test_stationarity.py

test_stationarity.py

from pandas import Series
from statsmodels.tsa.stattools import adfuller
def test_stationarity(timeseries, windowroll = 12, cutoff = 0.05):    
    #Determing rolling statistics
    rolmean = pd.rolling_mean(timeseries, window=windowroll)
    rolstd = pd.rolling_std(timeseries, window=windowroll)
    #Plot rolling statistics:
    orig = plt.plot(timeseries, color='blue',label='Original')
    mean = plt.plot(rolmean, color='red', label='Rolling Mean')
    std = plt.plot(rolstd, color='black', label = 'Rolling Std')
    plt.legend(loc='best')
    plt.title('Rolling Mean & Standard Deviation')
    plt.show(block=False)
    
    #Perform Dickey-Fuller test:
    # H_0 in adfuller is unit root exists (Non-Stationary)
    # We must observe significant p-value to convince ourselves tha the series is stationary
    print ('Results of Dickey-Fuller Test:')
    dftest = adfuller(timeseries, autolag='AIC')
    dfoutput = pd.Series(dftest[0:4], index=['Test Statistic','p-value','#Lags Used','Number of Observations Used'])
    pvalue = dftest[1]
    if pvalue <= cutoff:
        print('p-value = '+ str(pvalue) + ' The series '+ timeseries.name + ' is likely stationary.')
        #return True
    else:
        print('p-value = '+ str(pvalue) + ' The series '+ timeseries.name + ' is likely non-stationary.')
        #return False
    for key,value in dftest[4].items():
        dfoutput['Critical Value (%s)'%key] = value
    print (dfoutput)

#%%
series = Series.from_csv('C:\\Users\\kdura\\Desktop\\eurusdclose.csv', header=0)
test_stationarity(series,12)