#0015

Precision, Recall, and F1

MediumML18 min15 XP

Problem

Given TP, FP, and FN counts, return a dictionary with precision, recall, and F1. If a denominator is zero, return 0 for that metric.

Why This Matters

These metrics explain different failure modes. Precision asks "when we predict positive, are we right?" Recall asks "of actual positives, how many did we catch?"

Function Signature

def classification_metrics(tp, fp, fn):

Examples

Example 1

Inputtp = 8, fp = 2, fn = 4

Outputprecision = 0.8, recall = 0.6667, f1 = 0.7273

8 of 10 predicted positives were right; 8 of 12 real positives were caught.

Constraints

Counts are non-negative integers.
Return floats in a dictionary.
Handle zero denominators safely.

CodePython

def classification_metrics(tp, fp, fn):
    """
    Input example: tp = 8, fp = 2, fn = 4
    Return: precision = 0.8, recall = 0.6667, f1 = 0.7273
    Return the value from the function so the tests can compare it. Do not print unless the prompt asks.
    """
    # write your code here
    return {"precision": 0, "recall": 0, "f1": 0}

def classification_metrics(tp, fp, fn):
    """
    Input example: tp = 8, fp = 2, fn = 4
    Return: precision = 0.8, recall = 0.6667, f1 = 0.7273
    Return the value from the function so the tests can compare it. Do not print unless the prompt asks.
    """
    # write your code here
    return {"precision": 0, "recall": 0, "f1": 0}

Visible browser tests run here when available.

Testcases2 visible / 4 hidden categories

Typical metric values

Inputtp=8, fp=2, fn=4

Expectedprecision 0.8, recall 0.6667, f1 0.7273

The F1 score is the harmonic mean of precision and recall.

No predicted positives

Inputtp=0, fp=0, fn=5

Expectedprecision 0, recall 0, f1 0

The function should not divide by zero.

Hidden Test Categories

Perfect precision and recallPrecision high but recall lowRecall high but precision lowAll zero counts