Model Evaluation Patterns

Expert patterns for classification metrics, calibration, sliced evaluation, fairness, and LLM evaluation.

Pattern 1: Complete Classification Evaluation Report

All key metrics in one evaluation pass.

import numpy as np
import pandas as pd
from sklearn.metrics import (
    f1_score, accuracy_score, roc_auc_score, average_precision_score,
    matthews_corrcoef, confusion_matrix, classification_report,
    brier_score_loss, calibration_curve
)
from scipy import stats
import matplotlib.pyplot as plt