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

Compare commits

base: liurui:5191ff7c691bde6b4b2de6c2e298b1b117ffa0a7
Branches Tags
liurui:main
..
compare: liurui:f5286990fa6b84bc08351ce6b3722d401d7669f8
Branches Tags
liurui:main

3 Commits
5191ff7c69 ... f5286990fa

Author SHA1 Message Date
jingboyitiji
f5286990fa Merge branch 'main' of https://gitea.jayhgq.cn/liurui/PriceForecast 2025-03-25 10:46:04 +08:00
jingboyitiji
308e831468 原油周度，周一模型名称列表取值更改 2025-03-25 10:39:43 +08:00
jingboyitiji
7cf3cda87a 石油焦日度预测调试 2025-03-20 16:29:25 +08:00
14 changed files with 787 additions and 1358 deletions
Show Stats Expand all files Collapse all files

18
aisenzhecode/沥青/沥青定性模型每日推送-ytj.ipynb
View File

@ -18,22 +18,10 @@
"import numpy as np\n", "import numpy as np\n",
"# 变量定义\n", "# 变量定义\n",
"login_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n", "login_url = \"http://10.200.32.39/jingbo-api/api/server/login\"\n",
"# query_data_list_item_nos_url\n", "search_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos\"\n",
"search_url = \"http://10.200.32.39/jingbo-api/api/warehouse/dwDataItem/queryByItemNos\" #jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos\n",
"upload_url = \"http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList\"\n", "upload_url = \"http://10.200.32.39/jingbo-api/api/dw/dataValue/pushDataValueList\"\n",
"\n", "\n",
"\n", "\n",
"query_data_list_item_nos_data = {\n",
" \"funcModule\": \"数据项\",\n",
" \"funcOperation\": \"查询\",\n",
" \"data\": {\n",
" \"dateStart\": \"20200101\",\n",
" \"dateEnd\": \"20241231\",\n",
" \"dataItemNoList\": [\"Brentzdj\", \"Brentzgj\"] # 数据项编码,代表 brent最低价和最高价\n",
" }\n",
"}\n",
"\n",
"\n",
"login_data = {\n", "login_data = {\n",
" \"data\": {\n", " \"data\": {\n",
" \"account\": \"api_dev\",\n", " \"account\": \"api_dev\",\n",
@ -856,7 +844,7 @@
" # headers1 = {\"Authorization\": token_push}\n", " # headers1 = {\"Authorization\": token_push}\n",
" # res = requests.post(url=upload_url, headers=headers1, json=data1, timeout=(3, 5))\n", " # res = requests.post(url=upload_url, headers=headers1, json=data1, timeout=(3, 5))\n",
" \n", " \n",
"\n", " \n",
"\n", "\n",
"\n", "\n",
"\n", "\n",
@ -972,6 +960,8 @@
" # 保存新的xls文件\n", " # 保存新的xls文件\n",
" new_workbook.save(\"定性模型数据项12-11.xlsx\")\n", " new_workbook.save(\"定性模型数据项12-11.xlsx\")\n",
"\n", "\n",
"\n",
"\n",
"\n" "\n"
] ]
}, },

2
aisenzhecode/沥青/沥青定量价格预测每日推送-ytj.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 3,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {

BIN
aisenzhecode/液化石油气/化工品价格预测准确率.xlsx
View File

Binary file not shown.

2
aisenzhecode/聚合级丙烯/丙烯价格预测yij.ipynb
View File

@ -2,7 +2,7 @@
"cells": [ "cells": [
{ {
"cell_type": "code", "cell_type": "code",
"execution_count": null, "execution_count": 27,
"metadata": {}, "metadata": {},
"outputs": [ "outputs": [
{ {

320
config_shiyoujiao.py
View File

@ -1,320 +0,0 @@
import logging
import os
import logging.handlers
import datetime
from lib.tools import MySQLDB,SQLiteHandler
# eta 接口token
APPID = "XNLDvxZHHugj7wJ7"
SECRET = "iSeU4s6cKKBVbt94htVY1p0sqUMqb2xa"
# eta 接口url
sourcelisturl = 'http://10.189.2.78:8108/v1/edb/source/list'
classifylisturl = 'http://10.189.2.78:8108/v1/edb/classify/list?ClassifyType='
uniquecodedataurl = 'http://10.189.2.78:8108/v1/edb/data?UniqueCode=4991c37becba464609b409909fe4d992&StartDate=2024-02-01'
classifyidlisturl = 'http://10.189.2.78:8108/v1/edb/list?ClassifyId='
edbcodedataurl = 'http://10.189.2.78:8108/v1/edb/data?EdbCode='
edbdatapushurl = 'http://10.189.2.78:8108/v1/edb/push'
edbdeleteurl = 'http://10.189.2.78:8108/v1/edb/business/edb/del'
edbbusinessurl = 'http://10.189.2.78:8108/v1/edb/business/data/del'
edbcodelist = ['ID01385938','lmcads03 lme comdty',
'GC1 COMB Comdty',
'C2404171822',
'dxy curncy',
'S5443199 ',
'S5479800',
'S5443108',
'H7358586',
'LC3FM1 INDEX',
'CNY REGN Curncy',
's0105897',
'M0067419',
'M0066351',
'S0266372',
'S0266438',
'S0266506',
'ID01384463']
# 临时写死用指定的列,与上面的edbcode对应，后面更改
edbnamelist = [
'ds','y',
'LME铜价',
'黄金连1合约',
'Brent-WTI',
'美元指数',
'甲醇鲁南价格',
'甲醇太仓港口价格',
'山东丙烯主流价',
'丙烷（山东）',
'FEI丙烷 M1',
'在岸人民币汇率',
'南华工业品指数',
'PVC期货主力',
'PE期货收盘价',
'PP连续-1月',
'PP连续-5月',
'PP连续-9月',
'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）'
]
edbcodenamedict = {
'ID01385938':'PP：拉丝：1102K：市场价：青州：国家能源宁煤（日）',
'ID01384463':'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）',
'lmcads03 lme comdty':'LME铜价',
'GC1 COMB Comdty':'黄金连1合约',
'C2404171822':'Brent-WTI',
'dxy curncy':'美元指数',
'S5443199 ':'甲醇鲁南价格',
'S5479800':'甲醇太仓港口价格',
'S5443108':'山东丙烯主流价',
'H7358586':'丙烷（山东）',
'LC3FM1 INDEX':'FEI丙烷 M1',
'CNY REGN Curncy':'在岸人民币汇率',
's0105897':'南华工业品指数',
'M0067419':'PVC期货主力',
'M0066351':'PE期货收盘价',
'S0266372':'PP连续-1月',
'S0266438':'PP连续-5月',
'S0266506':'PP连续-9月',
}
# eta自有数据指标编码
modelsindex = {
'NHITS': 'SELF0000077',
'Informer':'SELF0000078',
'LSTM':'SELF0000079',
'iTransformer':'SELF0000080',
'TSMixer':'SELF0000081',
'TSMixerx':'SELF0000082',
'PatchTST':'SELF0000083',
'RNN':'SELF0000084',
'GRU':'SELF0000085',
'TCN':'SELF0000086',
'BiTCN':'SELF0000087',
'DilatedRNN':'SELF0000088',
'MLP':'SELF0000089',
'DLinear':'SELF0000090',
'NLinear':'SELF0000091',
'TFT':'SELF0000092',
'FEDformer':'SELF0000093',
'StemGNN':'SELF0000094',
'MLPMultivariate':'SELF0000095',
'TiDE':'SELF0000096',
'DeepNPTS':'SELF0000097'
}
# 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": "",
"IndexName": "价格预测模型",
"Unit": "无",
"Frequency": "日度",
"SourceName": f"价格预测",
"Remark": 'ddd',
"DataList": [
{
"Date": "2024-05-02",
"Value": 333444
}
]
}
# eta 分类
# level：3才可以获取到数据，所以需要人工把能源化工下所有的level3级都找到
# url = 'http://10.189.2.78:8108/v1/edb/list?ClassifyId=1214'
#ParentId ":1160, 能源化工
# ClassifyId ":1214,原油 3912 石油焦
#ParentId ":1214,"，就是原油下所有的数据。
ClassifyId = 3707
############################################################################################################### 变量定义--测试环境
server_host = '192.168.100.53'
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"
upload_warning_url = f"http://{server_host}:8080/jingbo-dev/api/basicBuiness/crudeOilWarning/save"
query_data_list_item_nos_url = f"http://{server_host}:8080/jingbo-dev/api/warehouse/dwDataItem/queryDataListItemNos"
login_data = {
"data": {
"account": "api_test",
# "password": "MmVmNzNlOWI0MmY0ZDdjZGUwNzE3ZjFiMDJiZDZjZWU=", # Shihua@123456
"password": "ZTEwYWRjMzk0OWJhNTlhYmJlNTZlMDU3ZjIwZjg4M2U=", # 123456
"tenantHashCode": "8a4577dbd919675758d57999a1e891fe",
"terminal": "API"
},
"funcModule": "API",
"funcOperation": "获取token"
}
upload_data = {
"funcModule":'研究报告信息',
"funcOperation":'上传聚烯烃PP价格预测报告',
"data":{
"groupNo":'000128', # 用户组编号
"ownerAccount":'arui', #报告所属用户账号
"reportType":'OIL_PRICE_FORECAST', # 报告类型，固定为OIL_PRICE_FORECAST
"fileName": '2000-40-5-50--100-原油指标数据.xlsx-Brent活跃合约--2024-09-06-15-01-29-预测报告.pdf', #文件名称
"fileBase64": '' ,#文件内容base64
"categoryNo":'yyjgycbg', # 研究报告分类编码
"smartBusinessClassCode":'JXTJGYCBG', #分析报告分类编码
"reportEmployeeCode":"E40116", # 报告人
"reportDeptCode" :"D0044" ,# 报告部门
"productGroupCode":"RAW_MATERIAL" # 商品分类
}
}
warning_data = {
"groupNo":'000128', # 用户组编号
"funcModule":'原油特征停更预警',
"funcOperation":'原油特征停更预警',
"data":{
'WARNING_TYPE_NAME':'特征数据停更预警',
'WARNING_CONTENT':'',
'WARNING_DATE':''
}
}
query_data_list_item_nos_data = {
"funcModule": "数据项",
"funcOperation": "查询",
"data": {
"dateStart":"20200101",
"dateEnd":"20241231",
"dataItemNoList":["Brentzdj","Brentzgj"] # 数据项编码,代表 brent最低价和最高价
}
}
# 北京环境数据库
host = '192.168.101.27'
port = 3306
dbusername ='root'
password = '123456'
dbname = 'jingbo_test'
table_name = 'v_tbl_crude_oil_warning'
### 开关
is_train = False # 是否训练
is_debug = True # 是否调试
is_eta = True # 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_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_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_update_eta = False # 预测结果上传到eta
is_update_report = True # 是否上传报告
is_update_warning_data = False # 是否上传预警数据
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
# 连接到数据库
db_mysql = MySQLDB(host=host, user=dbusername, password=password, database=dbname)
db_mysql.connect()
print("数据库连接成功",host,dbname,dbusername)
# 数据截取日期
start_year = 2020 # 数据开始年份
end_time = '' # 数据截取日期
freq = 'B' # 时间频率，"D": 天 "W": 周"M": 月"Q": 季度"A": 年 "H": 小时 "T": 分钟 "S": 秒 "B": 工作日
delweekenday = True if freq == 'B' else False # 是否删除周末数据
is_corr = False # 特征是否参与滞后领先提升相关系数
add_kdj = False # 是否添加kdj指标
if add_kdj and is_edbnamelist:
edbnamelist = edbnamelist+['K','D','J']
### 模型参数
y = 'AVG-金能大唐久泰青州'
avg_cols = [
'PP：拉丝：1102K：出厂价：青州：国家能源宁煤（日）',
'PP：拉丝：L5E89：出厂价：华北（第二区域）：内蒙古久泰新材料（日）',
'PP：拉丝：L5E89：出厂价：河北、鲁北：大唐内蒙多伦（日）',
'PP：拉丝：HP550J：市场价：青岛：金能化学（日）'
]
offsite = 80
offsite_col = ['PP：拉丝：HP550J：市场价：青岛：金能化学（日）']
horizon =5 # 预测的步长
input_size = 40 # 输入序列长度
train_steps = 50 if is_debug else 1000 # 训练步数,用来限定epoch次数
val_check_steps = 30 # 评估频率
early_stop_patience_steps = 5 # 早停的耐心步数
# --- 交叉验证用的参数
test_size = 200 # 测试集大小，定义100，后面使用的时候重新赋值
val_size = test_size # 验证集大小,同测试集大小
### 特征筛选用到的参数
k = 100 # 特征筛选数量，如果是0或者值比特征数量大，代表全部特征
corr_threshold = 0.6 # 相关性大于0.6的特征
rote = 0.06 # 绘图上下界阈值
### 计算准确率
weight_dict = [0.4,0.15,0.1,0.1,0.25] # 权重
### 文件
data_set = '石油焦指标数据.xlsx' # 数据集文件
dataset = 'shiyoujiaodataset' # 数据集文件夹
# 数据库名称
db_name = os.path.join(dataset,'jbsh_juxiting.db')
sqlitedb = SQLiteHandler(db_name)
sqlitedb.connect()
settings = f'{input_size}-{horizon}-{train_steps}--{k}-{data_set}-{y}'
# 获取日期时间
# now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') # 获取当前日期时间
now = datetime.datetime.now().strftime('%Y-%m-%d') # 获取当前日期时间
reportname = f'PP大模型预测报告--{end_time}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号
if end_time == '':
end_time = now
### 邮件配置
username='1321340118@qq.com'
passwd='wgczgyhtyyyyjghi'
# recv=['liurui_test@163.com','52585119@qq.com']
recv=['liurui_test@163.com']
# recv=['liurui_test@163.com']
title='reportname'
content=y+'预测报告请看附件'
file=os.path.join(dataset,'reportname')
# file=os.path.join(dataset,'14-7-50--100-原油指标数据.xlsx-Brent连1合约价格--20240731175936-预测报告.pdf')
ssl=True
### 日志配置
# 创建日志目录（如果不存在）
log_dir = 'logs'
if not os.path.exists(log_dir):
os.makedirs(log_dir)
# 配置日志记录器
logger = logging.getLogger('my_logger')
logger.setLevel(logging.INFO)
# 配置文件处理器，将日志记录到文件
file_handler = logging.handlers.RotatingFileHandler(os.path.join(log_dir, 'pricepredict.log'), maxBytes=1024 * 1024, backupCount=5)
file_handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s'))
# 配置控制台处理器，将日志打印到控制台
console_handler = logging.StreamHandler()
console_handler.setFormatter(logging.Formatter('%(message)s'))
# 将处理器添加到日志记录器
logger.addHandler(file_handler)
logger.addHandler(console_handler)
# logger.info('当前配置：'+settings)

22
config_shiyoujiao_lvyong.py
View File

@ -143,7 +143,7 @@ modelsindex = {
} }
# 百川数据指标编码 # 百川数据指标编码
baichuanidnamedict = { baicangidnamedict = {
'1588348470396480000': '石油焦滨州-友泰', '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-海科瑞林',
'1588348470396480000.00': '石油焦东营-华联2', '1588348470396480000.00': '石油焦东营-华联2',
@ -160,8 +160,6 @@ baichuanidnamedict = {
} }
# 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 # 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": "",
@ -274,14 +272,14 @@ 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': 'syjlyycbdwdcr', # 'ciri': 'yyycbdwdcr',
'benzhou': 'syjlyycbdwdbz', # 'benzhou': 'yyycbdwdbz',
'cizhou': 'syjlyycbdwdcz', # 'cizhou': 'yyycbdwdcz',
'gezhou': 'syjlyycbdwdgz', # 'gezhou': 'yyycbdwdgz',
'ciyue': 'syjlyycbdwdcy', # 'ciyue': 'yyycbdwdcy',
'cieryue': 'syjlyycbdwdcey', # 'cieryue': 'yyycbdwdcey',
'cisanyue': 'syjlyycbdwdcsy', # 'cisanyue': 'yyycbdwdcsy',
'cisiyue': 'syjlyycbdwdcsiy', # 'cisiyue': 'yyycbdwdcsiy',
} }
# 北京环境数据库 # 北京环境数据库
@ -328,7 +326,7 @@ if add_kdj and is_edbnamelist:
edbnamelist = edbnamelist+['K', 'D', 'J'] edbnamelist = edbnamelist+['K', 'D', 'J']
# 模型参数 # 模型参数
y = '煅烧焦山东高硫(高端S < 3.5，普货)(元/吨)' y = 'B46cc7d0a90155b5bfd'
avg_cols = [ avg_cols = [
] ]

40
lib/dataread.py
View File

@ -57,7 +57,6 @@ global_config = {
'y': None, # 目标变量列名 'y': None, # 目标变量列名
'is_fivemodels': None, 'is_fivemodels': None,
'weight_dict': None, 'weight_dict': None,
'baicangidnamedict': None, # 百川id名称映射
# 模型参数 # 模型参数
'data_set': None, # 数据集名称 'data_set': None, # 数据集名称
@ -121,8 +120,6 @@ global_config = {
# 数据库配置 # 数据库配置
'sqlitedb': None, 'sqlitedb': None,
'db_mysql': None,
'baichuan_table_name': None,
} }
# 定义函数 # 定义函数
@ -1202,8 +1199,6 @@ class Config:
# 数据库配置 # 数据库配置
@property @property
def sqlitedb(self): return global_config['sqlitedb'] def sqlitedb(self): return global_config['sqlitedb']
@property
def db_mysql(self): return global_config['db_mysql']
config = Config() config = Config()
@ -2218,38 +2213,3 @@ def addtimecharacteristics(df, dataset):
df.drop(columns=['quarter_start', 'quarter'], inplace=True) 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) df.to_csv(os.path.join(dataset, '指标数据添加时间特征.csv'), index=False)
return df 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

301
main_shiyoujiao.py
View File

@ -1,301 +0,0 @@
# 读取配置
from lib.dataread import *
from lib.tools import SendMail,exception_logger
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
torch.set_float32_matmul_precision("high")
def predict_main():
"""
主预测函数，用于从 ETA 获取数据、处理数据、训练模型并进行预测。
参数:
signature (BinanceAPI): Binance API 实例。
etadata (EtaReader): ETA 数据读取器实例。
is_eta (bool): 是否从 ETA 获取数据。
data_set (str): 数据集名称。
dataset (str): 数据集路径。
add_kdj (bool): 是否添加 KDJ 指标。
is_timefurture (bool): 是否添加时间衍生特征。
end_time (str): 结束时间。
is_edbnamelist (bool): 是否使用 EDB 名称列表。
edbnamelist (list): EDB 名称列表。
y (str): 预测目标列名。
sqlitedb (SQLiteDB): SQLite 数据库实例。
is_corr (bool): 是否进行相关性分析。
horizon (int): 预测时域。
input_size (int): 输入数据大小。
train_steps (int): 训练步数。
val_check_steps (int): 验证检查步数。
early_stop_patience_steps (int): 早停耐心步数。
is_debug (bool): 是否调试模式。
dataset (str): 数据集名称。
is_train (bool): 是否训练模型。
is_fivemodels (bool): 是否使用五个模型。
val_size (float): 验证集大小。
test_size (float): 测试集大小。
settings (dict): 模型设置。
now (str): 当前时间。
etadata (EtaReader): ETA 数据读取器实例。
modelsindex (list): 模型索引列表。
data (str): 数据类型。
is_eta (bool): 是否从 ETA 获取数据。
返回:
None
"""
global end_time
signature = BinanceAPI(APPID, SECRET)
etadata = EtaReader(signature=signature,
classifylisturl=classifylisturl,
classifyidlisturl=classifyidlisturl,
edbcodedataurl=edbcodedataurl,
edbcodelist=edbcodelist,
edbdatapushurl=edbdatapushurl,
edbdeleteurl=edbdeleteurl,
edbbusinessurl=edbbusinessurl
)
# 获取数据
if is_eta:
logger.info('从eta获取数据...')
signature = BinanceAPI(APPID, SECRET)
etadata = EtaReader(signature=signature,
classifylisturl=classifylisturl,
classifyidlisturl=classifyidlisturl,
edbcodedataurl=edbcodedataurl,
edbcodelist=edbcodelist,
edbdatapushurl=edbdatapushurl,
edbdeleteurl=edbdeleteurl,
edbbusinessurl=edbbusinessurl,
)
df_zhibiaoshuju, df_zhibiaoliebiao = etadata.get_eta_api_shiyoujiao_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)
except :
logger.info('最高最低价拼接失败')
# 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)
# 数据处理
df = datachuli_juxiting(df_zhibiaoshuju, df_zhibiaoliebiao, y=y, dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
end_time=end_time)
else:
# 读取数据
logger.info('读取本地数据：' + os.path.join(dataset, data_set))
df,df_zhibiaoliebiao = getdata_juxiting(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
# 更改预测列名称
df.rename(columns={y: 'y'}, inplace=True)
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
# 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()
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:
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}')
import datetime
# 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',))
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)
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')
if is_corr:
df = corr_feature(df=df)
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_Juxiting(df,
horizon=horizon,
input_size=input_size,
train_steps=train_steps,
val_check_steps=val_check_steps,
early_stop_patience_steps=early_stop_patience_steps,
is_debug=is_debug,
dataset=dataset,
is_train=is_train,
is_fivemodels=is_fivemodels,
val_size=val_size,
test_size=test_size,
settings=settings,
now=now,
etadata=etadata,
modelsindex=modelsindex,
data=data,
is_eta=is_eta,
end_time=end_time,
)
logger.info('模型训练完成')
logger.info('训练数据绘图ing')
model_results3 = model_losss_juxiting(sqlitedb)
logger.info('训练数据绘图end')
# 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'PP大模型预测报告--{end_time}.pdf' # 报告文件名
reportname = reportname.replace(':', '-') # 替换冒号
pp_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')
# # LSTM 单变量模型
# ex_Lstm(df,input_seq_len=input_size,output_seq_len=horizon,is_debug=is_debug,dataset=dataset)
# # lstm 多变量模型
# ex_Lstm_M(df,n_days=input_size,out_days=horizon,is_debug=is_debug,datasetpath=dataset)
# # GRU 模型
# # ex_GRU(df)
# 发送邮件
m = SendMail(
username=username,
passwd=passwd,
recv=recv,
title=title,
content=content,
file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime),
ssl=ssl,
)
# m.send_mail()
if __name__ == '__main__':
# global end_time
# is_on = True
# # 遍历2024-11-25 到 2024-12-3 之间的工作日日期
# for i_time in pd.date_range('2025-1-20', '2025-2-6', freq='B'):
# end_time = i_time.strftime('%Y-%m-%d')
# try:
# predict_main()
# except:
# pass
predict_main()

438
main_shiyoujiao_lvyong.py
View File

@ -3,7 +3,7 @@
from lib.dataread import * from lib.dataread import *
from config_shiyoujiao_lvyong import * from config_shiyoujiao_lvyong import *
from lib.tools import SendMail, exception_logger 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 model_losss, shiyoujiao_lvyong_export_pdf
import datetime import datetime
import torch import torch
torch.set_float32_matmul_precision("high") torch.set_float32_matmul_precision("high")
@ -18,7 +18,6 @@ global_config.update({
'is_fivemodels': is_fivemodels, 'is_fivemodels': is_fivemodels,
'settings': settings, 'settings': settings,
'weight_dict': weight_dict, 'weight_dict': weight_dict,
'baichuanidnamedict': baichuanidnamedict,
# 模型参数 # 模型参数
@ -73,14 +72,11 @@ global_config.update({
'edbdatapushurl': edbdatapushurl, 'edbdatapushurl': edbdatapushurl,
'edbdeleteurl': edbdeleteurl, 'edbdeleteurl': edbdeleteurl,
'edbbusinessurl': edbbusinessurl, 'edbbusinessurl': edbbusinessurl,
'edbcodenamedict': edbcodenamedict,
'ClassifyId': ClassifyId, 'ClassifyId': ClassifyId,
'classifylisturl': classifylisturl, 'classifylisturl': classifylisturl,
# 数据库配置 # 数据库配置
'sqlitedb': sqlitedb, 'sqlitedb': sqlitedb,
'db_mysql': db_mysql,
'baichuan_table_name': baichuan_table_name,
}) })
@ -177,242 +173,228 @@ def predict_main():
返回: 返回:
None 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
end_time = global_config['end_time'] # if is_market:
# 获取数据 # logger.info('从市场信息平台获取数据...')
if is_eta: # try:
logger.info('从eta获取数据...') # # 如果是测试环境，最高价最低价取excel文档
signature = BinanceAPI(APPID, SECRET) # if server_host == '192.168.100.53':
etadata = EtaReader(signature=signature, # logger.info('从excel文档获取最高价最低价')
classifylisturl=global_config['classifylisturl'], # df_zhibiaoshuju = get_high_low_data(df_zhibiaoshuju)
classifyidlisturl=global_config['classifyidlisturl'], # else:
edbcodedataurl=global_config['edbcodedataurl'], # logger.info('从市场信息平台获取数据')
edbcodelist=global_config['edbcodelist'], # df_zhibiaoshuju = get_market_data(
edbdatapushurl=global_config['edbdatapushurl'], # end_time, df_zhibiaoshuju)
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: # except:
logger.info('从市场信息平台获取数据...') # logger.info('最高最低价拼接失败')
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)
except: # # 保存到xlsx文件的sheet表
logger.info('最高最低价拼接失败') # 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)
if len(global_config['baichuanidnamedict']) > 0: # # 数据处理
logger.info('从市场数据库获取百川数据...') # df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=global_config['y'], dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture,
baichuandf = get_baichuan_data(global_config['baichuanidnamedict']) # end_time=end_time)
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)
# 保存到xlsx文件的sheet表 # else:
with pd.ExcelWriter(os.path.join(dataset, data_set)) as file: # # 读取数据
df_zhibiaoshuju.to_excel(file, sheet_name='指标数据', index=False) # logger.info('读取本地数据：' + os.path.join(dataset, data_set))
df_zhibiaoliebiao.to_excel(file, sheet_name='指标列表', index=False) # 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
# 数据处理 # # 更改预测列名称
df = datachuli(df_zhibiaoshuju, df_zhibiaoliebiao, y=global_config['y'], dataset=dataset, add_kdj=add_kdj, is_timefurture=is_timefurture, # df.rename(columns={y: 'y'}, inplace=True)
end_time=end_time)
else: # if is_edbnamelist:
# 读取数据 # df = df[edbnamelist]
logger.info('读取本地数据：' + os.path.join(dataset, data_set)) # df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False)
df, df_zhibiaoliebiao = getdata(filename=os.path.join(dataset, data_set), y=y, dataset=dataset, add_kdj=add_kdj, # # 保存最新日期的y值到数据库
is_timefurture=is_timefurture, end_time=end_time) # 原始数据，未处理 # # 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
# 更改预测列名称 # # 将最新真实值保存到数据库
df.rename(columns={y: 'y'}, inplace=True) # 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())
if is_edbnamelist: # # 更新accuracy表的y值
df = df[edbnamelist] # if not sqlitedb.check_table_exists('accuracy'):
df.to_csv(os.path.join(dataset, '指标数据.csv'), index=False) # pass
# 保存最新日期的y值到数据库 # else:
# 取第一行数据存储到数据库中 # update_y = sqlitedb.select_data(
first_row = df[['ds', 'y']].tail(1) # 'accuracy', where_condition="y is null")
# 判断y的类型是否为float # if len(update_y) > 0:
if not isinstance(first_row['y'].values[0], float): # logger.info('更新accuracy表的y值')
logger.info(f'{end_time}预测目标数据为空，跳过') # # 找到update_y 中ds且df中的y的行
return None # 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}')
# 将最新真实值保存到数据库 # # 判断当前日期是不是周一
if not sqlitedb.check_table_exists('trueandpredict'): # is_weekday = datetime.datetime.now().weekday() == 0
first_row.to_sql('trueandpredict', sqlitedb.connection, index=False) # if is_weekday:
else: # logger.info('今天是周一，更新预测模型')
for row in first_row.itertuples(index=False): # # 计算最近60天预测残差最低的模型名称
row_dict = row._asdict() # model_results = sqlitedb.select_data(
config.logger.info(f'要保存的真实值：{row_dict}') # 'trueandpredict', order_by="ds DESC", limit="60")
# 判断ds是否为字符串类型,如果不是则转换为字符串类型 # # 删除空值率为90%以上的列
if isinstance(row_dict['ds'], (pd.Timestamp, datetime.datetime)): # if len(model_results) > 10:
row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d') # model_results = model_results.dropna(
elif not isinstance(row_dict['ds'], str): # thresh=len(model_results)*0.1, axis=1)
try: # # 删除空行
row_dict['ds'] = pd.to_datetime( # model_results = model_results.dropna()
row_dict['ds']).strftime('%Y-%m-%d') # modelnames = model_results.columns.to_list()[2:-1]
except: # for col in model_results[modelnames].select_dtypes(include=['object']).columns:
logger.warning(f"无法解析的时间格式: {row_dict['ds']}") # model_results[col] = model_results[col].astype(np.float32)
# row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d') # # 计算每个预测值与真实值之间的偏差率
# row_dict['ds'] = row_dict['ds'].strftime('%Y-%m-%d %H:%M:%S') # for model in modelnames:
check_query = sqlitedb.select_data( # model_results[f'{model}_abs_error_rate'] = abs(
'trueandpredict', where_condition=f"ds = '{row.ds}'") # model_results['y'] - model_results[model]) / model_results['y']
if len(check_query) > 0: # # 获取每行对应的最小偏差率值
set_clause = ", ".join( # min_abs_error_rate_values = model_results.apply(
[f"{key} = '{value}'" for key, value in row_dict.items()]) # lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
sqlitedb.update_data( # # 获取每行对应的最小偏差率值对应的列名
'trueandpredict', set_clause, where_condition=f"ds = '{row.ds}'") # min_abs_error_rate_column_name = model_results.apply(
continue # lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
sqlitedb.insert_data('trueandpredict', tuple( # # 将列名索引转换为列名
row_dict.values()), columns=row_dict.keys()) # 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',))
# 更新accuracy表的y值 # try:
if not sqlitedb.check_table_exists('accuracy'): # if is_weekday:
pass # # if True:
else: # logger.info('今天是周一，发送特征预警')
update_y = sqlitedb.select_data( # # 上传预警信息到数据库
'accuracy', where_condition="y is null") # warning_data_df = df_zhibiaoliebiao.copy()
if len(update_y) > 0: # warning_data_df = warning_data_df[warning_data_df['停更周期'] > 3][[
logger.info('更新accuracy表的y值') # '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']]
# 找到update_y 中ds且df中的y的行 # # 重命名列名
update_y = update_y[update_y['ds'] <= end_time] # warning_data_df = warning_data_df.rename(columns={'指标名称': 'INDICATOR_NAME', '指标id': 'INDICATOR_ID', '频度': 'FREQUENCY',
logger.info(f'要更新y的信息：{update_y}') # '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'})
# try: # from sqlalchemy import create_engine
for row in update_y.itertuples(index=False): # import urllib
try: # global password
row_dict = row._asdict() # if '@' in password:
yy = df[df['ds'] == row_dict['ds']]['y'].values[0] # password = urllib.parse.quote_plus(password)
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}')
# 判断当前日期是不是周一 # engine = create_engine(
is_weekday = datetime.datetime.now().weekday() == 0 # f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}')
if is_weekday: # warning_data_df['WARNING_DATE'] = datetime.date.today().strftime(
logger.info('今天是周一，更新预测模型') # "%Y-%m-%d %H:%M:%S")
# 计算最近60天预测残差最低的模型名称 # warning_data_df['TENANT_CODE'] = 'T0004'
model_results = sqlitedb.select_data( # # 插入数据之前查询表数据然后新增id列
'trueandpredict', order_by="ds DESC", limit="60") # existing_data = pd.read_sql(f"SELECT * FROM {table_name}", engine)
# 删除空值率为90%以上的列 # if not existing_data.empty:
if len(model_results) > 10: # max_id = existing_data['ID'].astype(int).max()
model_results = model_results.dropna( # warning_data_df['ID'] = range(
thresh=len(model_results)*0.1, axis=1) # max_id + 1, max_id + 1 + len(warning_data_df))
# 删除空行 # else:
model_results = model_results.dropna() # warning_data_df['ID'] = range(1, 1 + len(warning_data_df))
modelnames = model_results.columns.to_list()[2:-1] # warning_data_df.to_sql(
for col in model_results[modelnames].select_dtypes(include=['object']).columns: # table_name, con=engine, if_exists='append', index=False)
model_results[col] = model_results[col].astype(np.float32) # if is_update_warning_data:
# 计算每个预测值与真实值之间的偏差率 # upload_warning_info(len(warning_data_df))
for model in modelnames: # except:
model_results[f'{model}_abs_error_rate'] = abs( # logger.info('上传预警信息到数据库失败')
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: # if is_corr:
if is_weekday: # df = corr_feature(df=df)
# 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)
engine = create_engine( # df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用
f'mysql+pymysql://{dbusername}:{password}@{host}:{port}/{dbname}') # logger.info(f"开始训练模型...")
warning_data_df['WARNING_DATE'] = datetime.date.today().strftime( # row, col = df.shape
"%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: # now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
df = corr_feature(df=df) # 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'],
# )
df1 = df.copy() # 备份一下，后面特征筛选完之后加入ds y 列用 # logger.info('模型训练完成')
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') logger.info('训练数据绘图ing')
model_results3 = model_losss(sqlitedb, end_time=end_time) model_results3 = model_losss(sqlitedb, end_time=end_time)
@ -421,15 +403,15 @@ def predict_main():
# 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'石油焦铝用大模型日度预测--{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, shiyoujiao_lvyong_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')
push_market_value() # push_market_value()
# # 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)

2
main_yuanyou_zhoudu.py
View File

@ -301,7 +301,7 @@ def predict_main():
thresh=len(model_results)*0.1, axis=1) thresh=len(model_results)*0.1, axis=1)
# 删除空行 # 删除空行
model_results = model_results.dropna() model_results = model_results.dropna()
modelnames = model_results.columns.to_list()[2:-1] modelnames = model_results.columns.to_list()[2:-2]
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)
# 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

333
models/nerulforcastmodels.py
View File

@ -866,7 +866,7 @@ def model_losss_yongan(sqlitedb, end_time, table_name_prefix):
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[-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')
plt.ylabel('价格') plt.ylabel('价格')
@ -881,8 +881,8 @@ def model_losss_yongan(sqlitedb, end_time, table_name_prefix):
ax.axis('off') # 关闭坐标轴 ax.axis('off') # 关闭坐标轴
# 数值保留2位小数 # 数值保留2位小数
df = df.round(2) df = df.round(2)
df = df[-horizon:] df = df[-config.horizon:]
df['Day'] = [f'Day_{i}' for i in range(1, horizon+1)] df['Day'] = [f'Day_{i}' for i in range(1, config.horizon+1)]
# Day列放到最前面 # Day列放到最前面
df = df[['Day'] + list(df.columns[:-1])] df = df[['Day'] + list(df.columns[:-1])]
table = ax.table(cellText=df.values, table = ax.table(cellText=df.values,
@ -1297,7 +1297,7 @@ def model_losss(sqlitedb, end_time):
# plt.plot(df['ds'], df[model], label=model,marker='o') # plt.plot(df['ds'], df[model], label=model,marker='o')
plt.plot(df['ds'], df[most_model_name], label=model, marker='o') plt.plot(df['ds'], df[most_model_name], label=model, marker='o')
# 当前日期画竖虚线 # 当前日期画竖虚线
plt.axvline(x=df['ds'].iloc[-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')
# 设置横轴日期格式为年-月-日 # 设置横轴日期格式为年-月-日
@ -1338,7 +1338,7 @@ def model_losss(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[-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
@ -1357,8 +1357,8 @@ def model_losss(sqlitedb, end_time):
ax.axis('off') # 关闭坐标轴 ax.axis('off') # 关闭坐标轴
# 数值保留2位小数 # 数值保留2位小数
df = df.round(2) df = df.round(2)
df = df[-horizon:] df = df[-config.horizon:]
df['Day'] = [f'Day_{i}' for i in range(1, horizon+1)] df['Day'] = [f'Day_{i}' for i in range(1, config.horizon+1)]
# Day列放到最前面 # Day列放到最前面
df = df[['Day'] + list(df.columns[:-1])] df = df[['Day'] + list(df.columns[:-1])]
table = ax.table(cellText=df.values, table = ax.table(cellText=df.values,
@ -1388,10 +1388,10 @@ def model_losss(sqlitedb, end_time):
bbox_inches='tight') bbox_inches='tight')
plt.close() plt.close()
# _plt_predict_ture(df_combined3) _plt_predict_ture(df_combined3)
# _plt_modeltopten_predict_ture(df_combined4) # _plt_modeltopten_predict_ture(df_combined4)
# _plt_predict_table(df_combined3) _plt_predict_table(df_combined3)
# _plt_model_results3() _plt_model_results3()
return model_results3 return model_results3
@ -2461,6 +2461,319 @@ def brent_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, in
print(f"请求超时: {e}") print(f"请求超时: {e}")
@exception_logger
def shiyoujiao_lvyong_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, inputsize=5, dataset='dataset', time='2024-07-30', reportname='report.pdf', sqlitedb='jbsh_yuanyou.db'):
global y
# 创建内容对应的空列表
content = list()
# 获取特征的近一月值
import pandas as pd
feature_data_df = pd.read_csv(os.path.join(
config.dataset,'指标数据添加时间特征.csv'), parse_dates=['ds']).tail(60)
def draw_feature_trend(feature_data_df, features):
# 画特征近60天的趋势图
feature_df = feature_data_df[['ds', 'y']+features]
# 遍历X每一列，和yy画散点图 ，
for i, col in enumerate(features):
# try:
print(f'正在绘制第{i+1}个特征{col}与价格散点图...')
if col not in ['ds', 'y']:
fig, ax1 = plt.subplots(figsize=(10, 6))
# 在第一个坐标轴上绘制数据
sns.lineplot(data=feature_df, x='ds', y='y', ax=ax1, color='b')
ax1.set_xlabel('日期')
ax1.set_ylabel('y', color='b')
ax1.tick_params('y', colors='b')
# 在 ax1 上添加文本显示值，添加一定的偏移避免值与曲线重叠
for j in range(1, len(feature_df), 2):
value = feature_df['y'].iloc[j]
date = feature_df['ds'].iloc[j]
offset = 1.001
ax1.text(date, value * offset, str(round(value, 2)),
ha='center', va='bottom', color='b', fontsize=10)
# 创建第二个坐标轴
ax2 = ax1.twinx()
# 在第二个坐标轴上绘制数据
sns.lineplot(data=feature_df, x='ds', y=col, ax=ax2, color='r')
ax2.set_ylabel(col, color='r')
ax2.tick_params('y', colors='r')
# 在 ax2 上添加文本显示值，添加一定的偏移避免值与曲线重叠
for j in range(0, len(feature_df), 2):
value = feature_df[col].iloc[j]
date = feature_df['ds'].iloc[j]
offset = 1.0003
ax2.text(date, value * offset, str(round(value, 2)),
ha='center', va='bottom', color='r', fontsize=10)
# 添加标题
plt.title(col)
# 设置横坐标为日期格式并自动调整
locator = mdates.AutoDateLocator()
formatter = mdates.AutoDateFormatter(locator)
ax1.xaxis.set_major_locator(locator)
ax1.xaxis.set_major_formatter(formatter)
# 文件名特殊字符处理
col = col.replace('*', '-')
col = col.replace(':', '-')
col = col.replace(r'/', '-')
plt.savefig(os.path.join(config.dataset, f'{col}与价格散点图.png'))
content.append(Graphs.draw_img(
os.path.join(config.dataset, f'{col}与价格散点图.png')))
plt.close()
# except Exception as e:
# print(f'绘制第{i+1}个特征{col}与价格散点图时出错：{e}')
# 添加标题
content.append(Graphs.draw_title(f'{config.y}{time}预测报告'))
# 预测结果
content.append(Graphs.draw_little_title('一、预测结果：'))
# 添加历史走势及预测价格的走势图片
content.append(Graphs.draw_img(os.path.join(config.dataset, '历史价格-预测值.png')))
# 波动率画图逻辑
content.append(Graphs.draw_text('图示说明：'))
content.append(Graphs.draw_text(
' 确定置信区间：设置残差置信阈值，以每周最佳模型为基准，选取在置信区间的预测值作为置信区间;'))
# 取df中y列为空的行
import pandas as pd
df = pd.read_csv(os.path.join(config.dataset, 'predict.csv'), encoding='gbk')
df_true = pd.read_csv(os.path.join(
config.dataset,'指标数据添加时间特征.csv'), encoding='utf-8') # 获取预测日期对应的真实值
df_true = df_true[['ds', 'y']]
eval_df = pd.read_csv(os.path.join(
config.dataset,'model_evaluation.csv'), encoding='utf-8')
# 按评估指标排序，取前五
fivemodels_list = eval_df['模型(Model)'].values # 列表形式，后面当作列名索引使用
# 取 fivemodels_list 和 ds 列
df = df[['ds'] + fivemodels_list.tolist()]
# 拼接预测日期对应的真实值
df = pd.merge(df, df_true, on='ds', how='left')
# 删除全部为nan的列
df = df.dropna(how='all', axis=1)
# 选择除 'ds' 列外的数值列，并进行类型转换和四舍五入
num_cols = [col for col in df.columns if col !=
'ds' and pd.api.types.is_numeric_dtype(df[col])]
for col in num_cols:
df[col] = df[col].astype(float).round(2)
# 添加最大值、最小值、平均值三列
df['平均值'] = df[num_cols].mean(axis=1).round(2)
df['最大值'] = df[num_cols].max(axis=1)
df['最小值'] = df[num_cols].min(axis=1)
# df转置
df = df.T
# df重置索引
df = df.reset_index()
# 添加预测值表格
data = df.values.tolist()
col_width = 500/len(df.columns)
content.append(Graphs.draw_table(col_width, *data))
content.append(Graphs.draw_little_title('二、上一预测周期偏差率分析：'))
df = pd.read_csv(os.path.join(
config.dataset,'testandpredict_groupby.csv'), encoding='utf-8')
df4 = df.copy() # 计算偏差率使用
# 去掉created_dt 列
df4 = df4.drop(columns=['created_dt'])
# 计算模型偏差率
# 计算各列对于y列的差值百分比
df3 = pd.DataFrame() # 存储偏差率
# 删除有null的行
df4 = df4.dropna()
df3['ds'] = df4['ds']
for col in fivemodels_list:
df3[col] = round(abs(df4[col] - df4['y']) / df4['y'] * 100, 2)
# 找出决定系数前五的偏差率
df3 = df3[['ds']+fivemodels_list.tolist()][-inputsize:]
# 找出上一预测区间的时间
stime = df3['ds'].iloc[0]
etime = df3['ds'].iloc[-1]
# 添加偏差率表格
fivemodels = '、'.join(eval_df['模型(Model)'].values[:5]) # 字符串形式，后面写入字符串使用
content.append(Graphs.draw_text(
f'预测使用了{num_models}个模型进行训练，使用评估结果MAE前五的模型分别是 {fivemodels} ，模型上一预测区间 {stime} -- {etime}的偏差率(%)分别是：'))
# # 添加偏差率表格
df3 = df3.T
df3 = df3.reset_index()
data = df3.values.tolist()
col_width = 500/len(df3.columns)
content.append(Graphs.draw_table(col_width, *data))
content.append(Graphs.draw_little_title('上一周预测准确率：'))
df4 = sqlitedb.select_data('accuracy_rote', order_by='结束日期 desc', limit=1)
df4 = df4.T
df4 = df4.reset_index()
df4 = df4.T
data = df4.values.tolist()
col_width = 500/len(df4.columns)
content.append(Graphs.draw_table(col_width, *data))
content.append(Graphs.draw_little_title('三、预测过程解析：'))
# 特征、模型、参数配置
content.append(Graphs.draw_little_title('模型选择：'))
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：'))
content.append(Graphs.draw_text(f'使用40天的数据预测未来{inputsize}天的数据。'))
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:
for line in f.readlines():
content.append(Graphs.draw_text(line))
data = pd.read_csv(os.path.join(config.dataset, '指标数据添加时间特征.csv'),
encoding='utf-8') # 计算相关系数用
df_zhibiaofenlei = loadcsv(os.path.join(
config.dataset,'特征处理后的指标名称及分类.csv')) # 气泡图用
df_zhibiaoshuju = data.copy() # 气泡图用
# 绘制特征相关气泡图
grouped = df_zhibiaofenlei.groupby('指标分类')
grouped_corr = pd.DataFrame(columns=['指标分类', '指标数量', '相关性总和'])
content.append(Graphs.draw_little_title('按指标分类分别与预测目标进行皮尔逊相关系数分析：'))
content.append(Graphs.draw_text('''皮尔逊相关系数说明：'''))
content.append(Graphs.draw_text('''衡量两个特征之间的线性相关性。'''))
content.append(Graphs.draw_text('''
相关系数为1：表示两个变量之间存在完全正向的线性关系，即当一个变量增加时，另一个变量也相应增加，且变化是完全一致的。'''))
content.append(Graphs.draw_text(
'''相关系数为-1：表示两个变量之间存在完全负向的线性关系，即当一个变量增加时，另一个变量会相应减少，且变化是完全相反的'''))
content.append(Graphs.draw_text(
'''相关系数接近0：表示两个变量之间不存在线性关系，即它们的变化不会随着对方的变化而变化。'''))
for name, group in grouped:
cols = group['指标名称'].tolist()
config.logger.info(f'开始绘制{name}类指标的相关性直方图')
cols_subset = cols
feature_names = ['y'] + cols_subset
correlation_matrix = df_zhibiaoshuju[feature_names].corr()['y']
# 绘制特征相关性直方分布图
plt.figure(figsize=(10, 8))
sns.histplot(correlation_matrix.values.flatten(),
bins=20, kde=True, color='skyblue')
plt.title(f'{name}类指标(共{len(cols_subset)}个)相关性直方分布图')
plt.xlabel('相关系数')
plt.ylabel('频数')
plt.savefig(os.path.join(
config.dataset,f'{name}类指标相关性直方分布图.png'), bbox_inches='tight')
plt.close()
content.append(Graphs.draw_img(
os.path.join(config.dataset, f'{name}类指标相关性直方分布图.png')))
content.append(Graphs.draw_text(
f'{name}类指标(共{len(cols_subset)}个)的相关性直方分布图如上所示。'))
# 相关性大于0的特征
positive_corr_features = correlation_matrix[correlation_matrix > 0].sort_values(
ascending=False).index.tolist()[1:]
print(f'{name}下正相关的特征值有：', positive_corr_features)
if len(positive_corr_features) > 5:
positive_corr_features = positive_corr_features[0:5]
content.append(Graphs.draw_text(
f'{name}类指标中，与预测目标y正相关前五的特征有：{positive_corr_features}'))
draw_feature_trend(feature_data_df, positive_corr_features)
elif len(positive_corr_features) == 0:
pass
else:
positive_corr_features = positive_corr_features
content.append(Graphs.draw_text(
f'其中，与预测目标y正相关的特征有：{positive_corr_features}'))
draw_feature_trend(feature_data_df, positive_corr_features)
# 相关性小于0的特征
negative_corr_features = correlation_matrix[correlation_matrix < 0].sort_values(
ascending=True).index.tolist()
print(f'{name}下负相关的特征值有：', negative_corr_features)
if len(negative_corr_features) > 5:
negative_corr_features = negative_corr_features[:5]
content.append(Graphs.draw_text(
f'与预测目标y负相关前五的特征有：{negative_corr_features}'))
draw_feature_trend(feature_data_df, negative_corr_features)
elif len(negative_corr_features) == 0:
pass
else:
content.append(Graphs.draw_text(
f'{name}类指标中，与预测目标y负相关的特征有：{negative_corr_features}'))
draw_feature_trend(feature_data_df, negative_corr_features)
# 计算correlation_sum 第一行的相关性的绝对值的总和
correlation_sum = correlation_matrix.abs().sum()
config.logger.info(f'{name}类指标的相关性总和为：{correlation_sum}')
# 分组的相关性总和拼接到grouped_corr
goup_corr = pd.DataFrame(
{'指标分类': [name], '指标数量': [len(cols_subset)], '相关性总和': [correlation_sum]})
grouped_corr = pd.concat(
[grouped_corr, goup_corr], axis=0, ignore_index=True)
# 绘制相关性总和的气泡图
config.logger.info(f'开始绘制相关性总和的气泡图')
plt.figure(figsize=(10, 10))
sns.scatterplot(data=grouped_corr, x='相关性总和', y='指标数量', size='相关性总和', sizes=(
grouped_corr['相关性总和'].min()*5, grouped_corr['相关性总和'].max()*5), hue='指标分类', palette='viridis')
plt.title('指标分类相关性总和的气泡图')
plt.ylabel('数量')
plt.savefig(os.path.join(config.dataset, '指标分类相关性总和的气泡图.png'),
bbox_inches='tight')
plt.close()
content.append(Graphs.draw_img(os.path.join(config.dataset, '指标分类相关性总和的气泡图.png')))
content.append(Graphs.draw_text(
'气泡图中，横轴为指标分类，纵轴为指标分类下的特征数量，气泡的面积越大表示该分类中特征的相关系数和越大。'))
config.logger.info(f'绘制相关性总和的气泡图结束')
content.append(Graphs.draw_little_title('模型选择：'))
content.append(Graphs.draw_text(
f'预测使用了{num_models}个模型进行训练拟合，通过评估指标MAE从小到大排列，前5个模型的简介如下：'))
# 读取模型简介
with open(os.path.join(config.dataset, 'model_introduction.txt'), 'r', encoding='utf-8') as f:
for line in f:
line_split = line.strip().split('--')
if line_split[0] in fivemodels_list:
for introduction in line_split:
content.append(Graphs.draw_text(introduction))
content.append(Graphs.draw_little_title('模型评估：'))
df = pd.read_csv(os.path.join(
config.dataset,'model_evaluation.csv'), encoding='utf-8')
# 判断 df 的数值列转为float
for col in eval_df.columns:
if col not in ['模型(Model)']:
eval_df[col] = eval_df[col].astype(float)
eval_df[col] = eval_df[col].round(3)
# 筛选 fivemodels_list.tolist() 的行
eval_df = eval_df[eval_df['模型(Model)'].isin(fivemodels_list)]
# df转置
eval_df = eval_df.T
# df重置索引
eval_df = eval_df.reset_index()
eval_df = eval_df.T
# # 添加表格
data = eval_df.values.tolist()
col_width = 500/len(eval_df.columns)
content.append(Graphs.draw_table(col_width, *data))
content.append(Graphs.draw_text('评估指标释义：'))
content.append(Graphs.draw_text(
'1. 均方根误差(RMSE)：均方根误差是衡量预测值与实际值之间误差的一种方法，取值越小，误差越小，预测效果越好。'))
content.append(Graphs.draw_text(
'2. 平均绝对误差(MAE)：平均绝对误差是衡量预测值与实际值之间误差的一种方法，取值越小，误差越小，预测效果越好。'))
content.append(Graphs.draw_text(
'3. 平均平方误差(MSE)：平均平方误差是衡量预测值与实际值之间误差的一种方法，取值越小，误差越小，预测效果越好。'))
content.append(Graphs.draw_text('模型拟合：'))
# 添加图片
content.append(Graphs.draw_img(os.path.join(config.dataset, '预测值与真实值对比图.png')))
# 生成pdf文件
doc = SimpleDocTemplate(os.path.join(config.dataset, reportname), pagesize=letter)
doc.build(content)
# pdf 上传到数字化信息平台
try:
if config.is_update_report:
with open(os.path.join(config.dataset, reportname), 'rb') as f:
base64_data = base64.b64encode(f.read()).decode('utf-8')
upload_data["data"]["fileBase64"] = base64_data
upload_data["data"]["fileName"] = reportname
token = get_head_auth_report()
upload_report_data(token, upload_data)
except TimeoutError as e:
print(f"请求超时: {e}")
@exception_logger @exception_logger
def pp_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, inputsize=5, dataset='dataset', time='2024-07-30', reportname='report.pdf', sqlitedb='jbsh_yuanyou.db'): def pp_export_pdf(num_indicators=475, num_models=21, num_dayindicator=202, inputsize=5, dataset='dataset', time='2024-07-30', reportname='report.pdf', sqlitedb='jbsh_yuanyou.db'):
# 创建内容对应的空列表 # 创建内容对应的空列表

667
test/ETA获取数据.py
View File

File diff suppressed because it is too large Load Diff

BIN
成品油eta数据.xlsx
View File

Binary file not shown.

BIN
沥青eta数据.xlsx
View File

Binary file not shown.