LLM Evaluation

def llm_judge_quality(response, question):
    """Use GPT-5 to judge response quality."""
    prompt = f"""Rate the following response on a scale of 1-10 for:
1. Accuracy (factually correct)
2. Helpfulness (answers the question)
3. Clarity (well-written and understandable)

Question: {question}
Response: {response}

Provide ratings in JSON format:
{{
  "accuracy": <1-10>,
  "helpfulness": <1-10>,
  "clarity": <1-10>,
  "reasoning": "<brief explanation>"
}}
"""

    result = openai.ChatCompletion.create(
        model="gpt-5",
        messages=[{"role": "user", "content": prompt}],
        temperature=0
    )

    return json.loads(result.choices[0].message.content)

def compare_responses(question, response_a, response_b):
    """Compare two responses using LLM judge."""
    prompt = f"""Compare these two responses to the question and determine which is better.

Question: {question}

Response A: {response_a}

Response B: {response_b}

Which response is better and why? Consider accuracy, helpfulness, and clarity.

Answer with JSON:
{{
  "winner": "A" or "B" or "tie",
  "reasoning": "<explanation>",
  "confidence": <1-10>
}}
"""

    result = openai.ChatCompletion.create(
        model="gpt-5",
        messages=[{"role": "user", "content": prompt}],
        temperature=0
    )

    return json.loads(result.choices[0].message.content)

class AnnotationTask:
    """Structure for human annotation task."""

    def __init__(self, response, question, context=None):
        self.response = response
        self.question = question
        self.context = context

    def get_annotation_form(self):
        return {
            "question": self.question,
            "context": self.context,
            "response": self.response,
            "ratings": {
                "accuracy": {
                    "scale": "1-5",
                    "description": "Is the response factually correct?"
                },
                "relevance": {
                    "scale": "1-5",
                    "description": "Does it answer the question?"
                },
                "coherence": {
                    "scale": "1-5",
                    "description": "Is it logically consistent?"
                }
            },
            "issues": {
                "factual_error": False,
                "hallucination": False,
                "off_topic": False,
                "unsafe_content": False
            },
            "feedback": ""
        }

from sklearn.metrics import cohen_kappa_score

def calculate_agreement(rater1_scores, rater2_scores):
    """Calculate inter-rater agreement."""
    kappa = cohen_kappa_score(rater1_scores, rater2_scores)

    interpretation = {
        kappa < 0: "Poor",
        kappa < 0.2: "Slight",
        kappa < 0.4: "Fair",
        kappa < 0.6: "Moderate",
        kappa < 0.8: "Substantial",
        kappa <= 1.0: "Almost Perfect"
    }

    return {
        "kappa": kappa,
        "interpretation": interpretation[True]
    }

from scipy import stats
import numpy as np

class ABTest:
    def __init__(self, variant_a_name="A", variant_b_name="B"):
        self.variant_a = {"name": variant_a_name, "scores": []}
        self.variant_b = {"name": variant_b_name, "scores": []}

    def add_result(self, variant, score):
        """Add evaluation result for a variant."""
        if variant == "A":
            self.variant_a["scores"].append(score)
        else:
            self.variant_b["scores"].append(score)

    def analyze(self, alpha=0.05):
        """Perform statistical analysis."""
        a_scores = self.variant_a["scores"]
        b_scores = self.variant_b["scores"]

        # T-test
        t_stat, p_value = stats.ttest_ind(a_scores, b_scores)

        # Effect size (Cohen's d)
        pooled_std = np.sqrt((np.std(a_scores)**2 + np.std(b_scores)**2) / 2)
        cohens_d = (np.mean(b_scores) - np.mean(a_scores)) / pooled_std

        return {
            "variant_a_mean": np.mean(a_scores),
            "variant_b_mean": np.mean(b_scores),
            "difference": np.mean(b_scores) - np.mean(a_scores),
            "relative_improvement": (np.mean(b_scores) - np.mean(a_scores)) / np.mean(a_scores),
            "p_value": p_value,
            "statistically_significant": p_value < alpha,
            "cohens_d": cohens_d,
            "effect_size": self.interpret_cohens_d(cohens_d),
            "winner": "B" if np.mean(b_scores) > np.mean(a_scores) else "A"
        }

    @staticmethod
    def interpret_cohens_d(d):
        """Interpret Cohen's d effect size."""
        abs_d = abs(d)
        if abs_d < 0.2:
            return "negligible"
        elif abs_d < 0.5:
            return "small"
        elif abs_d < 0.8:
            return "medium"
        else:
            return "large"

class RegressionDetector:
    def __init__(self, baseline_results, threshold=0.05):
        self.baseline = baseline_results
        self.threshold = threshold

    def check_for_regression(self, new_results):
        """Detect if new results show regression."""
        regressions = []

        for metric in self.baseline.keys():
            baseline_score = self.baseline[metric]
            new_score = new_results.get(metric)

            if new_score is None:
                continue

            # Calculate relative change
            relative_change = (new_score - baseline_score) / baseline_score

            # Flag if significant decrease
            if relative_change < -self.threshold:
                regressions.append({
                    "metric": metric,
                    "baseline": baseline_score,
                    "current": new_score,
                    "change": relative_change
                })

        return {
            "has_regression": len(regressions) > 0,
            "regressions": regressions
        }

class BenchmarkRunner:
    def __init__(self, benchmark_dataset):
        self.dataset = benchmark_dataset

    def run_benchmark(self, model, metrics):
        """Run model on benchmark and calculate metrics."""
        results = {metric.name: [] for metric in metrics}

        for example in self.dataset:
            # Generate prediction
            prediction = model.predict(example["input"])

            # Calculate each metric
            for metric in metrics:
                score = metric.calculate(
                    prediction=prediction,
                    reference=example["reference"],
                    context=example.get("context")
                )
                results[metric.name].append(score)

        # Aggregate results
        return {
            metric: {
                "mean": np.mean(scores),
                "std": np.std(scores),
                "min": min(scores),
                "max": max(scores)
            }
            for metric, scores in results.items()
        }