feat: 升级深度学习模型为 Temporal Fusion Transformer 架构
- 将 LSTMMLPRegressor 重构为 TemporalFusionRegressor，采用 Transformer Encoder 替代 LSTM - 新增 LearnedAttentionPooling 和 GatedResidualBlock 模块增强模型表达能力 - 优化训练策略，使用 OneCycleLR 调度器和样本加权机制 - 改进缺勤事件采样算法，基于压力、健康、家庭等维度更精确地计算缺勤时长 - 更新 .gitignore 排除原始数据文件，删除不再使用的原始 CSV 文件
This commit is contained in:
@@ -161,68 +161,109 @@ def sample_event(rng, employee):
|
||||
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'
|
||||
leave_probs = [0.26, 0.22, 0.11, 0.14, 0.03, 0.02, 0.07, 0.03, 0.12]
|
||||
if employee['是否慢性病史'] == 1 or employee['年度体检异常标记'] == 1:
|
||||
leave_probs = [0.34, 0.18, 0.08, 0.1, 0.02, 0.02, 0.08, 0.04, 0.14]
|
||||
elif employee['子女数量'] >= 2:
|
||||
leave_probs = [0.22, 0.24, 0.1, 0.12, 0.03, 0.02, 0.12, 0.02, 0.13]
|
||||
leave_type = weighted_choice(rng, leave_type_items, leave_probs)
|
||||
|
||||
if leave_type in ['病假', '工伤假']:
|
||||
reason_category = weighted_choice(rng, ['身体不适', '就医复查', '职业疲劳'], [0.52, 0.3, 0.18])
|
||||
elif leave_type == '产检育儿假':
|
||||
reason_category = weighted_choice(rng, ['子女照护', '家庭事务', '身体不适'], [0.6, 0.25, 0.15])
|
||||
elif leave_type in ['婚假', '丧假']:
|
||||
reason_category = weighted_choice(rng, ['家庭事务', '突发事件'], [0.72, 0.28])
|
||||
elif leave_type in ['年假', '调休']:
|
||||
reason_category = weighted_choice(rng, ['职业疲劳', '家庭事务', '交通受阻'], [0.52, 0.28, 0.2])
|
||||
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],
|
||||
['身体不适', '家庭事务', '子女照护', '交通受阻', '突发事件', '职业疲劳'],
|
||||
[0.2, 0.22, 0.14, 0.12, 0.12, 0.2],
|
||||
)
|
||||
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))
|
||||
|
||||
medical_certificate = int(
|
||||
leave_type in ['病假', '工伤假']
|
||||
or reason_category in ['身体不适', '就医复查']
|
||||
or (employee['是否慢性病史'] == 1 and leave_type == '其他')
|
||||
)
|
||||
urgent_leave = int(
|
||||
leave_type in ['病假', '工伤假']
|
||||
or reason_category in ['突发事件', '身体不适']
|
||||
or (near_holiday == 0 and leave_type == '事假' and rng.random() < 0.35)
|
||||
)
|
||||
continuous_absence = int(
|
||||
leave_type in ['病假', '工伤假', '产检育儿假']
|
||||
and (employee['近90天缺勤次数'] >= 2 or employee['近180天请假总时长'] >= 28)
|
||||
)
|
||||
previous_overtime = int(
|
||||
employee['月均加班时长'] >= 30
|
||||
or (employee['月均加班时长'] >= 24 and weekday in [1, 2, 5])
|
||||
or (employee['是否夜班岗位'] == 1 and rng.random() < 0.65)
|
||||
)
|
||||
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
|
||||
pressure_score = (
|
||||
employee['月均加班时长'] * 0.032
|
||||
+ employee['通勤时长分钟'] * 0.018
|
||||
+ employee['是否夜班岗位'] * 0.75
|
||||
+ employee['是否跨城通勤'] * 0.32
|
||||
+ previous_overtime * 0.35
|
||||
)
|
||||
health_score = (
|
||||
employee['是否慢性病史'] * 1.2
|
||||
+ employee['年度体检异常标记'] * 0.55
|
||||
+ (employee['BMI'] >= 28) * 0.3
|
||||
+ (employee['近30天睡眠时长均值'] < 6.4) * 0.45
|
||||
)
|
||||
family_score = employee['子女数量'] * 0.18 + employee['是否独生子女家庭负担'] * 0.28
|
||||
resilience_score = (
|
||||
(0.55 if employee['绩效等级'] == 'A' else 0.25 if employee['绩效等级'] == 'B' else 0.0)
|
||||
+ min(employee['司龄年数'] / 26, 0.65)
|
||||
+ min(employee['每周运动频次'] * 0.06, 0.25)
|
||||
)
|
||||
|
||||
base = 0.35
|
||||
base += pressure_score
|
||||
base += health_score
|
||||
base += family_score
|
||||
base += 0.4 if employee['心理压力等级'] == '高' else (0.18 if employee['心理压力等级'] == '中' else -0.05)
|
||||
base += 0.18 if near_holiday else 0.0
|
||||
base += 0.35 if continuous_absence else 0.0
|
||||
base += 0.28 if employee['近90天缺勤次数'] >= 3 else 0.0
|
||||
base += 0.18 if employee['近180天请假总时长'] >= 36 else 0.0
|
||||
base -= resilience_score
|
||||
|
||||
leave_bonus = {
|
||||
'病假': 2.0,
|
||||
'病假': 2.1,
|
||||
'事假': 0.8,
|
||||
'年假': 0.1,
|
||||
'年假': 0.15,
|
||||
'调休': 0.1,
|
||||
'婚假': 3.0,
|
||||
'婚假': 3.1,
|
||||
'丧假': 2.8,
|
||||
'产检育儿假': 2.4,
|
||||
'工伤假': 3.8,
|
||||
'其他': 0.5,
|
||||
'产检育儿假': 2.35,
|
||||
'工伤假': 3.9,
|
||||
'其他': 0.55,
|
||||
}
|
||||
reason_bonus = {
|
||||
'身体不适': 1.0,
|
||||
'家庭事务': 0.5,
|
||||
'子女照护': 0.8,
|
||||
'家庭事务': 0.55,
|
||||
'子女照护': 0.75,
|
||||
'交通受阻': 0.2,
|
||||
'突发事件': 0.6,
|
||||
'职业疲劳': 0.7,
|
||||
'就医复查': 1.2,
|
||||
'就医复查': 1.15,
|
||||
}
|
||||
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,
|
||||
'制造业': 0.42,
|
||||
'互联网': 0.22,
|
||||
'零售连锁': 0.28,
|
||||
'物流运输': 0.5,
|
||||
'金融服务': 0.12,
|
||||
'医药健康': 0.24,
|
||||
'建筑工程': 0.4,
|
||||
}
|
||||
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}
|
||||
@@ -233,18 +274,21 @@ def sample_event(rng, employee):
|
||||
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)
|
||||
duration += 0.55 if medical_certificate else 0.0
|
||||
duration += 0.28 if urgent_leave else -0.06
|
||||
|
||||
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 == '病假' and employee['是否慢性病史'] == 1:
|
||||
duration += 0.85
|
||||
if leave_type == '工伤假':
|
||||
duration += 1.0 + employee['是否夜班岗位'] * 0.3
|
||||
if leave_type in ['婚假', '丧假']:
|
||||
duration += 0.7 + 0.18 * near_holiday
|
||||
if leave_type == '产检育儿假':
|
||||
duration += 0.55 + employee['子女数量'] * 0.12
|
||||
if leave_type in ['年假', '调休']:
|
||||
duration *= rng.uniform(0.7, 0.95)
|
||||
duration *= 0.82 if near_holiday == 0 else 0.9
|
||||
|
||||
duration = round(float(np.clip(duration, 0.5, 24.0)), 1)
|
||||
duration = round(float(np.clip(duration + rng.normal(0, 0.35), 0.5, 18.0)), 1)
|
||||
|
||||
event = employee.copy()
|
||||
event.update({
|
||||
|
||||
Reference in New Issue
Block a user