02121309

common/database_dml.py

@@ -175,7 +175,7 @@ def insert_h5_model_into_mongo(model,feature_scaler_bytes,target_scaler_bytes ,a
     })
     print("模型成功保存到 MongoDB！")
 
-def insert_trained_model_into_mongo(model ,args):
+def insert_trained_model_into_mongo(model, args):
     mongodb_connection,mongodb_database,model_table,model_name = ("mongodb://root:sdhjfREWFWEF23e@192.168.1.43:30000/",
                                 args['mongodb_database'],args['model_table'],args['model_name'])
 
@@ -204,7 +204,7 @@ def insert_trained_model_into_mongo(model ,args):
     })
     print("模型成功保存到 MongoDB！")
 
-def insert_scaler_model_into_mongo(feature_scaler_bytes, args):
+def insert_scaler_model_into_mongo(feature_scaler_bytes, scaled_target_bytes, args):
     mongodb_connection,mongodb_database,scaler_table,model_table,model_name = ("mongodb://root:sdhjfREWFWEF23e@192.168.1.43:30000/",
                                 args['mongodb_database'],args['scaler_table'],args['model_table'],args['model_name'])
     client = MongoClient(mongodb_connection)
@@ -216,6 +216,7 @@ def insert_scaler_model_into_mongo(feature_scaler_bytes, args):
     # Save the scalers in MongoDB as binary data
     collection.insert_one({
         "feature_scaler": feature_scaler_bytes.read(),
+        "target_scaler": scaled_target_bytes.read()
     })
     print("scaler_model inserted successfully!")
 
@@ -246,7 +247,7 @@ def get_h5_model_from_mongo(args):
         return None
 
 
-def get_scaler_model_from_mongo(args):
+def get_scaler_model_from_mongo(args, feature_scaler=False):
     mongodb_connection, mongodb_database, scaler_table, = ("mongodb://root:sdhjfREWFWEF23e@192.168.1.43:30000/",
                                                            args['mongodb_database'], args['scaler_table'])
     client = MongoClient(mongodb_connection)
@@ -259,6 +260,8 @@ def get_scaler_model_from_mongo(args):
 
     feature_scaler_bytes = BytesIO(scaler_doc["feature_scaler"])
     feature_scaler = joblib.load(feature_scaler_bytes)
+    if feature_scaler:
+        return feature_scaler
     target_scaler_bytes = BytesIO(scaler_doc["target_scaler"])
     target_scaler = joblib.load(target_scaler_bytes)
     return feature_scaler,target_scaler

data_processing/data_operation/data_handler.py

@@ -4,10 +4,12 @@
 # @Time      :2025/1/8 14:56
 # @Author    :David
 # @Company: shenyang JY
-import argparse
+import argparse, numbers, joblib
 import pandas as pd
-from pyexpat import features
-
+from io import BytesIO
+from bson.decimal128 import Decimal128
+from sklearn.preprocessing import MinMaxScaler
+from common.processing_data_common import missing_features, str_to_list
 from common.data_cleaning import *
 
 class DataHandler(object):
@@ -40,7 +42,33 @@ class DataHandler(object):
 
         return train_x, valid_x, train_y, valid_y
 
-    def get_timestep_features(self, norm_data, col_time, features, target, is_train):   # 这段代码基于pandas方法的优化
+    def get_predict_data(self, dfs, features):
+        test_x = []
+        for i, df in enumerate(dfs, start=1):
+            if len(df) < self.opt.Model["time_step"]:
+                self.logger.info("特征处理-预测数据-不满足time_step")
+                continue
+            datax = self.get_predict_features(df, features)
+            test_x.extend(datax)
+
+        test_x = [np.array([x[0].values for x in test_x]), np.array([x[1].values for x in test_x])]
+        return test_x
+
+    def get_predict_features(self, norm_data, features):
+        """
+        均分数据，获取预测数据集
+        """
+        time_step = self.opt.Model["time_step"]
+        feature_data = norm_data.reset_index(drop=True)
+        time_step_loc = time_step - 1
+        iters = int(len(feature_data)) / self.opt.Model['time_step']
+        features_x = np.array([feature_data.loc[i*time_step:i*time_step + time_step_loc, features].reset_index(drop=True) for i in range(iters)])
+        return features_x
+
+    def get_timestep_features(self, norm_data, col_time, features, target, is_train):
+        """
+        步长分割数据，获取时序训练集
+        """
         time_step = self.opt.Model["time_step"]
         feature_data = norm_data.reset_index(drop=True)
         time_step_loc = time_step - 1
@@ -56,6 +84,9 @@ class DataHandler(object):
         return features_x, features_y
 
     def fill_train_data(self, unite, col_time):
+        """
+        补值
+        """
         unite[col_time] = pd.to_datetime(unite[col_time])
         unite['time_diff'] = unite[col_time].diff()
         dt_short = pd.Timedelta(minutes=15)
@@ -122,3 +153,69 @@ class DataHandler(object):
                 vx.append(data[0])
                 vy.append(data[1])
         return tx, vx, ty, vy
+
+    def train_data_handler(self, data, opt):
+        """
+        训练数据预处理：
+        清洗+补值+归一化
+        Args:
+            data: 从mongo中加载的数据
+            opt：参数命名空间
+        return:
+            x_train
+            x_valid
+            y_train
+            y_valid
+        """
+        col_time, features, target = opt.col_time, opt.features, opt.target
+        # 清洗处理好的限电记录
+        if 'is_limit' in data.columns:
+            data = data[data['is_limit'] == False]
+        # 筛选特征，数值化
+        train_data = data[[col_time] + features + [target]]
+        # 清洗特征平均缺失率大于20%的天
+        # train_data = missing_features(train_data, features, col_time)
+        train_data = train_data.sort_values(by=col_time)
+        # train_data = train_data.sort_values(by=col_time).fillna(method='ffill').fillna(method='bfill')
+        # 对清洗完限电的数据进行特征预处理：1.空值异常值清洗 2.缺值补值
+        train_data_cleaned = key_field_row_cleaning(train_data, features + [target], self.logger)
+        train_data_cleaned = train_data_cleaned.applymap(
+            lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x, numbers.Number) else x)
+        # 创建特征和目标的标准化器
+        train_scaler = MinMaxScaler(feature_range=(0, 1))
+        target_scaler = MinMaxScaler(feature_range=(0, 1))
+        # 标准化特征和目标
+        scaled_train_data = train_scaler.fit_transform(train_data_cleaned[features])
+        scaled_target = target_scaler.fit_transform(train_data[[target]])
+        train_data_cleaned[features] = scaled_train_data
+        train_data_cleaned[[target]] = scaled_target
+        train_datas = self.fill_train_data(train_data_cleaned, col_time)
+        # 保存两个scaler
+        scaled_train_bytes = BytesIO()
+        scaled_target_bytes = BytesIO()
+
+        joblib.dump(scaled_train_data, scaled_train_bytes)
+        joblib.dump(scaled_target, scaled_target_bytes)
+        scaled_train_bytes.seek(0)  # Reset pointer to the beginning of the byte stream
+        scaled_target_bytes.seek(0)
+
+        train_x, valid_x, train_y, valid_y = self.get_train_data(train_datas, col_time, features, target)
+        return train_x, valid_x, train_y, valid_y, scaled_train_bytes, scaled_target_bytes
+
+    def pre_data_handler(self, data, feature_scaler, args):
+        """
+        预测数据简单处理
+        Args:
+            data: 从mongo中加载的数据
+            opt：参数命名空间
+        return:
+            scaled_features: 反归一化的特征
+        """
+        if 'is_limit' in data.columns:
+            data = data[data['is_limit'] == False]
+        features, time_steps, col_time, model_name, col_reserve = str_to_list(args['features']), int(
+            args['time_steps']), args['col_time'], args['model_name'], str_to_list(args['col_reserve'])
+        pre_data = data.sort_values(by=col_time)
+        scaled_features = feature_scaler.transform(pre_data[features])
+        pre_x = self.get_predict_data([scaled_features], features)
+        return pre_x

models_processing/model_koi/nn_bp.py

@@ -1,259 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-# time: 2024/5/6 13:25
-# file: time_series.py
-# author: David
-# company: shenyang JY
-import json, copy
-import numpy as np
-from flask import Flask, request
-import time
-import traceback
-import logging, argparse
-from sklearn.preprocessing import MinMaxScaler
-from io import BytesIO
-import joblib
-from tensorflow.keras.layers import Input, Dense, LSTM, concatenate, Conv1D, Conv2D, MaxPooling1D, Reshape, Flatten
-from tensorflow.keras.models import Model, load_model
-from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, TensorBoard, ReduceLROnPlateau
-from tensorflow.keras import optimizers, regularizers
-import tensorflow.keras.backend as K
-import tensorflow as tf
-from bson.decimal128 import Decimal128
-from common.data_cleaning import cleaning, key_field_row_cleaning
-from common.database_dml import *
-from common.processing_data_common import missing_features, str_to_list
-from data_processing.data_operation.data_handler import DataHandler
-from threading import Lock
-import time, yaml
-import random, numbers
-import matplotlib.pyplot as plt
-model_lock = Lock()
-from common.logs import Log
-logger = logging.getLogger()
-# logger = Log('models-processing').logger
-np.random.seed(42)  # NumPy随机种子
-# tf.set_random_seed(42)  # TensorFlow随机种子
-app = Flask('nn_bp——service')
-
-with app.app_context():
-    with open('../model_koi/bp.yaml', 'r', encoding='utf-8') as f:
-        arguments = yaml.safe_load(f)
-
-dh = DataHandler(logger, arguments)
-def train_data_handler(data, opt):
-    """
-    训练数据预处理：
-    清洗+补值+归一化
-    Aras:
-        data: 从mongo中加载的数据
-        opt：参数命名空间
-    return:
-        x_train
-        x_valid
-        y_train
-        y_valid
-    """
-    col_time, features, target = opt.col_time, opt.features, opt.target
-    # 清洗处理好的限电记录
-    if 'is_limit' in data.columns:
-        data = data[data['is_limit'] == False]
-    # 筛选特征，数值化
-    train_data = data[[col_time]+features+[target]]
-    # 清洗特征平均缺失率大于20%的天
-    train_data = missing_features(train_data, features, col_time)
-    train_data = train_data.sort_values(by=col_time)
-    # train_data = train_data.sort_values(by=col_time).fillna(method='ffill').fillna(method='bfill')
-    # 对清洗完限电的数据进行特征预处理：1.空值异常值清洗 2.缺值补值
-    train_data_cleaned = key_field_row_cleaning(train_data, features+[target], logger)
-    train_data_cleaned = train_data_cleaned.applymap(lambda x: float(x.to_decimal()) if isinstance(x, Decimal128) else float(x) if isinstance(x, numbers.Number) else x)
-    # 创建特征和目标的标准化器
-    train_scaler = MinMaxScaler(feature_range=(0, 1))
-    # 标准化特征和目标
-    scaled_train_data = train_scaler.fit_transform(train_data_cleaned[features+[target]])
-    train_data_cleaned[features+[target]] = scaled_train_data
-    train_datas = dh.fill_train_data(train_data_cleaned, col_time)
-    # 保存两个scaler
-    scaled_train_bytes = BytesIO()
-    joblib.dump(scaled_train_data, scaled_train_bytes)
-    scaled_train_bytes.seek(0)  # Reset pointer to the beginning of the byte stream
-    train_x, valid_x, train_y, valid_y = dh.get_train_data(train_datas, col_time, features, target)
-    return train_x, valid_x, train_y, valid_y, scaled_train_bytes
-
-def pre_data_handler(data, args):
-    if 'is_limit' in data.columns:
-        data = data[data['is_limit'] == False]
-    features, time_steps, col_time, model_name,col_reserve =  str_to_list(args['features']), int(args['time_steps']),args['col_time'],args['model_name'],str_to_list(args['col_reserve'])
-    feature_scaler,target_scaler = get_scaler_model_from_mongo(args)
-    pre_data = data.sort_values(by=col_time)
-    scaled_features = feature_scaler.transform(pre_data[features])
-    return scaled_features
-
-class BPHandler(object):
-    def __init__(self, logger):
-        self.logger = logger
-        self.model = None
-
-    def get_model(self, args):
-        """
-        单例模式+线程锁，防止在异步加载时引发线程安全
-        """
-        try:
-            with model_lock:
-                # NPHandler.model = NPHandler.get_keras_model(opt)
-                self.model = get_h5_model_from_mongo(args)
-        except Exception as e:
-            self.logger.info("加载模型权重失败:{}".format(e.args))
-
-    @staticmethod
-    def get_keras_model(opt):
-        # db_loss = NorthEastLoss(opt)
-        # south_loss = SouthLoss(opt)
-        from models_processing.losses.loss_cdq import rmse
-        l1_reg = regularizers.l1(opt.Model['lambda_value_1'])
-        l2_reg = regularizers.l2(opt.Model['lambda_value_2'])
-        nwp_input = Input(shape=(opt.Model['time_step'], opt.Model['input_size']), name='nwp')
-
-        con1 = Conv1D(filters=64, kernel_size=1, strides=1, padding='valid', activation='relu', kernel_regularizer=l2_reg)(nwp_input)
-        d1 = Dense(32, activation='relu', name='d1', kernel_regularizer=l1_reg)(con1)
-        nwp = Dense(8, activation='relu', name='d2', kernel_regularizer=l1_reg)(d1)
-
-        output = Dense(1, name='d5')(nwp)
-        output_f = Flatten()(output)
-        model = Model(nwp_input, output_f)
-        adam = optimizers.Adam(learning_rate=opt.Model['learning_rate'], beta_1=0.9, beta_2=0.999, epsilon=1e-7, amsgrad=True)
-        reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.01, patience=5, verbose=1)
-        model.compile(loss=rmse, optimizer=adam)
-        return model
-
-    def train_init(self, opt):
-        try:
-            if opt.Model['add_train']:
-                # 进行加强训练，支持修模
-                base_train_model = get_h5_model_from_mongo(vars(opt))
-                base_train_model.summary()
-                self.logger.info("已加载加强训练基础模型")
-            else:
-                base_train_model = self.get_keras_model(opt)
-            return base_train_model
-        except Exception as e:
-            self.logger.info("加强训练加载模型权重失败:{}".format(e.args))
-
-    def training(self, opt, train_and_valid_data):
-        model = self.train_init(opt)
-        # tf.reset_default_graph() # 清除默认图
-        train_x, train_y, valid_x, valid_y = train_and_valid_data
-        print("----------", np.array(train_x[0]).shape)
-        print("++++++++++", np.array(train_x[1]).shape)
-        model.summary()
-        check_point = ModelCheckpoint(filepath='./var/' + 'fmi.h5', monitor='val_loss',  save_best_only=True, mode='auto')
-        early_stop = EarlyStopping(monitor='val_loss', patience=opt.Model['patience'], mode='auto')
-        history = model.fit(train_x, train_y, batch_size=opt.Model['batch_size'], epochs=opt.Model['epoch'], verbose=2,  validation_data=(valid_x, valid_y), callbacks=[check_point, early_stop], shuffle=False)
-        loss = np.round(history.history['loss'], decimals=5)
-        val_loss = np.round(history.history['val_loss'], decimals=5)
-        self.logger.info("-----模型训练经过{}轮迭代-----".format(len(loss)))
-        self.logger.info("训练集损失函数为：{}".format(loss))
-        self.logger.info("验证集损失函数为：{}".format(val_loss))
-        return model
-
-    def predict(self, test_x, batch_size=1):
-        result = self.model.predict(test_x, batch_size=batch_size)
-        self.logger.info("执行预测方法")
-        return result
-
-@app.route('/nn_bp_training', methods=['POST'])
-def model_training_bp():
-    # 获取程序开始时间
-    start_time = time.time()
-    result = {}
-    success = 0
-    bp = BPHandler(logger)
-    print("Program starts execution!")
-    args_dict = request.values.to_dict()
-    args = arguments.deepcopy()
-    args.update(args_dict)
-    try:
-        opt = argparse.Namespace(**args)
-        logger.info(args_dict)
-        train_data = get_data_from_mongo(args_dict)
-        train_x, valid_x, train_y, valid_y, scaled_train_bytes = train_data_handler(train_data, opt)
-        bp_model = bp.training(opt, [train_x, valid_x, train_y, valid_y])
-        args_dict['params'] = json.dumps(args)
-        args_dict['gen_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
-        insert_trained_model_into_mongo(bp_model, args_dict)
-        insert_scaler_model_into_mongo(scaled_train_bytes, args_dict)
-        success = 1
-    except Exception as e:
-        my_exception = traceback.format_exc()
-        my_exception.replace("\n", "\t")
-        result['msg'] = my_exception
-    end_time = time.time()
-
-    result['success'] = success
-    result['args'] = args
-    result['start_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(start_time))
-    result['end_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(end_time))
-    print("Program execution ends!")
-    return result
-
-
-@app.route('/nn_bp_predict', methods=['POST'])
-def model_prediction_bp():
-    # 获取程序开始时间
-    start_time = time.time()
-    result = {}
-    success = 0
-    bp = BPHandler(logger)
-    print("Program starts execution!")
-    params_dict = request.values.to_dict()
-    args = arguments.deepcopy()
-    args.update(params_dict)
-    try:
-        print('args', args)
-        logger.info(args)
-        predict_data = get_data_from_mongo(args)
-        scaled_features = pre_data_handler(predict_data, args)
-        bp.get_model(args)
-        result = bp.predict(scaled_features, args)
-        insert_data_into_mongo(result, args)
-        success = 1
-    except Exception as e:
-        my_exception = traceback.format_exc()
-        my_exception.replace("\n", "\t")
-        result['msg'] = my_exception
-    end_time = time.time()
-
-    result['success'] = success
-    result['args'] = args
-    result['start_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(start_time))
-    result['end_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(end_time))
-    print("Program execution ends!")
-    return result
-
-if __name__ == "__main__":
-    print("Program starts execution!")
-    logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-    logger = logging.getLogger("model_training_bp log")
-    from waitress import serve
-
-    # serve(app, host="0.0.0.0", port=10103, threads=4)
-    print("server start!")
-
-    bp = BPHandler(logger)
-    args_dict = {"mongodb_database": 'david_test', 'scaler_table': 'j00083_scaler', 'model_name': 'bp1.0.test',
-    'model_table': 'j00083_model', 'mongodb_read_table': 'j00083', 'col_time': 'dateTime',
-    'features': 'speed10,direction10,speed30,direction30,speed50,direction50,speed70,direction70,speed90,direction90,speed110,direction110,speed150,direction150,speed170,direction170'}
-    args_dict['features'] = args_dict['features'].split(',')
-    arguments.update(args_dict)
-    opt = argparse.Namespace(**arguments)
-    opt.Model['input_size'] = len(opt.features)
-    train_data = get_data_from_mongo(args_dict)
-    train_x, valid_x, train_y, valid_y, scaled_train_bytes = train_data_handler(train_data, opt)
-
-    bp_model = bp.training(opt, [train_x, train_y, valid_x, valid_y])
-
-    args_dict['gen_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
-    args_dict['params'] = arguments
-    args_dict['descr'] = '测试'
-    insert_trained_model_into_mongo(bp_model, args_dict)
-    insert_scaler_model_into_mongo(scaled_train_bytes, args_dict)

models_processing/model_koi/tf_bp.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+# @FileName  :nn_bp.py
+# @Time      :2025/2/12 10:41
+# @Author    :David
+# @Company: shenyang JY
+
+
+from tensorflow.keras.layers import Input, Dense, LSTM, concatenate, Conv1D, Conv2D, MaxPooling1D, Reshape, Flatten
+from tensorflow.keras.models import Model, load_model
+from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping, TensorBoard, ReduceLROnPlateau
+from tensorflow.keras import optimizers, regularizers
+import numpy as np
+from common.database_dml import *
+from threading import Lock
+model_lock = Lock()
+
+class BPHandler(object):
+    def __init__(self, logger):
+        self.logger = logger
+        self.model = None
+
+    def get_model(self, args):
+        """
+        单例模式+线程锁，防止在异步加载时引发线程安全
+        """
+        try:
+            with model_lock:
+                # NPHandler.model = NPHandler.get_keras_model(opt)
+                self.model = get_h5_model_from_mongo(args)
+        except Exception as e:
+            self.logger.info("加载模型权重失败:{}".format(e.args))
+
+    @staticmethod
+    def get_keras_model(opt):
+        # db_loss = NorthEastLoss(opt)
+        # south_loss = SouthLoss(opt)
+        from models_processing.losses.loss_cdq import rmse
+        l1_reg = regularizers.l1(opt.Model['lambda_value_1'])
+        l2_reg = regularizers.l2(opt.Model['lambda_value_2'])
+        nwp_input = Input(shape=(opt.Model['time_step'], opt.Model['input_size']), name='nwp')
+
+        con1 = Conv1D(filters=64, kernel_size=1, strides=1, padding='valid', activation='relu', kernel_regularizer=l2_reg)(nwp_input)
+        d1 = Dense(32, activation='relu', name='d1', kernel_regularizer=l1_reg)(con1)
+        nwp = Dense(8, activation='relu', name='d2', kernel_regularizer=l1_reg)(d1)
+
+        output = Dense(1, name='d5')(nwp)
+        output_f = Flatten()(output)
+        model = Model(nwp_input, output_f)
+        adam = optimizers.Adam(learning_rate=opt.Model['learning_rate'], beta_1=0.9, beta_2=0.999, epsilon=1e-7, amsgrad=True)
+        reduce_lr = ReduceLROnPlateau(monitor='val_loss', factor=0.01, patience=5, verbose=1)
+        model.compile(loss=rmse, optimizer=adam)
+        return model
+
+    def train_init(self, opt):
+        try:
+            if opt.Model['add_train']:
+                # 进行加强训练，支持修模
+                base_train_model = get_h5_model_from_mongo(vars(opt))
+                base_train_model.summary()
+                self.logger.info("已加载加强训练基础模型")
+            else:
+                base_train_model = self.get_keras_model(opt)
+            return base_train_model
+        except Exception as e:
+            self.logger.info("加强训练加载模型权重失败:{}".format(e.args))
+
+    def training(self, opt, train_and_valid_data):
+        model = self.train_init(opt)
+        # tf.reset_default_graph() # 清除默认图
+        train_x, train_y, valid_x, valid_y = train_and_valid_data
+        print("----------", np.array(train_x[0]).shape)
+        print("++++++++++", np.array(train_x[1]).shape)
+        model.summary()
+        check_point = ModelCheckpoint(filepath='./var/' + 'fmi.h5', monitor='val_loss',  save_best_only=True, mode='auto')
+        early_stop = EarlyStopping(monitor='val_loss', patience=opt.Model['patience'], mode='auto')
+        history = model.fit(train_x, train_y, batch_size=opt.Model['batch_size'], epochs=opt.Model['epoch'], verbose=2,  validation_data=(valid_x, valid_y), callbacks=[check_point, early_stop], shuffle=False)
+        loss = np.round(history.history['loss'], decimals=5)
+        val_loss = np.round(history.history['val_loss'], decimals=5)
+        self.logger.info("-----模型训练经过{}轮迭代-----".format(len(loss)))
+        self.logger.info("训练集损失函数为：{}".format(loss))
+        self.logger.info("验证集损失函数为：{}".format(val_loss))
+        return model
+
+    def predict(self, test_x, batch_size=1):
+        result = self.model.predict(test_x, batch_size=batch_size)
+        self.logger.info("执行预测方法")
+        return result
+
+
+if __name__ == "__main__":
+    run_code = 0

models_processing/model_koi/tf_bp_pre.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+# -*- coding:utf-8 -*-
+# @FileName  :nn_bp_pre.py
+# @Time      :2025/2/12 10:39
+# @Author    :David
+# @Company: shenyang JY
+import json, copy
+import numpy as np
+from flask import Flask, request
+import logging, argparse, traceback
+from common.database_dml import *
+from common.processing_data_common import missing_features, str_to_list
+from data_processing.data_operation.data_handler import DataHandler
+from threading import Lock
+import time, yaml
+model_lock = Lock()
+from itertools import chain
+from common.logs import Log
+from tf_bp import BPHandler
+# logger = Log('tf_bp').logger()
+logger = Log('tf_bp').logger
+np.random.seed(42)  # NumPy随机种子
+# tf.set_random_seed(42)  # TensorFlow随机种子
+app = Flask('tf_bp_pre——service')
+
+with app.app_context():
+    with open('../model_koi/bp.yaml', 'r', encoding='utf-8') as f:
+        arguments = yaml.safe_load(f)
+
+    dh = DataHandler(logger, arguments)
+    bp = BPHandler(logger)
+
+
+@app.route('/nn_bp_predict', methods=['POST'])
+def model_prediction_bp():
+    # 获取程序开始时间
+    start_time = time.time()
+    result = {}
+    success = 0
+    bp = BPHandler(logger)
+    print("Program starts execution!")
+    params_dict = request.values.to_dict()
+    args = arguments.deepcopy()
+    args.update(params_dict)
+    try:
+        print('args', args)
+        logger.info(args)
+        predict_data = get_data_from_mongo(args)
+        feature_scaler, target_scaler = get_scaler_model_from_mongo(args)
+        scaled_pre_x = dh.pre_data_handler(predict_data, feature_scaler, args)
+        bp.get_model(args)
+        # result = bp.predict(scaled_pre_x, args)
+        result = list(chain.from_iterable(target_scaler.inverse_transform([bp.predict(scaled_pre_x).flatten()])))
+        insert_data_into_mongo(result, args)
+        success = 1
+    except Exception as e:
+        my_exception = traceback.format_exc()
+        my_exception.replace("\n", "\t")
+        result['msg'] = my_exception
+    end_time = time.time()
+
+    result['success'] = success
+    result['args'] = args
+    result['start_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(start_time))
+    result['end_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(end_time))
+    print("Program execution ends!")
+    return result
+
+
+if __name__ == "__main__":
+    run_code = 0

models_processing/model_koi/tf_bp_train.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# time: 2024/5/6 13:25
+# file: time_series.py
+# author: David
+# company: shenyang JY
+import json, copy
+import numpy as np
+from flask import Flask, request
+import traceback
+import logging, argparse
+from data_processing.data_operation.data_handler import DataHandler
+import time, yaml
+from models_processing.model_koi.tf_bp import BPHandler
+from common.database_dml import *
+import matplotlib.pyplot as plt
+from common.logs import Log
+logger = logging.getLogger()
+# logger = Log('models-processing').logger
+np.random.seed(42)  # NumPy随机种子
+# tf.set_random_seed(42)  # TensorFlow随机种子
+app = Flask('tf_bp_train——service')
+
+with app.app_context():
+    with open('../model_koi/bp.yaml', 'r', encoding='utf-8') as f:
+        arguments = yaml.safe_load(f)
+
+    dh = DataHandler(logger, arguments)
+    bp = BPHandler(logger)
+
+@app.route('/nn_bp_training', methods=['POST'])
+def model_training_bp():
+    # 获取程序开始时间
+    start_time = time.time()
+    result = {}
+    success = 0
+    print("Program starts execution!")
+    args_dict = request.values.to_dict()
+    args = arguments.deepcopy()
+    args.update(args_dict)
+    try:
+        opt = argparse.Namespace(**args)
+        logger.info(args_dict)
+        train_data = get_data_from_mongo(args_dict)
+        train_x, valid_x, train_y, valid_y, scaled_train_bytes, scaled_target_bytes = dh.train_data_handler(train_data, opt)
+        bp_model = bp.training(opt, [train_x, valid_x, train_y, valid_y])
+        args_dict['params'] = json.dumps(args)
+        args_dict['gen_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
+        insert_trained_model_into_mongo(bp_model, args_dict)
+        insert_scaler_model_into_mongo(scaled_train_bytes, scaled_target_bytes, args)
+        success = 1
+    except Exception as e:
+        my_exception = traceback.format_exc()
+        my_exception.replace("\n", "\t")
+        result['msg'] = my_exception
+    end_time = time.time()
+
+    result['success'] = success
+    result['args'] = args
+    result['start_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(start_time))
+    result['end_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(end_time))
+    print("Program execution ends!")
+    return result
+
+
+if __name__ == "__main__":
+    print("Program starts execution!")
+    logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+    logger = logging.getLogger("model_training_bp log")
+    from waitress import serve
+
+    # serve(app, host="0.0.0.0", port=10103, threads=4)
+    print("server start!")
+    args_dict = {"mongodb_database": 'david_test', 'scaler_table': 'j00083_scaler', 'model_name': 'bp1.0.test',
+    'model_table': 'j00083_model', 'mongodb_read_table': 'j00083', 'col_time': 'dateTime',
+    'features': 'speed10,direction10,speed30,direction30,speed50,direction50,speed70,direction70,speed90,direction90,speed110,direction110,speed150,direction150,speed170,direction170'}
+    args_dict['features'] = args_dict['features'].split(',')
+    arguments.update(args_dict)
+    dh = DataHandler(logger, arguments)
+    bp = BPHandler(logger)
+    opt = argparse.Namespace(**arguments)
+    opt.Model['input_size'] = len(opt.features)
+    train_data = get_data_from_mongo(args_dict)
+    train_x, valid_x, train_y, valid_y, scaled_train_bytes = dh.train_data_handler(train_data, opt)
+
+    bp_model = bp.training(opt, [train_x, train_y, valid_x, valid_y])
+
+    args_dict['gen_time'] = time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time()))
+    args_dict['params'] = arguments
+    args_dict['descr'] = '测试'
+    insert_trained_model_into_mongo(bp_model, args_dict)
+    insert_scaler_model_into_mongo(scaled_train_bytes, args_dict)