import os import sys import numpy as np import pandas as pd sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) import config INDUSTRIES = { '制造业': {'shift_bias': 0.9, 'overtime_bias': 0.8, 'night_bias': 0.8}, '互联网': {'shift_bias': 0.2, 'overtime_bias': 1.0, 'night_bias': 0.2}, '零售连锁': {'shift_bias': 0.7, 'overtime_bias': 0.5, 'night_bias': 0.3}, '物流运输': {'shift_bias': 0.9, 'overtime_bias': 0.7, 'night_bias': 0.9}, '金融服务': {'shift_bias': 0.1, 'overtime_bias': 0.7, 'night_bias': 0.1}, '医药健康': {'shift_bias': 0.6, 'overtime_bias': 0.6, 'night_bias': 0.5}, '建筑工程': {'shift_bias': 0.5, 'overtime_bias': 0.8, 'night_bias': 0.3}, } def season_from_month(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 weighted_choice(rng, items, probs): probs = np.array(probs, dtype=float) probs = probs / probs.sum() return rng.choice(items, p=probs) def build_company_pool(rng, company_count=180): industries = list(INDUSTRIES.keys()) scales = ['100人以下', '100-499人', '500-999人', '1000-4999人', '5000人及以上'] city_tiers = ['一线', '新一线', '二线', '三线及以下'] companies = [] for idx in range(company_count): industry = weighted_choice(rng, industries, [0.22, 0.14, 0.14, 0.14, 0.1, 0.12, 0.14]) companies.append({ '企业编号': f'C{idx + 1:03d}', '所属行业': industry, '企业规模': weighted_choice(rng, scales, [0.15, 0.28, 0.2, 0.24, 0.13]), '所在城市等级': weighted_choice(rng, city_tiers, [0.18, 0.34, 0.3, 0.18]), }) return companies def build_employee_pool(rng, companies, employee_count=2600): genders = ['男', '女'] employment_types = ['正式员工', '劳务派遣', '外包驻场', '实习生'] departments = ['生产', '研发', '销售', '客服', '职能', '仓储物流', '门店运营'] job_families = ['管理', '专业技术', '销售业务', '生产操作', '行政支持', '客服坐席'] job_levels = ['初级', '中级', '高级', '主管', '经理及以上'] educations = ['中专及以下', '大专', '本科', '硕士', '博士'] marital = ['未婚', '已婚', '离异/其他'] housing = ['自有住房', '租房', '宿舍'] shifts = ['标准白班', '两班倒', '三班倒', '弹性班'] performance = ['A', 'B', 'C', 'D'] stress = ['低', '中', '高'] employees = [] for idx in range(employee_count): company = companies[rng.integers(0, len(companies))] industry = company['所属行业'] age = int(np.clip(rng.normal(33, 7), 20, 55)) tenure = round(float(np.clip(age - 21 + rng.normal(0, 2), 0.2, 32)), 1) family_bias = 0.6 if age >= 30 else 0.25 married = weighted_choice(rng, marital, [0.45, 0.48, 0.07] if age < 30 else [0.18, 0.72, 0.1]) children = int(np.clip(rng.poisson(0.4 if married == '未婚' else family_bias), 0, 3)) industry_profile = INDUSTRIES[industry] shift = weighted_choice( rng, shifts, [ max(0.1, 1 - industry_profile['shift_bias']), 0.35 * industry_profile['shift_bias'], 0.25 * industry_profile['shift_bias'], 0.2, ], ) night_flag = int(shift == '三班倒' or (shift == '两班倒' and rng.random() < industry_profile['night_bias'])) overtime = float(np.clip(rng.normal(22 + 18 * industry_profile['overtime_bias'], 10), 0, 90)) commute_minutes = float(np.clip(rng.normal(42, 18), 8, 130)) commute_km = float(np.clip(commute_minutes * rng.uniform(0.35, 0.75), 2, 65)) performance_level = weighted_choice(rng, performance, [0.18, 0.46, 0.26, 0.1]) chronic_flag = int(rng.random() < max(0.05, (age - 26) * 0.01)) check_abnormal = int(chronic_flag == 1 or rng.random() < 0.14) sleep_hours = round(float(np.clip(rng.normal(6.9 - 0.35 * night_flag, 0.8), 4.5, 9.0)), 1) exercise = int(np.clip(rng.poisson(2.2), 0, 7)) smoking = int(rng.random() < (0.22 if rng.random() < 0.55 else 0.08)) drinking = int(rng.random() < 0.27) stress_level = weighted_choice( rng, stress, [0.22, 0.52, 0.26 + min(0.15, overtime / 120)], ) bmi = round(float(np.clip(rng.normal(24.2, 3.2), 17.5, 36.5)), 1) history_count = int(np.clip(rng.poisson(1.2 + chronic_flag * 0.6 + children * 0.15), 0, 8)) history_hours = float(np.clip(rng.normal(18 + chronic_flag * 10 + history_count * 3, 10), 0, 120)) discipline = int(np.clip(rng.poisson(0.2), 0, 4)) team_size = int(np.clip(rng.normal(11, 5), 3, 40)) manager_span = int(np.clip(team_size + rng.normal(3, 2), 4, 60)) local_hukou = int(rng.random() < 0.58) cross_city = int(commute_minutes > 65 or (local_hukou == 0 and rng.random() < 0.35)) sedentary = int(weighted_choice(rng, [0, 1], [0.45, 0.55]) if company['所属行业'] in ['互联网', '金融服务'] else rng.random() < 0.3) employees.append({ '企业编号': company['企业编号'], '所属行业': industry, '企业规模': company['企业规模'], '所在城市等级': company['所在城市等级'], '用工类型': weighted_choice(rng, employment_types, [0.74, 0.12, 0.1, 0.04]), '部门条线': weighted_choice(rng, departments, [0.18, 0.16, 0.14, 0.11, 0.12, 0.14, 0.15]), '岗位序列': weighted_choice(rng, job_families, [0.08, 0.24, 0.16, 0.2, 0.12, 0.2]), '岗位级别': weighted_choice(rng, job_levels, [0.34, 0.32, 0.18, 0.11, 0.05]), '员工编号': f'E{idx + 1:05d}', '性别': weighted_choice(rng, genders, [0.56, 0.44]), '年龄': age, '司龄年数': tenure, '最高学历': weighted_choice(rng, educations, [0.14, 0.28, 0.4, 0.15, 0.03]), '婚姻状态': married, '是否本地户籍': local_hukou, '子女数量': children, '是否独生子女家庭负担': int(children >= 2 or (married == '已婚' and rng.random() < 0.18)), '居住类型': weighted_choice(rng, housing, [0.38, 0.48, 0.14]), '班次类型': shift, '是否夜班岗位': night_flag, '月均加班时长': round(overtime, 1), '近30天出勤天数': int(np.clip(rng.normal(21.5, 2.2), 14, 27)), '近90天缺勤次数': history_count, '近180天请假总时长': round(history_hours, 1), '通勤时长分钟': round(commute_minutes, 1), '通勤距离公里': round(commute_km, 1), '是否跨城通勤': cross_city, '绩效等级': performance_level, '近12月违纪次数': discipline, '团队人数': team_size, '直属上级管理跨度': manager_span, 'BMI': bmi, '是否慢性病史': chronic_flag, '年度体检异常标记': check_abnormal, '近30天睡眠时长均值': sleep_hours, '每周运动频次': exercise, '是否吸烟': smoking, '是否饮酒': drinking, '心理压力等级': stress_level, '是否长期久坐岗位': sedentary, }) return employees def sample_event(rng, employee): month = int(rng.integers(1, 13)) weekday = int(rng.integers(1, 8)) near_holiday = int(rng.random() < (0.3 if month in [1, 2, 4, 5, 9, 10] else 0.16)) leave_type_items = ['病假', '事假', '年假', '调休', '婚假', '丧假', '产检育儿假', '工伤假', '其他'] leave_type = weighted_choice(rng, leave_type_items, [0.3, 0.22, 0.12, 0.14, 0.03, 0.02, 0.06, 0.02, 0.09]) if employee['子女数量'] > 0 and rng.random() < 0.14: reason_category = '子女照护' else: reason_category = weighted_choice( rng, ['身体不适', '家庭事务', '交通受阻', '突发事件', '职业疲劳', '就医复查'], [0.28, 0.19, 0.09, 0.11, 0.2, 0.13], ) medical_certificate = int(leave_type in ['病假', '工伤假'] or reason_category in ['身体不适', '就医复查']) urgent_leave = int(rng.random() < (0.45 if leave_type in ['病假', '事假', '工伤假'] else 0.18)) continuous_absence = int(rng.random() < (0.2 if leave_type in ['病假', '产检育儿假', '工伤假'] else 0.08)) previous_overtime = int(rng.random() < min(0.85, employee['月均加班时长'] / 65)) season = season_from_month(month) channel = weighted_choice(rng, ['系统申请', '主管代提', '临时电话报备'], [0.68, 0.18, 0.14]) base = 0.95 base += min(employee['月均加班时长'] / 28, 1.8) base += min(employee['通勤时长分钟'] / 65, 1.2) base += employee['是否夜班岗位'] * 0.9 base += employee['是否慢性病史'] * 1.25 base += employee['年度体检异常标记'] * 0.6 base += 0.35 * employee['子女数量'] base += 0.5 if employee['心理压力等级'] == '高' else (0.2 if employee['心理压力等级'] == '中' else -0.1) base += 0.4 if employee['是否跨城通勤'] else 0 base += 0.35 if previous_overtime else 0 base += 0.35 if near_holiday else 0 base += 0.3 if continuous_absence else 0 base += 0.3 if employee['近90天缺勤次数'] >= 3 else 0 base -= 0.35 if employee['绩效等级'] == 'A' else (0.15 if employee['绩效等级'] == 'B' else 0) base -= min(employee['司龄年数'] / 40, 0.5) base -= min(employee['每周运动频次'] * 0.08, 0.3) base -= 0.2 if employee['近30天睡眠时长均值'] >= 7.5 else 0 leave_bonus = { '病假': 2.0, '事假': 0.8, '年假': 0.1, '调休': 0.1, '婚假': 3.0, '丧假': 2.8, '产检育儿假': 2.4, '工伤假': 3.8, '其他': 0.5, } reason_bonus = { '身体不适': 1.0, '家庭事务': 0.5, '子女照护': 0.8, '交通受阻': 0.2, '突发事件': 0.6, '职业疲劳': 0.7, '就医复查': 1.2, } industry_bonus = { '制造业': 0.35, '互联网': 0.2, '零售连锁': 0.25, '物流运输': 0.4, '金融服务': 0.1, '医药健康': 0.2, '建筑工程': 0.35, } season_bonus = {1: 0.35, 2: 0.0, 3: 0.15, 4: 0.05} weekday_bonus = {1: 0.05, 2: 0.0, 3: 0.0, 4: 0.05, 5: 0.15, 6: 0.25, 7: 0.3} duration = base duration += leave_bonus[leave_type] duration += reason_bonus[reason_category] duration += industry_bonus[employee['所属行业']] duration += season_bonus[season] duration += weekday_bonus[weekday] duration += 0.55 if medical_certificate else 0 duration += 0.4 if urgent_leave else -0.05 duration += rng.normal(0, 0.9) if leave_type in ['婚假', '丧假', '工伤假'] and rng.random() < 0.5: duration += rng.uniform(1.5, 5) if leave_type == '病假' and employee['是否慢性病史'] == 1 and rng.random() < 0.35: duration += rng.uniform(1, 4) if leave_type in ['年假', '调休']: duration *= rng.uniform(0.7, 0.95) duration = round(float(np.clip(duration, 0.5, 24.0)), 1) event = employee.copy() event.update({ '缺勤月份': month, '星期几': weekday, '是否节假日前后': near_holiday, '季节': season, '请假申请渠道': channel, '请假类型': leave_type, '请假原因大类': reason_category, '是否提供医院证明': medical_certificate, '是否临时请假': urgent_leave, '是否连续缺勤': continuous_absence, '前一工作日是否加班': previous_overtime, '缺勤时长（小时）': duration, }) return event def attach_event_timeline(df): df = df.copy() rng = np.random.default_rng(config.RANDOM_STATE) base_date = np.datetime64('2025-01-01') timelines = [] for employee_id, group in df.groupby('员工编号', sort=False): group = group.copy().reset_index(drop=True) event_count = len(group) offsets = np.sort(rng.integers(0, 365, size=event_count)) group['事件日期'] = [ str(pd.Timestamp(base_date + np.timedelta64(int(offset), 'D')).date()) for offset in offsets ] group['事件日期索引'] = offsets.astype(int) group['事件序号'] = np.arange(1, event_count + 1) group['员工历史事件数'] = event_count timelines.append(group) return pd.concat(timelines, ignore_index=True) def validate_dataset(df): required_columns = [ '员工编号', '所属行业', '岗位序列', '月均加班时长', '通勤时长分钟', '是否慢性病史', '请假类型', '事件序号', '事件日期索引', '员工历史事件数', '缺勤时长（小时）', ] for column in required_columns: if column not in df.columns: raise ValueError(f'Missing required column: {column}') if len(df) < 10000: raise ValueError('Synthetic dataset is smaller than expected') if df['员工编号'].nunique() < 2000: raise ValueError('Employee coverage is too small') high_risk_ratio = (df['缺勤时长（小时）'] > 8).mean() if not 0.15 <= high_risk_ratio <= 0.4: raise ValueError(f'High risk ratio out of range: {high_risk_ratio:.3f}') medical_mean = df[df['是否提供医院证明'] == 1]['缺勤时长（小时）'].mean() no_medical_mean = df[df['是否提供医院证明'] == 0]['缺勤时长（小时）'].mean() if medical_mean <= no_medical_mean: raise ValueError('Medical certificate signal is not effective') night_mean = df[df['是否夜班岗位'] == 1]['缺勤时长（小时）'].mean() day_mean = df[df['是否夜班岗位'] == 0]['缺勤时长（小时）'].mean() if night_mean <= day_mean: raise ValueError('Night shift signal is not effective') def generate_dataset(output_path=None, sample_count=12000, random_state=None): rng = np.random.default_rng(config.RANDOM_STATE if random_state is None else random_state) companies = build_company_pool(rng) employees = build_employee_pool(rng, companies) events = [] employee_idx = rng.integers(0, len(employees), size=sample_count) for idx in employee_idx: events.append(sample_event(rng, employees[int(idx)])) df = attach_event_timeline(pd.DataFrame(events)) validate_dataset(df) if output_path: os.makedirs(os.path.dirname(output_path), exist_ok=True) df.to_csv(output_path, index=False, encoding='utf-8-sig') return df def ensure_dataset(): if not os.path.exists(config.RAW_DATA_PATH): generate_dataset(config.RAW_DATA_PATH) return try: df = pd.read_csv(config.RAW_DATA_PATH) validate_dataset(df) except Exception: generate_dataset(config.RAW_DATA_PATH) if __name__ == '__main__': dataset = generate_dataset(config.RAW_DATA_PATH) print(f'Generated dataset: {config.RAW_DATA_PATH}') print(dataset.head())