Metrics Report
MetricsReport is a Python package that generates classification and regression metrics report for machine learning models.
Features
- AutoDetect the type of task
- Save report in .html and .md format
- Has several plotting functions
Installation
You can install MetricsReport using pip:
pip install metricsreport
Usage
from metricsreport import MetricsReport
# sample classification data
y_true = [1, 0, 0, 1, 0, 1, 0, 1]
y_pred = [0.8, 0.3, 0.1, 0.9, 0.4, 0.7, 0.2, 0.6]
# generate report
report = MetricsReport(y_true, y_pred, threshold=0.5)
# print all metrics
print(report.metrics)
# plot ROC curve
report.plot_roc_curve()
# saved MetricsReport (html) in folder: report_metrics
report.save_report()
More examples in the folder ./examples:
Constructor
MetricsReport(y_true, y_pred, threshold: float = 0.5)
y_true: list- A list of true target values.
y_pred: list- A list of predicted target values.
threshold: float- Threshold for generating binary classification metrics. Default is 0.5.
Plots
following methods can be used to generate plots:
plot_roc_curve(): Generates a ROC curve plot.plot_all_count_metrics(): Generates a count metrics plot.plot_precision_recall_curve(): Generates a precision-recall curve plot.plot_confusion_matrix(): Generates a confusion matrix plot.plot_class_distribution(): Generates a class distribution plot.plot_class_hist(): Generates a class histogram plot.plot_calibration_curve(): Generates a calibration curve plot.plot_lift_curve(): Generates a lift curve plot.plot_cumulative_gain(): Generates a cumulative gain curve plot.
Dependencies
- numpy
- pandas
- matplotlib
- scikit-learn
- scikit-plot
License
This project is licensed under the MIT License.
Metadata
Release files for metricsreport 2025.7.23
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| metricsreport-2025.7.23.tar.gz | 14.1 kB | Without provenance | Details for metricsreport-2025.7.23.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| metricsreport-2025.7.23-py3-none-any.whl | Python 3 | none | any | Details for metricsreport-2025.7.23-py3-none-any.whl |
Total release size: 28.4 kB
Release files / metricsreport-2025.7.23.tar.gz
| Download URL | metricsreport-2025.7.23.tar.gz |
|---|---|
| Size | 14.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0bc5c06640b608b69a352e014b8f263aa570dea63a2365682d9de39f1a0066b0
|
|
BLAKE2b-256 checksum How to use checksums |
5f30455d307ac0a2bbc802fc97ee09b571e600a0c87734e7a68f3fee3cf0b177
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.12.2 Linux/6.8.8-2-pve
|
Release files / metricsreport-2025.7.23-py3-none-any.whl
| Download URL | metricsreport-2025.7.23-py3-none-any.whl |
|---|---|
| Size | 14.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
4f5247b171f033bb6647b66fd7e36d2d6fedb985652554e04227e010d5e16495
|
|
BLAKE2b-256 checksum How to use checksums |
735556501ebee023a9f6cbe29be88753b32ed315d2f1a6dfd4829d673e4b8911
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.12.2 Linux/6.8.8-2-pve
|
Security for metricsreport 2025.7.23
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.