Evaluation metrics (accuracy, F1, confusion matrix) in NLP - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to calculate accuracy score for predictions.

NLP

from sklearn.metrics import [1]

true_labels = [0, 1, 1, 0, 1]
pred_labels = [0, 0, 1, 0, 1]

acc = [1](true_labels, pred_labels)
print(f"Accuracy: {acc}")

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

Aconfusion_matrix

Bf1_score

Caccuracy_score

Dclassification_report

Attempts:

3 left

💡 Hint

Common Mistakes

Using f1_score instead of accuracy_score for accuracy calculation.

Confusing confusion_matrix output with accuracy value.

The accuracy_score function calculates the ratio of correct predictions to total predictions.

2fill in blank

medium

Complete the code to calculate F1 score for binary classification.

NLP

from sklearn.metrics import f1_score

true_labels = [1, 0, 1, 1, 0]
pred_labels = [1, 0, 0, 1, 0]

f1 = f1_score(true_labels, pred_labels, [1]='binary')
print(f"F1 Score: {f1}")

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

Aaverage

Bpos_label

Clabels

Dzero_division

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'pos_label' instead of 'average' parameter.

Omitting the 'average' parameter causing errors in multiclass.

The 'average' parameter specifies the type of averaging performed on the data for F1 score calculation.

3fill in blank

hard

Fix the error in the code to correctly compute confusion matrix.

NLP

from sklearn.metrics import confusion_matrix

true = [1, 0, 1, 1, 0]
pred = [1, 1, 1, 0, 0]

cm = confusion_matrix([1], pred)
print(cm)

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

Atrue

Bpred

Caverage

Dlabels

Attempts:

3 left

💡 Hint

Common Mistakes

Swapping true and predicted labels in confusion_matrix function.

Passing parameters unrelated to labels.

The first argument to confusion_matrix must be the true labels, followed by predicted labels.

4fill in blank

hard

Fill both blanks to create a confusion matrix and extract true positives.

NLP

from sklearn.metrics import confusion_matrix

true = [0, 1, 0, 1, 1]
pred = [0, 0, 0, 1, 1]

cm = confusion_matrix(true, pred)
true_positives = cm[1][2]
print(f"True Positives: {true_positives}")

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

A[1]

B[1, 1]

C[0, 0]

D[0]

Attempts:

3 left

💡 Hint

Common Mistakes

Using cm[0][0] which is true negatives, not true positives.

Using incorrect indices causing index errors.

True positives are located at row 1, column 1 in the confusion matrix, accessed by cm[1][1].

5fill in blank

hard

Fill all three blanks to compute accuracy, F1 score, and confusion matrix for predictions.

NLP

from sklearn.metrics import [1], [2], [3]

true = [1, 0, 1, 0, 1]
pred = [1, 0, 0, 0, 1]

acc = [1](true, pred)
f1 = [2](true, pred, average='binary')
cm = [3](true, pred)

print(f"Accuracy: {acc}")
print(f"F1 Score: {f1}")
print(f"Confusion Matrix:\n{cm}")

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

Aaccuracy_score

Bf1_score

Cconfusion_matrix

Dclassification_report

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up metric function names or parameters.

Forgetting to specify average='binary' for f1_score.

Use accuracy_score for accuracy, f1_score for F1, and confusion_matrix for confusion matrix.