Function coinT() tests if two time series are stationary using ADF test and Hurst exponent. Time series are stored in cvs files 1511x6 each, but for testing only a vector of the 5th column is returned by function stock(), there are 50 files in total. It seems that the program is using too much memory as it makes the PC crash after running for ~30 secs, it works fine on 15 files, but crashes on larger sets(>50).
Can somebody please help me out to find where is the memory leak, I've tried splitting computations in to multiple functions and deleting object, but it didn't help much.
import numpy as np
import pandas as pd
import statsmodels.tsa.stattools as ts
import csv
import timeit
from numpy import log, polyfit, sqrt, std, subtract
from pandas.stats.api import ols
import os
src = 'C:/Users/PC/Desktop/Magistr/Ibpython/testing/'
filenames = next(os.walk(src))[2] #load all stock file names into array
cointegratedPairs = []
def hurst(ts):
"""Returns the Hurst Exponent of the time series vector ts
H<0.5 - The time series is mean reverting
H=0.5 - The time series is a Geometric Brownian Motion
H>0.5 - The time series is trending"""
# Create the range of lag values
lags = range(2, 100)
# Calculate the array of the variances of the lagged differences
tau = [sqrt(std(subtract(ts[lag:], ts[:-lag]))) for lag in lags]
# Use a linear fit to estimate the Hurst Exponent
poly = polyfit(log(lags), log(tau), 1)
del lags
del tau
# Return the Hurst exponent from the polyfit output
return poly[0]*2.0
#Convert file into an array
def stock(filename):
#read file into array and get it's length
delimiter = ","
with open(src + filename,'r') as dest_f:
data_iter = csv.reader(dest_f,
delimiter = delimiter,
quotechar = '"')
data = [data for data in data_iter]
data_array = np.asarray(data)[:,5]
return data_array
del data
del data_array
#Check if two time series are cointegrated
def coinTest(itemX, itemY):
indVar = map(float, stock(itemX)[0:1000]) #2009.05.22 - 2013.05.14
depVar = map(float, stock(itemY)[0:1000]) #2009.05.22 - 2013.05.14
#Calculate optimal hedge ratio "beta"
df = pd.DataFrame()
df[itemX] = indVar
df[itemY] = depVar
res = ols(y=df[itemY], x=df[itemX])
beta_hr = res.beta.x
alpha = res.beta.intercept
df["res"] = df[itemY] - beta_hr*df[itemX] - alpha
#Calculate the CADF test on the residuals
cadf = ts.adfuller(df["res"])
#Reject the null hypothesis at 1% confidence level
if cadf[4]['1%'] > cadf[0]:
#Hurst exponent test if residuals are mean reverting
if hurst(df["res"]) < 0.4:
cointegratedPairs.append((itemY,itemX))
del indVar
del depVar
del df[itemX]
del df[itemY]
del df["res"]
del cadf
#Main function
def coinT():
limit = 0
TotalPairs = 0
for itemX in filenames:
for itemY in filenames[limit:]:
TotalPairs +=1
if itemX == itemY:
next
else:
coinTest(itemX, itemY)
limit +=1
