LSTM时间序列预测销量

#!usr/bin/env python # -*- coding: utf-8 -*- import numpy as np from math import sqrt from numpy import concatenate from matplotlib import pyplot from pandas import read_csv from pandas import DataFrame from pandas import concat from sklearn.preprocessing import MinMaxScaler from sklearn.preprocessing import LabelEncoder from sklearn.metrics import mean_squared_error from keras.models import Sequential from keras.layers import LSTM, Dense, Dropout,Activation from keras import optimizers from keras import regularizers # convert series to supervised learning 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() # input sequence (t-n, ... t-1) 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)] # forecast sequence (t, t+1, ... t+n) 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)] # put it all together agg = concat(cols, axis=1) agg.columns = names # drop rows with NaN values if dropnan: agg.dropna(inplace=True) return agg # load dataset dataset = read_csv('D:\zxq.csv', header=0, index_col=0) values = dataset.values # integer encode direction encoder = LabelEncoder() values[:,3] = encoder.fit_transform(values[:,3]) # ensure all data is float values = values.astype('float64') # normalize features scaler = MinMaxScaler(feature_range=(0, 1)) scaled = scaler.fit_transform(values) # frame as supervised learning reframed = series_to_supervised(scaled, 1, 1) # drop columns we don't want to predict reframed.drop(reframed.columns[[7,8,9,10,11]], axis=1, inplace=True) print(reframed.head()) # split into train and test sets values = reframed.values n_train_hours = -13 train = values[:n_train_hours+1, :] test = values[n_train_hours:, :] # split into input and outputs train_X, train_y = train[:, :-1], train[:, -1] test_X, test_y = test[:, :-1], test[:, -1] # reshape input to be 3D [samples, timesteps, features] train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1])) test_X = test_X.reshape((test_X.shape[0], 1, test_X.shape[1])) print(train_X.shape, train_y.shape, test_X.shape, test_y.shape) # design network model = Sequential() model.add(LSTM(128,input_shape=(train_X.shape[1], train_X.shape[2]),return_sequences=True)) model.add(Dropout(0.3)) model.add(LSTM(128,return_sequences=False )) model.add(Dropout(0.3)) model.add(Dense(1)) #model.add(Activation('sigmoid')) adam = optimizers.Adam(lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=1e-08) model.compile(loss='mae', optimizer=adam) # fit network history = model.fit(train_X, train_y, epochs=400, batch_size=8, validation_data=(test_X, test_y),shuffle=False) # plot history pyplot.plot(history.history['loss'], label='train') pyplot.plot(history.history['val_loss'], label='test') pyplot.legend() pyplot.show() # make a prediction yhat = model.predict(test_X) test_X = test_X.reshape((test_X.shape[0], test_X.shape[2])) # invert scaling for forecast inv_yhat = concatenate((yhat, test_X[:, 1:]), axis=1) inv_yhat = scaler.inverse_transform(inv_yhat) inv_yhat = inv_yhat[:,0] # invert scaling for actual test_y = test_y.reshape((len(test_y), 1)) inv_y = concatenate((test_y, test_X[:, 1:]), axis=1) inv_y = scaler.inverse_transform(inv_y) inv_y = inv_y[:,0] print(inv_yhat ) # 做ROC曲线 pyplot.figure() pyplot.plot(range(len(inv_yhat)),inv_yhat, 'b', label="predict") pyplot.plot(range(len(inv_y)),inv_y, 'r', label="test") pyplot.legend(loc="upper right") # 显示图中的标签 pyplot.xlabel("the number of sales") pyplot.ylabel('value of sales') pyplot.show() # calculate RMSE rmse = sqrt(mean_squared_error(inv_y, inv_yhat)) print('Test RMSE: %.3f' % rmse)