ARIMA model basics in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the ARIMA model from the statsmodels library.

ML Python

from statsmodels.tsa.arima.model import [1]

Drag options to blanks, or click blank then click option'

AARIMA

BLinearRegression

CKMeans

DRandomForest

Attempts:

3 left

💡 Hint

Common Mistakes

Importing unrelated models like LinearRegression or KMeans.

Using incorrect module paths.

The ARIMA model is imported from statsmodels.tsa.arima.model as ARIMA.

2fill in blank

medium

Complete the code to create an ARIMA model with order (1, 1, 1) for the time series data 'data'.

ML Python

model = ARIMA(data, order=[1])

Drag options to blanks, or click blank then click option'

A(1, 0, 1)

B(1, 1, 1)

C(0, 1, 0)

D(2, 1, 2)

Attempts:

3 left

💡 Hint

Common Mistakes

Using order with zero differencing when data is non-stationary.

Confusing the order tuple values.

The order (1, 1, 1) means AR=1, differencing=1, MA=1, which is a common ARIMA setup.

3fill in blank

hard

Fix the error in the code to fit the ARIMA model and save the result in 'fitted_model'.

ML Python

fitted_model = model.[1]()

Drag options to blanks, or click blank then click option'

Afit

Btrain

Cpredict

Dtransform

Attempts:

3 left

💡 Hint

Common Mistakes

Using predict() before fitting the model.

Using non-existent methods like train().

The fit() method trains the ARIMA model on the data.

4fill in blank

hard

Fill both blanks to generate predictions for the next 5 time points using the fitted ARIMA model.

ML Python

forecast = fitted_model.[1](steps=[2])

Drag options to blanks, or click blank then click option'

Aforecast

Bpredict

C5

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using predict() instead of forecast() for future points.

Setting steps to a wrong number.

The forecast() method with steps=5 predicts the next 5 points.

5fill in blank

hard

Fill all three blanks to print the summary of the fitted ARIMA model and extract the AIC value.

ML Python

print(fitted_model.[1]())
aic_value = fitted_model.[2]
print('AIC:', [3])

Drag options to blanks, or click blank then click option'

Asummary

Baic

Caic_value

Dparams

Attempts:

3 left

💡 Hint

Common Mistakes

Trying to call aic as a method instead of attribute.

Printing the attribute directly without storing.

summary() prints model details; aic attribute holds the AIC value; we print the variable aic_value.