Compute Accuracy, Precision, Recall, F1

Metrics & Evaluation

Medium

Compute accuracy, precision, recall, and F1 for single-label predictions. Support averaging modes:

Loading visualization...

Input: y_true=[0,1,2,2], y_pred=[0,1,0,2]

Output (micro): accuracy≈0.75, precision≈0.75, recall≈0.75, f1≈0.75

Hint 1

Build a confusion matrix first, then compute TP, FP, FN for each class from the matrix.

Hint 2

For micro averaging, sum all TP, FP, FN across classes. For macro, compute per-class metrics then average.

Inputs: equal-length arrays of integer labels
Single-label multi-class classification
No external ML libraries
Return dict: {"accuracy": float, "precision": float, "recall": float, "f1": float}

Try Similar Problems

Metrics & Evaluation

Medium

Compute accuracy, precision, recall, and F1 for single-label predictions. Support averaging modes:

Loading visualization...

Input: y_true=[0,1,2,2], y_pred=[0,1,0,2]

Output (micro): accuracy≈0.75, precision≈0.75, recall≈0.75, f1≈0.75

Hint 1

Build a confusion matrix first, then compute TP, FP, FN for each class from the matrix.

Hint 2

For micro averaging, sum all TP, FP, FN across classes. For macro, compute per-class metrics then average.

Inputs: equal-length arrays of integer labels
Single-label multi-class classification
No external ML libraries
Return dict: {"accuracy": float, "precision": float, "recall": float, "f1": float}

Try Similar Problems

Case 1

Case 2

y_true =

Accepts: array

y_pred =

Accepts: array

average =

Accepts: string

pos_label =

Accepts: number