石油焦铝用日度预测代码
This commit is contained in:
jingboyitiji
parent
f5286990fa
commit
fa59c1cff4
@ -143,7 +143,7 @@ modelsindex = {
|
||||
}
|
||||
|
||||
# 百川数据指标编码
|
||||
baicangidnamedict = {
|
||||
baichuanidnamedict = {
|
||||
'1588348470396480000': '石油焦滨州-友泰',
|
||||
'1588348470396480000.00': '石油焦东营-海科瑞林',
|
||||
'1588348470396480000.00': '石油焦东营-华联2',
|
||||
@ -160,6 +160,8 @@ baicangidnamedict = {
|
||||
}
|
||||
|
||||
|
||||
# baichuanidnamedict = {'1588348470396475286': 'test1', '1666': 'test2'} # 北京环境测试用
|
||||
|
||||
# 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 = {
|
||||
"IndexCode": "",
|
||||
@ -272,14 +274,14 @@ push_data_value_list_data = {
|
||||
}
|
||||
# 八大维度数据项编码
|
||||
bdwd_items = {
|
||||
# 'ciri': 'yyycbdwdcr',
|
||||
# 'benzhou': 'yyycbdwdbz',
|
||||
# 'cizhou': 'yyycbdwdcz',
|
||||
# 'gezhou': 'yyycbdwdgz',
|
||||
# 'ciyue': 'yyycbdwdcy',
|
||||
# 'cieryue': 'yyycbdwdcey',
|
||||
# 'cisanyue': 'yyycbdwdcsy',
|
||||
# 'cisiyue': 'yyycbdwdcsiy',
|
||||
'ciri': 'syjlyycbdwdcr',
|
||||
'benzhou': 'syjlyycbdwdbz',
|
||||
'cizhou': 'syjlyycbdwdcz',
|
||||
'gezhou': 'syjlyycbdwdgz',
|
||||
'ciyue': 'syjlyycbdwdcy',
|
||||
'cieryue': 'syjlyycbdwdcey',
|
||||
'cisanyue': 'syjlyycbdwdcsy',
|
||||
'cisiyue': 'syjlyycbdwdcsiy',
|
||||
}
|
||||
|
||||
# 北京环境数据库
|
||||
@ -326,7 +328,7 @@ if add_kdj and is_edbnamelist:
|
||||
edbnamelist = edbnamelist+['K', 'D', 'J']
|
||||
|
||||
# 模型参数
|
||||
y = 'B46cc7d0a90155b5bfd'
|
||||
y = '煅烧焦山东高硫(高端S < 3.5，普货)(元/吨)'
|
||||
avg_cols = [
|
||||
|
||||
]
|
||||
|
||||
@ -57,6 +57,7 @@ global_config = {
|
||||
'y': None, # 目标变量列名
|
||||
'is_fivemodels': None,
|
||||
'weight_dict': None,
|
||||
'baicangidnamedict': None, # 百川id名称映射
|
||||
|
||||
# 模型参数
|
||||
'data_set': None, # 数据集名称
|
||||
@ -120,6 +121,8 @@ global_config = {
|
||||
|
||||
# 数据库配置
|
||||
'sqlitedb': None,
|
||||
'db_mysql': None,
|
||||
'baichuan_table_name': None,
|
||||
}
|
||||
# 定义函数
|
||||
|
||||
@ -1199,6 +1202,8 @@ class Config:
|
||||
# 数据库配置
|
||||
@property
|
||||
def sqlitedb(self): return global_config['sqlitedb']
|
||||
@property
|
||||
def db_mysql(self): return global_config['db_mysql']
|
||||
|
||||
|
||||
config = Config()
|
||||
@ -2213,3 +2218,38 @@ def addtimecharacteristics(df, dataset):
|
||||
df.drop(columns=['quarter_start', 'quarter'], inplace=True)
|
||||
df.to_csv(os.path.join(dataset, '指标数据添加时间特征.csv'), index=False)
|
||||
return df
|
||||
|
||||
|
||||
# 从数据库获取百川数据，接收一个百川id列表，返回df格式的数据
|
||||
def get_baichuan_data(baichuanidnamedict):
|
||||
baichuanidlist = list(baichuanidnamedict.keys())
|
||||
# 连接数据库
|
||||
db = config.db_mysql
|
||||
db.connect()
|
||||
# 执行SQL查询 select BAICHUAN_ID,DATA_DATE,DATA_VALUE from V_TBL_BAICHUAN_YINGFU_VALUE where BAICHUAN_ID in ('1588348470396475286','1666');
|
||||
sql = f"SELECT BAICHUAN_ID,DATA_DATE,DATA_VALUE FROM {global_config['baichuan_table_name']} WHERE BAICHUAN_ID in ({','.join(baichuanidlist)})"
|
||||
|
||||
# 获取查询结果
|
||||
results = db.execute_query(sql)
|
||||
df = pd.DataFrame(results, columns=[
|
||||
'BAICHUAN_ID', 'DATA_DATE', 'DATA_VALUE'])
|
||||
|
||||
# 按BAICHUAN_ID 进行分组，然后按DATA_DATE合并
|
||||
df1 = pd.DataFrame(columns=['DATA_DATE'])
|
||||
for baichuan_id, group in df.groupby('BAICHUAN_ID'):
|
||||
# group 删除BAICHUAN_ID列
|
||||
group.drop(columns=['BAICHUAN_ID'], inplace=True)
|
||||
# group DATA_value 转换为float类型,保留两位小数
|
||||
group['DATA_VALUE'] = group['DATA_VALUE'].astype(float).round(2)
|
||||
# group 更改列名
|
||||
group.rename(
|
||||
columns={'DATA_VALUE': baichuanidnamedict[baichuan_id]}, inplace=True)
|
||||
# 按DATA_DATE合并
|
||||
df1 = pd.merge(
|
||||
df1, group[['DATA_DATE', baichuanidnamedict[baichuan_id]]], on='DATA_DATE', how='outer')
|
||||
# 把DATA_DATE 列转换成日期格式
|
||||
df1['date'] = pd.to_datetime(
|
||||
df1['DATA_DATE']).dt.strftime('%Y-%m-%d')
|
||||
df1.drop(columns=['DATA_DATE'], inplace=True)
|
||||
|
||||
return df1
|
||||
|
||||
@ -3,7 +3,7 @@
|
||||
from lib.dataread import *
|
||||
from config_shiyoujiao_lvyong import *
|
||||
from lib.tools import SendMail, exception_logger
|
||||
from models.nerulforcastmodels import model_losss, shiyoujiao_lvyong_export_pdf
|
||||
from models.nerulforcastmodels import ex_Model, model_losss, model_losss_juxiting, brent_export_pdf, tansuanli_export_pdf, pp_export_pdf, model_losss_juxiting
|
||||
import datetime
|
||||
import torch
|
||||
torch.set_float32_matmul_precision("high")
|
||||
@ -18,6 +18,7 @@ global_config.update({
|
||||
'is_fivemodels': is_fivemodels,
|
||||
'settings': settings,
|
||||
'weight_dict': weight_dict,
|
||||
'baichuanidnamedict': baichuanidnamedict,
|
||||
|
||||
|
||||
# 模型参数
|
||||
@ -72,11 +73,14 @@ global_config.update({
|
||||
'edbdatapushurl': edbdatapushurl,
|
||||
'edbdeleteurl': edbdeleteurl,
|
||||
'edbbusinessurl': edbbusinessurl,
|
||||
'edbcodenamedict': edbcodenamedict,
|
||||
'ClassifyId': ClassifyId,
|
||||
'classifylisturl': classifylisturl,
|
||||
|
||||
# 数据库配置
|
||||
'sqlitedb': sqlitedb,
|
||||
'db_mysql': db_mysql,
|
||||
'baichuan_table_name': baichuan_table_name,
|
||||
})
|
||||
|
||||
|
||||
@ -173,228 +177,242 @@ def predict_main():
|
||||
返回:
|
||||
None
|
||||
"""
|
||||
# end_time = global_config['end_time']
|
||||
# # 获取数据
|
||||
# if is_eta:
|
||||
# logger.info('从eta获取数据...')
|
||||
# signature = BinanceAPI(APPID, SECRET)
|
||||
# etadata = EtaReader(signature=signature,
|
||||
# classifylisturl=global_config['classifylisturl'],
|
||||
# classifyidlisturl=global_config['classifyidlisturl'],
|
||||
# edbcodedataurl=global_config['edbcodedataurl'],
|
||||
# edbcodelist=global_config['edbcodelist'],
|
||||
# edbdatapushurl=global_config['edbdatapushurl'],
|
||||
# edbdeleteurl=global_config['edbdeleteurl'],
|
||||
# edbbusinessurl=global_config['edbbusinessurl'],
|
||||
# classifyId=global_config['ClassifyId'],
|
||||
# )
|
||||
# df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_shiyoujiao_lvyong_data(
|
||||
# data_set=data_set, dataset=dataset) # 原始数据，未处理
|
||||
|
||||
# if is_market:
|
||||
# logger.info('从市场信息平台获取数据...')
|
||||
# try:
|
||||
# # 如果是测试环境，最高价最低价取excel文档
|
||||
# if server_host == '192.168.100.53':
|
||||
# logger.info('从excel文档获取最高价最低价')
|
||||
# df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju)
|
||||
# else:
|
||||
# logger.info('从市场信息平台获取数据')
|
||||
# df_zhibiaoshuju = get_market_data(
|
||||
# end_time, df_zhibiaoshuju)
|
||||
end_time = global_config['end_time']
|
||||
# 获取数据
|
||||
if is_eta:
|
||||
logger.info('从eta获取数据...')
|
||||
signature = BinanceAPI(APPID, SECRET)
|
||||
etadata = EtaReader(signature=signature,
|
||||
classifylisturl=global_config['classifylisturl'],
|
||||
classifyidlisturl=global_config['classifyidlisturl'],
|
||||
edbcodedataurl=global_config['edbcodedataurl'],
|
||||
edbcodelist=global_config['edbcodelist'],
|
||||
edbdatapushurl=global_config['edbdatapushurl'],
|
||||
edbdeleteurl=global_config['edbdeleteurl'],
|
||||
edbbusinessurl=global_config['edbbusinessurl'],
|
||||
classifyId=global_config['ClassifyId'],
|
||||
)
|
||||
df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_shiyoujiao_lvyong_data(
|
||||
data_set=data_set, dataset=dataset) # 原始数据，未处理
|
||||
|
||||
# except:
|
||||
# logger.info('最高最低价拼接失败')
|
||||
if is_market:
|
||||
logger.info('从市场信息平台获取数据...')
|
||||
try:
|
||||
# 如果是测试环境，最高价最低价取excel文档
|
||||
if server_host == '192.168.100.53':
|
||||
logger.info('从excel文档获取最高价最低价')
|
||||
df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju)
|
||||
else:
|
||||
logger.info('从市场信息平台获取数据')
|
||||
df_zhibiaoshuju = get_market_data(
|
||||
end_time, df_zhibiaoshuju)
|
||||
|
||||
# # 保存到xlsx文件的sheet表
|
||||
# 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_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
|
||||
except:
|
||||
logger.info('最高最低价拼接失败')
|
||||
|
||||
# # 数据处理
|
||||
# df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=global_config['y'], dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
|
||||
# end_time=end_time)
|
||||
if len(global_config['baichuanidnamedict']) > 0:
|
||||
logger.info('从市场数据库获取百川数据...')
|
||||
baichuandf = get_baichuan_data(global_config['baichuanidnamedict'])
|
||||
df_zhibiaoshuju = pd.merge(
|
||||
df_zhibiaoshuju, baichuandf, on='date', how='outer')
|
||||
# 指标列表添加百川数据
|
||||
df_baichuanliebiao = pd.DataFrame(
|
||||
global_config['baichuanidnamedict'].items(), columns=['指标id', '指标名称'])
|
||||
df_baichuanliebiao['指标分类'] = '百川'
|
||||
df_baichuanliebiao['频度'] = '其他'
|
||||
df_zhibiaoliebiao = pd.concat(
|
||||
[df_zhibiaoliebiao, df_baichuanliebiao], axis=0)
|
||||
|
||||
# else:
|
||||
# # 读取数据
|
||||
# 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,
|
||||
# is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理
|
||||
# 保存到xlsx文件的sheet表
|
||||
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_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False)
|
||||
|
||||
# # 更改预测列名称
|
||||
# df.rename(columns={y: 'y'}, inplace=True)
|
||||
# 数据处理
|
||||
df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=global_config['y'], dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
|
||||
end_time=end_time)
|
||||
|
||||
# if is_edbnamelist:
|
||||
# df = df[edbnamelist]
|
||||
# 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
|
||||
# # 取第一行数据存储到数据库中
|
||||
# first_row = df[['ds', 'y']].tail(1)
|
||||
# # 判断y的类型是否为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')
|
||||
# return None
|
||||
else:
|
||||
# 读取数据
|
||||
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,
|
||||
is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理
|
||||
|
||||
# # 将最新真实值保存到数据库
|
||||
# if not sqlitedb.check_table_exists('trueandpredict'):
|
||||
# first_row.to_sql('trueandpredict', sqlitedb.connection, index=False)
|
||||
# else:
|
||||
# for row in first_row.itertuples(index=False):
|
||||
# row_dict = row._asdict()
|
||||
# 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
|
||||
# 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 %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())
|
||||
# 更改预测列名称
|
||||
df.rename(columns={y: 'y'}, inplace=True)
|
||||
|
||||
# # 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:
|
||||
# for row in update_y.itertuples(index=False):
|
||||
# try:
|
||||
# row_dict = row._asdict()
|
||||
# yy = df[df['ds'] == row_dict['ds']]['y'].values[0]
|
||||
# LOW = df[df['ds'] == row_dict['ds']]['Brentzdj'].values[0]
|
||||
# HIGH = df[df['ds'] == row_dict['ds']]['Brentzgj'].values[0]
|
||||
# sqlitedb.update_data(
|
||||
# 'accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
|
||||
# except:
|
||||
# logger.info(f'更新accuracy表的y值失败：{row_dict}')
|
||||
# # except Exception as e:
|
||||
# # logger.info(f'更新accuracy表的y值失败：{e}')
|
||||
if is_edbnamelist:
|
||||
df = df[edbnamelist]
|
||||
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
|
||||
# 取第一行数据存储到数据库中
|
||||
first_row = df[['ds', 'y']].tail(1)
|
||||
# 判断y的类型是否为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')
|
||||
return None
|
||||
|
||||
# # 判断当前日期是不是周一
|
||||
# is_weekday = datetime.datetime.now().weekday() == 0
|
||||
# if is_weekday:
|
||||
# logger.info('今天是周一，更新预测模型')
|
||||
# # 计算最近60天预测残差最低的模型名称
|
||||
# model_results = sqlitedb.select_data(
|
||||
# 'trueandpredict', order_by="ds DESC", limit="60")
|
||||
# # 删除空值率为90%以上的列
|
||||
# if len(model_results) > 10:
|
||||
# model_results = model_results.dropna(
|
||||
# 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]
|
||||
# for col in model_results[modelnames].select_dtypes(include=['object']).columns:
|
||||
# model_results[col] = model_results[col].astype(np.float32)
|
||||
# # 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',))
|
||||
# 将最新真实值保存到数据库
|
||||
if not sqlitedb.check_table_exists('trueandpredict'):
|
||||
first_row.to_sql('trueandpredict', sqlitedb.connection, index=False)
|
||||
else:
|
||||
for row in first_row.itertuples(index=False):
|
||||
row_dict = row._asdict()
|
||||
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
|
||||
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 %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())
|
||||
|
||||
# try:
|
||||
# if is_weekday:
|
||||
# # if True:
|
||||
# logger.info('今天是周一，发送特征预警')
|
||||
# # 上传预警信息到数据库
|
||||
# warning_data_df = df_zhibiaoliebiao.copy()
|
||||
# warning_data_df = warning_data_df[warning_data_df['停更周期'] > 3][[
|
||||
# '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']]
|
||||
# # 重命名列名
|
||||
# warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY',
|
||||
# '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'})
|
||||
# from sqlalchemy import create_engine
|
||||
# import urllib
|
||||
# global password
|
||||
# if '@' in password:
|
||||
# password = urllib.parse.quote_plus(password)
|
||||
# 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:
|
||||
for row in update_y.itertuples(index=False):
|
||||
try:
|
||||
row_dict = row._asdict()
|
||||
yy = df[df['ds'] == row_dict['ds']]['y'].values[0]
|
||||
LOW = df[df['ds'] == row_dict['ds']]['Brentzdj'].values[0]
|
||||
HIGH = df[df['ds'] == row_dict['ds']]['Brentzgj'].values[0]
|
||||
sqlitedb.update_data(
|
||||
'accuracy', f"y = {yy},LOW_PRICE = {LOW},HIGH_PRICE = {HIGH}", where_condition=f"ds = '{row_dict['ds']}'")
|
||||
except:
|
||||
logger.info(f'更新accuracy表的y值失败：{row_dict}')
|
||||
# except Exception as e:
|
||||
# logger.info(f'更新accuracy表的y值失败：{e}')
|
||||
|
||||
# engine = create_engine(
|
||||
# f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}')
|
||||
# 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')
|
||||
# 判断当前日期是不是周一
|
||||
is_weekday = datetime.datetime.now().weekday() == 0
|
||||
if is_weekday:
|
||||
logger.info('今天是周一，更新预测模型')
|
||||
# 计算最近60天预测残差最低的模型名称
|
||||
model_results = sqlitedb.select_data(
|
||||
'trueandpredict', order_by="ds DESC", limit="60")
|
||||
# 删除空值率为90%以上的列
|
||||
if len(model_results) > 10:
|
||||
model_results = model_results.dropna(
|
||||
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]
|
||||
for col in model_results[modelnames].select_dtypes(include=['object']).columns:
|
||||
model_results[col] = model_results[col].astype(np.float32)
|
||||
# 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',))
|
||||
|
||||
# if is_corr:
|
||||
# df = corr_feature(df=df)
|
||||
try:
|
||||
if is_weekday:
|
||||
# if True:
|
||||
logger.info('今天是周一，发送特征预警')
|
||||
# 上传预警信息到数据库
|
||||
warning_data_df = df_zhibiaoliebiao.copy()
|
||||
warning_data_df = warning_data_df[warning_data_df['停更周期'] > 3][[
|
||||
'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']]
|
||||
# 重命名列名
|
||||
warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY',
|
||||
'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'})
|
||||
from sqlalchemy import create_engine
|
||||
import urllib
|
||||
global password
|
||||
if '@' in password:
|
||||
password = urllib.parse.quote_plus(password)
|
||||
|
||||
# df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用
|
||||
# logger.info(f"开始训练模型...")
|
||||
# row, col = df.shape
|
||||
engine = create_engine(
|
||||
f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}')
|
||||
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')
|
||||
|
||||
# now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
|
||||
# ex_Model(df,
|
||||
# horizon=global_config['horizon'],
|
||||
# input_size=global_config['input_size'],
|
||||
# train_steps=global_config['train_steps'],
|
||||
# val_check_steps=global_config['val_check_steps'],
|
||||
# early_stop_patience_steps=global_config['early_stop_patience_steps'],
|
||||
# is_debug=global_config['is_debug'],
|
||||
# dataset=global_config['dataset'],
|
||||
# is_train=global_config['is_train'],
|
||||
# is_fivemodels=global_config['is_fivemodels'],
|
||||
# val_size=global_config['val_size'],
|
||||
# test_size=global_config['test_size'],
|
||||
# settings=global_config['settings'],
|
||||
# now=now,
|
||||
# etadata=global_config['etadata'],
|
||||
# modelsindex=global_config['modelsindex'],
|
||||
# data=data,
|
||||
# is_eta=global_config['is_eta'],
|
||||
# end_time=global_config['end_time'],
|
||||
# )
|
||||
if is_corr:
|
||||
df = corr_feature(df=df)
|
||||
|
||||
# logger.info('模型训练完成')
|
||||
df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用
|
||||
logger.info(f"开始训练模型...")
|
||||
row, col = df.shape
|
||||
|
||||
now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
|
||||
ex_Model(df,
|
||||
horizon=global_config['horizon'],
|
||||
input_size=global_config['input_size'],
|
||||
train_steps=global_config['train_steps'],
|
||||
val_check_steps=global_config['val_check_steps'],
|
||||
early_stop_patience_steps=global_config['early_stop_patience_steps'],
|
||||
is_debug=global_config['is_debug'],
|
||||
dataset=global_config['dataset'],
|
||||
is_train=global_config['is_train'],
|
||||
is_fivemodels=global_config['is_fivemodels'],
|
||||
val_size=global_config['val_size'],
|
||||
test_size=global_config['test_size'],
|
||||
settings=global_config['settings'],
|
||||
now=now,
|
||||
etadata=global_config['etadata'],
|
||||
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('训练数据绘图ing')
|
||||
model_results3 = model_losss(sqlitedb, end_time=end_time)
|
||||
@ -403,15 +421,15 @@ def predict_main():
|
||||
# 模型报告
|
||||
logger.info('制作报告ing')
|
||||
title = f'{settings}--{end_time}-预测报告' # 报告标题
|
||||
reportname = f'石油焦铝用大模型日度预测--{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
|
||||
shiyoujiao_lvyong_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),
|
||||
|
||||
logger.info('制作报告end')
|
||||
logger.info('模型训练完成')
|
||||
|
||||
# push_market_value()
|
||||
push_market_value()
|
||||
|
||||
# # LSTM 单变量模型
|
||||
# ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset)
|
||||
|
||||
Loading…
Reference in New Issue
Block a user