Precision and recall are two core metrics for evaluating binary classification models, especially when class imbalance makes accuracy misleading. In this problem, you’ll compute both metrics from ground-truth labels and model predictions.

The formulas are:
$$
\text{Precision}=\frac{TP}{TP+FP}, \quad \text{Recall}=\frac{TP}{TP+FN}
$$

## Requirements

Implement the function
```python
def precision_recall(y_true, y_pred):
    \"""
    Computes precision and recall for binary classification.

    Args:
        y_true (np.ndarray): Ground-truth labels (0 or 1).
        y_pred (np.ndarray): Predicted labels (0 or 1).

    Returns:
        tuple[float, float]: (precision, recall)
    \"""
    # Your solution below
```

**Rules:**
- Treat label `1` as the positive class and `0` as the negative class.
- Compute `TP`, `FP`, and `FN` from `y_true` and `y_pred`, then return `(precision, recall)`.
- Return results as floats (not percentages).
- Don’t use any prebuilt metric functions (e.g., from `sklearn`).
- Use NumPy vectorized operations for efficiency.

## Example

```python
y_true = np.array([1, 0, 1, 1, 0, 0])
y_pred = np.array([1, 0, 0, 1, 1, 0])

precision_recall(y_true, y_pred)
```

Output:
```python
(0.6666666667, 0.6666666667)
```

Pairs Exceeding Product 11

Basic Calculator

Precision and recall

Solve this easy level ML coding question from General. The premier LeetCode for ML platform to master Python, SQL, and Machine Learning algorithms.

357. Precision and recall

Examples

Constraints

Similar Questions

Argument	Type
y_pred	np.ndarray
y_true	np.ndarray