liurui/PriceForecast
Template
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

聚烯烃每周最佳模型逻辑调整

Browse Source
This commit is contained in:
workpc 2025-04-21 17:33:12 +08:00
parent 8074647329
commit 5a8e3ae007
5 changed files with 61 additions and 59 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
config_jingbo_yuedu.py
View File

@ -39,35 +39,35 @@ edbnamelist = [
] ]
# eta自有数据指标编码 # eta自有数据指标编码 次月
modelsindex = { modelsindex = {
'NHITS': 'SELF0000001', 'NHITS': 'SELF0000143',
'Informer': 'SELF0000057', 'Informer': 'SELF0000144',
'LSTM': 'SELF0000058', 'LSTM': 'SELF0000145',
'iTransformer': 'SELF0000059', 'iTransformer': 'SELF0000146',
'TSMixer': 'SELF0000060', 'TSMixer': 'SELF0000147',
'TSMixerx': 'SELF0000061', 'TSMixerx': 'SELF0000148',
'PatchTST': 'SELF0000062', 'PatchTST': 'SELF0000149',
'RNN': 'SELF0000063', 'RNN': 'SELF0000150',
'GRU': 'SELF0000064', 'GRU': 'SELF0000151',
'TCN': 'SELF0000065', 'TCN': 'SELF0000152',
'BiTCN': 'SELF0000066', 'BiTCN': 'SELF0000153',
'DilatedRNN': 'SELF0000067', 'DilatedRNN': 'SELF0000154',
'MLP': 'SELF0000068', 'MLP': 'SELF0000155',
'DLinear': 'SELF0000069', 'DLinear': 'SELF0000156',
'NLinear': 'SELF0000070', 'NLinear': 'SELF0000157',
'TFT': 'SELF0000071', 'TFT': 'SELF0000158',
'FEDformer': 'SELF0000072', 'FEDformer': 'SELF0000159',
'StemGNN': 'SELF0000073', 'StemGNN': 'SELF0000160',
'MLPMultivariate': 'SELF0000074', 'MLPMultivariate': 'SELF0000161',
'TiDE': 'SELF0000075', 'TiDE': 'SELF0000162',
'DeepNPTS': 'SELF0000076' 'DeepNPTS': 'SELF0000163',
} }
# eta 上传预测结果的请求体，后面发起请求的时候更改 model datalist 数据 # eta 上传预测结果的请求体，后面发起请求的时候更改 model datalist 数据
data = { data = {
"IndexCode": "", "IndexCode": "",
"IndexName": "价格预测模型", "IndexName": "价格预测xx模型-次月",
"Unit": "无", "Unit": "无",
"Frequency": "日度", "Frequency": "日度",
"SourceName": f"价格预测", "SourceName": f"价格预测",
@ -305,7 +305,7 @@ is_timefurture = True # 是否使用时间特征
is_fivemodels = False # 是否使用之前保存的最佳的5个模型 is_fivemodels = False # 是否使用之前保存的最佳的5个模型
is_edbcode = False # 特征使用edbcoding列表中的 is_edbcode = False # 特征使用edbcoding列表中的
is_edbnamelist = False # 自定义特征，对应上面的edbnamelist is_edbnamelist = False # 自定义特征，对应上面的edbnamelist
is_update_eta = False # 预测结果上传到eta is_update_eta = True # 预测结果上传到eta
is_update_report = True # 是否上传报告 is_update_report = True # 是否上传报告
is_update_warning_data = False # 是否上传预警数据 is_update_warning_data = False # 是否上传预警数据
is_update_predict_value = True # 是否上传预测值到市场信息平台 is_update_predict_value = True # 是否上传预测值到市场信息平台

44
config_jingbo_zhoudu.py
View File

@ -39,29 +39,29 @@ edbnamelist = [
] ]
# eta自有数据指标编码 # eta自有数据指标编码 次周
modelsindex = { modelsindex = {
'NHITS': 'SELF0000001', 'NHITS': 'SELF0000099',
'Informer': 'SELF0000057', 'Informer': 'SELF0000100',
'LSTM': 'SELF0000058', 'LSTM': 'SELF0000101',
'iTransformer': 'SELF0000059', 'iTransformer': 'SELF0000102',
'TSMixer': 'SELF0000060', 'TSMixer': 'SELF0000103',
'TSMixerx': 'SELF0000061', 'TSMixerx': 'SELF0000104',
'PatchTST': 'SELF0000062', 'PatchTST': 'SELF0000105',
'RNN': 'SELF0000063', 'RNN': 'SELF0000106',
'GRU': 'SELF0000064', 'GRU': 'SELF0000107',
'TCN': 'SELF0000065', 'TCN': 'SELF0000108',
'BiTCN': 'SELF0000066', 'BiTCN': 'SELF0000109',
'DilatedRNN': 'SELF0000067', 'DilatedRNN': 'SELF0000110',
'MLP': 'SELF0000068', 'MLP': 'SELF0000111',
'DLinear': 'SELF0000069', 'DLinear': 'SELF0000112',
'NLinear': 'SELF0000070', 'NLinear': 'SELF0000113',
'TFT': 'SELF0000071', 'TFT': 'SELF0000114',
'FEDformer': 'SELF0000072', 'FEDformer': 'SELF0000115',
'StemGNN': 'SELF0000073', 'StemGNN': 'SELF0000116',
'MLPMultivariate': 'SELF0000074', 'MLPMultivariate': 'SELF0000117',
'TiDE': 'SELF0000075', 'TiDE': 'SELF0000118',
'DeepNPTS': 'SELF0000076' 'DeepNPTS': 'SELF0000119',
} }
# eta 上传预测结果的请求体，后面发起请求的时候更改 model datalist 数据 # eta 上传预测结果的请求体，后面发起请求的时候更改 model datalist 数据

3
config_juxiting.py
View File

@ -219,7 +219,6 @@ push_data_value_list_data = {
} }
# 八大维度数据项编码 # 八大维度数据项编码
bdwd_items = { bdwd_items = {
'ciri': 'jxtppbdwdcr', 'ciri': 'jxtppbdwdcr',
@ -243,7 +242,7 @@ table_name = 'v_tbl_crude_oil_warning'
# 开关 # 开关
is_train = True # 是否训练 is_train = True # 是否训练
is_debug = False # 是否调试 is_debug = False # 是否调试
is_eta = True # 是否使用eta接口 is_eta = False # 是否使用eta接口
is_market = False # 是否通过市场信息平台获取特征 ,在is_eta 为true 的情况下生效 is_market = False # 是否通过市场信息平台获取特征 ,在is_eta 为true 的情况下生效
is_timefurture = True # 是否使用时间特征 is_timefurture = True # 是否使用时间特征
is_fivemodels = False # 是否使用之前保存的最佳的5个模型 is_fivemodels = False # 是否使用之前保存的最佳的5个模型

7
main_juxiting.py
View File

@ -302,12 +302,13 @@ def predict_main():
# 计算最近60天预测残差最低的模型名称 # 计算最近60天预测残差最低的模型名称
model_results = sqlitedb.select_data( model_results = sqlitedb.select_data(
'trueandpredict', order_by="ds DESC", limit="60") 'trueandpredict', order_by="ds DESC", limit="60")
# 删除created_dt,y列空行
model_results = model_results.dropna(
subset=['created_dt', 'y'])
# 删除空值率为90%以上的列 # 删除空值率为90%以上的列
if len(model_results) > 10:
model_results = model_results.dropna( model_results = model_results.dropna(
thresh=len(model_results)*0.1, axis=1) thresh=len(model_results)*0.1, axis=1)
# 删除空行
model_results = model_results.dropna()
modelnames = model_results.columns.to_list()[2:-1] modelnames = model_results.columns.to_list()[2:-1]
for col in model_results[modelnames].select_dtypes(include=['object']).columns: for col in model_results[modelnames].select_dtypes(include=['object']).columns:
model_results[col] = model_results[col].astype(np.float32) model_results[col] = model_results[col].astype(np.float32)

10
models/nerulforcastmodels.py
View File

@ -250,7 +250,8 @@ def ex_Model(df, horizon, input_size, train_steps, val_check_steps, early_stop_p
list.append({'Date': date, 'Value': value}) list.append({'Date': date, 'Value': value})
data['DataList'] = list data['DataList'] = list
data['IndexCode'] = modelsindex[m] data['IndexCode'] = modelsindex[m]
data['IndexName'] = f'价格预测{m}模型' # data['IndexName'] = f'价格预测{m}模型'
data['IndexName'] = data['IndexName'].replece('xx', m)
data['Remark'] = m data['Remark'] = m
etadata.push_data(data) etadata.push_data(data)
@ -1248,7 +1249,6 @@ def model_losss(sqlitedb, end_time):
except Exception as e: except Exception as e:
config.logger.info(f'准确率计算错误{e}') config.logger.info(f'准确率计算错误{e}')
def _add_abs_error_rate(): def _add_abs_error_rate():
# 计算每个预测值与真实值之间的偏差率 # 计算每个预测值与真实值之间的偏差率
for model in allmodelnames: for model in allmodelnames:
@ -1822,7 +1822,8 @@ def model_losss_juxitingbak(sqlitedb, end_time):
plt.text(i, j, str(j), ha='center', va='bottom') plt.text(i, j, str(j), ha='center', va='bottom')
# 当前日期画竖虚线 # 当前日期画竖虚线
plt.axvline(x=df['ds'].iloc[-config.horizon], color='r', linestyle='--') plt.axvline(x=df['ds'].iloc[-config.horizon],
color='r', linestyle='--')
plt.legend() plt.legend()
plt.xlabel('日期') plt.xlabel('日期')
# 自动设置横轴日期显示 # 自动设置横轴日期显示
@ -2356,7 +2357,8 @@ def brent_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, in
content.append(Graphs.draw_little_title('模型选择：')) content.append(Graphs.draw_little_title('模型选择：'))
content.append(Graphs.draw_text( content.append(Graphs.draw_text(
f'本次预测使用了一个专门收集时间序列的NeuralForecast库中的{num_models}个模型：')) f'本次预测使用了一个专门收集时间序列的NeuralForecast库中的{num_models}个模型：'))
content.append(Graphs.draw_text(f'使用{config.input_size}个数据预测未来{inputsize}个数据。')) content.append(Graphs.draw_text(
f'使用{config.input_size}个数据预测未来{inputsize}个数据。'))
content.append(Graphs.draw_little_title('指标情况：')) content.append(Graphs.draw_little_title('指标情况：'))
with open(os.path.join(config.dataset, '特征频度统计.txt'), encoding='utf-8') as f: with open(os.path.join(config.dataset, '特征频度统计.txt'), encoding='utf-8') as f:
for line in f.readlines(): for line in f.readlines():