Model comparison strategies in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to split data into training and testing sets.

ML Python

from sklearn.model_selection import [1]
X_train, X_test, y_train, y_test = [1](X, y, test_size=0.2, random_state=42)

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

Atrain_test_split

Btrain_test_ratio

CGridSearchCV

Dcross_val_score

Attempts:

3 left

2fill in blank

medium

Complete the code to perform 5-fold cross-validation on a model.

ML Python

from sklearn.model_selection import cross_val_score
scores = cross_val_score(model, X, y, cv=[1])

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

A3

B5

C1

D10

Attempts:

3 left

3fill in blank

hard

Fix the error in the code to calculate accuracy score after predictions.

ML Python

from sklearn.metrics import accuracy_score
accuracy = accuracy_score(y_true, [1])

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

Ay_pred

By_true

Cy_score

Dy_train

Attempts:

3 left

4fill in blank

hard

Fill both blanks to create a dictionary of mean cross-validation scores for each model.

ML Python

cv_scores = {model_name: cross_val_score(model, X, y, cv=5).[1]() for model_name, model in [2].items()}

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

Amean

Bmax

Cmodels

Dscores

Attempts:

3 left

5fill in blank

hard

Fill all three blanks to select the best model based on highest mean cross-validation score.

ML Python

best_model_name = max(cv_scores, key=lambda k: cv_scores[[1]])
best_score = cv_scores[[2]]
print(f"Best model: [3] with score {best_score:.2f}")

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

Ak

Bbest_model_name

Dcv_scores

Attempts:

3 left