Searching over model order
In this exercise you are faced with a dataset which appears to be an ARMA model. You can see the ACF and PACF in the plot below. In order to choose the best order for this model you are going to have to do a search over lots of potential model orders to find the best set.

The ARIMA
model class and the time series DataFrame df
are available in your environment.
Este ejercicio forma parte del curso
ARIMA Models in Python
Instrucciones del ejercicio
- Loop over values of
p
from 0-2. - Loop over values of
q
from 0-2. - Train and fit an ARMA(p,q) model.
- Append a tuple of
(p,q, AIC value, BIC value)
toorder_aic_bic
.
Ejercicio interactivo práctico
Prueba este ejercicio y completa el código de muestra.
# Create empty list to store search results
order_aic_bic=[]
# Loop over p values from 0-2
for p in range(____):
# Loop over q values from 0-2
for q in range(____):
# create and fit ARMA(p,q) model
model = ARIMA(df, order=____)
results = model.fit()
# Append order and results tuple
order_aic_bic.append((____))