Skip to content

Commit

Permalink
Fix typo in readme for output values of confusion matrix when `normal…
Browse files Browse the repository at this point in the history
…ize` is used

 * Also, specify valid values for `normalize` in Inputs section.
  • Loading branch information
dantp-ai committed Dec 10, 2024
1 parent 55f1bc6 commit b12d719
Showing 1 changed file with 2 additions and 2 deletions.
4 changes: 2 additions & 2 deletions metrics/confusion_matrix/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -54,11 +54,11 @@ At minimum, this metric requires predictions and references as inputs.
- **references** (`list` of `int`): Ground truth labels.
- **labels** (`list` of `int`): List of labels to index the matrix. This may be used to reorder or select a subset of labels.
- **sample_weight** (`list` of `float`): Sample weights.
- **normalize** (`str`): Normalizes confusion matrix over the true (rows), predicted (columns) conditions or all the population.
- **normalize** (`str`): Normalizes confusion matrix over the true (rows), predicted (columns) conditions or all the population. (Valid values are `'pred', 'all', 'true'` or `None`).


### Output Values
- **confusion_matrix**(`list` of `list` of `str`): Confusion matrix. Minimum possible value is 0. Maximum possible value is 1.0, or the number of examples input, if `normalize` is set to `True`.
- **confusion_matrix** (`list` of `list` of `str`): Confusion matrix. Minimum possible value is 0. Maximum possible value is 1.0, or the number of examples in the input, if `normalize` is set to `None` (default value).

Output Example(s):
```python
Expand Down

0 comments on commit b12d719

Please sign in to comment.