feat: 将数据集从国外员工缺勤数据替换为中国企业缺勤模拟数据

- 新增中国企业员工缺勤模拟数据集生成脚本(generate_dataset.py)，覆盖7个行业、180家企业、2600名员工
  - 重构 config.py，更新特征字段为中文名称，调整目标列、员工ID、行业类型等配置
  - 重构 clustering.py，简化聚类逻辑，更新聚类特征和群体命名（高压通勤型、健康波动型等）
  - 重构 feature_mining.py，更新相关性分析和群体比较维度（按行业、班次、婚姻状态等）
  - 新增 model_features.py 定义模型训练特征
  - 更新 preprocessing.py 和 train_model.py 适配新数据结构
  - 更新各 API 路由默认参数（model: random_forest, dimension: industry）
  - 前端更新主题样式和各视图组件适配中文字段
  - 更新系统名称为 China Enterprise Absence Analysis System

backend/core/model_features.py

@@ -0,0 +1,326 @@
+import numpy as np
+import pandas as pd
+from sklearn.preprocessing import LabelEncoder
+
+import config
+
+
+TARGET_COLUMN = config.TARGET_COLUMN
+ID_COLUMN = config.EMPLOYEE_ID_COLUMN
+COMPANY_COLUMN = config.COMPANY_ID_COLUMN
+LEAKY_COLUMNS = [ID_COLUMN, COMPANY_COLUMN]
+ORDINAL_COLUMNS = [
+    '企业规模',
+    '所在城市等级',
+    '岗位级别',
+    '最高学历',
+    '绩效等级',
+    '心理压力等级',
+    '工龄分层',
+    '年龄分层',
+    '通勤分层',
+    '加班分层',
+]
+NUMERICAL_OUTLIER_COLUMNS = [
+    '年龄',
+    '司龄年数',
+    '月均加班时长',
+    '近30天出勤天数',
+    '近90天缺勤次数',
+    '近180天请假总时长',
+    '通勤时长分钟',
+    '通勤距离公里',
+    '团队人数',
+    '直属上级管理跨度',
+    'BMI',
+    '近30天睡眠时长均值',
+    '每周运动频次',
+]
+DEFAULT_PREDICTION_INPUT = {
+    'industry': '制造业',
+    'company_size': '1000-4999人',
+    'city_tier': '新一线',
+    'age': 31,
+    'tenure_years': 4.5,
+    'education_level': '本科',
+    'marital_status': '已婚',
+    'job_family': '专业技术',
+    'job_level': '中级',
+    'employment_type': '正式员工',
+    'shift_type': '标准白班',
+    'is_night_shift': 0,
+    'monthly_overtime_hours': 26,
+    'attendance_days_30d': 22,
+    'absence_count_90d': 1,
+    'leave_hours_180d': 18,
+    'commute_minutes': 42,
+    'commute_km': 18,
+    'cross_city_commute': 0,
+    'performance_level': 'B',
+    'disciplinary_count_12m': 0,
+    'team_size': 10,
+    'manager_span': 14,
+    'bmi': 24.5,
+    'chronic_disease_flag': 0,
+    'annual_check_abnormal_flag': 0,
+    'sleep_hours': 7.1,
+    'exercise_frequency': 2,
+    'smoking_flag': 0,
+    'drinking_flag': 0,
+    'stress_level': '中',
+    'sedentary_job_flag': 1,
+    'local_hukou_flag': 1,
+    'children_count': 1,
+    'single_child_burden_flag': 0,
+    'absence_month': 5,
+    'weekday': 2,
+    'near_holiday_flag': 0,
+    'leave_channel': '系统申请',
+    'leave_type': '病假',
+    'leave_reason_category': '身体不适',
+    'medical_certificate_flag': 1,
+    'urgent_leave_flag': 1,
+    'continuous_absence_flag': 0,
+    'previous_day_overtime_flag': 1,
+}
+
+
+def make_target_bins(y):
+    y_series = pd.Series(y)
+    bins = pd.cut(
+        y_series,
+        bins=[0, 4, 8, 12, np.inf],
+        labels=['low', 'medium', 'high', 'extreme'],
+        include_lowest=True,
+    )
+    return bins.astype(str)
+
+
+def normalize_columns(df):
+    df = df.copy()
+    df.columns = [col.strip() for col in df.columns]
+    return df
+
+
+def prepare_modeling_dataframe(df):
+    df = normalize_columns(df)
+    drop_cols = [col for col in LEAKY_COLUMNS if col in df.columns]
+    if drop_cols:
+        df = df.drop(columns=drop_cols)
+    return df
+
+
+def fit_outlier_bounds(df, columns, lower_pct=1, upper_pct=99):
+    bounds = {}
+    for col in columns:
+        if col in df.columns and pd.api.types.is_numeric_dtype(df[col]):
+            bounds[col] = (
+                float(df[col].quantile(lower_pct / 100)),
+                float(df[col].quantile(upper_pct / 100)),
+            )
+    return bounds
+
+
+def apply_outlier_bounds(df, bounds):
+    df = df.copy()
+    for col, (lower, upper) in bounds.items():
+        if col in df.columns:
+            df[col] = df[col].clip(lower, upper)
+    return df
+
+
+def engineer_features(df):
+    df = df.copy()
+    df['加班通勤压力指数'] = (
+        df['月均加班时长'] * 0.45
+        + df['通勤时长分钟'] * 0.35
+        + df['是否夜班岗位'] * 12
+        + df['前一工作日是否加班'] * 6
+    ) / 10
+    df['家庭负担指数'] = (
+        df['子女数量'] * 1.2
+        + df['是否独生子女家庭负担'] * 1.5
+        + (df['婚姻状态'] == '已婚').astype(int) * 0.6
+    )
+    df['健康风险指数'] = (
+        df['是否慢性病史'] * 2
+        + df['年度体检异常标记'] * 1.2
+        + (df['BMI'] >= 28).astype(int) * 1.1
+        + df['是否吸烟'] * 0.8
+        + df['是否饮酒'] * 0.4
+        + (df['近30天睡眠时长均值'] < 6.5).astype(int) * 1.2
+    )
+    df['岗位稳定性指数'] = (
+        df['司龄年数'] * 0.3
+        + (df['绩效等级'] == 'A').astype(int) * 1.2
+        + (df['绩效等级'] == 'B').astype(int) * 0.8
+        - df['近12月违纪次数'] * 0.7
+    )
+    df['节假日风险标记'] = (
+        (df['是否节假日前后'] == 1) | (df['请假类型'].isin(['事假', '年假', '调休']))
+    ).astype(int)
+    df['排班压力标记'] = (
+        (df['班次类型'].isin(['两班倒', '三班倒'])) | (df['是否夜班岗位'] == 1)
+    ).astype(int)
+    df['缺勤历史强度'] = df['近90天缺勤次数'] * 1.5 + df['近180天请假总时长'] / 12
+    df['生活规律指数'] = (
+        df['近30天睡眠时长均值'] * 0.6
+        + df['每周运动频次'] * 0.7
+        - df['是否吸烟'] * 1.1
+        - df['是否饮酒'] * 0.5
+    )
+    df['管理负荷指数'] = df['团队人数'] * 0.4 + df['直属上级管理跨度'] * 0.25
+
+    df['工龄分层'] = pd.cut(df['司龄年数'], bins=[0, 2, 5, 10, 40], labels=['1', '2', '3', '4'])
+    df['年龄分层'] = pd.cut(df['年龄'], bins=[18, 25, 32, 40, 60], labels=['1', '2', '3', '4'])
+    df['通勤分层'] = pd.cut(df['通勤时长分钟'], bins=[0, 25, 45, 70, 180], labels=['1', '2', '3', '4'])
+    df['加班分层'] = pd.cut(df['月均加班时长'], bins=[-1, 10, 25, 45, 120], labels=['1', '2', '3', '4'])
+    return df
+
+
+def fit_label_encoders(df, ordinal_columns=None):
+    ordinal_columns = ordinal_columns or ORDINAL_COLUMNS
+    df = df.copy()
+    encoders = {}
+    object_columns = df.select_dtypes(include=['object', 'category']).columns.tolist()
+    encode_columns = sorted(set(object_columns + [col for col in ordinal_columns if col in df.columns]))
+    for col in encode_columns:
+        encoder = LabelEncoder()
+        df[col] = encoder.fit_transform(df[col].astype(str))
+        encoders[col] = encoder
+    return df, encoders
+
+
+def apply_label_encoders(df, encoders):
+    df = df.copy()
+    for col, encoder in encoders.items():
+        if col not in df.columns:
+            continue
+        value_map = {cls: idx for idx, cls in enumerate(encoder.classes_)}
+        df[col] = df[col].astype(str).map(lambda value: value_map.get(value, 0))
+    return df
+
+
+def extract_xy(df):
+    y = df[TARGET_COLUMN].values if TARGET_COLUMN in df.columns else None
+    X_df = df.drop(columns=[TARGET_COLUMN]) if TARGET_COLUMN in df.columns else df.copy()
+    return X_df, y
+
+
+def build_prediction_dataframe(data):
+    feature_row = {
+        '企业编号': 'PREDICT_COMPANY',
+        '所属行业': data.get('industry', DEFAULT_PREDICTION_INPUT['industry']),
+        '企业规模': data.get('company_size', DEFAULT_PREDICTION_INPUT['company_size']),
+        '所在城市等级': data.get('city_tier', DEFAULT_PREDICTION_INPUT['city_tier']),
+        '用工类型': data.get('employment_type', DEFAULT_PREDICTION_INPUT['employment_type']),
+        '部门条线': data.get('department_line', '研发'),
+        '岗位序列': data.get('job_family', DEFAULT_PREDICTION_INPUT['job_family']),
+        '岗位级别': data.get('job_level', DEFAULT_PREDICTION_INPUT['job_level']),
+        '员工编号': 'PREDICT_EMPLOYEE',
+        '性别': data.get('gender', '男'),
+        '年龄': data.get('age', DEFAULT_PREDICTION_INPUT['age']),
+        '司龄年数': data.get('tenure_years', DEFAULT_PREDICTION_INPUT['tenure_years']),
+        '最高学历': data.get('education_level', DEFAULT_PREDICTION_INPUT['education_level']),
+        '婚姻状态': data.get('marital_status', DEFAULT_PREDICTION_INPUT['marital_status']),
+        '是否本地户籍': data.get('local_hukou_flag', DEFAULT_PREDICTION_INPUT['local_hukou_flag']),
+        '子女数量': data.get('children_count', DEFAULT_PREDICTION_INPUT['children_count']),
+        '是否独生子女家庭负担': data.get(
+            'single_child_burden_flag',
+            DEFAULT_PREDICTION_INPUT['single_child_burden_flag'],
+        ),
+        '居住类型': data.get('housing_type', '租房'),
+        '班次类型': data.get('shift_type', DEFAULT_PREDICTION_INPUT['shift_type']),
+        '是否夜班岗位': data.get('is_night_shift', DEFAULT_PREDICTION_INPUT['is_night_shift']),
+        '月均加班时长': data.get(
+            'monthly_overtime_hours',
+            DEFAULT_PREDICTION_INPUT['monthly_overtime_hours'],
+        ),
+        '近30天出勤天数': data.get(
+            'attendance_days_30d',
+            DEFAULT_PREDICTION_INPUT['attendance_days_30d'],
+        ),
+        '近90天缺勤次数': data.get('absence_count_90d', DEFAULT_PREDICTION_INPUT['absence_count_90d']),
+        '近180天请假总时长': data.get('leave_hours_180d', DEFAULT_PREDICTION_INPUT['leave_hours_180d']),
+        '通勤时长分钟': data.get('commute_minutes', DEFAULT_PREDICTION_INPUT['commute_minutes']),
+        '通勤距离公里': data.get('commute_km', DEFAULT_PREDICTION_INPUT['commute_km']),
+        '是否跨城通勤': data.get(
+            'cross_city_commute',
+            DEFAULT_PREDICTION_INPUT['cross_city_commute'],
+        ),
+        '绩效等级': data.get('performance_level', DEFAULT_PREDICTION_INPUT['performance_level']),
+        '近12月违纪次数': data.get(
+            'disciplinary_count_12m',
+            DEFAULT_PREDICTION_INPUT['disciplinary_count_12m'],
+        ),
+        '团队人数': data.get('team_size', DEFAULT_PREDICTION_INPUT['team_size']),
+        '直属上级管理跨度': data.get('manager_span', DEFAULT_PREDICTION_INPUT['manager_span']),
+        'BMI': data.get('bmi', DEFAULT_PREDICTION_INPUT['bmi']),
+        '是否慢性病史': data.get(
+            'chronic_disease_flag',
+            DEFAULT_PREDICTION_INPUT['chronic_disease_flag'],
+        ),
+        '年度体检异常标记': data.get(
+            'annual_check_abnormal_flag',
+            DEFAULT_PREDICTION_INPUT['annual_check_abnormal_flag'],
+        ),
+        '近30天睡眠时长均值': data.get('sleep_hours', DEFAULT_PREDICTION_INPUT['sleep_hours']),
+        '每周运动频次': data.get(
+            'exercise_frequency',
+            DEFAULT_PREDICTION_INPUT['exercise_frequency'],
+        ),
+        '是否吸烟': data.get('smoking_flag', DEFAULT_PREDICTION_INPUT['smoking_flag']),
+        '是否饮酒': data.get('drinking_flag', DEFAULT_PREDICTION_INPUT['drinking_flag']),
+        '心理压力等级': data.get('stress_level', DEFAULT_PREDICTION_INPUT['stress_level']),
+        '是否长期久坐岗位': data.get(
+            'sedentary_job_flag',
+            DEFAULT_PREDICTION_INPUT['sedentary_job_flag'],
+        ),
+        '缺勤月份': data.get('absence_month', DEFAULT_PREDICTION_INPUT['absence_month']),
+        '星期几': data.get('weekday', DEFAULT_PREDICTION_INPUT['weekday']),
+        '是否节假日前后': data.get('near_holiday_flag', DEFAULT_PREDICTION_INPUT['near_holiday_flag']),
+        '季节': _season_from_month(data.get('absence_month', DEFAULT_PREDICTION_INPUT['absence_month'])),
+        '请假申请渠道': data.get('leave_channel', DEFAULT_PREDICTION_INPUT['leave_channel']),
+        '请假类型': data.get('leave_type', DEFAULT_PREDICTION_INPUT['leave_type']),
+        '请假原因大类': data.get(
+            'leave_reason_category',
+            DEFAULT_PREDICTION_INPUT['leave_reason_category'],
+        ),
+        '是否提供医院证明': data.get(
+            'medical_certificate_flag',
+            DEFAULT_PREDICTION_INPUT['medical_certificate_flag'],
+        ),
+        '是否临时请假': data.get('urgent_leave_flag', DEFAULT_PREDICTION_INPUT['urgent_leave_flag']),
+        '是否连续缺勤': data.get(
+            'continuous_absence_flag',
+            DEFAULT_PREDICTION_INPUT['continuous_absence_flag'],
+        ),
+        '前一工作日是否加班': data.get(
+            'previous_day_overtime_flag',
+            DEFAULT_PREDICTION_INPUT['previous_day_overtime_flag'],
+        ),
+    }
+    return pd.DataFrame([feature_row])
+
+
+def _season_from_month(month):
+    month = int(month)
+    if month in [12, 1, 2]:
+        return 1
+    if month in [3, 4, 5]:
+        return 2
+    if month in [6, 7, 8]:
+        return 3
+    return 4
+
+
+def align_feature_frame(df, feature_names):
+    aligned = df.copy()
+    for feature in feature_names:
+        if feature not in aligned.columns:
+            aligned[feature] = 0
+    return aligned[feature_names]
+
+
+def to_float_array(df):
+    return df.values.astype(float)