聚烯烃配置上传eta
This commit is contained in:
workpc
parent
dd3538a4e9
commit
386af8007f
@ -1,7 +1,7 @@
|
||||
# 读取配置
|
||||
from lib.dataread import *
|
||||
from lib.tools import SendMail,exception_logger
|
||||
from models.nerulforcastmodels import ex_Model,model_losss,model_losss_juxiting,brent_export_pdf,tansuanli_export_pdf,pp_export_pdf,model_losss_juxiting
|
||||
from models.nerulforcastmodels import ex_Model_Juxiting,model_losss,model_losss_juxiting,brent_export_pdf,tansuanli_export_pdf,pp_export_pdf,model_losss_juxiting
|
||||
|
||||
import glob
|
||||
import torch
|
||||
@ -226,7 +226,7 @@ def predict_main():
|
||||
row, col = df.shape
|
||||
|
||||
now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
|
||||
ex_Model(df,
|
||||
ex_Model_Juxiting(df,
|
||||
horizon=horizon,
|
||||
input_size=input_size,
|
||||
train_steps=train_steps,
|
||||
|
||||
@ -228,6 +228,197 @@ def ex_Model(df,horizon,input_size,train_steps,val_check_steps,early_stop_patien
|
||||
# return nf_test_preds
|
||||
return
|
||||
|
||||
@exception_logger
|
||||
def ex_Model_Juxiting(df,horizon,input_size,train_steps,val_check_steps,early_stop_patience_steps,
|
||||
is_debug,dataset,is_train,is_fivemodels,val_size,test_size,settings,now,
|
||||
etadata,modelsindex,data,is_eta,end_time):
|
||||
'''
|
||||
模型训练与预测
|
||||
:param df: 数据集
|
||||
horizon # 预测的步长
|
||||
input_size # 输入序列长度
|
||||
train_steps # 训练步数,用来限定epoch次数
|
||||
val_check_steps # 评估频率
|
||||
early_stop_patience_steps # 早停的耐心步数
|
||||
:return: 预测结果
|
||||
'''
|
||||
|
||||
# 模型预测列表列名
|
||||
# columns2 = [
|
||||
# 'NHITS',
|
||||
# 'Informer',
|
||||
# 'LSTM',
|
||||
# 'iTransformer',
|
||||
# 'TSMixer',
|
||||
# 'TSMixerx',
|
||||
# 'PatchTST',
|
||||
# 'RNN',
|
||||
# 'GRU',
|
||||
# 'TCN',
|
||||
# # 'DeepAR',
|
||||
# 'DeepAR-median',
|
||||
# 'DeepAR-lo-90',
|
||||
# 'DeepAR-lo-80',
|
||||
# 'DeepAR-hi-80',
|
||||
# 'DeepAR-hi-90',
|
||||
# 'BiTCN',
|
||||
# 'DilatedRNN',
|
||||
# 'MLP',
|
||||
# 'DLinear',
|
||||
# 'NLinear',
|
||||
# 'TFT',
|
||||
# 'FEDformer',
|
||||
# 'StemGNN',
|
||||
# 'MLPMultivariate',
|
||||
# 'TiDE',
|
||||
# 'DeepNPT',
|
||||
# ]
|
||||
|
||||
df= df.replace(',', '', regex=True)
|
||||
df = df.rename(columns={'date': 'ds'})
|
||||
df['y'] = pd.to_numeric(df['y'], errors='coerce')
|
||||
df['ds'] = pd.to_datetime(df['ds'], errors='coerce') # 使用errors='coerce'来处理无效日期
|
||||
# df 数值列转为 float32
|
||||
for col in df.select_dtypes(include=['int']).columns:
|
||||
df[col] = df[col].astype(np.float32)
|
||||
|
||||
# 设置中文字体
|
||||
plt.rcParams['font.sans-serif'] = ['SimHei'] # 用来正常显示中文标签
|
||||
plt.rcParams['axes.unicode_minus'] = False # 用来正常显示负号
|
||||
|
||||
|
||||
|
||||
# 不筛选特征用下面的
|
||||
df_reg = df
|
||||
df_reg.sort_values('ds', inplace=True)
|
||||
if is_debug:
|
||||
df_reg = df_reg[-1000:-1]
|
||||
|
||||
# 计算训练集的结束索引，占总数据的90%
|
||||
split_index = int(0.9* len(df_reg))
|
||||
|
||||
# 按照时间顺序划分训练集和测试集
|
||||
df_train = df_reg[:split_index]
|
||||
df_test = df_reg[-split_index:]
|
||||
df_train['unique_id'] = 1
|
||||
df_test['unique_id'] = 1
|
||||
|
||||
# 显示划分后的数据集的前几行
|
||||
logger.info("Training set head:")
|
||||
logger.info(df_train.head())
|
||||
|
||||
logger.info("\nTesting set head:")
|
||||
logger.info(df_test.head())
|
||||
|
||||
|
||||
models = [
|
||||
NHITS (h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', activation='ReLU', early_stop_patience_steps=early_stop_patience_steps),
|
||||
Informer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps ),
|
||||
LSTM(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
iTransformer(h=horizon, input_size=input_size,n_series = 1, max_steps=train_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
TSMixer(h=horizon, input_size=input_size, n_series = 1, max_steps=train_steps, early_stop_patience_steps=early_stop_patience_steps),
|
||||
TSMixerx(h=horizon, input_size=input_size,n_series = 1, max_steps=train_steps, early_stop_patience_steps=early_stop_patience_steps),
|
||||
PatchTST(h=horizon, input_size=input_size, max_steps=train_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
RNN(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
GRU(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
TCN(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
# DeepAR(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
BiTCN(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
DilatedRNN(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
MLP(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
DLinear(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
NLinear(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
TFT(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
FEDformer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
StemGNN(h=horizon, input_size=input_size,n_series = 1, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
MLPMultivariate(h=horizon, input_size=input_size,n_series = 1, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
TiDE(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
DeepNPTS(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', early_stop_patience_steps=early_stop_patience_steps),
|
||||
|
||||
# VanillaTransformer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ), //报错了
|
||||
# Autoformer(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ), //报错了
|
||||
# NBEATS(h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard', ),
|
||||
# NBEATSx (h=horizon, input_size=input_size, max_steps=train_steps, val_check_steps=val_check_steps, scaler_type='standard',activation='ReLU', ), //报错
|
||||
# HINT(h=horizon),
|
||||
|
||||
]
|
||||
|
||||
if is_fivemodels:
|
||||
# 获取之前存好的最好的五个模型
|
||||
with open(os.path.join(dataset,'best_modelnames.txt'), 'r',encoding='utf-8') as f:
|
||||
best_modelnames = f.readlines()[0]
|
||||
logger.info(f'获取本地最佳模型名称：{best_modelnames}')
|
||||
|
||||
# 重新拼接models
|
||||
all_models = models
|
||||
models = []
|
||||
for model in all_models:
|
||||
if model._get_name() in best_modelnames:
|
||||
models.append(model)
|
||||
|
||||
# 创建NeuralForecast实例并训练模型
|
||||
nf = NeuralForecast(models=models, freq=freq)
|
||||
|
||||
from joblib import dump, load
|
||||
if is_train:
|
||||
# 模型交叉验证
|
||||
nf_preds = nf.cross_validation(df=df_train, val_size=val_size, test_size=test_size, n_windows=None)
|
||||
nf_preds.to_csv(os.path.join(dataset,"cross_validation.csv"),index=False)
|
||||
|
||||
nf_preds = nf_preds.reset_index()
|
||||
# 保存模型
|
||||
# 生成文件名，按时间 精确到分
|
||||
filename = f'{settings}--{now}.joblib'
|
||||
#文件名去掉冒号
|
||||
filename = filename.replace(':', '-') # 替换冒号
|
||||
dump(nf, os.path.join(dataset,filename))
|
||||
else:
|
||||
# glob获取dataset下最新的joblib文件
|
||||
import glob
|
||||
filename = max(glob.glob(os.path.join(dataset,'*.joblib')), key=os.path.getctime)
|
||||
logger.info('读取模型：'+ filename)
|
||||
nf = load(filename)
|
||||
# 测试集预测
|
||||
nf_test_preds = nf.cross_validation(df=df_test, val_size=val_size, test_size=test_size, n_windows=None)
|
||||
# 测试集预测结果保存
|
||||
nf_test_preds.to_csv(os.path.join(dataset,"cross_validation.csv"),index=False)
|
||||
|
||||
df_test['ds'] = pd.to_datetime(df_test['ds'], errors='coerce')
|
||||
|
||||
#进行未来时间预测
|
||||
df_predict=nf.predict(df_test).reset_index()
|
||||
# 去掉index列
|
||||
df_predict.drop(columns=['index'], inplace=True)
|
||||
df_predict.astype({col: 'float32' for col in df_predict.columns if col not in ['ds'] })
|
||||
|
||||
# 添加预测时间
|
||||
df_predict['created_dt'] = end_time
|
||||
|
||||
# 保存预测值
|
||||
df_predict.to_csv(os.path.join(dataset,"predict.csv"),index=False)
|
||||
|
||||
# 将预测结果保存到数据库
|
||||
save_to_database(sqlitedb,df_predict,'predict',end_time)
|
||||
|
||||
# 把预测值上传到eta
|
||||
if is_update_eta:
|
||||
df_predict['ds'] = pd.to_datetime(df_predict['ds'])
|
||||
dates = df_predict['ds'].dt.strftime('%Y-%m-%d')
|
||||
|
||||
for m in modelsindex.keys():
|
||||
list = []
|
||||
for date,value in zip(dates,df_predict[m].round(2)):
|
||||
list.append({'Date':date,'Value':value})
|
||||
data['DataList'] = list
|
||||
data['IndexCode'] = modelsindex[m]
|
||||
data['IndexName'] = f'价格预测{m}模型'
|
||||
data['Remark'] = m
|
||||
etadata.push_data(data)
|
||||
|
||||
|
||||
# return nf_test_preds
|
||||
return
|
||||
|
||||
|
||||
# 雍安环境预测评估指数
|
||||
@exception_logger
|
||||
|
||||
Loading…
Reference in New Issue
Block a user