2311020116_CreditCardFraudDetection/tests/test_features.py

import pytest
from src.features import (
    TransactionFeatures, EvaluationResult, ExplanationResult,
    ActionPlan, DecisionResult, ModelMetrics, TrainingResult,
    TransactionClass, ConfidenceLevel, Priority,
    FeatureContribution, Action
)


def test_transaction_features():
    features = TransactionFeatures(
        time=0.0,
        v1=-1.36, v2=-0.07, v3=2.54, v4=1.38, v5=-0.34,
        v6=0.46, v7=0.24, v8=0.10, v9=0.36, v10=0.09,
        v11=-0.55, v12=-0.62, v13=-0.99, v14=-0.31, v15=1.47,
        v16=-0.47, v17=0.21, v18=0.03, v19=0.40, v20=0.25,
        v21=-0.02, v22=0.28, v23=-0.11, v24=0.07, v25=0.13,
        v26=-0.19, v27=0.13, v28=-0.02, amount=149.62
    )
    assert features.time == 0.0
    assert features.amount == 149.62
    assert len(features.to_array()) == 30


def test_evaluation_result():
    result = EvaluationResult(
        predicted_class=1,
        class_name=TransactionClass.FRAUD,
        fraud_probability=0.95,
        normal_probability=0.05,
        confidence=ConfidenceLevel.HIGH
    )
    assert result.predicted_class == 1
    assert result.class_name == TransactionClass.FRAUD
    assert result.fraud_probability == 0.95
    assert result.confidence == ConfidenceLevel.HIGH


def test_feature_contribution():
    contribution = FeatureContribution(
        feature_name="V14",
        value=-0.99,
        importance=0.15,
        contribution=-0.15,
        impact="负"
    )
    assert contribution.feature_name == "V14"
    assert contribution.value == -0.99
    assert contribution.importance == 0.15
    assert contribution.impact == "负"


def test_explanation_result():
    explanation = ExplanationResult(
        model_type="RandomForestClassifier",
        predicted_class=TransactionClass.FRAUD,
        key_features=[],
        overall_explanation="测试解释"
    )
    assert explanation.model_type == "RandomForestClassifier"
    assert explanation.predicted_class == TransactionClass.FRAUD


def test_action():
    action = Action(
        priority=Priority.URGENT,
        action="冻结账户",
        reason="检测到欺诈"
    )
    assert action.priority == Priority.URGENT
    assert action.action == "冻结账户"


def test_action_plan():
    plan = ActionPlan(
        predicted_class=TransactionClass.FRAUD,
        confidence=ConfidenceLevel.HIGH,
        actions=[]
    )
    assert plan.predicted_class == TransactionClass.FRAUD
    assert plan.confidence == ConfidenceLevel.HIGH


def test_decision_result():
    result = DecisionResult(
        evaluation=EvaluationResult(
            predicted_class=1,
            class_name=TransactionClass.FRAUD,
            fraud_probability=0.95,
            normal_probability=0.05,
            confidence=ConfidenceLevel.HIGH
        ),
        explanation=ExplanationResult(
            model_type="RandomForestClassifier",
            predicted_class=TransactionClass.FRAUD,
            key_features=[],
            overall_explanation="测试"
        ),
        action_plan=ActionPlan(
            predicted_class=TransactionClass.FRAUD,
            confidence=ConfidenceLevel.HIGH,
            actions=[]
        ),
        timestamp="2026-01-15"
    )
    assert result.evaluation.predicted_class == 1
    assert result.explanation.model_type == "RandomForestClassifier"
    assert result.action_plan.predicted_class == TransactionClass.FRAUD


def test_model_metrics():
    metrics = ModelMetrics(
        accuracy=0.95,
        precision=0.90,
        recall=0.85,
        f1_score=0.87,
        pr_auc=0.92
    )
    assert metrics.accuracy == 0.95
    assert metrics.precision == 0.90
    assert metrics.pr_auc == 0.92


def test_training_result():
    result = TrainingResult(
        model_name="random_forest",
        metrics=ModelMetrics(
            accuracy=0.95,
            precision=0.90,
            recall=0.85,
            f1_score=0.87,
            pr_auc=0.92
        ),
        confusion_matrix=[[100, 5], [10, 85]]
    )
    assert result.model_name == "random_forest"
    assert result.metrics.accuracy == 0.95