def statefulRNNforecasting(dataset,lookBack,inputDim = 1,hiddenNum = 100 ,outputDim = 1 ,unit = "GRU",epoch = 50,batchSize = 10,varFlag=False, minLen = 15, maxLen = 30,inputNum = 150):
# 归一化数据
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# 分割序列为样本,并整理成RNN的输入形式
train,test = util.divideTrainTest(dataset)
trainX,trainY = util.createSamples(train,lookBack)
testX, testY = util.createSamples(test,lookBack)
# 构建模型并训练
RNNModel = staRNNs.statefulRNNsModel(inputDim, hiddenNum, outputDim, unit=unit, batchSize=batchSize, lag=lookBack)
if varFlag:
vtrainX, vtrainY = util.createVariableDataset(train, minLen, maxLen, inputNum)
RNNModel.train(vtrainX, vtrainY, epoch, batchSize)
else:
RNNModel.train(trainX, trainY, epoch, batchSize)
# 预测
trainPred = RNNModel.predict(trainX, batchSize)
testPred = RNNModel.predict(testX, batchSize)
# 还原数据
trainPred = scaler.inverse_transform(trainPred)
trainY = scaler.inverse_transform(trainY)
testPred = scaler.inverse_transform(testPred)
testY = scaler.inverse_transform(testY)
dataset = scaler.inverse_transform(dataset)
# 评估指标
# MAE = eval.calcMAE(trainY, trainPred)
# print ("train MAE",MAE)
# MRSE = eval.calcRMSE(trainY, trainPred)
# print ("train MRSE",MRSE)
# MAPE = eval.calcMAPE(trainY, trainPred)
# print ("train MAPE",MAPE)
MAE = eval.calcMAE(testY,testPred)
print ("test MAE",MAE)
MRSE = eval.calcRMSE(testY,testPred)
print ("test RMSE",MRSE)
MAPE = eval.calcMAPE(testY,testPred)
print ("test MAPE",MAPE)
SMAPE = eval.calcSMAPE(testY, testPred)
print("test MAPE", SMAPE)
# util.LBtest(testY-testPred)
# plt.plot(testY-testPred)
# plt.show()
#util.plot(trainPred,trainY,testPred,testY)
return trainPred, testPred, MAE, MRSE, SMAPE
def RNN_forecasting(dataset,
lookBack,
lr,
inputDim=1,
hiddenNum=64,
outputDim=1,
unit="GRU",
epoch=20,
batchSize=30,
varFlag=False,
minLen=15,
maxLen=30,
step=5):
# 归一化数据
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# 分割序列为样本,并整理成RNN的输入形式
train, test = util.divideTrainTest(dataset)
trainX = None
trainY = None
vtrainX = None
vtrainY = None
testX = None
testY = None
vtestX = None
vtestY = None
# 构建模型并训练
RNNModel = RNNs.RNNsModel(inputDim, hiddenNum, outputDim, unit, lr)
if varFlag:
vtrainX, vtrainY = util.createVariableDataset(train, minLen, maxLen,
step)
vtestX, vtestY = util.createVariableDataset(test, minLen, maxLen, step)
print("trainX shape is", vtrainX.shape)
print("trainY shape is", vtrainY.shape)
print("testX shape is", vtestX.shape)
print("testY shape is", vtestY.shape)
RNNModel.train(vtrainX, vtrainY, epoch, batchSize)
else:
trainX, trainY = util.createSamples(train, lookBack)
testX, testY = util.createSamples(test, lookBack)
print("trainX shape is", trainX.shape)
print("trainY shape is", trainY.shape)
print("testX shape is", testX.shape)
print("testY shape is", testY.shape)
RNNModel.train(trainX, trainY, epoch, batchSize)
# 预测
if varFlag:
trainPred = RNNModel.predictVarLen(vtrainX, minLen, maxLen, step)
testPred = RNNModel.predictVarLen(vtestX, minLen, maxLen, step)
trainPred = trainPred.reshape(-1, 1)
else:
trainPred = RNNModel.predict(trainX)
testPred = RNNModel.predict(testX)
trainPred = trainPred.reshape(-1, 1)
if varFlag:
# 转化一下test的label
testY = util.transform_groundTruth(vtestY, minLen, maxLen, step)
testY = testY.reshape(-1, 1)
testPred = testPred.reshape(-1, 1)
print("testY", testY.shape)
print("testPred", testPred.shape)
# 还原数据
testPred = scaler.inverse_transform(testPred)
testY = scaler.inverse_transform(testY)
# 评估指标
MAE = eval.calcMAE(testY, testPred)
print("test MAE", MAE)
MRSE = eval.calcRMSE(testY, testPred)
print("test RMSE", MRSE)
MAPE = eval.calcMAPE(testY, testPred)
print("test MAPE", MAPE)
SMAPE = eval.calcSMAPE(testY, testPred)
print("test SMAPE", SMAPE)
#util.plot(trainPred,trainY,testPred,testY)
return trainPred, testPred, MAE, MRSE, SMAPE
def diffLagEnsmble(dataset,
minLag,
maxLag,
step,
epoch,
batchSize=10,
inputDim=1,
outputDim=1,
hiddenNum=50,
unit="GRU"):
# 归一化数据
dataset = dataset.reshape(-1, 1)
scaler = MinMaxScaler()
dataset = scaler.fit_transform(dataset)
# 分割序列为样本,并整理成RNN的输入形式
train, test = util.divideTrainTest(dataset)
modelList = []
#在所有lag下独立地训练若干个RNN
for lag in range(minLag, maxLag + 1, step):
print("lag is ", lag)
trainX, trainY = util.createPaddedDataset(train, lag, maxLag)
#testX, testY = util.createPaddedDataset(test, lag, maxLag)
RNNModel = RNNs.RNNsModel(inputDim, hiddenNum, outputDim, unit)
RNNModel.train(trainX, trainY, epoch, batchSize)
modelList.append(RNNModel)
print("the number of model is ", len(modelList))
# 变长分割test数据
testX, testY = util.createVariableDataset(test, minLag, maxLag, step)
print("testX", testX.shape)
print("testY", testY.shape)
lagContainNum = (maxLag - minLag) // step + 1
print("lag contains num is ", lagContainNum)
# 对每个数据点上不同的lag用不同的模型做预测，目前是简单取平均
testNum = len(testX)
testPred = []
for i in range(0, testNum, lagContainNum):
predList = []
for j in range(0, lagContainNum):
singlePred = modelList[j].predict(testX[i + j:i + j + 1, :, :])
predList.append(singlePred)
testPred.append(np.mean(predList))
# 还原数据
testPred = scaler.inverse_transform(testPred)
testY = scaler.inverse_transform(testY)
testY = util.transformGroundTruth(testY, minLag, maxLag, step)
testPred = np.array(testPred)
print("testY", testY.shape)
print("testPred", testPred.shape)
# 评估
MAE = eval.calcMAE(testY, testPred)
print("test MAE", MAE)
MRSE = eval.calcRMSE(testY, testPred)
print("test RMSE", MRSE)
MAPE = eval.calcMAPE(testY, testPred)
print("test MAPE", MAPE)
SMAPE = eval.calcSMAPE(testY, testPred)
print("test SMAPE", SMAPE)
# plt.plot(testY)
# plt.plot(testPred)
# plt.show()
return testPred, MAE, MRSE, SMAPE