qbiocode.evaluation package

Evaluation Module for QBioCode

This module provides comprehensive evaluation tools for machine learning models and datasets. It includes functions for model performance assessment, dataset complexity analysis, and automated model execution.

Available Functions

• modeleval: Evaluate model performance with multiple metrics

• evaluation_metrics: Calculate accuracy and Brier score from predictions

• evaluate: Comprehensive dataset complexity evaluation

• model_run: Automated model training and evaluation pipeline

Usage

>>> from qbiocode.evaluation import modeleval, evaluate
>>> # Evaluate model performance
>>> metrics = modeleval(y_true, y_pred, y_proba)
>>> # Evaluate dataset complexity
>>> complexity_metrics = evaluate(X, y)

Submodules:

• qbiocode.evaluation.dataset_evaluation module
• qbiocode.evaluation.graph_evaluation module
• qbiocode.evaluation.model_evaluation module
• qbiocode.evaluation.model_run module

Summary

__all__ Functions:

evaluate	This function evaluates a dataset and returns a transposed summary DataFrame with various statistical measures, derived from the dataset.
evaluation_metrics	Calculate evaluation metrics for classification predictions.
model_run	This function runs the ML methods, with or without a grid search, as specified in the config.yaml file.
modeleval	Evaluates the model performance using accuracy, F1 score, and AUC.