def testVWAP(self):
taqBaseDir = "/Users/leonmaclin/Documents/sampleTAQ/"
filePathName = "trades/20070620/IBM_trades.binRT"
start930 = 19 * 60 * 60 * 1000 / 2
end4 = 16 * 60 * 60 * 1000
vwap = VWAP(TAQTradesReader(taqBaseDir + filePathName), start930, end4)
print("There were %d trades and a VWAP price of %f" %
(vwap.getN(), vwap.getVWAP()))
def testName(self):
startTS = 18 * 60 * 60 * 1000 / 2 # 930AM
endTS = 16 * 60 * 60 * 1000 # 4PM
numBuckets = 2
baseDir = '/Users/leonmaclin/Documents/sampleTAQ/'
fileName = 'trades/20070620/IBM_trades.binRT'
data = TAQTradesReader(baseDir + fileName)
returnBuckets = ReturnBuckets(data, startTS, endTS, numBuckets)
self.assertTrue(returnBuckets.getN() == 2)
def getTradesFile(
self,
dateString, # eg "20070620", a string
ticker):
filePathName = self._baseDir + "trades/" + dateString + "/" + ticker + "_trades.binRT"
if (not (os.path.exists(filePathName))):
raise Exception("File %s doesn't exist" % filePathName)
if (not (access(filePathName, R_OK))):
raise Exception("You don't have access to %s" % filePathName)
return TAQTradesReader(filePathName)
def test_classifyAll(self):
filePathName = "/Users/leonmaclin/Documents/sampleTAQ/trades/20070620/IBM_trades.binRT"
data = TAQTradesReader(filePathName)
tickTest = TickTest()
startOfDay = 18 * 60 * 60 * 1000 / 2
endOfDay = startOfDay + ( 13 * 60 * 60 * 1000 / 2 )
classifications = tickTest.classifyAll( data, startOfDay, endOfDay )
# To see the first 10 prices, enable Window > Show view > Expressions
# In the Expressions window, paste: list(map(lambda i: data.getPrice(i), range( 0, 10 )))
self.assertTrue( data.getPrice(1) < data.getPrice(0) )
# Each classification is a tuple containing timestamp, price, and classification
self.assertTrue( classifications[ 0 ][ 2 ] == 0 ) # 1st good price has a classification of 0
self.assertTrue( classifications[ 1 ][ 2 ] == -1 ) # 2nd good price has a classification of -1
# We now look at the back of the queue
self.assertTrue( classifications[-4][1] < classifications[-3][1] ) # 4th last price is less than 3rd last price
self.assertAlmostEqual( classifications[-3][1], classifications[-2][1], 0.00001 ) # 3rd last price and 2nd last price are the same
self.assertAlmostEqual( classifications[-2][1], classifications[-1][1], 0.00001 ) # 2nd last price and last price are the same
self.assertTrue( classifications[-3][2] == 1 )
self.assertTrue( classifications[-2][2] == 1 )
self.assertTrue( classifications[-1][2] == 1 )
def testConstructor(self):
startTS = None
endTS = None
numBuckets = 2
baseDir = "/Users/leonmaclin/Documents/sampleTAQ/"
fileName = "trades/20070620/IBM_trades.binRT"
data = TAQTradesReader( baseDir + fileName )
fpb = FirstPriceBuckets( data, numBuckets, startTS, endTS )
self.assertTrue( fpb.getN() == 2 )
self.assertTrue( fpb.getTimestamp( 0 ) == 34241000 and fpb.getTimestamp( 1 ) == 45901000 )
self.assertTrue( fpb.getPrice( 0 ) > ( 106.5 - 0.0001 ) and fpb.getPrice( 0 ) < ( 106.5 + 0.0001 ) )
self.assertTrue( fpb.getPrice( 1 ) > ( 106.73999786376953 - 0.0001 ) and fpb.getPrice( 1 ) < ( 106.73999786376953 + 0.0001 ) )
def testConstructor(self):
startTS = None
endTS = None
numBuckets = 2
baseDir = '/Users/leonmaclin/Documents/sampleTAQ/'
fileName = 'trades/20070620/IBM_trades.binRT'
data = TAQTradesReader(baseDir + fileName)
fpb = LastPriceBuckets(data, numBuckets, startTS, endTS)
self.assertTrue(fpb.getN() == 2)
self.assertTrue(
fpb.getTimestamp(0) == 45896000
and fpb.getTimestamp(1) == 57599000)
self.assertTrue(
fpb.getPrice(0) > (106.72000122070312 - 0.0001)
and fpb.getPrice(0) < (106.72000122070312 + 0.0001))
self.assertTrue(
fpb.getPrice(1) > (106.0 - 0.0001) and fpb.getPrice(1) <
(106.0 + 0.0001))
print("Finished")
def test1(self):
dirc = '/Users/Zibin/NYU/twriter.gz'
w = TradeWriter(dirc, 1) # Create a .gz file on directory
r = TAQTradesReader('/Users/Zibin/Documents/R/trades/20070620/NVDA_trades.binRT') # Read a file
# Using tested readers, test for expected values
baseTS = r.getSecsFromEpocToMidn() * 1000
ts = baseTS + r.getMillisFromMidn(0)
s = r.getSize(0)
p = r.getPrice(0)
w.writer(r,1,1) # write to the file
b = BinReader(dirc, '>QIIf', 100) # use binreader to read
ts0, _, size0, p0 = b.next()
b.close()
self.assertEquals( ts0, ts ) # Check if time stamps are equal
self.assertEquals( size0, s ) # Check if numbers of shares are equal
self.assertAlmostEquals( p0, p ) # Check if prices are equal
def testXMinuteReturns(self):
taqBaseDir = "/Users/canelbiryol/Documents/sampleTAQ/"
filePathName = "trades/20070620/IBM_trades.binRT"
data = TAQTradesReader(taqBaseDir + filePathName)
def ori_vs_adj_trade_NVDA():
dayStartNVDA = '20070910' # Start day
dayEndNVDA = '20070911' # End day
parentddir1 = os.path.abspath(os.path.join(os.path.dirname(__file__), os.path.pardir))
parentddir2 = os.path.abspath(os.path.join(parentddir1, os.path.pardir))
oriTradeStartNVDA = TAQTradesReader(os.path.join(parentddir2, 'R/trades/'+dayStartNVDA+'/NVDA_trades.binRT'))
oriTradeEndNVDA = TAQTradesReader(os.path.join(parentddir2, 'R/trades/'+dayEndNVDA+'/NVDA_trades.binRT'))
oriPriceNVDA = [] # List to store price
oriShareNVDA = [] # List to store number of shares
timeList = [] # List to store time stamp
# Append data to each of the lists
for i in range(oriTradeStartNVDA.getN()):
oriPriceNVDA.append(oriTradeStartNVDA.getPrice(i))
oriShareNVDA.append(oriTradeStartNVDA.getSize(i))
timeList.append(1189396800000 + oriTradeStartNVDA.getTimestamp(i))
for i in range(oriTradeEndNVDA.getN()):
oriPriceNVDA.append(oriTradeEndNVDA.getPrice(i))
oriShareNVDA.append(oriTradeEndNVDA.getSize(i))
timeList.append(1189483200000 + oriTradeEndNVDA.getTimestamp(i))
# convert data format to datetime
dateTimeList = []
for timeStamp in timeList:
dateTimeList.append(datetime.fromtimestamp(timeStamp/1000))
adjTradeStartNVDA = BinReader(os.path.join(os.getcwd(), 'adjusted_trades/NVDA_trades.gz'), '>QIIf', 100)
ts0, _, size0, p0 = adjTradeStartNVDA.next()
ts = []
ts.append(ts0)
share = []
share.append(size0)
price = []
price.append(p0)
while adjTradeStartNVDA.hasNext():
t, i, s, p = adjTradeStartNVDA.next()
ts.append(t)
share.append(s)
price.append(p)
sIdx = binarySearch(ts, 0, len(ts)-1, timeList[0]) # find the start index
eIdx = binarySearch(ts, 0, len(ts)-1, timeList[-1]) # find the end index
pList = price[sIdx:eIdx+1]
sList = share[sIdx:eIdx+1]
adjTradeStartNVDA.close() # close bin reader
plt.figure(figsize=(9,6))
ax = plt.gca()
xfmt = mdates.DateFormatter('%m-%d %H:%M')
ax.xaxis.set_major_formatter(xfmt)
plt.plot(dateTimeList[:-5], oriPriceNVDA[:-5], ls = 'None', marker = 'o', ms = 5, color = 'y', label = 'original')
plt.plot(dateTimeList[:-5], pList, ls = 'None', marker = 'x', ms = 2 , color = 'black', label = 'adjusted')
plt.xticks([datetime.strptime('2007-09-10 10:00:00', '%Y-%m-%d %H:%M:%S'),
datetime.strptime('2007-09-10 15:00:00', '%Y-%m-%d %H:%M:%S'),
datetime.strptime('2007-09-11 09:30:00', '%Y-%m-%d %H:%M:%S'),
datetime.strptime('2007-09-11 15:00:00', '%Y-%m-%d %H:%M:%S')])
plt.title('Original NVDA Trade Price VS Adjusted NVDA Trade Price')
plt.xlabel('Time')
plt.ylabel('Price')
plt.legend()
plt.show()
plt.figure(figsize=(9,6))
ax = plt.gca()
xfmt = mdates.DateFormatter('%m-%d %H:%M')
ax.xaxis.set_major_formatter(xfmt)
plt.plot(dateTimeList[:-5], oriShareNVDA[:-5], ls = 'None', marker = 'o', ms = 5, color = 'y', label = 'original')
plt.plot(dateTimeList[:-5], sList, ls = 'None', marker = 'x', ms = 2 , color = 'black', label = 'adjusted')
plt.xticks([datetime.strptime('2007-09-10 10:00:00', '%Y-%m-%d %H:%M:%S'),
datetime.strptime('2007-09-10 15:00:00', '%Y-%m-%d %H:%M:%S'),
datetime.strptime('2007-09-11 09:30:00', '%Y-%m-%d %H:%M:%S'),
datetime.strptime('2007-09-11 15:00:00', '%Y-%m-%d %H:%M:%S')])
plt.ylim(0,10000)
plt.title('Original NVDA Trade Share VS Adjusted NVDA Trade Share')
plt.xlabel('Time')
plt.ylabel('Number of Shares')
plt.legend()
plt.show()
def test1(self):
fileName = '/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/data/sampleTAQ/sampleTAQ/trades/20070620/IBM_trades.binRT'
reader = TAQTradesReader(fileName)
print(reader.getN())
def test1(self):
# Stocks and trades
s_p500 = '/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/s_p500.xlsx'
stackedTrades = np.array(
[['20070620', 34241000, 106.5, 85200.0],
['20070621', 57596000, 106.61000061035156, 500.0],
['20070621', 57596000, 106.61000061035156, 200.0],
['20070621', 57597000, 106.5999984741211, 200.0],
['20070621', 57597000, 106.5999984741211, 200.0],
['20070621', 57597000, 106.5999984741211, 200.0]])
stackedQuotes = np.array(
[['20070620', 34241000, 106.5, 85200.0, 106.1, 8200.0],
['20070621', 57597000, 106.5, 85200.0, 106.1, 800.0],
['20070621', 57597000, 106.5, 85200.0, 106.1, 800.0],
['20070621', 57597000, 106.5, 85200.0, 106.1, 800.0],
['20070621', 57597000, 106.5, 85200.0, 106.1, 800.0]])
# Directories where to store
filepathadj = '/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/adj/'
filepathcln = '/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/cln/'
# Multipliers map
multmap = AdjustingHashmap(s_p500)
# Write after reading and adjusting
adjuster = TAQAdjust(stackedQuotes, stackedTrades, 'IBM', multmap)
adjuster.setPriceMult("20070621", 2.0)
adjuster.setVolMult("20070621", 4.0)
adjuster.adjustQuote()
adjuster.adjustTrade()
adjuster.storeAdjustedQuotes(filepathadj)
adjuster.storeAdjustedTrades(filepathadj)
# Write after reading and cleaning
cleaner = TAQCleaner(stackedQuotes, stackedTrades, 'IBM')
stackedQuotes = stackedQuotes[cleaner.cleanQuotesIndices() == True, :]
stackedTrades = stackedTrades[cleaner.cleanTradesIndices() == True, :]
cleaner.storeCleanedQuotes(filepathcln)
cleaner.storeCleanedTrades(filepathcln)
# Read results
readerclnQ = TAQQuotesReader(
'/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/cln/quotes/20070620/IBM_quotes.binRQ'
)
readerclnT = TAQTradesReader(
'/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/cln/trades/20070620/IBM_trades.binRT'
)
readeradjQ = TAQQuotesReader(
'/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/adj/quotes/20070620/IBM_quotes.binRQ'
)
readeradjT = TAQTradesReader(
'/media/louis/DATA/documents/cours/NYU/SPRING_18/ATQS/HK1/adj/trades/20070620/IBM_trades.binRT'
)
# Using previously tested readers, test for expected values
self.assertEquals(readerclnQ.getN(), 5)
self.assertEquals(readerclnQ.getSecsFromEpocToMidn(), 0)
self.assertEquals(readerclnQ.getMillisFromMidn(readerclnQ.getN() - 1),
57597000)
self.assertEquals(readerclnQ.getBidSize(readerclnQ.getN() - 1), 21300)
self.assertEquals(readerclnQ.getAskSize(readerclnQ.getN() - 1), 200)
self.assertAlmostEquals(readerclnQ.getAskPrice(readerclnQ.getN() - 1),
53.0499, 3)
self.assertAlmostEquals(readerclnQ.getBidPrice(readerclnQ.getN() - 1),
53.25, 3)
# Using previously tested readers, test for expected values
self.assertEquals(readeradjQ.getN(), 5)
self.assertEquals(readeradjQ.getSecsFromEpocToMidn(), 0)
self.assertEquals(readeradjQ.getMillisFromMidn(readeradjQ.getN() - 1),
57597000)
self.assertEquals(readeradjQ.getBidSize(readeradjQ.getN() - 1), 21300)
self.assertEquals(readeradjQ.getAskSize(readeradjQ.getN() - 1), 200)
self.assertAlmostEquals(readeradjQ.getAskPrice(readeradjQ.getN() - 1),
53.0499, 3)
self.assertAlmostEquals(readeradjQ.getBidPrice(readeradjQ.getN() - 1),
53.25, 3)
# Using previously tested readers, test for expected values
self.assertEquals(readerclnT.getN(), 6)
self.assertEquals(readerclnT.getSecsFromEpocToMidn(), 0)
self.assertEquals(readerclnT.getMillisFromMidn(readerclnT.getN() - 1),
57597000)
self.assertEquals(readerclnT.getSize(readerclnT.getN() - 1), 50)
self.assertAlmostEquals(readerclnT.getPrice(readerclnT.getN() - 1),
53.29999, 3)
# Using previously tested readers, test for expected values
self.assertEquals(readeradjT.getN(), 6)
self.assertEquals(readeradjT.getSecsFromEpocToMidn(), 0)
self.assertEquals(readeradjT.getMillisFromMidn(readeradjT.getN() - 1),
57597000)
self.assertEquals(readeradjT.getSize(readeradjT.getN() - 1), 50)
self.assertAlmostEquals(readerclnT.getPrice(readeradjT.getN() - 1),
53.29999, 3)
def test1(self):
fileName = 'D:/TAQClean/trades/20070620/IBM_trades.binRT'
reader = TAQTradesReader( fileName )
print( reader.getN() )
print( reader.getTimestamp(1) )