yfinance.py

from statsmodels.tsa.stattools import adfuller
from statsmodels.tsa.seasonal import seasonal_decompose
import statsmodels.api as sm
from sklearn.metrics import mean_squared_error, mean_absolute_error
import math

#Test for staionarity
def test_stationarity(timeseries):
    #Determing rolling statistics
    rolling_mean = timeseries.rolling(12).mean()
    rolling_std = timeseries.rolling(12).std()
    #Plot rolling statistics:
    plt.plot(timeseries, color='blue',label='Original')
    plt.plot(rolling_mean, color='red', label='Rolling Mean')
    plt.plot(rolling_std, color='black', label = 'Rolling Std')
    plt.legend(loc='best')
    plt.title('Rolling Mean and Standard Deviation')
    plt.show(block=False)
    
    print("Results of dickey fuller test")

    timeseries = timeseries.iloc[:,0].values
    adfuller_result = adfuller(timeseries,autolag='AIC')
    print(adfuller_result)
    """ By setting the autolag='AIC' the adfuller will choose the number of lags that yields the lowest AIC (Akaike information criterion ). 
    This is usually a good option to follow. 
    The Akaike information criterion (AIC) is an estimator of prediction error and 
    thereby relative quality of statistical models for a given set of data."""
    
    # output for dft will give us without defining what the values are.
    #hence we manually write what values does it explain using a for loop
    output = pd.Series(adfuller_result[0:4],index=['Test Statistics','p-value','No. of lags used','Number of observations used'])
    
    for key,values in adfuller_result[4].items():
        output['critical value (%s)'%key] =  values
    print(output)
    
test_stationarity(tsla_closing_prices_df)