import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn import preprocessing
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.metrics import mean_squared_error
import warnings
warnings.filterwarnings('ignore')
#读取数据
data = pd.read_csv('air.csv',header=None,encoding='utf8')
arr = data.values[:,0]
#构造数据集
timespan = 6
size = 3
dim = 1
x,y =[],[]
for i in range(len(arr)-timespan):
x.append(arr[i:i+timespan])
y.append(arr[i+timespan])
x = np.array(x)
y = np.array(y)
scale_x = preprocessing.MinMaxScaler(feature_range=(0,1))
scale_y = preprocessing.MinMaxScaler(feature_range=(0,1))
X = scale_x.fit_transform(x)
Y = scale_y.fit_transform(y.reshape(-1,1))
train_size = len(X)-size
lx = X.reshape(X.shape[0],timespan,dim)
x_train,x_test = lx[0:train_size],lx[train_size:]
y_train,y_test = Y[0:train_size],Y[train_size:]
print('Train: x = {} y = {}'.format(x_train.shape,y_train.shape))
print('Test: x = {} y = {}'.format(x_test.shape,y_test.shape))
#建立网络(adam)
hiddennum = 12
batch_size = 20
model = Sequential()
model.add(LSTM(hiddennum,return_sequences=True,input_shape=(timespan,dim)))
model.add(LSTM(hiddennum))
model.add(Dense(1,activation='linear'))
model.compile(optimizer='adam',loss='mse')
model.fit(x_train,y_train,batch_size=batch_size,epochs=100,verbose=0)
predict_train = scale_y.inverse_transform(model.predict(x_train,batch_size=batch_size))
actual_train = scale_y.inverse_transform(y_train)
train_acc = np.sqrt(mean_squared_error(actual_train,predict_train))
predict_test = scale_y.inverse_transform(model.predict(x_test,batch_size=batch_size))
actual_test = scale_y.inverse_transform(y_test)
print('网络层数 = ',len(model.layers),' 优化算法 = adam')
test_acc = np.sqrt(mean_squared_error(actual_test,predict_test))
print('Train mse = ',round(train_acc,4))
print('Test mse = ',round(test_acc,4))
#建立网络(rmsprop)
model = Sequential()
model.add(LSTM(hiddennum,return_sequences=True,input_shape=(timespan,dim)))
model.add(LSTM(hiddennum))
model.add(Dense(1,activation='linear'))
model.compile(optimizer='rmsprop',loss='mse')
model.fit(x_train,y_train,batch_size=batch_size,epochs=100,verbose=0)
predict_train = scale_y.inverse_transform(model.predict(x_train,batch_size=batch_size))
actual_train = scale_y.inverse_transform(y_train)
train_acc = np.sqrt(mean_squared_error(actual_train,predict_train))
predict_test = scale_y.inverse_transform(model.predict(x_test,batch_size=batch_size))
actual_test = scale_y.inverse_transform(y_test)
print('网络层数 = ',len(model.layers),' 优化算法 = rmsprop')
test_acc = np.sqrt(mean_squared_error(actual_test,predict_test))
print('Train mse = ',round(train_acc,4))
print('Test mse = ',round(test_acc,4))
#建立网络(sgd)
model = Sequential()
model.add(LSTM(hiddennum,return_sequences=True,input_shape=(timespan,dim)))
model.add(LSTM(hiddennum))
model.add(Dense(1,activation='linear'))
model.compile(optimizer='sgd',loss='mse')
model.fit(x_train,y_train,batch_size=batch_size,epochs=100,verbose=0)
predict_train = scale_y.inverse_transform(model.predict(x_train,batch_size=batch_size))
actual_train = scale_y.inverse_transform(y_train)
train_acc = np.sqrt(mean_squared_error(actual_train,predict_train))
predict_test = scale_y.inverse_transform(model.predict(x_test,batch_size=batch_size))
actual_test = scale_y.inverse_transform(y_test)
print('网络层数 = ',len(model.layers),' 优化算法 = sgd')
test_acc = np.sqrt(mean_squared_error(actual_test,predict_test))
print('Train mse = ',round(train_acc,4))
print('Test mse = ',round(test_acc,4))