123 lines
5.6 KiB
Python
123 lines
5.6 KiB
Python
|
# 读取配置
|
||
|
|
from config_jingbo import *
|
||
|
|
from lib.tools import *
|
||
|
|
from lib.dataread import *
|
||
|
|
from models.nerulforcastmodels import ex_Model,model_losss,brent_export_pdf
|
||
|
|
from models.lstmmodels import ex_Lstm_M,ex_Lstm
|
||
|
|
from models.grumodels import ex_GRU
|
||
|
|
import glob
|
||
|
|
import torch
|
||
|
|
torch.set_float32_matmul_precision("high")
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
signature = BinanceAPI(APPID, SECRET)
|
||
|
|
|
||
|
|
# 遍历参数训练模型
|
||
|
|
input_size_list = [14]
|
||
|
|
horizon_list = [7]
|
||
|
|
train_steps_list = [500,1000,1500,2000]
|
||
|
|
k_list = [10,18,25,50,100]
|
||
|
|
end_time_list = ['2024-07-03']
|
||
|
|
is_debug = False
|
||
|
|
is_fivemodels = False # 是否使用之前保存的最佳的5个模型
|
||
|
|
delweekenday = True
|
||
|
|
# 组合上面三个参数
|
||
|
|
for i in range(len(input_size_list)):
|
||
|
|
for h in range(len(horizon_list)):
|
||
|
|
for j in range(len(train_steps_list)):
|
||
|
|
for k in range(len(k_list)):
|
||
|
|
for end_time in end_time_list:
|
||
|
|
input_size = input_size_list[i]
|
||
|
|
horizons = horizon_list[h]
|
||
|
|
train_steps = train_steps_list[j]
|
||
|
|
K = k_list[k]
|
||
|
|
settings = f'{input_size}-{horizon_list[h]}-{train_steps}-{K}-{data_set}-{end_time}-{y}'
|
||
|
|
logger.info(f'当前配置：{settings}')
|
||
|
|
|
||
|
|
# 获取数据
|
||
|
|
if is_eta:
|
||
|
|
etadata = EtaReader(signature=signature,
|
||
|
|
classifylisturl = classifylisturl,
|
||
|
|
classifyidlisturl=classifyidlisturl,
|
||
|
|
edbcodedataurl=edbcodedataurl,
|
||
|
|
edbcodelist=edbcodelist
|
||
|
|
)
|
||
|
|
df = etadata.get_eta_api_data(data_set=data_set,dataset=dataset) # 原始数据，未处理
|
||
|
|
else:
|
||
|
|
filename = os.path.join(dataset,data_set)
|
||
|
|
logger.info(f'未启用Eta数据,将读取本地数据{filename}')
|
||
|
|
df = pd.read_excel(filename,sheet_name='指标数据')
|
||
|
|
|
||
|
|
# 数据处理
|
||
|
|
df = datachuli(df=df,dataset=dataset,end_time=end_time,y=y,delweekenday=delweekenday)
|
||
|
|
|
||
|
|
if is_timefurture:
|
||
|
|
df = addtimecharacteristics(df=df,dataset=dataset)
|
||
|
|
|
||
|
|
# 更改预测列名称
|
||
|
|
df.rename(columns={y:'y'},inplace=True)
|
||
|
|
|
||
|
|
logger.info(f"开始训练模型...")
|
||
|
|
row,col = df.shape
|
||
|
|
logger.info(f'当前配置：{settings}')
|
||
|
|
# 获取日期时间 计算今天日期 %Y-%m-%d-%H-%M-%S
|
||
|
|
from datetime import datetime
|
||
|
|
now = datetime.now().strftime('%Y-%m-%d-%H-%M-%S')
|
||
|
|
ex_Model(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
|
||
|
|
)
|
||
|
|
|
||
|
|
# 模型评估
|
||
|
|
model_results3 = model_losss(df,dataset=dataset,horizon=horizon)
|
||
|
|
# 模型报告
|
||
|
|
|
||
|
|
reportname = f'{settings}--{now}-预测报告.pdf' # 报告文件名
|
||
|
|
reportname = reportname.replace(':', '-') # 替换冒号
|
||
|
|
title = f'{settings}--{now}-预测报告' # 报告标题
|
||
|
|
brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time,
|
||
|
|
reportname=reportname),
|
||
|
|
|
||
|
|
# 发送邮件
|
||
|
|
m = SendMail(
|
||
|
|
username=username,
|
||
|
|
passwd=passwd,
|
||
|
|
recv=recv,
|
||
|
|
title=title,
|
||
|
|
content=content,
|
||
|
|
file=max(glob.glob(os.path.join(dataset,reportname)), key=os.path.getctime),
|
||
|
|
ssl=ssl,
|
||
|
|
)
|
||
|
|
# m.send_mail()
|
||
|
|
|
||
|
|
# # 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()
|