uv pip install "alquimia-fair-forge[toxicity]"

from fair_forge.metrics.toxicity import Toxicity
from fair_forge.statistical import FrequentistMode
from your_retriever import MyRetriever

# Define group prototypes for demographic detection
group_prototypes = {
    "gender": ["women", "men", "female", "male", "woman", "man"],
    "race": ["Asian", "African", "European", "Hispanic", "Black", "White"],
    "religion": ["Christian", "Muslim", "Jewish", "Hindu", "Buddhist"],
    "sexuality": ["LGBTQ+", "gay", "lesbian", "bisexual", "heterosexual"],
}

# Run the metric
metrics = Toxicity.run(
    MyRetriever,
    group_prototypes=group_prototypes,
    group_default_threshold=0.40,
    statistical_mode=FrequentistMode(),
    verbose=True,
)

# Analyze results
for metric in metrics:
    print(f"Session: {metric.session_id}")

    # Cluster profiling
    print("Cluster Profiling:")
    for cluster_id, toxicity in metric.cluster_profiling.items():
        print(f"  Cluster {cluster_id}: {toxicity:.4f}")

    # Group profiling
    if metric.group_profiling:
        gp = metric.group_profiling.frequentist
        print(f"DIDT: {gp.DIDT:.4f}")
        print(f"  DR: {gp.DR:.4f}")
        print(f"  ASB: {gp.ASB:.4f}")
        print(f"  DTO: {gp.DTO:.4f}")

class ToxicityMetric(BaseMetric):
    session_id: str
    assistant_id: str
    cluster_profiling: dict[float, float]  # cluster_id -> toxicity_score
    group_profiling: GroupProfiling | None
    assistant_space: AssistantSpace

class GroupProfiling(BaseModel):
    mode: Literal["frequentist", "bayesian"]
    groups: list[str]           # Detected groups
    N_i: dict[str, int]         # Mention counts per group
    K_i: dict[str, int]         # Toxic mention counts per group
    frequentist: FrequentistGroupProfiling | None
    bayesian: BayesianGroupProfiling | None

class FrequentistGroupProfiling(BaseModel):
    DR: float   # Demographic Representation (0-1)
    ASB: float  # Associated Sentiment Bias (0-1)
    DTO: float  # Directed Toxicity per Group (0-1)
    DIDT: float # Aggregate score (0-1)

from fair_forge.statistical import FrequentistMode

metrics = Toxicity.run(
    MyRetriever,
    group_prototypes=group_prototypes,
    statistical_mode=FrequentistMode(),
)

# Returns point estimates
gp = metrics[0].group_profiling.frequentist
print(f"DIDT: {gp.DIDT}")  # Single float value

from fair_forge.statistical import BayesianMode

bayesian = BayesianMode(
    mc_samples=5000,
    ci_level=0.95,
    dirichlet_prior=1.0,
    beta_prior_a=1.0,
    beta_prior_b=1.0,
    rng_seed=42,
)

metrics = Toxicity.run(
    MyRetriever,
    group_prototypes=group_prototypes,
    statistical_mode=bayesian,
)

# Returns distributions with credible intervals
summary = metrics[0].group_profiling.bayesian.summary
print(f"DIDT: {summary['DIDT'].mean:.4f} [{summary['DIDT'].ci_low:.4f}, {summary['DIDT'].ci_high:.4f}]")

DIDT = w_DR * DR + w_ASB * ASB + w_DTO * DTO

# Define prototypes relevant to your domain
group_prototypes = {
    "age": ["young", "old", "elderly", "teenager", "millennial", "boomer"],
    "occupation": ["doctor", "lawyer", "teacher", "engineer", "artist"],
    "socioeconomic": ["wealthy", "poor", "middle-class", "homeless"],
}

metrics = Toxicity.run(
    MyRetriever,
    group_prototypes=group_prototypes,
)

from fair_forge.extractors.embedding import EmbeddingGroupExtractor
from sentence_transformers import SentenceTransformer

# Create custom extractor with specific model
embedder = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2")
extractor = EmbeddingGroupExtractor(
    embedder=embedder,
    group_prototypes=group_prototypes,
    thresholds={"gender": 0.35, "race": 0.40},
    default_threshold=0.45,
)

metrics = Toxicity.run(
    MyRetriever,
    group_extractor=extractor,
)

# Fine-tune clustering for your data
metrics = Toxicity.run(
    MyRetriever,
    group_prototypes=group_prototypes,
    toxicity_min_cluster_size=10,         # Larger clusters
    toxicity_cluster_selection_method="leaf",  # Finer clusters
    umap_n_neighbors=30,                   # More neighbors for UMAP
    umap_min_dist=0.05,                    # Tighter clusters
)

import matplotlib.pyplot as plt
import numpy as np

metric = metrics[0]
latent_space = np.array(metric.assistant_space.latent_space)
labels = np.array(metric.assistant_space.cluster_labels)

plt.figure(figsize=(10, 8))
scatter = plt.scatter(
    latent_space[:, 0],
    latent_space[:, 1],
    c=labels,
    cmap='tab10',
    alpha=0.7
)
plt.colorbar(scatter, label='Cluster')
plt.xlabel('UMAP Dimension 1')
plt.ylabel('UMAP Dimension 2')
plt.title('Response Clusters (Toxicity Analysis)')
plt.show()

from fair_forge.metrics.toxicity import Toxicity
from fair_forge.statistical import FrequentistMode, BayesianMode
from fair_forge.core.retriever import Retriever
from fair_forge.schemas.common import Dataset, Batch

class MyRetriever(Retriever):
    def load_dataset(self) -> list[Dataset]:
        return [
            Dataset(
                session_id="eval-001",
                assistant_id="my-assistant",
                language="english",
                context="",
                conversation=[
                    Batch(qa_id="q1", query="...", assistant="Response 1..."),
                    Batch(qa_id="q2", query="...", assistant="Response 2..."),
                ]
            )
        ]

# Define groups
group_prototypes = {
    "gender": ["women", "men", "female", "male"],
    "race": ["Asian", "African", "European", "Hispanic"],
    "religion": ["Christian", "Muslim", "Jewish", "Hindu"],
}

# Run with Frequentist mode
freq_metrics = Toxicity.run(
    MyRetriever,
    group_prototypes=group_prototypes,
    group_default_threshold=0.40,
    statistical_mode=FrequentistMode(),
    toxicity_min_cluster_size=2,
    verbose=True,
)

# Run with Bayesian mode
bayes_metrics = Toxicity.run(
    MyRetriever,
    group_prototypes=group_prototypes,
    group_default_threshold=0.40,
    statistical_mode=BayesianMode(mc_samples=5000, ci_level=0.95),
    toxicity_min_cluster_size=2,
    verbose=True,
)

# Compare results
print("Frequentist vs Bayesian Comparison")
print("=" * 50)

freq_gp = freq_metrics[0].group_profiling
bayes_gp = bayes_metrics[0].group_profiling

for component in ['DR', 'ASB', 'DTO', 'DIDT']:
    freq_val = getattr(freq_gp.frequentist, component)
    bayes_summary = bayes_gp.bayesian.summary[component]

    print(f"{component}:")
    print(f"  Frequentist: {freq_val:.4f}")
    print(f"  Bayesian: {bayes_summary.mean:.4f} [{bayes_summary.ci_low:.4f}, {bayes_summary.ci_high:.4f}]")