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

整理代码

Browse Source
This commit is contained in:
workpc 2024-12-19 09:23:27 +08:00
parent 98c24327ee
commit 1ddbd5badc
2 changed files with 30 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
config_jingbo.py
View File

@ -250,9 +250,9 @@ 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 = 'Brent连1合约价格' # 原油指标数据的目标变量 Brent连1合约价格 Brent活跃合约
# y = '期货结算价(连续):布伦特原油:前一个观测值' # ineoil的目标变量
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
@ -267,10 +267,12 @@ k = 100 # 特征筛选数量，如果是0或者值比特征数量大，代表全
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 = '原油指标数据.xlsx' # 数据集文件
# data_set = 'INE_OIL(1).csv'
### 文件夹
dataset = 'yuanyoudataset' # 数据集文件夹
# 数据库名称

15
models/nerulforcastmodels.py
View File

@ -495,28 +495,30 @@ def model_losss(sqlitedb,end_time):
df['ACCURACY'] = df.apply(calculate_accuracy, axis=1)
# df['ACCURACY'] = df.apply(is_within_range, axis=1)
# 取结束日期上一周的日期
def get_week_date(end_time):
endtime = end_time
endtimeweek = datetime.datetime.strptime(endtime, '%Y-%m-%d')
up_week = endtimeweek - datetime.timedelta(days=endtimeweek.weekday() + 14)
up_week_dates = [up_week + datetime.timedelta(days=i) for i in range(14)][4:-2]
up_week_dates = [date.strftime('%Y-%m-%d') for date in up_week_dates]
#
return up_week_dates
up_week_dates = get_week_date(end_time)
# 计算准确率并保存结果
def _get_accuracy_rate(df,up_week_dates,endtime):
df3 = df.copy()
df3 = df3[df3['CREAT_DATE'].isin(up_week_dates)]
df3 = df3[df3['ds'].isin(up_week_dates)]
# df3.to_csv(os.path.join(dataset,f'accuracy_{endtime}.csv'),index=False)
total = len(df3)
accuracy_rote = 0
# 设置权重字典
weight_dict = [0.4,0.15,0.1,0.1,0.25]
for i,group in df3.groupby('ds'):
print('权重：',weight_dict[len(group)-1])
print('准确率：',(group['ACCURACY'].sum()/len(group))*weight_dict[len(group)-1])
accuracy_rote += (group['ACCURACY'].sum()/len(group))*weight_dict[len(group)-1]
df3.to_csv(os.path.join(dataset,f'accuracy_{endtime}.csv'),index=False)
df4 = pd.DataFrame(columns=['开始日期','结束日期','准确率'])
df4.loc[len(df4)] = {'开始日期':up_week_dates[0],'结束日期':up_week_dates[-1],'准确率':accuracy_rote}
print(df4)
df4.to_sql("accuracy_rote", con=sqlitedb.connection, if_exists='append', index=False)
_get_accuracy_rate(df,up_week_dates,end_time)
def _add_abs_error_rate():
# 计算每个预测值与真实值之间的偏差率
@ -534,7 +536,6 @@ def model_losss(sqlitedb,end_time):
# 将最小偏差率对应的模型的预测值添加到DataFrame中
df_combined3['min_abs_error_rate_prediction'] = min_abs_error_rate_predictions
df_combined3['min_abs_error_rate_column_name'] = min_abs_error_rate_column_name
# _add_abs_error_rate()
# 判断 df 的数值列转为float