GRU模型预测.py,gru模型全称,Python

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 Dense from keras.layers import GRU import numpy as np # 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('京哈高速(1).csv', header=0, index_col=0) values = dataset.values # integer encode direction #encoder = LabelEncoder() #values[:,4] = encoder.fit_transform(values[:,4]) # ensure all data is float values = values.astype('float32') # 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[[4,5]], axis=1, inplace=True) #改为[3,4]可预测速度 print(reframed.head()) # split into train and test sets values = reframed.values n_train_hours = 400 #设置训练样本量 train = values[:n_train_hours, :] test = values[n_train_hours:, :] # split into input and outputs train_X, train_y = train[:, :-1], train[4:, -1] train_X_1 = train_X[:-4, :] train_X_2 = train_X[1:-3, :] train_X_3 = train_X[2:-2, :] train_X_4 = train_X[3:-1, :] train_X_5 = train_X[4:, :] com = np.array([train_X_1, train_X_2, train_X_3, train_X_4, train_X_5]) train_X = com.transpose((1,0,2)) #print(arr5) print(train_X) test_X, test_y = test[:, :-1], test[4:, -1] test_X_1 = test_X[:-4, :] test_X_2 = test_X[1:-3, :] test_X_3 = test_X[2:-2, :] test_X_4 = test_X[3:-1, :] test_X_5 = test_X[4:, :] com1 = np.array([test_X_1, test_X_2, test_X_3, test_X_4, test_X_5]) test_X = com1.transpose((1,0,2)) # reshape input to be 3D [samples, timesteps, features] #trainxshape = int (train_X.shape[0]/10) #testxshape=int(test_X.shape[0]/10) #train_X = train_X.reshape((trainxshape, 10, train_X.shape[1])) #test_X = test_X.reshape((testxshape, 10, test_X.shape[1])) print(train_X.shape, train_y.shape, test_X.shape, test_y.shape) # design network model = Sequential() model.add(GRU(50, input_shape=(train_X.shape[1], train_X.shape[2]))) model.add(Dense(1)) model.compile(loss='mae', optimizer='adam') # fit network history = model.fit(train_X, train_y, epochs=50, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False) # 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_2[:, 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_2[:, 1:]), axis=1) inv_y = scaler.inverse_transform(inv_y) inv_y = inv_y[:,0] # calculate RMSE rmse = sqrt(mean_squared_error(inv_y, inv_yhat)) print('Test RMSE: %.3f' % rmse) #np.savetxt('new.csv', inv_yhat, delimiter=',')#存储预测结果 #np.savetxt('true.csv', inv_y, delimiter=',')#存储真实数据