ds-utils-metrics - Evaluate models with metrics and visualization charts
Provides evaluation metrics and visualization charts for sklearn-compatible machine learning models, including classification, probability, error, time-series, and regression analysis.
Tags
Updated: 2026-10-12Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Compute classification metrics
- Plot confusion matrices
- Plot learning curves
- Visualize probability accuracy
- Plot ROC curves
- Plot precision-recall curves
- Analyze prediction errors
- Generate error analysis reports
- Score directional accuracy
- Score directional bias
- Score regression AUC
- Plot regression curves
Inputs
- Ground-truth labels
- Predicted labels
- Predicted probabilities
- Training data
- Test data
- Classifier instances
- Class labels
- Metric settings
Outputs
- Matplotlib Axes
- Plotly Figures
- Error analysis reports
- Evaluation scores
Requirements
- Python environment
- Installed data-science-utils package
- Sklearn-compatible models
- Matplotlib for Matplotlib plots
- Plotly for interactive figures