, featureParams, featureKey, instrumentManager):
        
        return pd.Series(0, index = instrumentManager.getAllInstrumentsByInstrumentId())

class BuyHoldPnL(Feature):
    
    @classmethod
    def computeForInstrument(cls, updateNum, time, featureParams, featureKey, instrumentManager):
        instrumentLookbackData = instrumentManager.getLookbackInstrumentFeatures()

        priceData = instrumentLookbackData.getFeatureDf('adjClose')
         
        if len(priceData) < 2:
            return pd.Series(0, index = instrumentManager.getAllInstrumentsByInstrumentId())
        else:
            bhpnl = instrumentLookbackData.getFeatureDf(featureKey).iloc[-1]
            bhpnl += priceData.iloc[-1] - priceData.iloc[-2]

        return bhpnl

class ScoreFeature(Feature):
    
    @classmethod
    def computeForInstrument(cls, updateNum, time, featureParams, featureKey, instrumentManager):
        instrumentLookbackData = instrumentManager.getLookbackInstrumentFeatures()
        if len(instrumentLookbackData.getFeatureDf(featureParams['featureName1'])) > 0:
            feature1 = instrumentLookbackData.getFeatureDf(featureParams['featureName1']).iloc[-1]
            feature2 = instrumentLookbackData.getFeatureDf(featureParams['featureName2']).iloc[-1]
            
            for instrumentId in feature1.index:
                pnls = instrumentLookbackData.getFeatureDf('pnl')[instrumentId]
                positions = instrumentLookbackData.getFeatureDf('position')[instrumentId]
                
                print(instrumentId)
                print('pnl: %.2f'%pnls[-1])
                if len(positions) > 2 and np.abs(positions[-1] - positions[-2]) > 0:
                    print('Position changed to: %.2f'%positions[-1])
            
            toRtn = (feature1 - feature2) / feature2.abs()
            toRtn[toRtn.isnull()] = 0
            toRtn[toRtn == np.Inf] = 0
        else:
            toRtn=0

        return toRtn

This is the part where the magic takes place, all the logic for prediction and carrying out trades goes here


In [13]:
class MyTradingFunctions():

    def __init__(self):
        self.count = 0
        self.params = {}

    def getSymbolsToTrade(self):
        '''
        Specify the stock names that you want to trade.
        '''
        
        return ['AAPL']

    def getInstrumentFeatureConfigDicts(self):
        '''
        Specify all Features you want to use by creating config dictionaries.
        Create one dictionary per feature and return them in an array.

        Feature config Dictionary have the following keys:

        featureId: a str for the type of feature you want to use
        featureKey: {optional} a str for the key you will use to call this feature
                    If not present, will just use featureId
        params: {optional} A dictionary with which contains other optional params if needed by the feature

        msDict = {
            'featureKey': 'ms_5',
            'featureId': 'moving_sum',
            'params': {
                'period': 5,
                'featureName': 'basis'
            }
        }

        return [msDict]

        You can now use this feature by in getPRediction() calling it's featureKey, 'ms_5'
        '''

        ma1Dict = {
            'featureKey': 'ma_90',
            'featureId': 'moving_average',
            'params': {
                'period': 90,
                'featureName': 'adjClose'
            }
        }
        mom30Dict = {
            'featureKey': 'mom_30',
            'featureId': 'momentum',
            'params': {
                'period': 30,
                'featureName': 'adjClose'
            }
        }
        mom10Dict = {
            'featureKey': 'mom_10',
            'featureId': 'momentum',
            'params': {
                'period': 10,
                'featureName': 'adjClose'
            }
        }
        
        return [ma1Dict, mom10Dict, mom30Dict]

    def getPrediction(self, time, updateNum, instrumentManager, predictions):
        '''
        Combine all the features to create the desired predictions for each stock.
        'predictions' is Pandas Series with stock as index and predictions as values
        We first call the holder for all the instrument features for all stocks as
            lookbackInstrumentFeatures = instrumentManager.getLookbackInstrumentFeatures()
        Then call the dataframe for a feature using its feature_key as
            ms5Data = lookbackInstrumentFeatures.getFeatureDf('ms_5')
        This returns a dataFrame for that feature for ALL stocks for all times upto lookback time
        Now you can call just the last data point for ALL stocks as
            ms5 = ms5Data.iloc[-1]
        You can call last datapoint for one stock 'ABC' as
            value_for_abs = ms5['ABC']

        Output of the prediction function is used by the toolbox to make further trading decisions and evaluate your score.
        '''

        # self.updateCount() - uncomment if you want a counter

        # holder for all the instrument features for all instruments
        lookbackInstrumentFeatures = instrumentManager.getLookbackInstrumentFeatures()

        #############################################################################################
        ### TODO : FILL THIS FUNCTION TO RETURN A BUY (1) or SELL (0) prediction for each stock  ###
        ### USE TEMPLATE BELOW AS EXAMPLE
        ###
        ### HINT: Use the Hurst Exponent 
        ### http://analytics-magazine.org/the-hurst-exponent-predictability-of-time-series/
        #############################################################################################
        
        # Here's an example implementation of the hurst exponent
        def hurst_f(input_ts, lags_to_test=20):  
            # interpretation of return value
            # hurst < 0.5 - input_ts is mean reverting
            # hurst = 0.5 - input_ts is effectively random/geometric brownian motion
            # hurst > 0.5 - input_ts is trending
            tau = []
            lagvec = []  
            #  Step through the different lags  
            for lag in range(2, lags_to_test):  
                #  produce price difference with lag  
                pp = np.subtract(input_ts[lag:], input_ts[:-lag])  
                #  Write the different lags into a vector  
                lagvec.append(lag)  
                #  Calculate the variance of the differnce vector  
                tau.append(np.sqrt(np.std(pp)))  
            #  linear fit to double-log graph (gives power)  
            m = np.polyfit(np.log10(lagvec), np.log10(tau), 1)  
            # calculate hurst  
            hurst = m[0]*2

            return hurst 

        # dataframe for a historical instrument feature (ma_90 in this case). The index is the timestamps
        # of upto lookback data points. The columns of this dataframe are the stock symbols/instrumentIds.
        mom30Data = lookbackInstrumentFeatures.getFeatureDf('mom_30')
        ma90Data = lookbackInstrumentFeatures.getFeatureDf('ma_90')

        if len(ma90Data.index) > 20:
            mom30 = mom30Data.iloc[-1]
            # Go long if momentum is positive
            predictions[mom30 > 0] = 1
            # Go short if momentum is negative
            predictions[mom30 <= 0] = 0          
        else:
            # If no sufficient data then don't take any positions
            predictions.values[:] = 0.5
        return predictions

    def updateCount(self):
        self.count = self.count + 1

Here's another example of a custom feature


In [14]:
class MyCustomFeature(Feature):
    ''''
    Custom Feature to implement for instrument. This function would return the value of the feature you want to implement.
    1. create a new class MyCustomFeatureClassName for the feature and implement your logic in the function computeForInstrument() -

    2. modify function getCustomFeatures() to return a dictionary with Id for this class
        (follow formats like {'my_custom_feature_identifier': MyCustomFeatureClassName}.
        Make sure 'my_custom_feature_identifier' doesnt conflict with any of the pre defined feature Ids

        def getCustomFeatures(self):
            return {'my_custom_feature_identifier': MyCustomFeatureClassName}

    3. create a dict for this feature in getInstrumentFeatureConfigDicts() above. Dict format is:
            customFeatureDict = {'featureKey': 'my_custom_feature_key',
                                'featureId': 'my_custom_feature_identifier',
                                'params': {'param1': 'value1'}}
    You can now use this feature by calling it's featureKey, 'my_custom_feature_key' in getPrediction()
    '''
    
    @classmethod
    def computeForInstrument(cls, updateNum, time, featureParams, featureKey, instrumentManager):
        # Custom parameter which can be used as input to computation of this feature
        param1Value = featureParams['param1']

        # A holder for the all the instrument features
        lookbackInstrumentFeatures = instrumentManager.getLookbackInstrumentFeatures()

        # dataframe for a historical instrument feature (basis in this case). The index is the timestamps
        # atmost upto lookback data points. The columns of this dataframe are the stocks/instrumentIds.
        lookbackInstrumentValue = lookbackInstrumentFeatures.getFeatureDf('adjClose')

        # The last row of the previous dataframe gives the last calculated value for that feature (basis in this case)
        # This returns a series with stocks/instrumentIds as the index.
        currentValue = lookbackInstrumentValue.iloc[-1]

        if param1Value == 'value1':
            return currentValue * 0.1
        else:
            return currentValue * 0.5

Time to run the backtester!


In [15]:
tf = MyTradingFunctions()
tsParams = MyTradingParams(tf)
tradingSystem = TradingSystem(tsParams)
results = tradingSystem.startTrading()


Processing data for stock: AAPL
20% done...
40% done...
60% done...
80% done...
Logging all the available market metrics in tensorboard
Logging all the available instrument metrics in tensorboard
2015-01-02 00:00:00
2015-01-05 00:00:00
AAPL
pnl: 0.00
2015-01-06 00:00:00
AAPL
pnl: 0.00
2015-01-07 00:00:00
AAPL
pnl: 0.00
2015-01-08 00:00:00
AAPL
pnl: 0.00
2015-01-09 00:00:00
AAPL
pnl: 0.00
2015-01-12 00:00:00
AAPL
pnl: 0.00
2015-01-13 00:00:00
AAPL
pnl: 0.00
2015-01-14 00:00:00
AAPL
pnl: 0.00
2015-01-15 00:00:00
AAPL
pnl: 0.00
2015-01-16 00:00:00
AAPL
pnl: 0.00
2015-01-19 00:00:00
AAPL
pnl: 0.00
2015-01-20 00:00:00
AAPL
pnl: 0.00
2015-01-21 00:00:00
AAPL
pnl: 0.00
2015-01-22 00:00:00
AAPL
pnl: 0.00
2015-01-23 00:00:00
AAPL
pnl: 0.00
2015-01-26 00:00:00
AAPL
pnl: 0.00
2015-01-27 00:00:00
AAPL
pnl: 0.00
2015-01-28 00:00:00
AAPL
pnl: 0.00
2015-01-29 00:00:00
AAPL
pnl: 0.00
2015-01-30 00:00:00
AAPL
pnl: 0.00
2015-02-02 00:00:00
AAPL
pnl: 0.00
2015-02-03 00:00:00
AAPL
pnl: 0.00
Position changed to: -1.00
2015-02-04 00:00:00
AAPL
pnl: -0.02
2015-02-05 00:00:00
AAPL
pnl: -0.85
2015-02-06 00:00:00
AAPL
pnl: -1.63
2015-02-09 00:00:00
AAPL
pnl: -0.70
2015-02-10 00:00:00
AAPL
pnl: -1.43
2015-02-11 00:00:00
AAPL
pnl: -3.54
2015-02-12 00:00:00
AAPL
pnl: -6.16
2015-02-13 00:00:00
AAPL
pnl: -7.61
2015-02-16 00:00:00
AAPL
pnl: -8.18
2015-02-17 00:00:00
AAPL
pnl: -8.18
2015-02-18 00:00:00
AAPL
pnl: -8.87
2015-02-19 00:00:00
AAPL
pnl: -9.69
2015-02-20 00:00:00
AAPL
pnl: -9.44
2015-02-23 00:00:00
AAPL
pnl: -10.40
2015-02-24 00:00:00
AAPL
pnl: -13.62
2015-02-25 00:00:00
AAPL
pnl: -12.85
2015-02-26 00:00:00
AAPL
pnl: -9.75
2015-02-27 00:00:00
AAPL
pnl: -11.25
2015-03-02 00:00:00
AAPL
pnl: -9.45
2015-03-03 00:00:00
AAPL
pnl: -10.03
2015-03-04 00:00:00
AAPL
pnl: -10.28
2015-03-05 00:00:00
AAPL
pnl: -9.52
2015-03-06 00:00:00
AAPL
pnl: -7.57
2015-03-09 00:00:00
AAPL
pnl: -7.74
2015-03-10 00:00:00
AAPL
pnl: -8.24
2015-03-11 00:00:00
AAPL
pnl: -5.82
2015-03-12 00:00:00
AAPL
pnl: -3.74
2015-03-13 00:00:00
AAPL
pnl: -5.77
2015-03-16 00:00:00
AAPL
pnl: -4.98
2015-03-17 00:00:00
AAPL
pnl: -6.23
2015-03-18 00:00:00
AAPL
pnl: -8.15
2015-03-19 00:00:00
AAPL
pnl: -9.46
2015-03-20 00:00:00
AAPL
pnl: -8.57
2015-03-23 00:00:00
AAPL
pnl: -7.10
2015-03-24 00:00:00
AAPL
pnl: -8.30
2015-03-25 00:00:00
AAPL
pnl: -7.83
2015-03-26 00:00:00
AAPL
pnl: -4.79
2015-03-27 00:00:00
AAPL
pnl: -5.58
2015-03-30 00:00:00
AAPL
pnl: -4.67
2015-03-31 00:00:00
AAPL
pnl: -7.53
2015-04-01 00:00:00
AAPL
pnl: -5.75
2015-04-02 00:00:00
AAPL
pnl: -5.59
2015-04-03 00:00:00
AAPL
pnl: -6.57
2015-04-06 00:00:00
AAPL
pnl: -6.57
2015-04-07 00:00:00
AAPL
pnl: -8.43
2015-04-08 00:00:00
AAPL
pnl: -7.20
2015-04-09 00:00:00
AAPL
pnl: -6.82
2015-04-10 00:00:00
AAPL
pnl: -7.71
2015-04-13 00:00:00
AAPL
pnl: -8.20
2015-04-14 00:00:00
AAPL
pnl: -7.97
2015-04-15 00:00:00
AAPL
pnl: -7.47
2015-04-16 00:00:00
AAPL
pnl: -7.91
2015-04-17 00:00:00
AAPL
pnl: -7.35
2015-04-20 00:00:00
AAPL
pnl: -6.04
2015-04-21 00:00:00
AAPL
pnl: -8.66
2015-04-22 00:00:00
AAPL
pnl: -8.03
2015-04-23 00:00:00
AAPL
pnl: -9.60
2015-04-24 00:00:00
AAPL
pnl: -10.56
2015-04-27 00:00:00
AAPL
pnl: -11.12
2015-04-28 00:00:00
AAPL
pnl: -13.30
2015-04-29 00:00:00
AAPL
pnl: -11.38
2015-04-30 00:00:00
AAPL
pnl: -9.61
2015-05-01 00:00:00
AAPL
pnl: -6.41
2015-05-04 00:00:00
AAPL
pnl: -9.90
2015-05-05 00:00:00
AAPL
pnl: -9.67
2015-05-06 00:00:00
AAPL
pnl: -7.01
2015-05-07 00:00:00
AAPL
pnl: -6.28
2015-05-08 00:00:00
AAPL
pnl: -6.99
2015-05-11 00:00:00
AAPL
pnl: -9.17
2015-05-12 00:00:00
AAPL
pnl: -7.97
2015-05-13 00:00:00
AAPL
pnl: -7.56
2015-05-14 00:00:00
AAPL
pnl: -7.68
2015-05-15 00:00:00
AAPL
pnl: -10.39
2015-05-18 00:00:00
AAPL
pnl: -10.23
2015-05-19 00:00:00
AAPL
pnl: -11.54
2015-05-20 00:00:00
AAPL
pnl: -11.43
2015-05-21 00:00:00
AAPL
pnl: -11.42
2015-05-22 00:00:00
AAPL
pnl: -12.64
2015-05-25 00:00:00
AAPL
pnl: -13.70
2015-05-26 00:00:00
AAPL
pnl: -13.70
2015-05-27 00:00:00
AAPL
pnl: -11.01
2015-05-28 00:00:00
AAPL
pnl: -13.24
2015-05-29 00:00:00
AAPL
pnl: -13.00
2015-06-01 00:00:00
AAPL
pnl: -11.62
2015-06-02 00:00:00
AAPL
pnl: -11.86
2015-06-03 00:00:00
AAPL
pnl: -11.32
2015-06-04 00:00:00
AAPL
pnl: -11.47
2015-06-05 00:00:00
AAPL
pnl: -10.77
2015-06-08 00:00:00
AAPL
pnl: -10.12
2015-06-09 00:00:00
AAPL
pnl: -9.33
2015-06-10 00:00:00
AAPL
pnl: -8.98
2015-06-11 00:00:00
AAPL
pnl: -10.33
2015-06-12 00:00:00
AAPL
pnl: -10.06
2015-06-15 00:00:00
AAPL
pnl: -8.75
2015-06-16 00:00:00
AAPL
pnl: -8.52
2015-06-17 00:00:00
AAPL
pnl: -9.15
2015-06-18 00:00:00
AAPL
pnl: -8.87
2015-06-19 00:00:00
AAPL
pnl: -9.41
2015-06-22 00:00:00
AAPL
pnl: -8.23
2015-06-23 00:00:00
AAPL
pnl: -9.16
2015-06-24 00:00:00
AAPL
pnl: -8.62
2015-06-25 00:00:00
AAPL
pnl: -9.62
2015-06-26 00:00:00
AAPL
pnl: -9.06
2015-06-29 00:00:00
AAPL
pnl: -8.37
2015-06-30 00:00:00
AAPL
pnl: -6.32
2015-07-01 00:00:00
AAPL
pnl: -7.15
2015-07-02 00:00:00
AAPL
pnl: -8.23
2015-07-03 00:00:00
AAPL
pnl: -8.08
2015-07-06 00:00:00
AAPL
pnl: -8.08
2015-07-07 00:00:00
AAPL
pnl: -7.68
2015-07-08 00:00:00
AAPL
pnl: -7.39
2015-07-09 00:00:00
AAPL
pnl: -4.51
2015-07-10 00:00:00
AAPL
pnl: -2.21
2015-07-13 00:00:00
AAPL
pnl: -5.17
2015-07-14 00:00:00
AAPL
pnl: -7.36
2015-07-15 00:00:00
AAPL
pnl: -7.32
2015-07-16 00:00:00
AAPL
pnl: -8.43
2015-07-17 00:00:00
AAPL
pnl: -9.99
2015-07-20 00:00:00
AAPL
pnl: -11.01
2015-07-21 00:00:00
AAPL
pnl: -13.27
2015-07-22 00:00:00
AAPL
pnl: -12.05
2015-07-23 00:00:00
AAPL
pnl: -6.96
2015-07-24 00:00:00
AAPL
pnl: -6.90
2015-07-27 00:00:00
AAPL
pnl: -6.29
2015-07-28 00:00:00
AAPL
pnl: -4.70
2015-07-29 00:00:00
AAPL
pnl: -5.26
2015-07-30 00:00:00
AAPL
pnl: -4.90
2015-07-31 00:00:00
AAPL
pnl: -4.33
2015-08-03 00:00:00
AAPL
pnl: -3.34
2015-08-04 00:00:00
AAPL
pnl: -0.71
2015-08-05 00:00:00
AAPL
pnl: 2.79
2015-08-06 00:00:00
AAPL
pnl: 2.09
2015-08-07 00:00:00
AAPL
pnl: 1.86
2015-08-10 00:00:00
AAPL
pnl: 1.50
2015-08-11 00:00:00
AAPL
pnl: -2.39
2015-08-12 00:00:00
AAPL
pnl: 3.38
2015-08-13 00:00:00
AAPL
pnl: 1.76
2015-08-14 00:00:00
AAPL
pnl: 1.84
2015-08-17 00:00:00
AAPL
pnl: 1.09
2015-08-18 00:00:00
AAPL
pnl: -0.02
2015-08-19 00:00:00
AAPL
pnl: 0.59
2015-08-20 00:00:00
AAPL
pnl: 1.97
2015-08-21 00:00:00
AAPL
pnl: 4.16
2015-08-24 00:00:00
AAPL
pnl: 10.54
2015-08-25 00:00:00
AAPL
pnl: 12.98
2015-08-26 00:00:00
AAPL
pnl: 12.41
2015-08-27 00:00:00
AAPL
pnl: 6.90
2015-08-28 00:00:00
AAPL
pnl: 3.91
2015-08-31 00:00:00
AAPL
pnl: 3.57
2015-09-01 00:00:00
AAPL
pnl: 4.06
2015-09-02 00:00:00
AAPL
pnl: 8.72
2015-09-03 00:00:00
AAPL
pnl: 4.45
2015-09-04 00:00:00
AAPL
pnl: 6.27
2015-09-07 00:00:00
AAPL
pnl: 7.29
2015-09-08 00:00:00
AAPL
pnl: 7.29
2015-09-09 00:00:00
AAPL
pnl: 4.47
2015-09-10 00:00:00
AAPL
pnl: 6.47
2015-09-11 00:00:00
AAPL
pnl: 4.23
2015-09-14 00:00:00
AAPL
pnl: 2.71
2015-09-15 00:00:00
AAPL
pnl: 1.70
2015-09-16 00:00:00
AAPL
pnl: 0.80
2015-09-17 00:00:00
AAPL
pnl: 0.68
2015-09-18 00:00:00
AAPL
pnl: 2.98
2015-09-21 00:00:00
AAPL
pnl: 3.42
2015-09-22 00:00:00
AAPL
pnl: 1.79
2015-09-23 00:00:00
AAPL
pnl: 3.46
2015-09-24 00:00:00
AAPL
pnl: 2.61
2015-09-25 00:00:00
AAPL
pnl: 1.98
2015-09-28 00:00:00
AAPL
pnl: 2.25
2015-09-29 00:00:00
AAPL
pnl: 4.35
2015-09-30 00:00:00
AAPL
pnl: 7.48
2015-10-01 00:00:00
AAPL
pnl: 6.33
2015-10-02 00:00:00
AAPL
pnl: 7.00
2015-10-05 00:00:00
AAPL
pnl: 6.26
2015-10-06 00:00:00
AAPL
pnl: 5.89
2015-10-07 00:00:00
AAPL
pnl: 5.40
2015-10-08 00:00:00
AAPL
pnl: 5.89
2015-10-09 00:00:00
AAPL
pnl: 7.07
2015-10-12 00:00:00
AAPL
pnl: 4.65
2015-10-13 00:00:00
AAPL
pnl: 5.13
2015-10-14 00:00:00
AAPL
pnl: 4.95
2015-10-15 00:00:00
AAPL
pnl: 6.42
2015-10-16 00:00:00
AAPL
pnl: 4.89
2015-10-19 00:00:00
AAPL
pnl: 5.65
2015-10-20 00:00:00
AAPL
pnl: 5.01
2015-10-21 00:00:00
AAPL
pnl: 3.12
2015-10-22 00:00:00
AAPL
pnl: 3.13
2015-10-23 00:00:00
AAPL
pnl: 1.52
2015-10-26 00:00:00
AAPL
pnl: -1.79
2015-10-27 00:00:00
AAPL
pnl: 1.72
2015-10-28 00:00:00
AAPL
pnl: 2.40
2015-10-29 00:00:00
AAPL
pnl: -1.97
2015-10-30 00:00:00
AAPL
pnl: -3.14
2015-11-02 00:00:00
AAPL
pnl: -2.18
2015-11-03 00:00:00
AAPL
pnl: -3.74
2015-11-04 00:00:00
AAPL
pnl: -5.03
2015-11-05 00:00:00
AAPL
pnl: -4.50
2015-11-06 00:00:00
AAPL
pnl: -3.98
2015-11-09 00:00:00
AAPL
pnl: -4.11
2015-11-10 00:00:00
AAPL
pnl: -3.65
2015-11-11 00:00:00
AAPL
pnl: -0.12
2015-11-12 00:00:00
AAPL
pnl: 0.50
2015-11-13 00:00:00
AAPL
pnl: 0.86
2015-11-16 00:00:00
AAPL
pnl: 4.00
2015-11-17 00:00:00
AAPL
pnl: 2.29
2015-11-18 00:00:00
AAPL
pnl: 2.75
2015-11-19 00:00:00
AAPL
pnl: -0.60
2015-11-20 00:00:00
AAPL
pnl: -1.99
2015-11-23 00:00:00
AAPL
pnl: -2.47
2015-11-24 00:00:00
AAPL
pnl: -1.03
2015-11-25 00:00:00
AAPL
pnl: -2.08
2015-11-26 00:00:00
AAPL
pnl: -1.29
2015-11-27 00:00:00
AAPL
pnl: -1.29
2015-11-30 00:00:00
AAPL
pnl: -1.09
2015-12-01 00:00:00
AAPL
pnl: -1.54
2015-12-02 00:00:00
AAPL
pnl: -0.65
2015-12-03 00:00:00
AAPL
pnl: 0.34
2015-12-04 00:00:00
AAPL
pnl: 1.34
2015-12-07 00:00:00
AAPL
pnl: -2.22
2015-12-08 00:00:00
AAPL
pnl: -1.52
2015-12-09 00:00:00
AAPL
pnl: -1.48
2015-12-10 00:00:00
AAPL
pnl: 0.95
2015-12-11 00:00:00
AAPL
pnl: 0.44
2015-12-14 00:00:00
AAPL
pnl: 3.22
2015-12-15 00:00:00
AAPL
pnl: 3.87
2015-12-16 00:00:00
AAPL
pnl: 5.72
2015-12-17 00:00:00
AAPL
pnl: 4.93
2015-12-18 00:00:00
AAPL
pnl: 7.12
2015-12-21 00:00:00
AAPL
pnl: 9.87
2015-12-22 00:00:00
AAPL
pnl: 8.66
2015-12-23 00:00:00
AAPL
pnl: 8.75
2015-12-24 00:00:00
AAPL
pnl: 7.47
2015-12-25 00:00:00
AAPL
pnl: 8.01
2015-12-28 00:00:00
AAPL
pnl: 8.01
2015-12-29 00:00:00
AAPL
pnl: 9.13
2015-12-30 00:00:00
AAPL
pnl: 7.35
2015-12-31 00:00:00
AAPL
pnl: 8.67
2016-01-01 00:00:00
AAPL
pnl: 10.58
2016-01-04 00:00:00
AAPL
pnl: 10.58
2016-01-05 00:00:00
AAPL
pnl: 10.50
2016-01-06 00:00:00
AAPL
pnl: 12.95
2016-01-07 00:00:00
AAPL
pnl: 14.82
2016-01-08 00:00:00
AAPL
pnl: 18.77
2016-01-11 00:00:00
AAPL
pnl: 18.30
2016-01-12 00:00:00
AAPL
pnl: 16.84
2016-01-13 00:00:00
AAPL
pnl: 15.51
2016-01-14 00:00:00
AAPL
pnl: 17.90
2016-01-15 00:00:00
AAPL
pnl: 15.92
2016-01-18 00:00:00
AAPL
pnl: 18.14
2016-01-19 00:00:00
AAPL
pnl: 18.14
2016-01-20 00:00:00
AAPL
pnl: 18.58
2016-01-21 00:00:00
AAPL
pnl: 18.46
2016-01-22 00:00:00
AAPL
pnl: 18.91
2016-01-25 00:00:00
AAPL
pnl: 14.15
2016-01-26 00:00:00
AAPL
pnl: 15.99
2016-01-27 00:00:00
AAPL
pnl: 15.48
2016-01-28 00:00:00
AAPL
pnl: 21.59
2016-01-29 00:00:00
AAPL
pnl: 20.97
2016-02-01 00:00:00
AAPL
pnl: 17.95
2016-02-02 00:00:00
AAPL
pnl: 18.79
2016-02-03 00:00:00
AAPL
pnl: 20.61
2016-02-04 00:00:00
AAPL
pnl: 18.87
2016-02-05 00:00:00
AAPL
pnl: 18.15
2016-02-08 00:00:00
AAPL
pnl: 20.56
2016-02-09 00:00:00
AAPL
pnl: 19.63
2016-02-10 00:00:00
AAPL
pnl: 19.65
2016-02-11 00:00:00
AAPL
pnl: 20.33
2016-02-12 00:00:00
AAPL
pnl: 20.86
2016-02-15 00:00:00
AAPL
pnl: 20.59
2016-02-16 00:00:00
AAPL
pnl: 20.59
2016-02-17 00:00:00
AAPL
pnl: 18.11
2016-02-18 00:00:00
AAPL
pnl: 16.73
2016-02-19 00:00:00
AAPL
pnl: 18.46
2016-02-22 00:00:00
AAPL
pnl: 18.67
2016-02-23 00:00:00
AAPL
pnl: 17.89
2016-02-24 00:00:00
AAPL
pnl: 19.93
2016-02-25 00:00:00
AAPL
pnl: 18.61
2016-02-26 00:00:00
AAPL
pnl: 18.00
2016-02-29 00:00:00
AAPL
pnl: 17.86
2016-03-01 00:00:00
AAPL
pnl: 18.06
2016-03-02 00:00:00
AAPL
pnl: 14.47
2016-03-03 00:00:00
AAPL
pnl: 14.27
2016-03-04 00:00:00
AAPL
pnl: 13.57
2016-03-07 00:00:00
AAPL
pnl: 12.16
2016-03-08 00:00:00
AAPL
pnl: 13.22
2016-03-09 00:00:00
AAPL
pnl: 14.01
2016-03-10 00:00:00
AAPL
pnl: 13.92
2016-03-11 00:00:00
AAPL
pnl: 13.88
2016-03-14 00:00:00
AAPL
pnl: 12.86
2016-03-15 00:00:00
AAPL
pnl: 12.61
2016-03-16 00:00:00
AAPL
pnl: 10.69
2016-03-17 00:00:00
AAPL
pnl: 9.39
2016-03-18 00:00:00
AAPL
pnl: 9.55
2016-03-21 00:00:00
AAPL
pnl: 9.43
2016-03-22 00:00:00
AAPL
pnl: 9.44
2016-03-23 00:00:00
AAPL
pnl: 8.69
2016-03-24 00:00:00
AAPL
pnl: 9.24
2016-03-25 00:00:00
AAPL
pnl: 9.67
2016-03-28 00:00:00
AAPL
pnl: 9.67
2016-03-29 00:00:00
AAPL
pnl: 10.12
2016-03-30 00:00:00
AAPL
pnl: 7.79
2016-03-31 00:00:00
AAPL
pnl: 6.03
2016-04-01 00:00:00
AAPL
pnl: 6.57
2016-04-04 00:00:00
AAPL
pnl: 5.63
2016-04-05 00:00:00
AAPL
pnl: 4.57
2016-04-06 00:00:00
AAPL
pnl: 5.80
2016-04-07 00:00:00
AAPL
pnl: 4.72
2016-04-08 00:00:00
AAPL
pnl: 6.99
2016-04-11 00:00:00
AAPL
pnl: 6.87
2016-04-12 00:00:00
AAPL
pnl: 6.54
2016-04-13 00:00:00
AAPL
pnl: 5.21
2016-04-14 00:00:00
AAPL
pnl: 3.71
2016-04-15 00:00:00
AAPL
pnl: 3.66
2016-04-18 00:00:00
AAPL
pnl: 5.76
2016-04-19 00:00:00
AAPL
pnl: 7.98
2016-04-20 00:00:00
AAPL
pnl: 8.51
2016-04-21 00:00:00
AAPL
pnl: 8.30
2016-04-22 00:00:00
AAPL
pnl: 9.39
2016-04-25 00:00:00
AAPL
pnl: 9.66
2016-04-26 00:00:00
AAPL
pnl: 10.22
2016-04-27 00:00:00
AAPL
pnl: 10.90
2016-04-28 00:00:00
AAPL
pnl: 17.01
2016-04-29 00:00:00
AAPL
pnl: 19.80
2016-05-02 00:00:00
AAPL
pnl: 20.82
2016-05-03 00:00:00
AAPL
pnl: 20.91
2016-05-04 00:00:00
AAPL
pnl: 19.47
2016-05-05 00:00:00
AAPL
pnl: 20.40
2016-05-06 00:00:00
AAPL
pnl: 20.76
2016-05-09 00:00:00
AAPL
pnl: 21.25
2016-05-10 00:00:00
AAPL
pnl: 21.18
2016-05-11 00:00:00
AAPL
pnl: 20.59
2016-05-12 00:00:00
AAPL
pnl: 21.44
2016-05-13 00:00:00
AAPL
pnl: 23.48
2016-05-16 00:00:00
AAPL
pnl: 23.32
2016-05-17 00:00:00
AAPL
pnl: 20.16
2016-05-18 00:00:00
AAPL
pnl: 20.52
2016-05-19 00:00:00
AAPL
pnl: 19.52
2016-05-20 00:00:00
AAPL
pnl: 19.85
2016-05-23 00:00:00
AAPL
pnl: 18.90
2016-05-24 00:00:00
AAPL
pnl: 17.76
2016-05-25 00:00:00
AAPL
pnl: 16.37
2016-05-26 00:00:00
AAPL
pnl: 14.76
2016-05-27 00:00:00
AAPL
pnl: 14.01
2016-05-30 00:00:00
AAPL
pnl: 14.07
2016-05-31 00:00:00
AAPL
pnl: 14.07
2016-06-01 00:00:00
AAPL
pnl: 14.53
2016-06-02 00:00:00
AAPL
pnl: 15.85
2016-06-03 00:00:00
AAPL
pnl: 16.54
2016-06-06 00:00:00
AAPL
pnl: 16.36
2016-06-07 00:00:00
AAPL
pnl: 15.69
2016-06-08 00:00:00
AAPL
pnl: 15.31
2016-06-09 00:00:00
AAPL
pnl: 15.40
2016-06-10 00:00:00
AAPL
pnl: 14.73
2016-06-13 00:00:00
AAPL
pnl: 15.50
2016-06-14 00:00:00
AAPL
pnl: 16.90
2016-06-15 00:00:00
AAPL
pnl: 16.79
2016-06-16 00:00:00
AAPL
pnl: 17.09
2016-06-17 00:00:00
AAPL
pnl: 16.70
2016-06-20 00:00:00
AAPL
pnl: 18.79
2016-06-21 00:00:00
AAPL
pnl: 19.01
2016-06-22 00:00:00
AAPL
pnl: 18.25
2016-06-23 00:00:00
AAPL
pnl: 18.58
2016-06-24 00:00:00
AAPL
pnl: 18.07
2016-06-27 00:00:00
AAPL
pnl: 20.61
2016-06-28 00:00:00
AAPL
pnl: 21.89
2016-06-29 00:00:00
AAPL
pnl: 20.43
2016-06-30 00:00:00
AAPL
pnl: 19.67
2016-07-01 00:00:00
AAPL
pnl: 18.54
2016-07-04 00:00:00
AAPL
pnl: 18.27
2016-07-05 00:00:00
AAPL
pnl: 18.27
2016-07-06 00:00:00
AAPL
pnl: 19.11
2016-07-07 00:00:00
AAPL
pnl: 18.60
2016-07-08 00:00:00
AAPL
pnl: 18.22
2016-07-11 00:00:00
AAPL
pnl: 17.52
2016-07-12 00:00:00
AAPL
pnl: 17.24
2016-07-13 00:00:00
AAPL
pnl: 16.83
2016-07-14 00:00:00
AAPL
pnl: 17.34
2016-07-15 00:00:00
AAPL
pnl: 15.54
2016-07-18 00:00:00
AAPL
pnl: 15.55
2016-07-19 00:00:00
AAPL
pnl: 14.56
2016-07-20 00:00:00
AAPL
pnl: 14.52
2016-07-21 00:00:00
AAPL
pnl: 14.44
2016-07-22 00:00:00
AAPL
pnl: 14.94
2016-07-25 00:00:00
AAPL
pnl: 15.66
2016-07-26 00:00:00
AAPL
pnl: 16.90
2016-07-27 00:00:00
AAPL
pnl: 17.53
2016-07-28 00:00:00
AAPL
pnl: 11.63
2016-07-29 00:00:00
AAPL
pnl: 10.32
2016-08-01 00:00:00
AAPL
pnl: 10.44
2016-08-02 00:00:00
AAPL
pnl: 8.71
2016-08-03 00:00:00
AAPL
pnl: 10.19
2016-08-04 00:00:00
AAPL
pnl: 8.95
2016-08-05 00:00:00
AAPL
pnl: 8.34
2016-08-08 00:00:00
AAPL
pnl: 6.82
2016-08-09 00:00:00
AAPL
pnl: 5.98
2016-08-10 00:00:00
AAPL
pnl: 5.56
2016-08-11 00:00:00
AAPL
pnl: 6.33
2016-08-12 00:00:00
AAPL
pnl: 6.39
2016-08-15 00:00:00
AAPL
pnl: 6.16
2016-08-16 00:00:00
AAPL
pnl: 4.93
2016-08-17 00:00:00
AAPL
pnl: 5.02
2016-08-18 00:00:00
AAPL
pnl: 5.17
2016-08-19 00:00:00
AAPL
pnl: 5.30
2016-08-22 00:00:00
AAPL
pnl: 5.04
2016-08-23 00:00:00
AAPL
pnl: 5.84
2016-08-24 00:00:00
AAPL
pnl: 5.52
2016-08-25 00:00:00
AAPL
pnl: 6.30
2016-08-26 00:00:00
AAPL
pnl: 6.73
2016-08-29 00:00:00
AAPL
pnl: 7.33
2016-08-30 00:00:00
AAPL
pnl: 7.44
2016-08-31 00:00:00
AAPL
pnl: 8.22
2016-09-01 00:00:00
AAPL
pnl: 8.12
2016-09-02 00:00:00
AAPL
pnl: 7.53
2016-09-05 00:00:00
AAPL
pnl: 6.58
2016-09-06 00:00:00
AAPL
pnl: 6.58
2016-09-07 00:00:00
AAPL
pnl: 6.61
2016-09-08 00:00:00
AAPL
pnl: 5.99
2016-09-09 00:00:00
AAPL
pnl: 8.67
2016-09-12 00:00:00
AAPL
pnl: 10.93
2016-09-13 00:00:00
AAPL
pnl: 8.75
2016-09-14 00:00:00
AAPL
pnl: 6.37
2016-09-15 00:00:00
AAPL
pnl: 2.76
2016-09-16 00:00:00
AAPL
pnl: -0.83
2016-09-19 00:00:00
AAPL
pnl: -0.22
2016-09-20 00:00:00
AAPL
pnl: 1.05
2016-09-21 00:00:00
AAPL
pnl: 1.06
2016-09-22 00:00:00
AAPL
pnl: 1.08
2016-09-23 00:00:00
AAPL
pnl: 0.07
2016-09-26 00:00:00
AAPL
pnl: 1.87
2016-09-27 00:00:00
AAPL
pnl: 1.71
2016-09-28 00:00:00
AAPL
pnl: 1.51
2016-09-29 00:00:00
AAPL
pnl: 0.70
2016-09-30 00:00:00
AAPL
pnl: 2.37
2016-10-03 00:00:00
AAPL
pnl: 1.55
2016-10-04 00:00:00
AAPL
pnl: 2.05
2016-10-05 00:00:00
AAPL
pnl: 1.60
2016-10-06 00:00:00
AAPL
pnl: 1.55
2016-10-07 00:00:00
AAPL
pnl: 0.76
2016-10-10 00:00:00
AAPL
pnl: 0.60
2016-10-11 00:00:00
AAPL
pnl: -1.29
2016-10-12 00:00:00
AAPL
pnl: -1.52
2016-10-13 00:00:00
AAPL
pnl: -2.51
2016-10-14 00:00:00
AAPL
pnl: -2.17
2016-10-17 00:00:00
AAPL
pnl: -2.78
2016-10-18 00:00:00
AAPL
pnl: -2.70
2016-10-19 00:00:00
AAPL
pnl: -2.63
2016-10-20 00:00:00
AAPL
pnl: -2.30
2016-10-21 00:00:00
AAPL
pnl: -2.24
2016-10-24 00:00:00
AAPL
pnl: -1.81
2016-10-25 00:00:00
AAPL
pnl: -2.80
2016-10-26 00:00:00
AAPL
pnl: -3.37
2016-10-27 00:00:00
AAPL
pnl: -0.85
2016-10-28 00:00:00
AAPL
pnl: 0.20
2016-10-31 00:00:00
AAPL
pnl: 0.92
2016-11-01 00:00:00
AAPL
pnl: 1.09
2016-11-02 00:00:00
AAPL
pnl: 3.03
2016-11-03 00:00:00
AAPL
pnl: 2.93
2016-11-04 00:00:00
AAPL
pnl: 4.06
2016-11-07 00:00:00
AAPL
pnl: 5.00
2016-11-08 00:00:00
AAPL
pnl: 3.51
2016-11-09 00:00:00
AAPL
pnl: 2.89
2016-11-10 00:00:00
AAPL
pnl: 3.06
2016-11-11 00:00:00
AAPL
pnl: 6.00
2016-11-14 00:00:00
AAPL
pnl: 5.39
2016-11-15 00:00:00
AAPL
pnl: 7.98
2016-11-16 00:00:00
AAPL
pnl: 6.65
2016-11-17 00:00:00
AAPL
pnl: 3.91
2016-11-18 00:00:00
AAPL
pnl: 3.95
2016-11-21 00:00:00
AAPL
pnl: 3.84
2016-11-22 00:00:00
AAPL
pnl: 2.26
2016-11-23 00:00:00
AAPL
pnl: 2.19
2016-11-24 00:00:00
AAPL
pnl: 2.73
2016-11-25 00:00:00
AAPL
pnl: 2.73
2016-11-28 00:00:00
AAPL
pnl: 2.20
2016-11-29 00:00:00
AAPL
pnl: 2.41
2016-11-30 00:00:00
AAPL
pnl: 2.51
2016-12-01 00:00:00
AAPL
pnl: 3.41
2016-12-02 00:00:00
AAPL
pnl: 4.39
2016-12-05 00:00:00
AAPL
pnl: 4.00
2016-12-06 00:00:00
AAPL
pnl: 4.75
2016-12-07 00:00:00
AAPL
pnl: 3.95
2016-12-08 00:00:00
AAPL
pnl: 2.92
2016-12-09 00:00:00
AAPL
pnl: 1.89
2016-12-12 00:00:00
AAPL
pnl: 0.15
2016-12-13 00:00:00
AAPL
pnl: 0.76
2016-12-14 00:00:00
AAPL
pnl: -1.03
2016-12-15 00:00:00
AAPL
pnl: -1.03
2016-12-16 00:00:00
AAPL
pnl: -1.63
2016-12-19 00:00:00
AAPL
pnl: -1.77
2016-12-20 00:00:00
AAPL
pnl: -2.41
2016-12-21 00:00:00
AAPL
pnl: -2.71
2016-12-22 00:00:00
AAPL
pnl: -2.81
2016-12-23 00:00:00
AAPL
pnl: -2.08
2016-12-26 00:00:00
AAPL
pnl: -2.30
2016-12-27 00:00:00
AAPL
pnl: -2.30
2016-12-28 00:00:00
AAPL
pnl: -3.00
2016-12-29 00:00:00
AAPL
pnl: -2.52
2016-12-30 00:00:00
AAPL
pnl: -2.50
2017-01-02 00:00:00
AAPL
pnl: -1.63
2017-01-03 00:00:00
AAPL
pnl: -1.63
2017-01-04 00:00:00
AAPL
pnl: -1.94
2017-01-05 00:00:00
AAPL
pnl: -1.82
2017-01-06 00:00:00
AAPL
pnl: -2.38
2017-01-09 00:00:00
AAPL
pnl: -3.62
2017-01-10 00:00:00
AAPL
pnl: -4.64
2017-01-11 00:00:00
AAPL
pnl: -4.76
2017-01-12 00:00:00
AAPL
pnl: -5.37
2017-01-13 00:00:00
AAPL
pnl: -4.89
2017-01-16 00:00:00
AAPL
pnl: -4.69
2017-01-17 00:00:00
AAPL
pnl: -4.69
2017-01-18 00:00:00
AAPL
pnl: -5.60
2017-01-19 00:00:00
AAPL
pnl: -5.59
2017-01-20 00:00:00
AAPL
pnl: -5.39
2017-01-23 00:00:00
AAPL
pnl: -5.60
2017-01-24 00:00:00
AAPL
pnl: -5.68
2017-01-25 00:00:00
AAPL
pnl: -5.58
2017-01-26 00:00:00
AAPL
pnl: -7.39
2017-01-27 00:00:00
AAPL
pnl: -7.45
2017-01-30 00:00:00
AAPL
pnl: -7.46
2017-01-31 00:00:00
AAPL
pnl: -7.15
2017-02-01 00:00:00
AAPL
pnl: -6.89
2017-02-02 00:00:00
AAPL
pnl: -13.92
2017-02-03 00:00:00
AAPL
pnl: -13.71
2017-02-06 00:00:00
AAPL
pnl: -14.23
2017-02-07 00:00:00
AAPL
pnl: -15.38
2017-02-08 00:00:00
AAPL
pnl: -16.56
2017-02-09 00:00:00
AAPL
pnl: -17.05
2017-02-10 00:00:00
AAPL
pnl: -17.95
2017-02-13 00:00:00
AAPL
pnl: -17.67
2017-02-14 00:00:00
AAPL
pnl: -18.78
2017-02-15 00:00:00
AAPL
pnl: -20.44
2017-02-16 00:00:00
AAPL
pnl: -20.90
2017-02-17 00:00:00
AAPL
pnl: -20.75
2017-02-20 00:00:00
AAPL
pnl: -21.10
2017-02-21 00:00:00
AAPL
pnl: -21.10
2017-02-22 00:00:00
AAPL
pnl: -22.04
2017-02-23 00:00:00
AAPL
pnl: -22.43
2017-02-24 00:00:00
AAPL
pnl: -21.88
2017-02-27 00:00:00
AAPL
pnl: -22.00
2017-02-28 00:00:00
AAPL
pnl: -22.26
2017-03-01 00:00:00
AAPL
pnl: -22.32
2017-03-02 00:00:00
AAPL
pnl: -24.99
2017-03-03 00:00:00
AAPL
pnl: -24.20
2017-03-06 00:00:00
AAPL
pnl: -24.98
2017-03-07 00:00:00
AAPL
pnl: -24.56
2017-03-08 00:00:00
AAPL
pnl: -24.73
2017-03-09 00:00:00
AAPL
pnl: -24.23
2017-03-10 00:00:00
AAPL
pnl: -23.93
2017-03-13 00:00:00
AAPL
pnl: -24.37
2017-03-14 00:00:00
AAPL
pnl: -24.43
2017-03-15 00:00:00
AAPL
pnl: -24.23
2017-03-16 00:00:00
AAPL
pnl: -25.63
2017-03-17 00:00:00
AAPL
pnl: -25.85
2017-03-20 00:00:00
AAPL
pnl: -25.18
2017-03-21 00:00:00
AAPL
pnl: -26.58
2017-03-22 00:00:00
AAPL
pnl: -25.04
2017-03-23 00:00:00
AAPL
pnl: -26.54
2017-03-24 00:00:00
AAPL
pnl: -26.07
2017-03-27 00:00:00
AAPL
pnl: -25.80
2017-03-28 00:00:00
AAPL
pnl: -26.03
2017-03-29 00:00:00
AAPL
pnl: -28.82
2017-03-30 00:00:00
AAPL
pnl: -29.12
2017-03-31 00:00:00
AAPL
pnl: -28.94
2017-04-03 00:00:00
AAPL
pnl: -28.68
2017-04-04 00:00:00
AAPL
pnl: -28.72
2017-04-05 00:00:00
AAPL
pnl: -29.74
2017-04-06 00:00:00
AAPL
pnl: -29.03
2017-04-07 00:00:00
AAPL
pnl: -28.68
2017-04-10 00:00:00
AAPL
pnl: -28.38
2017-04-11 00:00:00
AAPL
pnl: -28.22
2017-04-12 00:00:00
AAPL
pnl: -26.75
2017-04-13 00:00:00
AAPL
pnl: -26.91
2017-04-14 00:00:00
AAPL
pnl: -26.19
2017-04-17 00:00:00
AAPL
pnl: -26.19
2017-04-18 00:00:00
AAPL
pnl: -26.94
2017-04-19 00:00:00
AAPL
pnl: -26.33
2017-04-20 00:00:00
AAPL
pnl: -25.84
2017-04-21 00:00:00
AAPL
pnl: -27.52
2017-04-24 00:00:00
AAPL
pnl: -27.36
2017-04-25 00:00:00
AAPL
pnl: -28.66
2017-04-26 00:00:00
AAPL
pnl: -29.51
2017-04-27 00:00:00
AAPL
pnl: -28.70
2017-04-28 00:00:00
AAPL
pnl: -28.81
2017-05-01 00:00:00
AAPL
pnl: -28.67
2017-05-02 00:00:00
AAPL
pnl: -31.47
2017-05-03 00:00:00
AAPL
pnl: -32.36
2017-05-04 00:00:00
AAPL
pnl: -31.93
2017-05-05 00:00:00
AAPL
pnl: -31.42
2017-05-08 00:00:00
AAPL
pnl: -33.74
2017-05-09 00:00:00
AAPL
pnl: -37.61
2017-05-10 00:00:00
AAPL
pnl: -38.54
2017-05-11 00:00:00
AAPL
pnl: -37.85
2017-05-12 00:00:00
AAPL
pnl: -39.11
2017-05-15 00:00:00
AAPL
pnl: -41.17
2017-05-16 00:00:00
AAPL
pnl: -40.79
2017-05-17 00:00:00
AAPL
pnl: -40.57
2017-05-18 00:00:00
AAPL
pnl: -35.57
2017-05-19 00:00:00
AAPL
pnl: -37.76
2017-05-22 00:00:00
AAPL
pnl: -38.26
2017-05-23 00:00:00
AAPL
pnl: -39.15
2017-05-24 00:00:00
AAPL
pnl: -38.97
2017-05-25 00:00:00
AAPL
pnl: -38.53
2017-05-26 00:00:00
AAPL
pnl: -39.04
2017-05-29 00:00:00
AAPL
pnl: -38.79
2017-05-30 00:00:00
AAPL
pnl: -38.79
2017-05-31 00:00:00
AAPL
pnl: -38.84
2017-06-01 00:00:00
AAPL
pnl: -37.97
2017-06-02 00:00:00
AAPL
pnl: -38.37
2017-06-05 00:00:00
AAPL
pnl: -40.55
2017-06-06 00:00:00
AAPL
pnl: -39.09
2017-06-07 00:00:00
AAPL
pnl: -39.59
2017-06-08 00:00:00
AAPL
pnl: -40.47
2017-06-09 00:00:00
AAPL
pnl: -40.11
2017-06-12 00:00:00
AAPL
pnl: -34.35
2017-06-13 00:00:00
AAPL
pnl: -30.94
2017-06-14 00:00:00
AAPL
pnl: -32.06
2017-06-15 00:00:00
AAPL
pnl: -30.69
2017-06-16 00:00:00
AAPL
pnl: -29.85
2017-06-19 00:00:00
AAPL
pnl: -27.92
2017-06-20 00:00:00
AAPL
pnl: -31.82
2017-06-21 00:00:00
AAPL
pnl: -30.54
2017-06-22 00:00:00
AAPL
pnl: -31.37
2017-06-23 00:00:00
AAPL
pnl: -31.14
2017-06-26 00:00:00
AAPL
pnl: -31.76
2017-06-27 00:00:00
AAPL
pnl: -31.32
2017-06-28 00:00:00
AAPL
pnl: -29.32
2017-06-29 00:00:00
AAPL
pnl: -31.33
2017-06-30 00:00:00
AAPL
pnl: -29.27
2017-07-03 00:00:00
AAPL
pnl: -29.59
2017-07-04 00:00:00
AAPL
pnl: -29.10
2017-07-05 00:00:00
AAPL
pnl: -29.10
2017-07-06 00:00:00
AAPL
pnl: -29.66
2017-07-07 00:00:00
AAPL
pnl: -28.36
2017-07-10 00:00:00
AAPL
pnl: -29.75
2017-07-11 00:00:00
AAPL
pnl: -30.59
2017-07-12 00:00:00
AAPL
pnl: -31.04
2017-07-13 00:00:00
AAPL
pnl: -31.24
2017-07-14 00:00:00
AAPL
pnl: -33.19
2017-07-17 00:00:00
AAPL
pnl: -34.41
2017-07-18 00:00:00
AAPL
pnl: -34.90
2017-07-19 00:00:00
AAPL
pnl: -35.40
2017-07-20 00:00:00
AAPL
pnl: -36.30
2017-07-21 00:00:00
AAPL
pnl: -35.65
2017-07-24 00:00:00
AAPL
pnl: -35.58
2017-07-25 00:00:00
AAPL
pnl: -37.33
2017-07-26 00:00:00
AAPL
pnl: -37.95
2017-07-27 00:00:00
AAPL
pnl: -38.64
2017-07-28 00:00:00
AAPL
pnl: -35.86
2017-07-31 00:00:00
AAPL
pnl: -34.85
2017-08-01 00:00:00
AAPL
pnl: -34.11
2017-08-02 00:00:00
AAPL
pnl: -35.37
2017-08-03 00:00:00
AAPL
pnl: -42.17
2017-08-04 00:00:00
AAPL
pnl: -40.66
2017-08-07 00:00:00
AAPL
pnl: -41.45
2017-08-08 00:00:00
AAPL
pnl: -43.77
2017-08-09 00:00:00
AAPL
pnl: -44.99
2017-08-10 00:00:00
AAPL
pnl: -45.93
2017-08-11 00:00:00
AAPL
pnl: -41.01
2017-08-14 00:00:00
AAPL
pnl: -43.09
2017-08-15 00:00:00
AAPL
pnl: -45.37
2017-08-16 00:00:00
AAPL
pnl: -47.05
2017-08-17 00:00:00
AAPL
pnl: -46.43
2017-08-18 00:00:00
AAPL
pnl: -43.45
2017-08-21 00:00:00
AAPL
pnl: -43.11
2017-08-22 00:00:00
AAPL
pnl: -42.83
2017-08-23 00:00:00
AAPL
pnl: -45.30
2017-08-24 00:00:00
AAPL
pnl: -45.49
2017-08-25 00:00:00
AAPL
pnl: -44.81
2017-08-28 00:00:00
AAPL
pnl: -45.38
2017-08-29 00:00:00
AAPL
pnl: -46.93
2017-08-30 00:00:00
AAPL
pnl: -48.31
[Timestamp('2015-01-02 00:00:00', freq='C'), datetime.datetime(2017, 8, 30, 0, 0)]

Results for each timestamp are stored as csv file inside the folder ./runLogs, we also create logs using tensorboardX inside ./tb_logs so have a look at that as well using tensorboard --logdir=tb_logs


In [16]:
results


Out[16]:
{'instrument_names': ['AAPL'],
 'instrument_stats': [{'pnl': {'AAPL': -0.048736496000000004},
   'score': {'AAPL': -1.8440700333498883}}],
 'pnl': -0.048736496000000004,
 'trading_days': 694,
 'annual_return': -0.01797902430464371,
 'annual_vol': 0.024353421654489144,
 'sharpe_ratio': -0.7382545483636209,
 'score': -1.8440700333498883,
 'capitalUsage': 148.922734349998,
 'total_profit': 340.53843999999987,
 'maxDrawdown': 72.22124399999996,
 'maxPortfolioValue': 1023.484748,
 'total_loss': 389.2749359999995,
 'variance': 2.3535283582592883,
 'capital': 850.675049900002,
 'count_profit': 311,
 'portfolio_value': 951.263504,
 'count_loss': 338}

In [ ]: