爱用建站平台,博客做单页网站,注册网站域名,企业管理网站的来历基于WIN10的64位系统演示
一、写在前面
这一期#xff0c;我们介绍大名鼎鼎的LSTM回归。
同样#xff0c;这里使用这个数据#xff1a;
《PLoS One》2015年一篇题目为《Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal…基于WIN10的64位系统演示
一、写在前面
这一期我们介绍大名鼎鼎的LSTM回归。
同样这里使用这个数据
《PLoS One》2015年一篇题目为《Comparison of Two Hybrid Models for Forecasting the Incidence of Hemorrhagic Fever with Renal Syndrome in Jiangsu Province, China》文章的公开数据做演示。数据为江苏省2004年1月至2012年12月肾综合症出血热月发病率。运用2004年1月至2011年12月的数据预测2012年12个月的发病率数据。 二、LSTM回归
1LSTM简介
LSTM (Long Short-Term Memory) 是一种特殊的RNN递归神经网络结构由Hochreiter和Schmidhuber在1997年首次提出。LSTM 被设计出来是为了避免长序列在训练过程中的长期依赖问题这是传统 RNNs 所普遍遇到问题。
aLSTM 的主要特点
a1三个门结构LSTM 包含三个门结构输入门、遗忘门和输出门。这些门决定了信息如何进入、被存储或被遗忘以及如何输出。
a2记忆细胞LSTM的核心是称为记忆细胞的结构。它可以保留、修改或访问的内部状态。通过门结构模型可以学会在记忆细胞中何时存储、忘记或检索信息。
a3长期依赖问题LSTM特别擅长学习、存储和使用长期信息从而避免了传统RNN在长序列上的梯度消失问题。
b为什么LSTM适合时间序列建模
b1序列数据的特性时间序列数据具有顺序性先前的数据点可能会影响后面的数据点。LSTM设计之初就是为了处理带有时间间隔、延迟和长期依赖关系的序列数据。
b2长期依赖在时间序列分析中某个事件可能会受到很早之前事件的影响。传统的RNNs由于梯度消失的问题很难捕捉这些长期依赖关系。但是LSTM结构可以有效地处理这种依赖关系。
b3记忆细胞对于时间序列预测能够记住过去的信息是至关重要的。LSTM的记忆细胞可以为模型提供这种存储和检索长期信息的能力。
b4灵活性LSTM模型可以与其他神经网络结构如CNN结合用于更复杂的时间序列任务例如多变量时间序列或序列生成。
综上所述由于LSTM的设计和特性它非常适合时间序列建模尤其是当数据具有长期依赖关系时。
2单步滚动预测
import pandas as pd
import numpy as np
from sklearn.metrics import mean_absolute_error, mean_squared_error
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras import layers, models, optimizers
from tensorflow.python.keras.optimizers import adam_v2# 读取数据
data pd.read_csv(data.csv)# 将时间列转换为日期格式
data[time] pd.to_datetime(data[time], format%b-%y)# 创建滞后期特征
lag_period 6
for i in range(lag_period, 0, -1):data[flag_{i}] data[incidence].shift(lag_period - i 1)# 删除包含 NaN 的行
data data.dropna().reset_index(dropTrue)# 划分训练集和验证集
train_data data[(data[time] 2004-01-01) (data[time] 2011-12-31)]
validation_data data[(data[time] 2012-01-01) (data[time] 2012-12-31)]# 定义特征和目标变量
X_train train_data[[lag_1, lag_2, lag_3, lag_4, lag_5, lag_6]].values
y_train train_data[incidence].values
X_validation validation_data[[lag_1, lag_2, lag_3, lag_4, lag_5, lag_6]].values
y_validation validation_data[incidence].values# 对于LSTM我们需要将输入数据重塑为 [samples, timesteps, features]
X_train X_train.reshape(X_train.shape[0], X_train.shape[1], 1)
X_validation X_validation.reshape(X_validation.shape[0], X_validation.shape[1], 1)# 构建LSTM回归模型
input_layer layers.Input(shape(X_train.shape[1], 1))x layers.LSTM(50, return_sequencesTrue)(input_layer)
x layers.LSTM(25, return_sequencesFalse)(x)
x layers.Dropout(0.1)(x)
x layers.Dense(25, activationrelu)(x)
x layers.Dropout(0.1)(x)
output_layer layers.Dense(1)(x)model models.Model(inputsinput_layer, outputsoutput_layer)model.compile(optimizeradam_v2.Adam(learning_rate0.001), lossmse)# 训练模型
history model.fit(X_train, y_train, epochs200, batch_size32, validation_data(X_validation, y_validation), verbose0)# 单步滚动预测函数
def rolling_forecast(model, initial_features, n_forecasts):forecasts []current_features initial_features.copy()for i in range(n_forecasts):# 使用当前的特征进行预测forecast model.predict(current_features.reshape(1, len(current_features), 1)).flatten()[0]forecasts.append(forecast)# 更新特征用新的预测值替换最旧的特征current_features np.roll(current_features, shift-1)current_features[-1] forecastreturn np.array(forecasts)# 使用训练集的最后6个数据点作为初始特征
initial_features X_train[-1].flatten()# 使用单步滚动预测方法预测验证集
y_validation_pred rolling_forecast(model, initial_features, len(X_validation))# 计算训练集上的MAE, MAPE, MSE 和 RMSE
mae_train mean_absolute_error(y_train, model.predict(X_train).flatten())
mape_train np.mean(np.abs((y_train - model.predict(X_train).flatten()) / y_train))
mse_train mean_squared_error(y_train, model.predict(X_train).flatten())
rmse_train np.sqrt(mse_train)# 计算验证集上的MAE, MAPE, MSE 和 RMSE
mae_validation mean_absolute_error(y_validation, y_validation_pred)
mape_validation np.mean(np.abs((y_validation - y_validation_pred) / y_validation))
mse_validation mean_squared_error(y_validation, y_validation_pred)
rmse_validation np.sqrt(mse_validation)print(验证集, mae_validation, mape_validation, mse_validation, rmse_validation)
print(训练集, mae_train, mape_train, mse_train, rmse_train)
看结果 3多步滚动预测-vol. 1
import pandas as pd
import numpy as np
from sklearn.metrics import mean_absolute_error, mean_squared_error
import tensorflow as tf
from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import Input, LSTM, Dense, Dropout, Flatten
from tensorflow.python.keras.optimizers import adam_v2# 读取数据
data pd.read_csv(data.csv)
data[time] pd.to_datetime(data[time], format%b-%y)n 6
m 2# 创建滞后期特征
for i in range(n, 0, -1):data[flag_{i}] data[incidence].shift(n - i 1)data data.dropna().reset_index(dropTrue)train_data data[(data[time] 2004-01-01) (data[time] 2011-12-31)]
validation_data data[(data[time] 2012-01-01) (data[time] 2012-12-31)]# 准备训练数据
X_train []
y_train []for i in range(len(train_data) - n - m 1):X_train.append(train_data.iloc[in-1][[flag_{j} for j in range(1, n1)]].values)y_train.append(train_data.iloc[in:inm][incidence].values)X_train np.array(X_train)
y_train np.array(y_train)
X_train X_train.astype(np.float32)
y_train y_train.astype(np.float32)# 构建LSTM模型
inputs Input(shape(n, 1))
x LSTM(64, return_sequencesTrue)(inputs)
x LSTM(32)(x)
x Dense(50, activationrelu)(x)
x Dropout(0.1)(x)
outputs Dense(m)(x)model Model(inputsinputs, outputsoutputs)model.compile(optimizeradam_v2.Adam(learning_rate0.001), lossmse)# 训练模型
model.fit(X_train, y_train, epochs200, batch_size32, verbose0)def lstm_rolling_forecast(data, model, n, m):y_pred []for i in range(len(data) - n):input_data data.iloc[in-1][[flag_{j} for j in range(1, n1)]].values.astype(np.float32).reshape(1, n, 1)pred model.predict(input_data)y_pred.extend(pred[0])for i in range(1, m):for j in range(len(y_pred) - i):y_pred[ji] (y_pred[ji] y_pred[j]) / 2return np.array(y_pred)# Predict for train_data and validation_data
y_train_pred_lstm lstm_rolling_forecast(train_data, model, n, m)[:len(y_train)]
y_validation_pred_lstm lstm_rolling_forecast(validation_data, model, n, m)[:len(validation_data) - n]# Calculate performance metrics for train_data
mae_train mean_absolute_error(train_data[incidence].values[n:len(y_train_pred_lstm)n], y_train_pred_lstm)
mape_train np.mean(np.abs((train_data[incidence].values[n:len(y_train_pred_lstm)n] - y_train_pred_lstm) / train_data[incidence].values[n:len(y_train_pred_lstm)n]))
mse_train mean_squared_error(train_data[incidence].values[n:len(y_train_pred_lstm)n], y_train_pred_lstm)
rmse_train np.sqrt(mse_train)# Calculate performance metrics for validation_data
mae_validation mean_absolute_error(validation_data[incidence].values[n:len(y_validation_pred_lstm)n], y_validation_pred_lstm)
mape_validation np.mean(np.abs((validation_data[incidence].values[n:len(y_validation_pred_lstm)n] - y_validation_pred_lstm) / validation_data[incidence].values[n:len(y_validation_pred_lstm)n]))
mse_validation mean_squared_error(validation_data[incidence].values[n:len(y_validation_pred_lstm)n], y_validation_pred_lstm)
rmse_validation np.sqrt(mse_validation)print(训练集, mae_train, mape_train, mse_train, rmse_train)
print(验证集, mae_validation, mape_validation, mse_validation, rmse_validation)
结果 4多步滚动预测-vol. 2
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_error, mean_squared_error
from tensorflow.python.keras.models import Sequential, Model
from tensorflow.python.keras.layers import Dense, LSTM, Input
from tensorflow.python.keras.optimizers import adam_v2# Loading and preprocessing the data
data pd.read_csv(data.csv)
data[time] pd.to_datetime(data[time], format%b-%y)n 6
m 2# 创建滞后期特征
for i in range(n, 0, -1):data[flag_{i}] data[incidence].shift(n - i 1)data data.dropna().reset_index(dropTrue)train_data data[(data[time] 2004-01-01) (data[time] 2011-12-31)]
validation_data data[(data[time] 2012-01-01) (data[time] 2012-12-31)]# 只对X_train、y_train、X_validation取奇数行
X_train train_data[[flag_{i} for i in range(1, n1)]].iloc[::2].reset_index(dropTrue).values
X_train X_train.reshape(X_train.shape[0], X_train.shape[1], 1)y_train_list [train_data[incidence].shift(-i) for i in range(m)]
y_train pd.concat(y_train_list, axis1)
y_train.columns [ftarget_{i1} for i in range(m)]
y_train y_train.iloc[::2].reset_index(dropTrue).dropna().values[:, 0]X_validation validation_data[[flag_{i} for i in range(1, n1)]].iloc[::2].reset_index(dropTrue).values
X_validation X_validation.reshape(X_validation.shape[0], X_validation.shape[1], 1)y_validation validation_data[incidence].values# Building the LSTM model
inputs Input(shape(n, 1))
x LSTM(50, activationrelu)(inputs)
x Dense(50, activationrelu)(x)
outputs Dense(1)(x)model Model(inputsinputs, outputsoutputs)
optimizer adam_v2.Adam(learning_rate0.001)
model.compile(optimizeroptimizer, lossmse)# Train the model
model.fit(X_train, y_train, epochs200, batch_size32, verbose0)# Predict on validation set
y_validation_pred model.predict(X_validation).flatten()# Compute metrics for validation set
mae_validation mean_absolute_error(y_validation[:len(y_validation_pred)], y_validation_pred)
mape_validation np.mean(np.abs((y_validation[:len(y_validation_pred)] - y_validation_pred) / y_validation[:len(y_validation_pred)]))
mse_validation mean_squared_error(y_validation[:len(y_validation_pred)], y_validation_pred)
rmse_validation np.sqrt(mse_validation)# Predict on training set
y_train_pred model.predict(X_train).flatten()# Compute metrics for training set
mae_train mean_absolute_error(y_train, y_train_pred)
mape_train np.mean(np.abs((y_train - y_train_pred) / y_train))
mse_train mean_squared_error(y_train, y_train_pred)
rmse_train np.sqrt(mse_train)print(验证集, mae_validation, mape_validation, mse_validation, rmse_validation)
print(训练集, mae_train, mape_train, mse_train, rmse_train)
结果 5多步滚动预测-vol. 3
import pandas as pd
import numpy as np
from sklearn.metrics import mean_absolute_error, mean_squared_error
from tensorflow.python.keras.models import Sequential, Model
from tensorflow.python.keras.layers import Dense, LSTM, Input
from tensorflow.python.keras.optimizers import adam_v2# 数据读取和预处理
data pd.read_csv(data.csv)
data_y pd.read_csv(data.csv)
data[time] pd.to_datetime(data[time], format%b-%y)
data_y[time] pd.to_datetime(data_y[time], format%b-%y)n 6for i in range(n, 0, -1):data[flag_{i}] data[incidence].shift(n - i 1)data data.dropna().reset_index(dropTrue)
train_data data[(data[time] 2004-01-01) (data[time] 2011-12-31)]
X_train train_data[[flag_{i} for i in range(1, n1)]]
m 3X_train_list []
y_train_list []for i in range(m):X_temp X_trainy_temp data_y[incidence].iloc[n i:len(data_y) - m 1 i]X_train_list.append(X_temp)y_train_list.append(y_temp)for i in range(m):X_train_list[i] X_train_list[i].iloc[:-(m-1)].valuesX_train_list[i] X_train_list[i].reshape(X_train_list[i].shape[0], X_train_list[i].shape[1], 1)y_train_list[i] y_train_list[i].iloc[:len(X_train_list[i])].values# 模型训练
models []
for i in range(m):# Building the LSTM modelinputs Input(shape(n, 1))x LSTM(50, activationrelu)(inputs)x Dense(50, activationrelu)(x)outputs Dense(1)(x)model Model(inputsinputs, outputsoutputs)optimizer adam_v2.Adam(learning_rate0.001)model.compile(optimizeroptimizer, lossmse)model.fit(X_train_list[i], y_train_list[i], epochs200, batch_size32, verbose0)models.append(model)validation_start_time train_data[time].iloc[-1] pd.DateOffset(months1)
validation_data data[data[time] validation_start_time]
X_validation validation_data[[flag_{i} for i in range(1, n1)]].values
X_validation X_validation.reshape(X_validation.shape[0], X_validation.shape[1], 1)y_validation_pred_list [model.predict(X_validation) for model in models]
y_train_pred_list [model.predict(X_train_list[i]) for i, model in enumerate(models)]def concatenate_predictions(pred_list):concatenated []for j in range(len(pred_list[0])):for i in range(m):concatenated.append(pred_list[i][j])return concatenatedy_validation_pred np.array(concatenate_predictions(y_validation_pred_list))[:len(validation_data[incidence])]
y_train_pred np.array(concatenate_predictions(y_train_pred_list))[:len(train_data[incidence]) - m 1]
y_validation_pred y_validation_pred.flatten()
y_train_pred y_train_pred.flatten()mae_validation mean_absolute_error(validation_data[incidence], y_validation_pred)
mape_validation np.mean(np.abs((validation_data[incidence] - y_validation_pred) / validation_data[incidence]))
mse_validation mean_squared_error(validation_data[incidence], y_validation_pred)
rmse_validation np.sqrt(mse_validation)mae_train mean_absolute_error(train_data[incidence][:-(m-1)], y_train_pred)
mape_train np.mean(np.abs((train_data[incidence][:-(m-1)] - y_train_pred) / train_data[incidence][:-(m-1)]))
mse_train mean_squared_error(train_data[incidence][:-(m-1)], y_train_pred)
rmse_train np.sqrt(mse_train)print(验证集, mae_validation, mape_validation, mse_validation, rmse_validation)
print(训练集, mae_train, mape_train, mse_train, rmse_train)
结果 三、数据
链接https://pan.baidu.com/s/1EFaWfHoG14h15KCEhn1STg?pwdq41n
提取码q41n
