数据代码.rar

# -*- coding: utf-8 -*- # 导入库pip install openpyxl -i https://pypi.tuna.tsinghua.edu.cn/simple import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn import metrics from sklearn.metrics import mean_squared_error # 评价指标 import matplotlib.pyplot as plt from keras.models import Sequential from keras.layers import Dense from keras.layers import LSTM, GRU from keras import optimizers import keras import tensorflow as tf print(keras.__version__) print(tf.__version__) # mse rmse mae rmape # adam sgd plt.rcParams['font.sans-serif'] = ['SimHei'] plt.rcParams['axes.unicode_minus'] = False import warnings warnings.filterwarnings("ignore") # 忽略一些警告 不影响运行 df=pd.read_excel("原始数据.xlsx") print(df.columns) print(df.head()) # print(df[['出库含沙量', '出库流量', '水位', '入库流量', '入库含沙量']]) # ['日期', '星期', '最高气温', '最低气温', '天气', '风向', '级数'] data_x=df[['出库含沙量', '出库流量', '水位', '入库流量', '入库含沙量']].values data_x=np.array(data_x,dtype=np.float16) print(data_x) # 序列长度 int_sequence_len=5 # 每个序列的长度 int_a = 5 train_x = [] train_y = [] for i in range(0, len(data_x)-int_sequence_len,1): train_x.append(data_x[i:i+int_sequence_len]) train_y.append(data_x[i+int_sequence_len][0]) print(len(train_x), len(train_y)) # print(train_y) # print(train_x) # 划分验证集和测试集 x_train, x_test, y_train, y_test = train_test_split(np.array(train_x), np.array(train_y), test_size=0.2, random_state=1) print(x_train.shape) print(len(x_train), len(x_test)) # 1243 311 x_train = x_train.reshape(len(x_train),int_sequence_len, int_a) # 三维度数据 全部数据长度 序列长度 每个序列维度 y_train = y_train.reshape(len(x_train),1) print(x_train.shape) print(y_train.shape) x_test = x_test.reshape(len(x_test),int_sequence_len, int_a) y_test = y_test.reshape(len(x_test),1) print(x_test.shape) print(y_test.shape) def create_model_1(): model = keras.models.Sequential([ keras.layers.LSTM(100, activation='sigmoid', input_shape=(int_sequence_len, int_a)), # (1,9) 要与三维度的(1243,1,9) 一一对应 # 序列长度 每个序列维度 keras.layers.Dense(32, activation='sigmoid'), # 全连接 keras.layers.Dense(1, activation='relu') # 1个全链接 ]) model.compile(loss='mean_absolute_error', optimizer='Adagrad') # 回归损失函数和优化器 return model op = optimizers.RMSprop(lr=0.01) # 学习率 model1 = create_model_1() model1.summary() history=model1.fit(x_train, y_train, validation_data=(x_train, y_train), epochs=200, batch_size=32, verbose=2, shuffle=True) # 训练世代 batch model1.save_weights('lstmmoxing_天气') # 模型保存 import matplotlib.pyplot as plt training_loss = history.history['loss'] test_loss = history.history['val_loss'] # 创建迭代数量 epoch_count = range(1, len(training_loss) + 1) # 可视化损失历史 plt.plot(epoch_count, training_loss, 'r--') plt.plot(epoch_count, test_loss, 'b-') plt.legend(['Training Loss', 'Test Loss']) plt.title("天气预测Epoch——loss") plt.xlabel('Epoch') plt.ylabel('Loss') plt.show() plt.clf() from sklearn.metrics import mean_squared_error # 均方误差 from sklearn.metrics import mean_absolute_error # 平方绝对误差 from sklearn.metrics import r2_score # R square # 调用 # 引用上边的模型实例 model_jiazai_1 = create_model_1() # 加载保存好的模型 model_jiazai_1.load_weights('lstmmoxing_天气') result = [] y1_pred_lstm = model_jiazai_1.predict(x_test) for i in range(len(y1_pred_lstm)): print("真实：", y_test[i]) print("预测：", y1_pred_lstm[i]) result.append([y_test[i][0], y1_pred_lstm[i][0]]) print("-----------------------") print(mean_squared_error(y_test, y1_pred_lstm)) print(mean_absolute_error(y_test, y1_pred_lstm)) print(r2_score(y_test, y1_pred_lstm)) # 所有画图 len_ = [i for i in range(len(y_test))] plt.xlabel('标签', fontsize=8) plt.ylabel('均值', fontsize=8) plt.plot(len_, y_test, label='y_test', color="blue") plt.plot(len_, y1_pred_lstm, label='y1_pred_lstm', color="yellow") plt.title("天气预测走势图") plt.show() plt.clf() # 输出到excle name = ['真实值', '预测值'] test = pd.DataFrame(columns=name, data=result) test.to_excel('result_天气.xlsx') # 输出 。。。excle表