Python时间序列LSTM预测系列教程（10）-多步预测

Multi-Step LSTM预测（1）

教程原文链接

关联教程：

Python时间序列LSTM预测系列教程（10）-多步预测

Python时间序列LSTM预测系列教程（11）-多步预测

数据集

Python时间序列LSTM预测系列教程（1）-单变量

数据准备与模型评估

1、拆分成训练和测试数据。

训练数据=前两年香皂销售数据

测试数据=剩下一年的香皂销售数据

2、Multi-Step 预测

假设需要预测3个月的销售数据

3、模型评估

用rolling-forcast(walk-forward)方式模型验证

测试数据每个时间步，滑动一个值，预测；之后测试数据的下一个真实观测值加入模型，并预测

用RMSE评估

持久模型（Persistence Model）

他是很好的时间序列预测的基准

是最简单的预测

原理：

用当前值作为之后的预测值

静态模型完整过程

1、转换成有监督数据

参考Python时间序列LSTM预测系列教程（8）-多变量中的方法

2、切分成训练和测试数据

3、训练模型

4、预测

5、评估

6、输出

静态模型预测代码解析

#coding=utf-8                                                                                                          from pandas import read_csv      from pandas import DataFrame     from pandas import concatfrom sklearn.metrics import mean_squared_errorfrom math import sqrtfrom matplotlib import pyplot    from pandas import datetime       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)#数据多了行标、列标    cols, names = list(), list()    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)]    for i in range(0, n_out, 1):         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    if dropnan:        agg.dropna(inplace=True)    return agg#拆分正训练+测试数据                                                                                                   def prepare_data(series, n_test, n_lay, n_seq):    raw_values = series.values    raw_values = raw_values.reshape(len(raw_values), 1)        supervised = series_to_supervised(raw_values, n_lay, n_seq)    supervised_values = supervised.values     train, test = supervised_values[0:-n_test], supervised_values[-n_test:]    return train, test #persistence model预测#用上一次观察值作为之后n_seq的预测值def persistence(last_ob, n_seq):    return [last_ob for i in range(n_seq)] #评估persistence modeldef make_forcast(train, test, n_lay, n_seq):    forcasts = list()    for i in range(len(test)):        x, y = test[i, 0:n_lag], test[i, n_lag:]        forcast = persistence(x[-1], n_seq)        forcasts.append(forcast)    return forcasts #预测评估def evaluate_forcasts(test, forcasts, n_lag, n_seq):for i in range(n_seq): actual = test[:, (n_lag+i)]        predicted = [forcast[i] for forcast in forcasts]        print 'predicted'        print predicted        rmse = sqrt(mean_squared_error(actual, predicted))        print 't+%d RMSE:%f'%((i+1), rmse)#1~n_seq各个长度的预测的rmse def plot_forcasts(series, forcasts, n_test):    #原始数据    pyplot.plot(series.values)    #预测数据    for i in range(len(forcasts)):        off_s = len(series)-n_test+i-1        off_e = off_s + len(forcasts[i])+1        xaxis = [x for x in range(off_s, off_e)]        yaxis = [series.values[off_s]]+forcasts[i]        print 'xaxis'        print xaxis        print 'yaxis'        print yaxis        print 'series.values[off_s]'        print series.values[off_s]        pyplot.plot(xaxis, yaxis, color='red')    pyplot.show() series = read_csv('data_set/shampoo-sales.csv', header=0, parse_dates=[0], index_col=0, squeeze=True, date_parser=parser) #一步数据，预测3步n_lag = 1n_seq = 3     n_test = 10#给了最后12个月，预测3个月，则能预测的次数是10，即10个3个月train, test = prepare_data(series, n_test, n_lag, n_seq)print 'train data'print trainprint 'test data'print testforecasts = make_forcast(train, test, n_lag, n_seq)print 'forecasts'print forecastsevaluate_forcasts(test, forecasts, n_lag, n_seq)plot_forcasts(series, forecasts, n_test+2)