# 自然写教学数据分析与学情诊断系统软件 V1.0
# analytics/student_profiler.py - 学生画像分析引擎

import logging
import math
from typing import Any, Dict, List, Optional, Tuple
from datetime import datetime, date, timedelta
from dataclasses import dataclass, field

logger = logging.getLogger("writech.analytics.profiler")


# ============================================================
#  画像分析数据模型
# ============================================================

@dataclass
class ScoreTrend:
    """成绩趋势数据点"""
    date: str
    score: float
    subject: str
    exam_type: str = ""  # homework/exam/practice


@dataclass
class SubjectAbility:
    """科目能力评估"""
    subject: str
    overall_score: float = 0.0
    knowledge_coverage: float = 0.0  # 知识点覆盖率
    practice_frequency: float = 0.0  # 练习频率（次/周）
    improvement_rate: float = 0.0    # 进步速率
    stability: float = 0.0          # 稳定性（分数方差的倒数）


@dataclass
class LearningHabit:
    """学习习惯画像"""
    avg_daily_minutes: float = 0.0
    peak_study_hour: int = 0       # 学习高峰时段（小时）
    weekly_pattern: List[float] = field(default_factory=list)  # 周一~日时长
    consistency_score: float = 0.0  # 学习规律性评分
    homework_timeliness: float = 0.0  # 作业及时提交率


@dataclass
class WritingAbility:
    """书写能力评估"""
    stroke_order_accuracy: float = 0.0  # 笔顺正确率
    writing_quality: float = 0.0        # 书写规范性
    writing_speed: float = 0.0          # 书写速度(字/分)
    char_structure_score: float = 0.0   # 字形结构评分
    improvement_trend: str = "stable"   # 进步趋势


@dataclass
class ComprehensiveProfile:
    """综合学情画像"""
    student_id: str
    student_name: str
    class_id: str
    grade: str
    school_id: str

    # 综合评分
    overall_score: float = 0.0
    rank_in_class: int = 0
    rank_in_grade: int = 0
    percentile: float = 0.0

    # 各科能力
    subject_abilities: List[SubjectAbility] = field(default_factory=list)

    # 学习习惯
    learning_habit: Optional[LearningHabit] = None

    # 书写能力
    writing_ability: Optional[WritingAbility] = None

    # 成绩趋势
    score_trends: List[ScoreTrend] = field(default_factory=list)

    # 分析时间
    analyzed_at: str = ""


# ============================================================
#  画像分析引擎
# ============================================================

class StudentProfiler:
    """
    学生画像分析引擎
    
    功能:
    1. 综合学情评分计算
    2. 各科目能力多维评估
    3. 学习习惯分析
    4. 书写能力评估
    5. 成绩趋势分析与预测
    6. 班级/年级排名计算
    """

    # 各维度权重（用于综合评分计算）
    WEIGHT_HOMEWORK_SCORE = 0.30   # 作业成绩权重
    WEIGHT_EXAM_SCORE = 0.35       # 考试成绩权重
    WEIGHT_PRACTICE = 0.15         # 练习表现权重
    WEIGHT_WRITING = 0.10          # 书写能力权重
    WEIGHT_HABIT = 0.10            # 学习习惯权重

    # 评分标准
    EXCELLENT_THRESHOLD = 90.0
    GOOD_THRESHOLD = 75.0
    PASS_THRESHOLD = 60.0

    def __init__(self):
        """初始化画像分析引擎"""
        logger.info("学生画像分析引擎初始化")

    async def build_profile(
        self,
        student_id: str,
        student_info: Dict[str, Any],
        period_days: int = 30,
    ) -> ComprehensiveProfile:
        """
        构建学生综合画像
        
        Args:
            student_id: 学生ID
            student_info: 学生基本信息
            period_days: 分析周期（天）
        
        Returns:
            综合学情画像
        """
        logger.info(
            "构建学生画像: %s, 分析周期=%d天", student_id, period_days
        )

        end_date = date.today()
        start_date = end_date - timedelta(days=period_days)

        # 1. 获取原始数据
        homework_data = await self._fetch_homework_data(
            student_id, start_date, end_date
        )
        exam_data = await self._fetch_exam_data(
            student_id, start_date, end_date
        )
        practice_data = await self._fetch_practice_data(
            student_id, start_date, end_date
        )
        writing_data = await self._fetch_writing_data(
            student_id, start_date, end_date
        )
        usage_data = await self._fetch_usage_data(
            student_id, start_date, end_date
        )

        # 2. 分析各维度
        subject_abilities = self._analyze_subject_abilities(
            homework_data, exam_data, practice_data
        )
        learning_habit = self._analyze_learning_habit(usage_data)
        writing_ability = self._analyze_writing_ability(writing_data)
        score_trends = self._analyze_score_trends(
            homework_data, exam_data
        )

        # 3. 计算综合评分
        overall_score = self._calculate_overall_score(
            subject_abilities, learning_habit, writing_ability
        )

        # 4. 计算排名
        rank_in_class, rank_in_grade, percentile = (
            await self._calculate_rankings(
                student_id,
                student_info.get("class_id", ""),
                student_info.get("grade", ""),
                overall_score,
            )
        )

        profile = ComprehensiveProfile(
            student_id=student_id,
            student_name=student_info.get("name", ""),
            class_id=student_info.get("class_id", ""),
            grade=student_info.get("grade", ""),
            school_id=student_info.get("school_id", ""),
            overall_score=round(overall_score, 1),
            rank_in_class=rank_in_class,
            rank_in_grade=rank_in_grade,
            percentile=round(percentile, 1),
            subject_abilities=subject_abilities,
            learning_habit=learning_habit,
            writing_ability=writing_ability,
            score_trends=score_trends,
            analyzed_at=datetime.now().isoformat(),
        )

        # 5. 写入ClickHouse画像宽表
        await self._save_profile(profile)

        logger.info(
            "画像构建完成: %s, 综合评分=%.1f, 班级排名=%d",
            student_id, overall_score, rank_in_class,
        )

        return profile

    async def _fetch_homework_data(
        self, student_id: str, start: date, end: date
    ) -> List[Dict[str, Any]]:
        """从ClickHouse获取作业成绩数据"""
        # query = """
        #     SELECT subject, score, total_score, submitted_at, is_on_time
        #     FROM homework_submissions
        #     WHERE student_id = %(sid)s
        #       AND submitted_at BETWEEN %(start)s AND %(end)s
        #     ORDER BY submitted_at
        # """
        # return await clickhouse_query(query, {
        #     "sid": student_id, "start": str(start), "end": str(end)
        # })
        return []

    async def _fetch_exam_data(
        self, student_id: str, start: date, end: date
    ) -> List[Dict[str, Any]]:
        """从ClickHouse获取考试成绩数据"""
        return []

    async def _fetch_practice_data(
        self, student_id: str, start: date, end: date
    ) -> List[Dict[str, Any]]:
        """获取练习（字帖/笔顺）数据"""
        return []

    async def _fetch_writing_data(
        self, student_id: str, start: date, end: date
    ) -> List[Dict[str, Any]]:
        """获取书写质量评分数据"""
        return []

    async def _fetch_usage_data(
        self, student_id: str, start: date, end: date
    ) -> List[Dict[str, Any]]:
        """获取应用使用时长数据"""
        return []

    def _analyze_subject_abilities(
        self,
        homework_data: List[Dict[str, Any]],
        exam_data: List[Dict[str, Any]],
        practice_data: List[Dict[str, Any]],
    ) -> List[SubjectAbility]:
        """
        各科目能力多维评估
        
        评估维度:
        - 作业/考试平均分
        - 知识点覆盖率（已接触/总知识点数）
        - 练习频率（次/周）
        - 进步速率（最近30天vs前30天分数差）
        - 稳定性（分数标准差的倒数归一化）
        """
        subject_map: Dict[str, Dict[str, List[float]]] = {}

        # 按科目聚合作业分数
        for hw in homework_data:
            subject = hw.get("subject", "unknown")
            subject_map.setdefault(subject, {"scores": [], "dates": []})
            total = hw.get("total_score", 100)
            score = hw.get("score", 0)
            normalized = (score / max(total, 1)) * 100
            subject_map[subject]["scores"].append(normalized)

        # 按科目聚合考试分数
        for exam in exam_data:
            subject = exam.get("subject", "unknown")
            subject_map.setdefault(subject, {"scores": [], "dates": []})
            total = exam.get("total_score", 100)
            score = exam.get("score", 0)
            normalized = (score / max(total, 1)) * 100
            subject_map[subject]["scores"].append(normalized)

        abilities: List[SubjectAbility] = []
        for subject, data in subject_map.items():
            scores = data["scores"]
            if not scores:
                continue

            avg_score = sum(scores) / len(scores)

            # 稳定性: 1 / (1 + std_dev) 归一化到0-1
            variance = sum((s - avg_score) ** 2 for s in scores) / max(
                len(scores), 1
            )
            std_dev = math.sqrt(variance)
            stability = 1.0 / (1.0 + std_dev / 10)  # 归一化

            # 进步速率: 后半段均分 - 前半段均分
            mid = len(scores) // 2
            if mid > 0:
                first_half_avg = sum(scores[:mid]) / mid
                second_half_avg = sum(scores[mid:]) / max(
                    len(scores) - mid, 1
                )
                improvement = second_half_avg - first_half_avg
            else:
                improvement = 0.0

            abilities.append(SubjectAbility(
                subject=subject,
                overall_score=round(avg_score, 1),
                stability=round(stability, 3),
                improvement_rate=round(improvement, 1),
            ))

        return abilities

    def _analyze_learning_habit(
        self, usage_data: List[Dict[str, Any]]
    ) -> LearningHabit:
        """
        学习习惯分析
        
        分析维度:
        - 日均学习时长
        - 学习高峰时段
        - 周学习模式（周一到周日）
        - 学习规律性评分
        """
        if not usage_data:
            return LearningHabit()

        # 按日期聚合使用时长
        daily_minutes: Dict[str, float] = {}
        hourly_counts: Dict[int, int] = {}
        weekday_minutes: Dict[int, List[float]] = {
            i: [] for i in range(7)
        }

        for record in usage_data:
            date_str = record.get("date", "")
            minutes = record.get("duration_minutes", 0)
            hour = record.get("start_hour", 0)

            daily_minutes[date_str] = (
                daily_minutes.get(date_str, 0) + minutes
            )
            hourly_counts[hour] = hourly_counts.get(hour, 0) + 1

        # 日均时长
        total_days = max(len(daily_minutes), 1)
        avg_daily = sum(daily_minutes.values()) / total_days

        # 学习高峰时段
        peak_hour = max(
            hourly_counts, key=hourly_counts.get, default=0
        )

        # 学习规律性: 日均时长的变异系数越小越规律
        if daily_minutes:
            values = list(daily_minutes.values())
            mean_val = sum(values) / len(values)
            variance = sum((v - mean_val) ** 2 for v in values) / len(
                values
            )
            std_val = math.sqrt(variance)
            cv = std_val / max(mean_val, 1)
            consistency = max(0.0, 1.0 - cv)  # 变异系数越小规律性越高
        else:
            consistency = 0.0

        return LearningHabit(
            avg_daily_minutes=round(avg_daily, 1),
            peak_study_hour=peak_hour,
            consistency_score=round(consistency, 3),
        )

    def _analyze_writing_ability(
        self, writing_data: List[Dict[str, Any]]
    ) -> WritingAbility:
        """
        书写能力评估
        
        基于笔顺准确率、书写规范性评分、书写速度等维度综合评估。
        通过对比最近和较早的数据判断进步趋势。
        """
        if not writing_data:
            return WritingAbility()

        # 计算各维度平均值
        stroke_scores = [
            d.get("stroke_order_score", 0) for d in writing_data
        ]
        quality_scores = [
            d.get("quality_score", 0) for d in writing_data
        ]
        speeds = [d.get("speed", 0) for d in writing_data]
        structure_scores = [
            d.get("structure_score", 0) for d in writing_data
        ]

        avg_stroke = sum(stroke_scores) / max(len(stroke_scores), 1)
        avg_quality = sum(quality_scores) / max(len(quality_scores), 1)
        avg_speed = sum(speeds) / max(len(speeds), 1)
        avg_structure = sum(structure_scores) / max(
            len(structure_scores), 1
        )

        # 判断趋势: 后半段 vs 前半段
        mid = len(quality_scores) // 2
        if mid > 0:
            early_avg = sum(quality_scores[:mid]) / mid
            recent_avg = sum(quality_scores[mid:]) / max(
                len(quality_scores) - mid, 1
            )
            if recent_avg - early_avg > 3:
                trend = "improving"
            elif early_avg - recent_avg > 3:
                trend = "declining"
            else:
                trend = "stable"
        else:
            trend = "stable"

        return WritingAbility(
            stroke_order_accuracy=round(avg_stroke, 1),
            writing_quality=round(avg_quality, 1),
            writing_speed=round(avg_speed, 1),
            char_structure_score=round(avg_structure, 1),
            improvement_trend=trend,
        )

    def _analyze_score_trends(
        self,
        homework_data: List[Dict[str, Any]],
        exam_data: List[Dict[str, Any]],
    ) -> List[ScoreTrend]:
        """生成成绩趋势数据"""
        trends: List[ScoreTrend] = []

        for hw in homework_data:
            total = hw.get("total_score", 100)
            score = hw.get("score", 0)
            normalized = (score / max(total, 1)) * 100
            trends.append(ScoreTrend(
                date=hw.get("submitted_at", "")[:10],
                score=round(normalized, 1),
                subject=hw.get("subject", ""),
                exam_type="homework",
            ))

        for exam in exam_data:
            total = exam.get("total_score", 100)
            score = exam.get("score", 0)
            normalized = (score / max(total, 1)) * 100
            trends.append(ScoreTrend(
                date=exam.get("exam_date", "")[:10],
                score=round(normalized, 1),
                subject=exam.get("subject", ""),
                exam_type="exam",
            ))

        # 按日期排序
        trends.sort(key=lambda t: t.date)
        return trends

    def _calculate_overall_score(
        self,
        subject_abilities: List[SubjectAbility],
        learning_habit: LearningHabit,
        writing_ability: WritingAbility,
    ) -> float:
        """
        计算综合评分（百分制）
        
        加权公式:
        综合分 = 作业成绩×0.30 + 考试成绩×0.35 + 练习×0.15 
                + 书写×0.10 + 学习习惯×0.10
        """
        # 作业/考试平均分
        if subject_abilities:
            academic_avg = sum(
                a.overall_score for a in subject_abilities
            ) / len(subject_abilities)
        else:
            academic_avg = 0.0

        # 书写能力评分（归一化到百分制）
        writing_score = writing_ability.writing_quality

        # 学习习惯评分（规律性×100）
        habit_score = learning_habit.consistency_score * 100

        # 加权综合
        overall = (
            academic_avg * (self.WEIGHT_HOMEWORK_SCORE + self.WEIGHT_EXAM_SCORE)
            + academic_avg * self.WEIGHT_PRACTICE
            + writing_score * self.WEIGHT_WRITING
            + habit_score * self.WEIGHT_HABIT
        )

        return min(100.0, max(0.0, overall))

    async def _calculate_rankings(
        self,
        student_id: str,
        class_id: str,
        grade: str,
        score: float,
    ) -> Tuple[int, int, float]:
        """
        计算班级排名和年级百分位排名
        
        从ClickHouse查询同班和同年级学生的综合评分，
        计算当前学生的排名位置。
        """
        # 查询同班学生评分
        # class_scores = await query_class_scores(class_id)
        # class_rank = sum(1 for s in class_scores if s > score) + 1

        # 查询同年级学生评分
        # grade_scores = await query_grade_scores(grade)
        # grade_rank = sum(1 for s in grade_scores if s > score) + 1
        # percentile = (1 - grade_rank / max(len(grade_scores), 1)) * 100

        return 0, 0, 0.0

    async def _save_profile(self, profile: ComprehensiveProfile) -> None:
        """将画像数据写入ClickHouse画像宽表"""
        # clickhouse_client.execute(
        #     "INSERT INTO student_profile VALUES",
        #     [profile_to_row(profile)],
        # )
        pass