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

Compare commits

base: liurui:c3e8eef4c90ef314771e7bff7f14cc5ae9b00000
Branches Tags
liurui:main
..
compare: liurui:92dcef28a456fc024ec63a05e28b47aba2d3cbe8
Branches Tags
liurui:main

No commits in common. "c3e8eef4c90ef314771e7bff7f14cc5ae9b00000" and "92dcef28a456fc024ec63a05e28b47aba2d3cbe8" have entirely different histories.
c3e8eef4c9 ... 92dcef28a4

4 changed files with 218 additions and 342 deletions
Show Stats Expand all files Collapse all files

29
config_jingbo.py
View File

@ -98,7 +98,6 @@ login_pushreport_url = f"http://{server_host}:8080/jingbo-dev/api/server/login"
upload_url = f"http://{server_host}:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" # 上传报告 upload_url = f"http://{server_host}:8080/jingbo-dev/api/analysis/reportInfo/researchUploadReportSave" # 上传报告
upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" # 停更预警 upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save" # 停更预警
query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" # 查询数据项编码 query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos" # 查询数据项编码
push_data_value_list_url = f"http://{server_host}:8080/jingbo-dev/api/dw/dataValue/pushDataValueList" # 上传数据项值
login_data = { login_data = {
"data": { "data": {
@ -151,33 +150,6 @@ query_data_list_item_nos_data = {
} }
} }
push_data_value_list_data = {
"funcModule": "数据表信息列表",
"funcOperation": "新增",
"data": [
{"dataItemNo":"91230600716676129",
"dataDate":"20230113",
"dataStatus":"add",
"dataValue":100.11
},
{"dataItemNo":"91230600716676129P|ETHYL_BEN|CAPACITY",
"dataDate":"20230113",
"dataStatus":"add",
"dataValue":100.55
},
{"dataItemNo":"91230600716676129P|ETHYL_BEN|CAPACITY",
"dataDate":"20230113",
"dataStatus":"add",
"dataValue":100.55
}
]
}
# 八大维度数据项编码
bdwd_items = {
'ciri' : 'yyycbdwdcr',
'benzhou': 'yyycbdwdbz',
}
# 北京环境数据库 # 北京环境数据库
host = '192.168.101.27' host = '192.168.101.27'
@ -200,7 +172,6 @@ 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 = False # 预测结果上传到eta
is_update_report = False # 是否上传报告 is_update_report = False # 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_del_corr = 0.6 # 是否删除相关性高的特征,取值为 0-1 ，0 为不删除，0.6 表示删除相关性小于0.6的特征 is_del_corr = 0.6 # 是否删除相关性高的特征,取值为 0-1 ，0 为不删除，0.6 表示删除相关性小于0.6的特征
is_del_tow_month = True # 是否删除两个月不更新的特征 is_del_tow_month = True # 是否删除两个月不更新的特征

40
lib/dataread.py
View File

@ -94,7 +94,6 @@ global_config = {
'offsite': None, # 站点名称 'offsite': None, # 站点名称
'edbcodenamedict': None, # EDB编码映射 'edbcodenamedict': None, # EDB编码映射
'rote': None, # 绘图上下界阈值 'rote': None, # 绘图上下界阈值
'bdwd_items':None,
# 接口配置（原有配置） # 接口配置（原有配置）
'login_pushreport_url': None, 'login_pushreport_url': None,
@ -1164,11 +1163,6 @@ class Config:
def query_data_list_item_nos_data( def query_data_list_item_nos_data(
self): return global_config['query_data_list_item_nos_data'] self): return global_config['query_data_list_item_nos_data']
@property
def push_data_value_list_url(self): return global_config['push_data_value_list_url']
@property
def push_data_value_list_data(self): return global_config['push_data_value_list_data']
# 字段映射 # 字段映射
@property @property
def offsite_col(self): return global_config['offsite_col'] def offsite_col(self): return global_config['offsite_col']
@ -2036,40 +2030,6 @@ def get_market_data(end_time, df):
df = pd.merge(df, df2, how='left', on='date') df = pd.merge(df, df2, how='left', on='date')
return df return df
def push_market_data(data):
'''
上传预测价格到市场信息平台
data: 预测价格数据,示例：
[
{"dataItemNo":"91230600716676129",
"dataDate":"20230113",
"dataStatus":"add",
"dataValue":100.11
},
{"dataItemNo":"91230600716676129P|ETHYL_BEN|CAPACITY",
"dataDate":"20230113",
"dataStatus":"add",
"dataValue":100.55
},
{"dataItemNo":"91230600716676129P|ETHYL_BEN|CAPACITY",
"dataDate":"20230113",
"dataStatus":"add",
"dataValue":100.55
}
]
'''
# 获取token
token = get_head_auth_report()
# 定义请求参数
config.push_data_value_list_data['data'] = data
# 发送请求
headers = {"Authorization": token}
config.logger.info('上传数据中...')
items_res = requests.post(url=config.push_data_value_list_url, headers=headers,
json=config.push_data_value_list_data, timeout=(3, 35))
json_data = json.loads(items_res.text)
config.logger.info(f"上传结果:{json_data}")
return json_data
def get_high_low_data(df): def get_high_low_data(df):
# 读取excel 从第五行开始 # 读取excel 从第五行开始

485
main_yuanyou.py
View File

@ -29,7 +29,6 @@ global_config.update({
'test_size': test_size, 'test_size': test_size,
'modelsindex': modelsindex, 'modelsindex': modelsindex,
'rote': rote, 'rote': rote,
'bdwd_items':bdwd_items,
# 特征工程开关 # 特征工程开关
'is_del_corr': is_del_corr, 'is_del_corr': is_del_corr,
@ -37,7 +36,6 @@ global_config.update({
'is_eta': is_eta, 'is_eta': is_eta,
'is_update_eta': is_update_eta, 'is_update_eta': is_update_eta,
'is_fivemodels': is_fivemodels, 'is_fivemodels': is_fivemodels,
'is_update_predict_value': is_update_predict_value,
'early_stop_patience_steps': early_stop_patience_steps, 'early_stop_patience_steps': early_stop_patience_steps,
# 时间参数 # 时间参数
@ -114,296 +112,243 @@ def predict_main():
返回: 返回:
None None
""" """
# end_time = global_config['end_time'] end_time = global_config['end_time']
# # 获取数据 # 获取数据
# if is_eta: if is_eta:
# logger.info('从eta获取数据...') logger.info('从eta获取数据...')
# signature = BinanceAPI(APPID, SECRET) signature = BinanceAPI(APPID, SECRET)
# etadata = EtaReader(signature=signature, etadata = EtaReader(signature=signature,
# classifylisturl=global_config['classifylisturl'], classifylisturl=global_config['classifylisturl'],
# classifyidlisturl=global_config['classifyidlisturl'], classifyidlisturl=global_config['classifyidlisturl'],
# edbcodedataurl=global_config['edbcodedataurl'], edbcodedataurl=global_config['edbcodedataurl'],
# edbcodelist=global_config['edbcodelist'], edbcodelist=global_config['edbcodelist'],
# edbdatapushurl=global_config['edbdatapushurl'], edbdatapushurl=global_config['edbdatapushurl'],
# edbdeleteurl=global_config['edbdeleteurl'], edbdeleteurl=global_config['edbdeleteurl'],
# edbbusinessurl=global_config['edbbusinessurl'], edbbusinessurl=global_config['edbbusinessurl'],
# classifyId=global_config['ClassifyId'], classifyId=global_config['ClassifyId'],
# ) )
# df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data( df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(
# data_set=data_set, dataset=dataset) # 原始数据，未处理 data_set=data_set, dataset=dataset) # 原始数据，未处理
# if is_market: if is_market:
# logger.info('从市场信息平台获取数据...') logger.info('从市场信息平台获取数据...')
# try: try:
# # 如果是测试环境，最高价最低价取excel文档 # 如果是测试环境，最高价最低价取excel文档
# if server_host == '192.168.100.53': if server_host == '192.168.100.53':
# logger.info('从excel文档获取最高价最低价') logger.info('从excel文档获取最高价最低价')
# df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju) df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju)
# else: else:
# logger.info('从市场信息平台获取数据') logger.info('从市场信息平台获取数据')
# df_zhibiaoshuju = get_market_data( df_zhibiaoshuju = get_market_data(
# end_time, df_zhibiaoshuju) end_time, df_zhibiaoshuju)
# except: except:
# logger.info('最高最低价拼接失败') logger.info('最高最低价拼接失败')
# # 保存到xlsx文件的sheet表 # 保存到xlsx文件的sheet表
# with pd.ExcelWriter(os.path.join(dataset, data_set)) as file: with pd.ExcelWriter(os.path.join(dataset, data_set)) as file:
# df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False) df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False)
# df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False) df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
# # 数据处理 # 数据处理
# df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
# end_time=end_time) end_time=end_time)
# else: else:
# # 读取数据 # 读取数据
# logger.info('读取本地数据：' + os.path.join(dataset, data_set)) logger.info('读取本地数据：' + os.path.join(dataset, data_set))
# df, df_zhibiaoliebiao = getdata(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj, df, df_zhibiaoliebiao = getdata(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj,
# is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理 is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理
# # 更改预测列名称 # 更改预测列名称
# df.rename(columns={y: 'y'}, inplace=True) df.rename(columns={y: 'y'}, inplace=True)
# if is_edbnamelist: if is_edbnamelist:
# df = df[edbnamelist] df = df[edbnamelist]
# df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False) df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False)
# # 保存最新日期的y值到数据库 # 保存最新日期的y值到数据库
# # 取第一行数据存储到数据库中 # 取第一行数据存储到数据库中
# first_row = df[['ds', 'y']].tail(1) first_row = df[['ds', 'y']].tail(1)
# # 判断y的类型是否为float # 判断y的类型是否为float
# if not isinstance(first_row['y'].values[0], float): if not isinstance(first_row['y'].values[0], float):
# logger.info(f'{end_time}预测目标数据为空，跳过') logger.info(f'{end_time}预测目标数据为空，跳过')
# return None return None
# # 将最新真实值保存到数据库 # 将最新真实值保存到数据库
# if not sqlitedb.check_table_exists('trueandpredict'): if not sqlitedb.check_table_exists('trueandpredict'):
# first_row.to_sql('trueandpredict', sqlitedb.connection, index=False) first_row.to_sql('trueandpredict', sqlitedb.connection, index=False)
# else: else:
# for row in first_row.itertuples(index=False): for row in first_row.itertuples(index=False):
# row_dict = row._asdict() row_dict = row._asdict()
# config.logger.info(f'要保存的真实值：{row_dict}') config.logger.info(f'要保存的真实值：{row_dict}')
# # 判断ds是否为字符串类型,如果不是则转换为字符串类型 # 判断ds是否为字符串类型,如果不是则转换为字符串类型
# if isinstance(row_dict['ds'], (pd.Timestamp, datetime.datetime)): if isinstance(row_dict['ds'], (pd.Timestamp, datetime.datetime)):
row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d')
elif not isinstance(row_dict['ds'], str):
try:
row_dict['ds'] = pd.to_datetime(
row_dict['ds']).strftime('%Y-%m-%d')
except:
logger.warning(f"无法解析的时间格式: {row_dict['ds']}")
# row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d') # row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d')
# elif not isinstance(row_dict['ds'], str): # row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S')
check_query = sqlitedb.select_data(
'trueandpredict', where_condition=f"ds = '{row.ds}'")
if len(check_query) > 0:
set_clause = ", ".join(
[f"{key} = '{value}'" for key, value in row_dict.items()])
sqlitedb.update_data(
'trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'")
continue
sqlitedb.insert_data('trueandpredict', tuple(
row_dict.values()), columns=row_dict.keys())
# 更新accuracy表的y值
if not sqlitedb.check_table_exists('accuracy'):
pass
else:
update_y = sqlitedb.select_data(
'accuracy', where_condition="y is null")
if len(update_y) > 0:
logger.info('更新accuracy表的y值')
# 找到update_y 中ds且df中的y的行
update_y = update_y[update_y['ds'] <= end_time]
logger.info(f'要更新y的信息：{update_y}')
# try: # try:
# row_dict['ds'] = pd.to_datetime( for row in update_y.itertuples(index=False):
# row_dict['ds']).strftime('%Y-%m-%d') try:
# except: row_dict = row._asdict()
# logger.warning(f"无法解析的时间格式: {row_dict['ds']}") yy = df[df['ds'] == row_dict['ds']]['y'].values[0]
# # row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d') LOW = df[df['ds'] == row_dict['ds']]['Brentzdj'].values[0]
# # row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S') HIGH = df[df['ds'] == row_dict['ds']]['Brentzgj'].values[0]
# check_query = sqlitedb.select_data( sqlitedb.update_data(
# 'trueandpredict', where_condition=f"ds = '{row.ds}'") 'accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
# if len(check_query) > 0: except:
# set_clause = ", ".join( logger.info(f'更新accuracy表的y值失败：{row_dict}')
# [f"{key} = '{value}'" for key, value in row_dict.items()]) # except Exception as e:
# sqlitedb.update_data( # logger.info(f'更新accuracy表的y值失败：{e}')
# 'trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'")
# continue
# sqlitedb.insert_data('trueandpredict', tuple(
# row_dict.values()), columns=row_dict.keys())
# # 更新accuracy表的y值 # 判断当前日期是不是周一
# if not sqlitedb.check_table_exists('accuracy'): is_weekday = datetime.datetime.now().weekday() == 0
# pass if is_weekday:
# else: logger.info('今天是周一，更新预测模型')
# update_y = sqlitedb.select_data( # 计算最近60天预测残差最低的模型名称
# 'accuracy', where_condition="y is null") model_results = sqlitedb.select_data(
# if len(update_y) > 0: 'trueandpredict', order_by="ds DESC", limit="60")
# logger.info('更新accuracy表的y值') # 删除空值率为90%以上的列
# # 找到update_y 中ds且df中的y的行 if len(model_results) > 10:
# update_y = update_y[update_y['ds'] <= end_time] model_results = model_results.dropna(
# logger.info(f'要更新y的信息：{update_y}') thresh=len(model_results)*0.1, axis=1)
# # try: # 删除空行
# for row in update_y.itertuples(index=False): model_results = model_results.dropna()
# try: modelnames = model_results.columns.to_list()[2:-1]
# row_dict = row._asdict() for col in model_results[modelnames].select_dtypes(include=['object']).columns:
# yy = df[df['ds'] == row_dict['ds']]['y'].values[0] model_results[col] = model_results[col].astype(np.float32)
# LOW = df[df['ds'] == row_dict['ds']]['Brentzdj'].values[0] # 计算每个预测值与真实值之间的偏差率
# HIGH = df[df['ds'] == row_dict['ds']]['Brentzgj'].values[0] for model in modelnames:
# sqlitedb.update_data( model_results[f'{model}_abs_error_rate'] = abs(
# 'accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'") model_results['y'] - model_results[model]) / model_results['y']
# except: # 获取每行对应的最小偏差率值
# logger.info(f'更新accuracy表的y值失败：{row_dict}') min_abs_error_rate_values = model_results.apply(
# # except Exception as e: lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
# # logger.info(f'更新accuracy表的y值失败：{e}') # 获取每行对应的最小偏差率值对应的列名
min_abs_error_rate_column_name = model_results.apply(
lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
# 将列名索引转换为列名
min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(
lambda x: x.split('_')[0])
# 取出现次数最多的模型名称
most_common_model = min_abs_error_rate_column_name.value_counts().idxmax()
logger.info(f"最近60天预测残差最低的模型名称：{most_common_model}")
# 保存结果到数据库
if not sqlitedb.check_table_exists('most_model'):
sqlitedb.create_table(
'most_model', columns="ds datetime, most_common_model TEXT")
sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime(
'%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',))
# # 判断当前日期是不是周一 try:
# is_weekday = datetime.datetime.now().weekday() == 0 if is_weekday:
# if is_weekday: # if True:
# logger.info('今天是周一，更新预测模型') logger.info('今天是周一，发送特征预警')
# # 计算最近60天预测残差最低的模型名称 # 上传预警信息到数据库
# model_results = sqlitedb.select_data( warning_data_df = df_zhibiaoliebiao.copy()
# 'trueandpredict', order_by="ds DESC", limit="60") warning_data_df = warning_data_df[warning_data_df['停更周期'] > 3][[
# # 删除空值率为90%以上的列 '指标名称', '指标id', '频度', '更新周期', '指标来源', '最后更新时间', '停更周期']]
# if len(model_results) > 10: # 重命名列名
# model_results = model_results.dropna( warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY',
# thresh=len(model_results)*0.1, axis=1) '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'})
# # 删除空行 from sqlalchemy import create_engine
# model_results = model_results.dropna() import urllib
# modelnames = model_results.columns.to_list()[2:-1] global password
# for col in model_results[modelnames].select_dtypes(include=['object']).columns: if '@' in password:
# model_results[col] = model_results[col].astype(np.float32) password = urllib.parse.quote_plus(password)
# # 计算每个预测值与真实值之间的偏差率
# for model in modelnames:
# model_results[f'{model}_abs_error_rate'] = abs(
# model_results['y'] - model_results[model]) / model_results['y']
# # 获取每行对应的最小偏差率值
# min_abs_error_rate_values = model_results.apply(
# lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
# # 获取每行对应的最小偏差率值对应的列名
# min_abs_error_rate_column_name = model_results.apply(
# lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
# # 将列名索引转换为列名
# min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(
# lambda x: x.split('_')[0])
# # 取出现次数最多的模型名称
# most_common_model = min_abs_error_rate_column_name.value_counts().idxmax()
# logger.info(f"最近60天预测残差最低的模型名称：{most_common_model}")
# # 保存结果到数据库
# if not sqlitedb.check_table_exists('most_model'):
# sqlitedb.create_table(
# 'most_model', columns="ds datetime, most_common_model TEXT")
# sqlitedb.insert_data('most_model', (datetime.datetime.now().strftime(
# '%Y-%m-%d %H:%M:%S'), most_common_model,), columns=('ds', 'most_common_model',))
# try: engine = create_engine(
# if is_weekday: f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}')
# # if True: warning_data_df['WARNING_DATE'] = datetime.date.today().strftime(
# logger.info('今天是周一，发送特征预警') "%Y-%m-%d %H:%M:%S")
# # 上传预警信息到数据库 warning_data_df['TENANT_CODE'] = 'T0004'
# warning_data_df = df_zhibiaoliebiao.copy() # 插入数据之前查询表数据然后新增id列
# warning_data_df = warning_data_df[warning_data_df['停更周期'] > 3][[ existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine)
# '指标名称', '指标id', '频度', '更新周期', '指标来源', '最后更新时间', '停更周期']] if not existing_data.empty:
# # 重命名列名 max_id = existing_data['ID'].astype(int).max()
# warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY', warning_data_df['ID'] = range(
# '更新周期': 'UPDATE_FREQUENCY', '指标来源': 'DATA_SOURCE', '最后更新时间': 'LAST_UPDATE_DATE', '停更周期': 'UPDATE_SUSPENSION_CYCLE'}) max_id + 1, max_id + 1 + len(warning_data_df))
# from sqlalchemy import create_engine else:
# import urllib warning_data_df['ID'] = range(1, 1 + len(warning_data_df))
# global password warning_data_df.to_sql(
# if '@' in password: table_name, con=engine, if_exists='append', index=False)
# password = urllib.parse.quote_plus(password) if is_update_warning_data:
upload_warning_info(len(warning_data_df))
except:
logger.info('上传预警信息到数据库失败')
# engine = create_engine( if is_corr:
# f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}') df = corr_feature(df=df)
# warning_data_df['WARNING_DATE'] = datetime.date.today().strftime(
# "%Y-%m-%d %H:%M:%S")
# warning_data_df['TENANT_CODE'] = 'T0004'
# # 插入数据之前查询表数据然后新增id列
# existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine)
# if not existing_data.empty:
# max_id = existing_data['ID'].astype(int).max()
# warning_data_df['ID'] = range(
# max_id + 1, max_id + 1 + len(warning_data_df))
# else:
# warning_data_df['ID'] = range(1, 1 + len(warning_data_df))
# warning_data_df.to_sql(
# table_name, con=engine, if_exists='append', index=False)
# if is_update_warning_data:
# upload_warning_info(len(warning_data_df))
# except:
# logger.info('上传预警信息到数据库失败')
# if is_corr: df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用
# df = corr_feature(df=df) logger.info(f"开始训练模型...")
row, col = df.shape
# df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用 now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
# logger.info(f"开始训练模型...") ex_Model(df,
# row, col = df.shape horizon=global_config['horizon'],
input_size=global_config['input_size'],
# now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') train_steps=global_config['train_steps'],
# ex_Model(df, val_check_steps=global_config['val_check_steps'],
# horizon=global_config['horizon'], early_stop_patience_steps=global_config['early_stop_patience_steps'],
# input_size=global_config['input_size'], is_debug=global_config['is_debug'],
# train_steps=global_config['train_steps'], dataset=global_config['dataset'],
# val_check_steps=global_config['val_check_steps'], is_train=global_config['is_train'],
# early_stop_patience_steps=global_config['early_stop_patience_steps'], is_fivemodels=global_config['is_fivemodels'],
# is_debug=global_config['is_debug'], val_size=global_config['val_size'],
# dataset=global_config['dataset'], test_size=global_config['test_size'],
# is_train=global_config['is_train'], settings=global_config['settings'],
# is_fivemodels=global_config['is_fivemodels'], now=now,
# val_size=global_config['val_size'], etadata=global_config['etadata'],
# test_size=global_config['test_size'], modelsindex=global_config['modelsindex'],
# settings=global_config['settings'], data=data,
# now=now, is_eta=global_config['is_eta'],
# etadata=global_config['etadata'], end_time=global_config['end_time'],
# modelsindex=global_config['modelsindex'], )
# data=data,
# is_eta=global_config['is_eta'],
# end_time=global_config['end_time'],
# )
# logger.info('模型训练完成') # logger.info('模型训练完成')
logger.info('训练数据绘图ing')
model_results3 = model_losss(sqlitedb, end_time=end_time)
# logger.info('训练数据绘图ing') logger.info('训练数据绘图end')
# model_results3 = model_losss(sqlitedb, end_time=end_time)
# logger.info('训练数据绘图end')
# # 模型报告 # # 模型报告
# logger.info('制作报告ing') logger.info('制作报告ing')
# title = f'{settings}--{end_time}-预测报告' # 报告标题 title = f'{settings}--{end_time}-预测报告' # 报告标题
# reportname = f'Brent原油大模型日度预测--{end_time}.pdf' # 报告文件名 reportname = f'Brent原油大模型日度预测--{end_time}.pdf' # 报告文件名
# reportname = reportname.replace(':', '-') # 替换冒号 reportname = reportname.replace(':', '-') # 替换冒号
# brent_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time, brent_export_pdf(dataset=dataset, num_models=5 if is_fivemodels else 22, time=end_time,
# reportname=reportname, sqlitedb=sqlitedb), reportname=reportname, sqlitedb=sqlitedb),
# logger.info('制作报告end') logger.info('制作报告end')
# logger.info('模型训练完成') logger.info('模型训练完成')
logger.info('发送预测结果到市场信息平台')
# 读取预测数据和模型评估数据
predict_file_path = os.path.join(config.dataset, 'predict.csv')
model_eval_file_path = os.path.join(config.dataset, 'model_evaluation.csv')
try:
predictdata_df = pd.read_csv(predict_file_path)
top_models_df = pd.read_csv(model_eval_file_path)
except FileNotFoundError as e:
logger.error(f"文件未找到: {e}")
return
predictdata = predictdata_df.copy()
# 取模型前十
top_models = top_models_df['模型(Model)'].head(10).tolist()
# 计算前十模型的均值
predictdata_df['top_models_mean'] = predictdata_df[top_models].mean(axis=1)
# 打印日期和前十模型均值
print(predictdata_df[['ds', 'top_models_mean']])
# 准备要推送的数据
first_date = predictdata_df['ds'].iloc[0].replace('-', '')
last_date = predictdata_df['ds'].iloc[-1].replace('-', '')
first_mean = predictdata_df['top_models_mean'].iloc[0]
last_mean = predictdata_df['top_models_mean'].iloc[-1]
predictdata = [
{
"dataItemNo": global_config['bdwd_items']['ciri'],
"dataDate": first_date,
"dataStatus": "add",
"dataValue": first_mean
},
{
"dataItemNo": global_config['bdwd_items']['benzhou'],
"dataDate": last_date,
"dataStatus": "add",
"dataValue": last_mean
}
]
print(predictdata)
# 推送数据到市场信息平台
try:
push_market_data(predictdata)
except Exception as e:
logger.error(f"推送数据失败: {e}")
# # LSTM 单变量模型 # # LSTM 单变量模型
# ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset) # ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset)

4
测试环境获取市场信息平台数据项.ipynb
View File

@ -280,7 +280,7 @@
], ],
"metadata": { "metadata": {
"kernelspec": { "kernelspec": {
"display_name": "predict", "display_name": "base",
"language": "python", "language": "python",
"name": "python3" "name": "python3"
}, },
@ -294,7 +294,7 @@
"name": "python", "name": "python",
"nbconvert_exporter": "python", "nbconvert_exporter": "python",
"pygments_lexer": "ipython3", "pygments_lexer": "ipython3",
"version": "3.11.9" "version": "3.11.7"
} }
}, },
"nbformat": 4, "nbformat": 4,