Python时间序列LSTM预测系列教程（4）-单变量

单变量LSTM预测模型（4）

教程原文连接

完整的LSTM案例

本案例将结合Python时间序列LSTM预测系列教程（2）~（3）中的案例

步骤概览

1、加载csv文件

2、数据格式转换

1）转换成监督数据

2）将数据转换成稳定的

3）缩放数据范围为 [-1,1]

3、将数据fit到有状态的LSTM模型

4、在测试数据上评估LSTM

5、预测性能报告

代码解析

# coding=utf-8                                                                                                              
from pandas import read_csv
from pandas import datetime
from pandas import concat
from pandas import DataFrame
from pandas import Series
from sklearn.metrics import mean_squared_error
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from math import sqrt
from matplotlib import pyplot
import numpy
 
#读取时间数据的格式化
def parser(x):
    return datetime.strptime(x, '%Y/%m/%d')
 
#转换成有监督数据
def timeseries_to_supervised(data, lag=1):
    df = DataFrame(data)
    columns = [df.shift(i) for i in range(1, lag+1)]#数据滑动一格，作为input，df原数据为output
    columns.append(df)
    df = concat(columns, axis=1)
    df.fillna(0, inplace=True)
    return df
 
#差分
def difference(dataset, interval=1):
    diff = list()
    for i in range(interval, len(dataset)):
        value = dataset[i] - dataset[i-interval]
        diff.append(value)          
    return Series(diff)             
                                    
#逆差分                             
def inverse_difference(history, yhat, interval=1):#历史数据，预测数据，差分间隔
    return yhat+history[-interval]  
                                    
#缩放                               
def scale(train, test):             
    #根据训练数据建立缩放器         
    scaler = MinMaxScaler(feature_range=(-1,1))   
    scaler = scaler.fit(train)      
    #转换train data                 
    train = train.reshape(train.shape[0], train.shape[1])
     train_scaled = scaler.transform(train)
    #转换test data
    test = test.reshape(test.shape[0], test.shape[1])
    test_scaled = scaler.transform(test)
    return scaler, train_scaled, test_scaled
    
#逆缩放
def invert_scale(scaler, X, value):
    new_row = [x for x in X] + [value]
    array = numpy.array(new_row)
    array = array.reshape(1, len(array))
    inverted = scaler.inverse_transform(array)
    return inverted[0, -1]
    
#fit LSTM来训练数据
def fit_lstm(train, batch_size, nb_epoch, neurons):
    X, y = train[:, 0:-1], train[:,-1]
    X = X.reshape(X.shape[0], 1, X.shape[1])
    model = Sequential()
    #添加LSTM层
    model.add(LSTM(neurons, batch_input_shape=(batch_size, X.shape[1], X.shape[2]), stateful=True))
    model.add(Dense(1))#输出层1个node
    #编译，损失函数mse+优化算法adam
    model.compile(loss='mean_squared_error', optimizer='adam')
    for i in range(nb_epoch):
        #按照batch_size，一次读取batch_size个数据
        model.fit(X, y, epochs=1, batch_size=batch_size, verbose=0, shuffle=False)
        model.reset_states()
    return model
    
#1步长预测
def forcast_lstm(model, batch_size, X):
    X = X.reshape(1, 1, len(X))
    yhat = model.predict(X, batch_size=batch_size)
    return yhat[0,0]
    
#加载数据
series = read_csv('data_set/shampoo-sales.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser)
    
#让数据变成稳定的
raw_values = series.values
diff_values = difference(raw_values, 1)
    
#变成有监督数据
supervised = timeseries_to_supervised(diff_values, 1)
supervised_values = supervised.values
                                                 
 #数据拆分：训练数据、测试数据
train, test = supervised_values[0:-12], supervised_values[-12:]
    
#数据缩放
scaler, train_scaled, test_scaled = scale(train, test)
    
#fit 模型
lstm_model = fit_lstm(train_scaled, 1, 3000, 4)#训练数据，batch_size，epoche次数, 神经元个数
#预测
train_reshaped = train_scaled[:,0].reshape(len(train_scaled), 1, 1)
lstm_model.predict(train_reshaped, batch_size=1)
    
#测试数据的前向验证
predictions = list()
for i in range(len(test_scaled)):
    #1步长预测
    X, y = test_scaled[i, 0:-1], test_scaled[i, -1]
    yhat = forcast_lstm(lstm_model, 1, X)
    #逆缩放
    yhat = invert_scale(scaler, X, yhat)
    #逆差分
    yhat = inverse_difference(raw_values, yhat, len(test_scaled)+1-i)
    predictions.append(yhat)
    expected = raw_values[len(train)+i+1]
    print('Moth=%d, Predicted=%f, Expected=%f'%(i+1, yhat, expected))
 
#性能报告
rmse = sqrt(mean_squared_error(raw_values[-12:], predictions))
print('Test RMSE:%.3f' %rmse)
#绘图
pyplot.plot(raw_values[-12:])
pyplot.plot(predictions)
pyplot.show()

输出结果

由于LSTM的初始权重使随机的，没有tuning过程

每次得出的结果不一样