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
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
import os
|
||||
|
||||
import joblib
|
||||
import numpy as np
|
||||
|
||||
import config
|
||||
from core.feature_mining import get_correlation_for_heatmap, group_comparison
|
||||
@@ -10,109 +10,95 @@ class AnalysisService:
|
||||
def __init__(self):
|
||||
self.models = {}
|
||||
self.feature_names = None
|
||||
|
||||
self.selected_features = None
|
||||
self.training_metadata = {}
|
||||
|
||||
def _ensure_models_loaded(self):
|
||||
if not self.models:
|
||||
model_files = {
|
||||
'random_forest': 'random_forest_model.pkl',
|
||||
'xgboost': 'xgboost_model.pkl',
|
||||
'lightgbm': 'lightgbm_model.pkl',
|
||||
}
|
||||
|
||||
for name, filename in model_files.items():
|
||||
model_path = os.path.join(config.MODELS_DIR, filename)
|
||||
if os.path.exists(model_path):
|
||||
try:
|
||||
self.models[name] = joblib.load(model_path)
|
||||
except Exception as e:
|
||||
print(f"Failed to load {name}: {e}")
|
||||
|
||||
feature_names_path = os.path.join(config.MODELS_DIR, 'feature_names.pkl')
|
||||
if os.path.exists(feature_names_path):
|
||||
self.feature_names = joblib.load(feature_names_path)
|
||||
|
||||
if self.models:
|
||||
return
|
||||
metadata_path = os.path.join(config.MODELS_DIR, 'training_metadata.pkl')
|
||||
if os.path.exists(metadata_path):
|
||||
self.training_metadata = joblib.load(metadata_path)
|
||||
model_files = {
|
||||
'random_forest': 'random_forest_model.pkl',
|
||||
'xgboost': 'xgboost_model.pkl',
|
||||
'lightgbm': 'lightgbm_model.pkl',
|
||||
'gradient_boosting': 'gradient_boosting_model.pkl',
|
||||
}
|
||||
allowed_models = self.training_metadata.get('available_models')
|
||||
if allowed_models:
|
||||
model_files = {k: v for k, v in model_files.items() if k in allowed_models}
|
||||
for name, filename in model_files.items():
|
||||
path = os.path.join(config.MODELS_DIR, filename)
|
||||
if os.path.exists(path):
|
||||
try:
|
||||
self.models[name] = joblib.load(path)
|
||||
except Exception as exc:
|
||||
print(f'Failed to load model {name}: {exc}')
|
||||
for filename, attr in [('feature_names.pkl', 'feature_names'), ('selected_features.pkl', 'selected_features')]:
|
||||
path = os.path.join(config.MODELS_DIR, filename)
|
||||
if os.path.exists(path):
|
||||
try:
|
||||
setattr(self, attr, joblib.load(path))
|
||||
except Exception as exc:
|
||||
print(f'Failed to load artifact {filename}: {exc}')
|
||||
|
||||
def get_feature_importance(self, model_type='random_forest'):
|
||||
self._ensure_models_loaded()
|
||||
|
||||
if model_type not in self.models:
|
||||
if self.models:
|
||||
model_type = list(self.models.keys())[0]
|
||||
else:
|
||||
return self._get_default_importance()
|
||||
|
||||
model_type = next(iter(self.models), 'default')
|
||||
if model_type == 'default':
|
||||
return self._get_default_importance()
|
||||
model = self.models[model_type]
|
||||
|
||||
try:
|
||||
if hasattr(model, 'feature_importances_'):
|
||||
importances = model.feature_importances_
|
||||
else:
|
||||
return self._get_default_importance()
|
||||
|
||||
feature_names = self.feature_names or [f'feature_{i}' for i in range(len(importances))]
|
||||
|
||||
if len(feature_names) != len(importances):
|
||||
feature_names = [f'feature_{i}' for i in range(len(importances))]
|
||||
|
||||
feature_importance = list(zip(feature_names, importances))
|
||||
feature_importance.sort(key=lambda x: x[1], reverse=True)
|
||||
|
||||
features = []
|
||||
for i, (name, imp) in enumerate(feature_importance[:15]):
|
||||
features.append({
|
||||
if not hasattr(model, 'feature_importances_'):
|
||||
return self._get_default_importance()
|
||||
|
||||
importances = model.feature_importances_
|
||||
feature_names = self.selected_features or self.feature_names or []
|
||||
if len(feature_names) != len(importances):
|
||||
feature_names = [f'feature_{idx}' for idx in range(len(importances))]
|
||||
ranked = sorted(zip(feature_names, importances), key=lambda item: item[1], reverse=True)[:15]
|
||||
return {
|
||||
'model_type': model_type,
|
||||
'features': [
|
||||
{
|
||||
'name': name,
|
||||
'name_cn': config.FEATURE_NAME_CN.get(name, name),
|
||||
'importance': round(float(imp), 4),
|
||||
'rank': i + 1
|
||||
})
|
||||
|
||||
return {
|
||||
'model_type': model_type,
|
||||
'features': features
|
||||
}
|
||||
except Exception as e:
|
||||
print(f"Error getting feature importance: {e}")
|
||||
return self._get_default_importance()
|
||||
|
||||
'importance': round(float(importance), 4),
|
||||
'rank': idx + 1,
|
||||
}
|
||||
for idx, (name, importance) in enumerate(ranked)
|
||||
],
|
||||
}
|
||||
|
||||
def _get_default_importance(self):
|
||||
default_features = [
|
||||
('Reason for absence', 0.25),
|
||||
('Transportation expense', 0.12),
|
||||
('Distance from Residence to Work', 0.10),
|
||||
('Service time', 0.08),
|
||||
('Age', 0.07),
|
||||
('Work load Average/day', 0.06),
|
||||
('Body mass index', 0.05),
|
||||
('Social drinker', 0.04),
|
||||
('Hit target', 0.03),
|
||||
('Son', 0.03),
|
||||
('Pet', 0.02),
|
||||
('Education', 0.02),
|
||||
('Social smoker', 0.01)
|
||||
defaults = [
|
||||
('加班通勤压力指数', 0.24),
|
||||
('健康风险指数', 0.18),
|
||||
('请假类型', 0.12),
|
||||
('通勤时长分钟', 0.1),
|
||||
('月均加班时长', 0.08),
|
||||
('近90天缺勤次数', 0.07),
|
||||
('心理压力等级', 0.06),
|
||||
('家庭负担指数', 0.05),
|
||||
]
|
||||
|
||||
features = []
|
||||
for i, (name, imp) in enumerate(default_features):
|
||||
features.append({
|
||||
'name': name,
|
||||
'name_cn': config.FEATURE_NAME_CN.get(name, name),
|
||||
'importance': imp,
|
||||
'rank': i + 1
|
||||
})
|
||||
|
||||
return {
|
||||
'model_type': 'default',
|
||||
'features': features
|
||||
'features': [
|
||||
{
|
||||
'name': name,
|
||||
'name_cn': config.FEATURE_NAME_CN.get(name, name),
|
||||
'importance': importance,
|
||||
'rank': idx + 1,
|
||||
}
|
||||
for idx, (name, importance) in enumerate(defaults)
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
def get_correlation(self):
|
||||
return get_correlation_for_heatmap()
|
||||
|
||||
|
||||
def get_group_comparison(self, dimension):
|
||||
valid_dimensions = ['drinker', 'smoker', 'education', 'children', 'pet']
|
||||
|
||||
if dimension not in valid_dimensions:
|
||||
raise ValueError(f"Invalid dimension: {dimension}. Must be one of {valid_dimensions}")
|
||||
|
||||
return group_comparison(dimension)
|
||||
|
||||
|
||||
|
||||
@@ -11,7 +11,7 @@ class ClusterService:
|
||||
def get_cluster_profile(self, n_clusters=3):
|
||||
return self.analyzer.get_cluster_profile(n_clusters)
|
||||
|
||||
def get_scatter_data(self, n_clusters=3, x_axis='Age', y_axis='Absenteeism time in hours'):
|
||||
def get_scatter_data(self, n_clusters=3, x_axis='月均加班时长', y_axis='缺勤时长（小时）'):
|
||||
return self.analyzer.get_scatter_data(n_clusters, x_axis, y_axis)
|
||||
|
||||
|
||||
|
||||
@@ -1,6 +1,3 @@
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
|
||||
import config
|
||||
from core.preprocessing import get_clean_data
|
||||
|
||||
@@ -8,154 +5,103 @@ from core.preprocessing import get_clean_data
|
||||
class DataService:
|
||||
def __init__(self):
|
||||
self._df = None
|
||||
|
||||
|
||||
@property
|
||||
def df(self):
|
||||
if self._df is None:
|
||||
self._df = get_clean_data()
|
||||
return self._df
|
||||
|
||||
|
||||
def get_basic_stats(self):
|
||||
df = self.df
|
||||
|
||||
total_records = len(df)
|
||||
total_employees = df['ID'].nunique()
|
||||
total_absent_hours = df['Absenteeism time in hours'].sum()
|
||||
avg_absent_hours = round(df['Absenteeism time in hours'].mean(), 2)
|
||||
max_absent_hours = int(df['Absenteeism time in hours'].max())
|
||||
min_absent_hours = int(df['Absenteeism time in hours'].min())
|
||||
|
||||
high_risk_count = len(df[df['Absenteeism time in hours'] > 8])
|
||||
high_risk_ratio = round(high_risk_count / total_records, 4)
|
||||
|
||||
total_employees = df[config.EMPLOYEE_ID_COLUMN].nunique()
|
||||
avg_absent_hours = round(df[config.TARGET_COLUMN].mean(), 2)
|
||||
max_absent_hours = round(float(df[config.TARGET_COLUMN].max()), 1)
|
||||
min_absent_hours = round(float(df[config.TARGET_COLUMN].min()), 1)
|
||||
high_risk_count = len(df[df[config.TARGET_COLUMN] > 8])
|
||||
return {
|
||||
'total_records': total_records,
|
||||
'total_employees': total_employees,
|
||||
'total_absent_hours': int(total_absent_hours),
|
||||
'avg_absent_hours': avg_absent_hours,
|
||||
'max_absent_hours': max_absent_hours,
|
||||
'min_absent_hours': min_absent_hours,
|
||||
'high_risk_ratio': high_risk_ratio
|
||||
'high_risk_ratio': round(high_risk_count / total_records, 4),
|
||||
'industries_covered': int(df['所属行业'].nunique()),
|
||||
}
|
||||
|
||||
|
||||
def get_monthly_trend(self):
|
||||
df = self.df
|
||||
|
||||
monthly = df.groupby('Month of absence').agg({
|
||||
'Absenteeism time in hours': ['sum', 'mean', 'count']
|
||||
}).reset_index()
|
||||
|
||||
monthly = df.groupby('缺勤月份').agg({config.TARGET_COLUMN: ['sum', 'mean', 'count']}).reset_index()
|
||||
monthly.columns = ['month', 'total_hours', 'avg_hours', 'record_count']
|
||||
|
||||
months = ['1月', '2月', '3月', '4月', '5月', '6月',
|
||||
'7月', '8月', '9月', '10月', '11月', '12月']
|
||||
|
||||
result = {
|
||||
'months': months,
|
||||
'total_hours': [],
|
||||
'avg_hours': [],
|
||||
'record_counts': []
|
||||
}
|
||||
|
||||
for i in range(1, 13):
|
||||
row = monthly[monthly['month'] == i]
|
||||
if len(row) > 0:
|
||||
result['total_hours'].append(int(row['total_hours'].values[0]))
|
||||
result = {'months': [], 'total_hours': [], 'avg_hours': [], 'record_counts': []}
|
||||
for month in range(1, 13):
|
||||
row = monthly[monthly['month'] == month]
|
||||
result['months'].append(f'{month}月')
|
||||
if len(row):
|
||||
result['total_hours'].append(round(float(row['total_hours'].values[0]), 1))
|
||||
result['avg_hours'].append(round(float(row['avg_hours'].values[0]), 2))
|
||||
result['record_counts'].append(int(row['record_count'].values[0]))
|
||||
else:
|
||||
result['total_hours'].append(0)
|
||||
result['avg_hours'].append(0)
|
||||
result['record_counts'].append(0)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def get_weekday_distribution(self):
|
||||
df = self.df
|
||||
|
||||
weekday = df.groupby('Day of the week').agg({
|
||||
'Absenteeism time in hours': ['sum', 'mean', 'count']
|
||||
}).reset_index()
|
||||
|
||||
weekday = df.groupby('星期几').agg({config.TARGET_COLUMN: ['sum', 'mean', 'count']}).reset_index()
|
||||
weekday.columns = ['weekday', 'total_hours', 'avg_hours', 'record_count']
|
||||
|
||||
result = {
|
||||
'weekdays': [],
|
||||
'weekday_codes': [],
|
||||
'total_hours': [],
|
||||
'avg_hours': [],
|
||||
'record_counts': []
|
||||
}
|
||||
|
||||
for code in [2, 3, 4, 5, 6]:
|
||||
result = {'weekdays': [], 'weekday_codes': [], 'total_hours': [], 'avg_hours': [], 'record_counts': []}
|
||||
for code in range(1, 8):
|
||||
row = weekday[weekday['weekday'] == code]
|
||||
result['weekdays'].append(config.WEEKDAY_NAMES.get(code, str(code)))
|
||||
result['weekday_codes'].append(code)
|
||||
if len(row) > 0:
|
||||
result['total_hours'].append(int(row['total_hours'].values[0]))
|
||||
if len(row):
|
||||
result['total_hours'].append(round(float(row['total_hours'].values[0]), 1))
|
||||
result['avg_hours'].append(round(float(row['avg_hours'].values[0]), 2))
|
||||
result['record_counts'].append(int(row['record_count'].values[0]))
|
||||
else:
|
||||
result['total_hours'].append(0)
|
||||
result['avg_hours'].append(0)
|
||||
result['record_counts'].append(0)
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def get_reason_distribution(self):
|
||||
df = self.df
|
||||
|
||||
reason = df.groupby('Reason for absence').agg({
|
||||
'Absenteeism time in hours': 'count'
|
||||
}).reset_index()
|
||||
|
||||
reason.columns = ['code', 'count']
|
||||
reason = df.groupby('请假原因大类').agg({config.TARGET_COLUMN: 'count'}).reset_index()
|
||||
reason.columns = ['name', 'count']
|
||||
reason = reason.sort_values('count', ascending=False)
|
||||
|
||||
total = reason['count'].sum()
|
||||
|
||||
result = {
|
||||
'reasons': []
|
||||
return {
|
||||
'reasons': [
|
||||
{
|
||||
'name': row['name'],
|
||||
'count': int(row['count']),
|
||||
'percentage': round(float(row['count']) / total * 100, 1),
|
||||
}
|
||||
for _, row in reason.iterrows()
|
||||
]
|
||||
}
|
||||
|
||||
for _, row in reason.iterrows():
|
||||
code = int(row['code'])
|
||||
result['reasons'].append({
|
||||
'code': code,
|
||||
'name': config.REASON_NAMES.get(code, f'原因{code}'),
|
||||
'count': int(row['count']),
|
||||
'percentage': round(row['count'] / total * 100, 1)
|
||||
})
|
||||
|
||||
return result
|
||||
|
||||
|
||||
def get_season_distribution(self):
|
||||
df = self.df
|
||||
|
||||
season = df.groupby('Seasons').agg({
|
||||
'Absenteeism time in hours': ['sum', 'mean', 'count']
|
||||
}).reset_index()
|
||||
|
||||
season = df.groupby('季节').agg({config.TARGET_COLUMN: ['sum', 'mean', 'count']}).reset_index()
|
||||
season.columns = ['season', 'total_hours', 'avg_hours', 'record_count']
|
||||
|
||||
total_records = season['record_count'].sum()
|
||||
|
||||
result = {
|
||||
'seasons': []
|
||||
}
|
||||
|
||||
result = {'seasons': []}
|
||||
for code in [1, 2, 3, 4]:
|
||||
row = season[season['season'] == code]
|
||||
if len(row) > 0:
|
||||
result['seasons'].append({
|
||||
'code': int(code),
|
||||
'name': config.SEASON_NAMES.get(code, f'季节{code}'),
|
||||
'total_hours': int(row['total_hours'].values[0]),
|
||||
'avg_hours': round(float(row['avg_hours'].values[0]), 2),
|
||||
'record_count': int(row['record_count'].values[0]),
|
||||
'percentage': round(row['record_count'].values[0] / total_records * 100, 1)
|
||||
})
|
||||
|
||||
if not len(row):
|
||||
continue
|
||||
result['seasons'].append({
|
||||
'code': code,
|
||||
'name': config.SEASON_NAMES.get(code, f'季节{code}'),
|
||||
'total_hours': round(float(row['total_hours'].values[0]), 1),
|
||||
'avg_hours': round(float(row['avg_hours'].values[0]), 2),
|
||||
'record_count': int(row['record_count'].values[0]),
|
||||
'percentage': round(float(row['record_count'].values[0]) / total_records * 100, 1),
|
||||
})
|
||||
return result
|
||||
|
||||
|
||||
|
||||
@@ -1,41 +1,25 @@
|
||||
import os
|
||||
import numpy as np
|
||||
|
||||
import joblib
|
||||
import numpy as np
|
||||
|
||||
import config
|
||||
from core.model_features import (
|
||||
align_feature_frame,
|
||||
apply_label_encoders,
|
||||
build_prediction_dataframe,
|
||||
engineer_features,
|
||||
to_float_array,
|
||||
)
|
||||
|
||||
|
||||
MODEL_INFO = {
|
||||
'random_forest': {
|
||||
'name': 'random_forest',
|
||||
'name_cn': '随机森林',
|
||||
'description': '基于决策树的集成学习算法'
|
||||
},
|
||||
'xgboost': {
|
||||
'name': 'xgboost',
|
||||
'name_cn': 'XGBoost',
|
||||
'description': '高效的梯度提升算法'
|
||||
},
|
||||
'lightgbm': {
|
||||
'name': 'lightgbm',
|
||||
'name_cn': 'LightGBM',
|
||||
'description': '微软轻量级梯度提升框架'
|
||||
},
|
||||
'gradient_boosting': {
|
||||
'name': 'gradient_boosting',
|
||||
'name_cn': 'GBDT',
|
||||
'description': '梯度提升决策树'
|
||||
},
|
||||
'extra_trees': {
|
||||
'name': 'extra_trees',
|
||||
'name_cn': '极端随机树',
|
||||
'description': '随机森林的变体，随机性更强'
|
||||
},
|
||||
'stacking': {
|
||||
'name': 'stacking',
|
||||
'name_cn': 'Stacking集成',
|
||||
'description': '多层堆叠集成学习'
|
||||
}
|
||||
'random_forest': {'name': 'random_forest', 'name_cn': '随机森林', 'description': '稳健的树模型集成'},
|
||||
'xgboost': {'name': 'xgboost', 'name_cn': 'XGBoost', 'description': '梯度提升树模型'},
|
||||
'lightgbm': {'name': 'lightgbm', 'name_cn': 'LightGBM', 'description': '轻量级梯度提升树'},
|
||||
'gradient_boosting': {'name': 'gradient_boosting', 'name_cn': 'GBDT', 'description': '梯度提升决策树'},
|
||||
'extra_trees': {'name': 'extra_trees', 'name_cn': '极端随机树', 'description': '高随机性的树模型'},
|
||||
'stacking': {'name': 'stacking', 'name_cn': 'Stacking集成', 'description': '多模型融合'},
|
||||
}
|
||||
|
||||
|
||||
@@ -47,326 +31,172 @@ class PredictService:
|
||||
self.selected_features = None
|
||||
self.label_encoders = {}
|
||||
self.model_metrics = {}
|
||||
self.training_metadata = {}
|
||||
self.default_model = 'random_forest'
|
||||
|
||||
|
||||
def _ensure_models_loaded(self):
|
||||
if not self.models:
|
||||
self.load_models()
|
||||
|
||||
|
||||
def load_models(self):
|
||||
metadata_path = os.path.join(config.MODELS_DIR, 'training_metadata.pkl')
|
||||
if os.path.exists(metadata_path):
|
||||
self.training_metadata = joblib.load(metadata_path)
|
||||
|
||||
model_files = {
|
||||
'random_forest': 'random_forest_model.pkl',
|
||||
'xgboost': 'xgboost_model.pkl',
|
||||
'lightgbm': 'lightgbm_model.pkl',
|
||||
'gradient_boosting': 'gradient_boosting_model.pkl',
|
||||
'extra_trees': 'extra_trees_model.pkl',
|
||||
'stacking': 'stacking_model.pkl'
|
||||
'stacking': 'stacking_model.pkl',
|
||||
}
|
||||
|
||||
allowed_models = self.training_metadata.get('available_models')
|
||||
if allowed_models:
|
||||
model_files = {k: v for k, v in model_files.items() if k in allowed_models}
|
||||
|
||||
for name, filename in model_files.items():
|
||||
model_path = os.path.join(config.MODELS_DIR, filename)
|
||||
if os.path.exists(model_path):
|
||||
path = os.path.join(config.MODELS_DIR, filename)
|
||||
if os.path.exists(path):
|
||||
try:
|
||||
self.models[name] = joblib.load(model_path)
|
||||
print(f"Loaded {name} model")
|
||||
except Exception as e:
|
||||
print(f"Failed to load {name}: {e}")
|
||||
|
||||
self.models[name] = joblib.load(path)
|
||||
except Exception as exc:
|
||||
print(f'Failed to load model {name}: {exc}')
|
||||
|
||||
if os.path.exists(config.SCALER_PATH):
|
||||
self.scaler = joblib.load(config.SCALER_PATH)
|
||||
|
||||
feature_names_path = os.path.join(config.MODELS_DIR, 'feature_names.pkl')
|
||||
if os.path.exists(feature_names_path):
|
||||
self.feature_names = joblib.load(feature_names_path)
|
||||
|
||||
selected_features_path = os.path.join(config.MODELS_DIR, 'selected_features.pkl')
|
||||
if os.path.exists(selected_features_path):
|
||||
self.selected_features = joblib.load(selected_features_path)
|
||||
|
||||
label_encoders_path = os.path.join(config.MODELS_DIR, 'label_encoders.pkl')
|
||||
if os.path.exists(label_encoders_path):
|
||||
self.label_encoders = joblib.load(label_encoders_path)
|
||||
|
||||
metrics_path = os.path.join(config.MODELS_DIR, 'model_metrics.pkl')
|
||||
if os.path.exists(metrics_path):
|
||||
self.model_metrics = joblib.load(metrics_path)
|
||||
|
||||
if self.model_metrics:
|
||||
valid_metrics = {k: v for k, v in self.model_metrics.items() if k in self.models}
|
||||
if valid_metrics:
|
||||
best_model = max(valid_metrics.items(), key=lambda x: x[1]['r2'])
|
||||
self.default_model = best_model[0]
|
||||
|
||||
for filename, attr in [
|
||||
('feature_names.pkl', 'feature_names'),
|
||||
('selected_features.pkl', 'selected_features'),
|
||||
('label_encoders.pkl', 'label_encoders'),
|
||||
('model_metrics.pkl', 'model_metrics'),
|
||||
]:
|
||||
path = os.path.join(config.MODELS_DIR, filename)
|
||||
if os.path.exists(path):
|
||||
try:
|
||||
setattr(self, attr, joblib.load(path))
|
||||
except Exception as exc:
|
||||
print(f'Failed to load artifact {filename}: {exc}')
|
||||
|
||||
valid_metrics = {key: value for key, value in self.model_metrics.items() if key in self.models}
|
||||
if valid_metrics:
|
||||
self.default_model = max(valid_metrics.items(), key=lambda item: item[1]['r2'])[0]
|
||||
|
||||
def get_available_models(self):
|
||||
self._ensure_models_loaded()
|
||||
|
||||
models = []
|
||||
for name in self.models.keys():
|
||||
info = MODEL_INFO.get(name, {
|
||||
'name': name,
|
||||
'name_cn': name,
|
||||
'description': ''
|
||||
}).copy()
|
||||
info = MODEL_INFO.get(name, {'name': name, 'name_cn': name, 'description': ''}).copy()
|
||||
info['is_available'] = True
|
||||
info['is_default'] = (name == self.default_model)
|
||||
|
||||
if name in self.model_metrics:
|
||||
info['metrics'] = self.model_metrics[name]
|
||||
else:
|
||||
info['metrics'] = {'r2': 0, 'rmse': 0, 'mae': 0}
|
||||
|
||||
info['is_default'] = name == self.default_model
|
||||
info['metrics'] = self.model_metrics.get(name, {'r2': 0, 'rmse': 0, 'mae': 0})
|
||||
models.append(info)
|
||||
|
||||
models.sort(key=lambda x: x['metrics']['r2'], reverse=True)
|
||||
|
||||
models.sort(key=lambda item: item['metrics']['r2'], reverse=True)
|
||||
return models
|
||||
|
||||
|
||||
def predict_single(self, data, model_type=None):
|
||||
self._ensure_models_loaded()
|
||||
|
||||
if model_type is None:
|
||||
model_type = self.default_model
|
||||
|
||||
model_type = model_type or self.default_model
|
||||
if model_type not in self.models:
|
||||
available = list(self.models.keys())
|
||||
if available:
|
||||
model_type = available[0]
|
||||
else:
|
||||
fallback = next(iter(self.models), None)
|
||||
if fallback is None:
|
||||
return self._get_default_prediction(data)
|
||||
|
||||
model = self.models[model_type]
|
||||
|
||||
model_type = fallback
|
||||
if self.scaler is None or self.feature_names is None:
|
||||
return self._get_default_prediction(data)
|
||||
|
||||
|
||||
features = self._prepare_features(data)
|
||||
|
||||
try:
|
||||
predicted_hours = model.predict([features])[0]
|
||||
predicted_hours = max(0, float(predicted_hours))
|
||||
except Exception as e:
|
||||
print(f"Prediction error: {e}")
|
||||
predicted_hours = self.models[model_type].predict([features])[0]
|
||||
predicted_hours = self._inverse_transform_prediction(predicted_hours)
|
||||
predicted_hours = max(0.5, float(predicted_hours))
|
||||
except Exception:
|
||||
return self._get_default_prediction(data)
|
||||
|
||||
|
||||
risk_level, risk_label = self._get_risk_level(predicted_hours)
|
||||
|
||||
confidence = 0.85
|
||||
if model_type in self.model_metrics:
|
||||
confidence = max(0.5, self.model_metrics[model_type].get('r2', 0.85))
|
||||
|
||||
confidence = max(0.5, self.model_metrics.get(model_type, {}).get('r2', 0.82))
|
||||
return {
|
||||
'predicted_hours': round(predicted_hours, 2),
|
||||
'risk_level': risk_level,
|
||||
'risk_label': risk_label,
|
||||
'confidence': round(confidence, 2),
|
||||
'model_used': model_type,
|
||||
'model_name_cn': MODEL_INFO.get(model_type, {}).get('name_cn', model_type)
|
||||
'model_name_cn': MODEL_INFO.get(model_type, {}).get('name_cn', model_type),
|
||||
}
|
||||
|
||||
|
||||
def predict_compare(self, data):
|
||||
self._ensure_models_loaded()
|
||||
|
||||
results = []
|
||||
|
||||
for name in self.models.keys():
|
||||
try:
|
||||
result = self.predict_single(data, name)
|
||||
result['model'] = name
|
||||
result['model_name_cn'] = MODEL_INFO.get(name, {}).get('name_cn', name)
|
||||
|
||||
if name in self.model_metrics:
|
||||
result['r2'] = self.model_metrics[name]['r2']
|
||||
else:
|
||||
result['r2'] = 0
|
||||
|
||||
results.append(result)
|
||||
except Exception as e:
|
||||
print(f"Compare error for {name}: {e}")
|
||||
|
||||
results.sort(key=lambda x: x.get('r2', 0), reverse=True)
|
||||
|
||||
result = self.predict_single(data, name)
|
||||
result['model'] = name
|
||||
result['model_name_cn'] = MODEL_INFO.get(name, {}).get('name_cn', name)
|
||||
result['r2'] = self.model_metrics.get(name, {}).get('r2', 0)
|
||||
results.append(result)
|
||||
results.sort(key=lambda item: item.get('r2', 0), reverse=True)
|
||||
if results:
|
||||
results[0]['recommended'] = True
|
||||
|
||||
return results
|
||||
|
||||
|
||||
def _prepare_features(self, data):
|
||||
feature_map = {
|
||||
'Reason for absence': data.get('reason_for_absence', 23),
|
||||
'Month of absence': data.get('month_of_absence', 7),
|
||||
'Day of the week': data.get('day_of_week', 3),
|
||||
'Seasons': data.get('seasons', 1),
|
||||
'Transportation expense': data.get('transportation_expense', 200),
|
||||
'Distance from Residence to Work': data.get('distance', 20),
|
||||
'Service time': data.get('service_time', 5),
|
||||
'Age': data.get('age', 30),
|
||||
'Work load Average/day': data.get('work_load', 250),
|
||||
'Hit target': data.get('hit_target', 95),
|
||||
'Disciplinary failure': data.get('disciplinary_failure', 0),
|
||||
'Education': data.get('education', 1),
|
||||
'Son': data.get('son', 0),
|
||||
'Social drinker': data.get('social_drinker', 0),
|
||||
'Social smoker': data.get('social_smoker', 0),
|
||||
'Pet': data.get('pet', 0),
|
||||
'Body mass index': data.get('bmi', 25)
|
||||
}
|
||||
|
||||
age = feature_map['Age']
|
||||
service_time = feature_map['Service time']
|
||||
work_load = feature_map['Work load Average/day']
|
||||
distance = feature_map['Distance from Residence to Work']
|
||||
expense = feature_map['Transportation expense']
|
||||
bmi = feature_map['Body mass index']
|
||||
son = feature_map['Son']
|
||||
pet = feature_map['Pet']
|
||||
social_drinker = feature_map['Social drinker']
|
||||
social_smoker = feature_map['Social smoker']
|
||||
hit_target = feature_map['Hit target']
|
||||
seasons = feature_map['Seasons']
|
||||
day_of_week = feature_map['Day of the week']
|
||||
|
||||
derived_features = {
|
||||
'workload_per_age': work_load / (age + 1),
|
||||
'expense_per_distance': expense / (distance + 1),
|
||||
'age_service_ratio': age / (service_time + 1),
|
||||
'has_children': 1 if son > 0 else 0,
|
||||
'has_pet': 1 if pet > 0 else 0,
|
||||
'family_responsibility': son + pet,
|
||||
'health_risk': 1 if (social_drinker == 1 or social_smoker == 1 or bmi > 30) else 0,
|
||||
'lifestyle_risk': int(social_drinker) + int(social_smoker),
|
||||
'age_group': 1 if age <= 30 else (2 if age <= 40 else (3 if age <= 50 else 4)),
|
||||
'service_group': 1 if service_time <= 5 else (2 if service_time <= 10 else (3 if service_time <= 20 else 4)),
|
||||
'bmi_category': 1 if bmi <= 18.5 else (2 if bmi <= 25 else (3 if bmi <= 30 else 4)),
|
||||
'workload_category': 1 if work_load <= 200 else (2 if work_load <= 250 else (3 if work_load <= 300 else 4)),
|
||||
'commute_category': 1 if distance <= 10 else (2 if distance <= 20 else (3 if distance <= 50 else 4)),
|
||||
'seasonal_risk': 1 if seasons in [1, 3] else 0,
|
||||
'weekday_risk': 1 if day_of_week in [2, 6] else 0,
|
||||
'hit_target_ratio': hit_target / 100,
|
||||
'experience_level': 1 if service_time <= 5 else (2 if service_time <= 10 else (3 if service_time <= 15 else 4)),
|
||||
'age_workload_interaction': age * work_load / 10000,
|
||||
'service_bmi_interaction': service_time * bmi / 100
|
||||
}
|
||||
|
||||
all_features = {**feature_map, **derived_features}
|
||||
|
||||
features = []
|
||||
for fname in self.feature_names:
|
||||
if fname in all_features:
|
||||
val = all_features[fname]
|
||||
|
||||
if fname in self.label_encoders:
|
||||
try:
|
||||
val = self.label_encoders[fname].transform([str(val)])[0]
|
||||
except:
|
||||
val = 0
|
||||
|
||||
features.append(float(val))
|
||||
else:
|
||||
features.append(0.0)
|
||||
|
||||
features = np.array(features).reshape(1, -1)
|
||||
features = self.scaler.transform(features)[0]
|
||||
|
||||
X_df = build_prediction_dataframe(data)
|
||||
X_df = engineer_features(X_df)
|
||||
X_df = apply_label_encoders(X_df, self.label_encoders)
|
||||
X_df = align_feature_frame(X_df, self.feature_names)
|
||||
features = self.scaler.transform(to_float_array(X_df))[0]
|
||||
if self.selected_features:
|
||||
selected_indices = []
|
||||
for sf in self.selected_features:
|
||||
if sf in self.feature_names:
|
||||
selected_indices.append(self.feature_names.index(sf))
|
||||
selected_indices = [self.feature_names.index(name) for name in self.selected_features if name in self.feature_names]
|
||||
if selected_indices:
|
||||
features = features[selected_indices]
|
||||
|
||||
return features
|
||||
|
||||
|
||||
def _inverse_transform_prediction(self, prediction):
|
||||
if self.training_metadata.get('target_transform') == 'log1p':
|
||||
return float(np.expm1(prediction))
|
||||
return float(prediction)
|
||||
|
||||
def _get_risk_level(self, hours):
|
||||
if hours < 4:
|
||||
return 'low', '低风险'
|
||||
elif hours <= 8:
|
||||
if hours <= 8:
|
||||
return 'medium', '中风险'
|
||||
else:
|
||||
return 'high', '高风险'
|
||||
|
||||
return 'high', '高风险'
|
||||
|
||||
def _get_default_prediction(self, data):
|
||||
base_hours = 5.0
|
||||
|
||||
expense = data.get('transportation_expense', 200)
|
||||
if expense > 300:
|
||||
base_hours += 1.0
|
||||
elif expense < 150:
|
||||
base_hours = 3.8
|
||||
base_hours += min(float(data.get('monthly_overtime_hours', 24)) / 20, 3.0)
|
||||
base_hours += min(float(data.get('commute_minutes', 40)) / 50, 2.0)
|
||||
base_hours += 1.6 if int(data.get('is_night_shift', 0)) == 1 else 0
|
||||
base_hours += 1.8 if int(data.get('chronic_disease_flag', 0)) == 1 else 0
|
||||
base_hours += 0.9 if int(data.get('near_holiday_flag', 0)) == 1 else 0
|
||||
base_hours += 0.8 if int(data.get('medical_certificate_flag', 0)) == 1 else 0
|
||||
base_hours += 0.5 * int(data.get('children_count', 0))
|
||||
if data.get('leave_type') in ['病假', '工伤假', '婚假', '丧假']:
|
||||
base_hours += 2.5
|
||||
if data.get('stress_level') == '高':
|
||||
base_hours += 0.9
|
||||
if data.get('performance_level') == 'A':
|
||||
base_hours -= 0.5
|
||||
|
||||
distance = data.get('distance', 20)
|
||||
if distance > 40:
|
||||
base_hours += 1.5
|
||||
elif distance > 25:
|
||||
base_hours += 0.8
|
||||
|
||||
service_time = data.get('service_time', 5)
|
||||
if service_time < 3:
|
||||
base_hours += 0.5
|
||||
elif service_time > 15:
|
||||
base_hours -= 0.5
|
||||
|
||||
age = data.get('age', 30)
|
||||
if age > 50:
|
||||
base_hours += 0.5
|
||||
elif age < 25:
|
||||
base_hours += 0.3
|
||||
|
||||
work_load = data.get('work_load', 250)
|
||||
if work_load > 300:
|
||||
base_hours += 1.5
|
||||
elif work_load > 260:
|
||||
base_hours += 0.5
|
||||
|
||||
bmi = data.get('bmi', 25)
|
||||
if bmi > 30:
|
||||
base_hours += 0.8
|
||||
elif bmi < 20:
|
||||
base_hours += 0.3
|
||||
|
||||
if data.get('social_drinker', 0) == 1:
|
||||
base_hours += 0.8
|
||||
if data.get('social_smoker', 0) == 1:
|
||||
base_hours += 0.5
|
||||
|
||||
son = data.get('son', 0)
|
||||
if son > 0:
|
||||
base_hours += 0.3 * son
|
||||
|
||||
pet = data.get('pet', 0)
|
||||
if pet > 0:
|
||||
base_hours -= 0.1 * pet
|
||||
|
||||
hit_target = data.get('hit_target', 95)
|
||||
if hit_target < 90:
|
||||
base_hours += 0.5
|
||||
|
||||
base_hours = max(0.5, base_hours)
|
||||
|
||||
risk_level, risk_label = self._get_risk_level(base_hours)
|
||||
|
||||
return {
|
||||
'predicted_hours': round(base_hours, 2),
|
||||
'predicted_hours': round(max(0.5, base_hours), 2),
|
||||
'risk_level': risk_level,
|
||||
'risk_label': risk_label,
|
||||
'confidence': 0.75,
|
||||
'confidence': 0.72,
|
||||
'model_used': 'default',
|
||||
'model_name_cn': '默认规则'
|
||||
'model_name_cn': '默认规则',
|
||||
}
|
||||
|
||||
|
||||
def get_model_info(self):
|
||||
self._ensure_models_loaded()
|
||||
|
||||
models = self.get_available_models()
|
||||
|
||||
return {
|
||||
'models': models,
|
||||
'models': self.get_available_models(),
|
||||
'training_info': {
|
||||
'train_samples': 2884,
|
||||
'test_samples': 722,
|
||||
'feature_count': len(self.feature_names) if self.feature_names else 20,
|
||||
'training_date': '2026-03-08'
|
||||
}
|
||||
'train_samples': self.training_metadata.get('train_samples', 0),
|
||||
'test_samples': self.training_metadata.get('test_samples', 0),
|
||||
'feature_count': self.training_metadata.get('feature_count_after_selection', 0),
|
||||
'training_date': self.training_metadata.get('training_date', ''),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user