multilabel-eval-metrics

MultiLabel Classifier Evaluation Metrics

This toolkit focuses on different evaluation metrics that can be used for evaluating the performance of a multilabel classifier.

Intro

The evaluation metrics for multi-label classification can be broadly classified into two categories:

Example-Based Evaluation Metrics
Label Based Evaluation Metrics

Metrics

Exact Match Ratio (EMR)
1/0 Loss
Hamming Loss
Example-Based Accuracy
Example-Based Precision
Label Based Metrics
Macro Averaged Accuracy
Macro Averaged Precision
Macro Averaged Recall
Micro Averaged Accuracy
Micro Averaged Precision
Micro Averaged Recall
α- Evaluation Score

Examples

from multilabel_eval_metrics import *
import numpy as np
if __name__=="__main__":
    y_true = np.array([[0, 1], [1, 1], [1, 1], [0, 1], [1, 0]])
    y_pred = np.array([[1, 1], [1, 0], [1, 1], [0, 1], [1, 0]])
    print(y_true)
    print(y_pred)
    result=MultiLabelMetrics(y_true,y_pred).get_metric_summary(show=True)

License

The multilabel-eval-metrics toolkit is provided by Donghua Chen with MIT License.

Reference

Evaluation Metrics for Multi-Label Classification

Release files for multilabel-eval-metrics 0.0.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for multilabel-eval-metrics 0.0.2
File	Size	Uploaded
multilabel-eval-metrics-0.0.2.tar.gz	10.3 kB	Apr 19, 2022	Details

Built distribution (wheel)

Table of built distributions (wheels) for multilabel-eval-metrics 0.0.2
File	Interpreter	ABI	Platform	Reset
multilabel_eval_metrics-0.0.2-py3-none-any.whl 8.4 kB Apr 19, 2022	Python 3	none	any	Details

Total release size: 18.7 kB

Release files / multilabel-eval-metrics-0.0.2.tar.gz

Download URL	multilabel-eval-metrics-0.0.2.tar.gz
Size	10.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`f410224fa78c7026e82c522391b3e7cd2e166d970c0827a9161e2f75e89f4d32`
BLAKE2b-256 checksum How to use checksums	`08ad3a85e01344f5c0cf5a14d79474d0120526b6c45dc88a444a4405c59702a3`
Upload date	Apr 19, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/4.8.3 pkginfo/1.7.1 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.6`

Release files / multilabel_eval_metrics-0.0.2-py3-none-any.whl

Download URL	multilabel_eval_metrics-0.0.2-py3-none-any.whl
Size	8.4 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`15865bc1f2ef573423ce08e2ea3a487d365e9080283cca0180be07d2efec48c2`
BLAKE2b-256 checksum How to use checksums	`86df8fb9ceee947b3dbd3880ea8a6767562d0446340c3eededc0eb582ba2f275`
Upload date	Apr 19, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.2 importlib_metadata/4.8.3 pkginfo/1.7.1 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.6`