Python時系列LSTM予測シリーズ学習ノート(11)-マルチステップ予測

この文書は次のとおりです.
https://machinelearningmastery.com/multi-step-time-series-forecasting-long-short-term-memory-networks-python/
https://blog.csdn.net/iyangdi/article/details/77895186
博文の学习の笔记、博主の笔风はすべてとても浪で、一部の细部は1笔持ったことがあって、本人は谦逊な态度で学习と整理を行って、笔记の内容はすべてコードの注釈の中にあります.不明な点は元ブロガーの文書で見ることができます.
データセットのダウンロード:https://datamarket.com/data/set/22r0/sales-of-shampoo-over-a-three-year-period
後でgithubを補充します
ソースアドレス:https://github.com/yangwohenmai/LSTM/tree/master/LSTM%E7%B3%BB%E5%88%97/Multi-Step%20LSTM%E9%A2%84%E6%B5%8B2
本文は実はiyangdiブロガーの最後のLSTMの文章で、後続は連載を続けていませんが、後の授業はJason Brownlee博士の文章の勉強を通じてアップロードし続けます.
本稿では,上記に基づいて,真実データを処理し,実戦的な多段階予測を行った.
前の章では、なぜデータが横線で予測されているのか疑問に思っている人もいるかもしれませんが、それらのデータは意味のない実験データだからです.
このセクションのデータは実際のデータです
コード分析は注釈に書かれています
 

from pandas import DataFrame
from pandas import Series
from pandas import concat
from pandas import read_csv
from pandas import datetime
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
from numpy import array


#      
def parser(x):
    return datetime.strptime(x, '%Y/%m/%d')


#                  
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
    n_vars = 1 if type(data) is list else data.shape[1]
    df = DataFrame(data)
    cols, names = list(), list()
    #   for            var1(t-1)，var1(t)，var1(t+1)，var1(t+2)
    for i in range(n_in, 0, -1):
        cols.append(df.shift(i))
        names += [('var%d(t-%d)' % (j + 1, i)) for j in range(n_vars)]
    #                    ，   var1(t-1)，var1(t)，var1(t+1)，var1(t+2)
    for i in range(0, n_out):
        cols.append(df.shift(-i))
        if i == 0:
            names += [('var%d(t)' % (j + 1)) for j in range(n_vars)]
        else:
            names += [('var%d(t+%d)' % (j + 1, i)) for j in range(n_vars)]
    #     
    agg = concat(cols, axis=1)
    agg.columns = names
    #  null    0
    if dropnan:
        agg.dropna(inplace=True)
    print(agg)
    return agg


#            ，      
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)


#                    
def prepare_data(series, n_test, n_lag, n_seq):
    #      
    raw_values = series.values
    #          
    diff_series = difference(raw_values, 1)
    diff_values = diff_series.values
    diff_values = diff_values.reshape(len(diff_values), 1)
    #        （-1,1）  
    scaler = MinMaxScaler(feature_range=(-1, 1))
    scaled_values = scaler.fit_transform(diff_values)
    scaled_values = scaled_values.reshape(len(scaled_values), 1)
    #          X，y
    supervised = series_to_supervised(scaled_values, n_lag, n_seq)
    supervised_values = supervised.values
    #             
    train, test = supervised_values[0:-n_test], supervised_values[-n_test:]
    return scaler, train, test


#   LSTM      
def fit_lstm(train, n_lag, n_seq, n_batch, nb_epoch, n_neurons):
    #          [samples, timesteps, features]
    X, y = train[:, 0:n_lag], train[:, n_lag:]
    X = X.reshape(X.shape[0], 1, X.shape[1])
    #     LSTM    ，      
    model = Sequential()
    model.add(LSTM(n_neurons, batch_input_shape=(n_batch, X.shape[1], X.shape[2]), stateful=True))
    model.add(Dense(y.shape[1]))
    model.compile(loss='mean_squared_error', optimizer='adam')
    #     ，             ，            
    for i in range(nb_epoch):
        model.fit(X, y, epochs=1, batch_size=n_batch, verbose=0, shuffle=False)
        model.reset_states()
    return model


#  LSTM   
def forecast_lstm(model, X, n_batch):
    #        [samples, timesteps, features]
    X = X.reshape(1, 1, len(X))
    #     
    forecast = model.predict(X, batch_size=n_batch)
    #        
    return [x for x in forecast[0, :]]


#           ，         
def make_forecasts(model, n_batch, train, test, n_lag, n_seq):
    forecasts = list()
    #         X        Y 
    for i in range(len(test)):
        X, y = test[i, 0:n_lag], test[i, n_lag:]
        #               
        forecast = forecast_lstm(model, X, n_batch)
        #         
        forecasts.append(forecast)
    return forecasts


#         （-1，1）     
def inverse_difference(last_ob, forecast):
    # invert first forecast
    inverted = list()
    inverted.append(forecast[0] + last_ob)
    # propagate difference forecast using inverted first value
    for i in range(1, len(forecast)):
        inverted.append(forecast[i] + inverted[i - 1])
    return inverted


#              
def inverse_transform(series, forecasts, scaler, n_test):
    inverted = list()
    for i in range(len(forecasts)):
        # create array from forecast
        forecast = array(forecasts[i])
        forecast = forecast.reshape(1, len(forecast))
        #             
        inv_scale = scaler.inverse_transform(forecast)
        inv_scale = inv_scale[0, :]
        # invert differencing
        index = len(series) - n_test + i - 1
        last_ob = series.values[index]
        #             
        inv_diff = inverse_difference(last_ob, inv_scale)
        #     
        inverted.append(inv_diff)
    return inverted


#           RMSE
def evaluate_forecasts(test, forecasts, n_lag, n_seq):
    for i in range(n_seq):
        actual = [row[i] for row in test]
        predicted = [forecast[i] for forecast in forecasts]
        rmse = sqrt(mean_squared_error(actual, predicted))
        print('t+%d RMSE: %f' % ((i + 1), rmse))


#                 
def plot_forecasts(series, forecasts, n_test):
    # plot the entire dataset in blue
    pyplot.plot(series.values)
    # plot the forecasts in red
    for i in range(len(forecasts)):
        off_s = len(series) - n_test + i - 1
        off_e = off_s + len(forecasts[i]) + 1
        xaxis = [x for x in range(off_s, off_e)]
        yaxis = [series.values[off_s]] + forecasts[i]
        pyplot.plot(xaxis, yaxis, color='red')
    # show the plot
    pyplot.show()


#     
series = read_csv('data_set/shampoo-sales.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser)
#       
n_lag = 1
n_seq = 3
n_test = 10
n_epochs = 1500
n_batch = 1
n_neurons = 1
#     
scaler, train, test = prepare_data(series, n_test, n_lag, n_seq)
#       
model = fit_lstm(train, n_lag, n_seq, n_batch, n_epochs, n_neurons)
#     
forecasts = make_forecasts(model, n_batch, train, test, n_lag, n_seq)
#             
forecasts = inverse_transform(series, forecasts, scaler, n_test + 2)
#        
actual = [row[n_lag:] for row in test]
actual = inverse_transform(series, actual, scaler, n_test + 2)
#            ，          
evaluate_forecasts(actual, forecasts, n_lag, n_seq)
#   
plot_forecasts(series, forecasts, n_test + 2)