model = VAR(df_train)
for i in [1, 2, 3, 4, 5, 6, 7, 8, 9]:
result = model.fit(i)
print('Lag Order =', i)
print('AIC : ', result.aic)
print('BIC : ', result.bic)
print('FPE : ', result.fpe)
print('HQIC: ', result.hqic, '\n')
# In[53]:
#An alternate method to choose the order(p) of the VAR models is to use the model.select_order(maxlags)method.
#The selected order(p) is the order that gives the lowest ‘AIC’, ‘BIC’, ‘FPE’ and ‘HQIC’ scores.
x = model.select_order(maxlags=12)
x.summary()
# ### Train the VAR Model
# In[54]:
model_fitted = model.fit(3)
model_fitted.summary()
# ### Check for Serial Correlation of Residuals
# In[56]:
#If there is any correlation left in the residuals, then,
#there is some pattern in the time series that is still left to be explained by the model.
adfuller(df_train_diff['y_538']) ## looks good
# the model
model = VAR(df_train_diff)
## choosing best P (order) of VAR model
for i in [1, 2, 3, 4, 5, 6, 7]:
result = model.fit(i)
print('Lag Order =', i)
print('AIC : ', result.aic)
print('BIC : ', result.bic)
print('FPE : ', result.fpe)
print('HQIC: ', result.hqic, '\n')
# 4 looks best here, lets try the automatic way
best = model.select_order(maxlags=7)
best.summary(
) ## hmm two for 4, two for 7. Try both and see what is better maybe?
# start with 4
fitted = model.fit(4)
fitted.summary()
## durbin-watson for serial error correlation
# 2 is good, 0 = positive correlation, 4 = negative correlation
from statsmodels.stats.stattools import durbin_watson
dw = durbin_watson(fitted.resid)
dw ## looks great!
## the forecast
lag_order = fitted.k_ar # to verify
for_forecast = df_train_diff.values[-lag_order:]
