def ANNforecasting(dataset,
inputDim,
hiddenNum=50,
outputDim=1,
epoch=20,
batchSize=30):
# 归一化数
#dataset = dataset.reshape(-1, 1)
scaler = MinMaxScaler(feature_range=(0.0, 1.0))
dataset = scaler.fit_transform(dataset)
# 分割序列为样本,此处不整理成RNN形式，采用标准形式
train, test = util.divideTrainTest(dataset)
trainX, trainY = util.createSamples(train, inputDim, RNN=False)
testX, testY = util.createSamples(test, inputDim, RNN=False)
print("trainX shape is", trainX.shape)
print("trainY shape is", trainY.shape)
# 构建模型并训练
ANNModel = ANN.ANNModel(inputDim, hiddenNum, outputDim)
t1 = time.time()
ANNModel.train(trainX, trainY, epoch, batchSize)
t2 = time.time() - t1
print("train time is", t2)
# 预测
trainPred = ANNModel.predict(trainX)
testPred = ANNModel.predict(testX)
# 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 SMAPE", SMAPE)
util.plot(trainPred, trainY, testPred, testY)
return trainPred, testPred, MAE, MRSE, SMAPE
def MLP_forecasting(dataset,
inputDim,
lr=1e-3,
hiddenNum=50,
outputDim=1,
epoch=20,
batchSize=30,
plot_flag=False):
# normalize time series
# dataset = dataset.reshape(-1, 1)
scaler = MinMaxScaler(feature_range=(0.0, 1.0)).fit(dataset)
dataset = scaler.transform(dataset)
# divide the series into training/testing samples
# NOTE: Not RNN format
train, test = util.divideTrainTest(dataset)
trainX, trainY = util.createSamples(train, inputDim, RNN=False)
testX, testY = util.createSamples(test, inputDim, RNN=False)
print("trainX shape is", trainX.shape)
print("trainY shape is", trainY.shape)
print("testX shape is", testX.shape)
print("testY shape is", testY.shape)
# buil model and train
MLP_model = MLP.MLP_Model(inputDim, hiddenNum, outputDim, lr)
t1 = time.time()
MLP_model.train(trainX, trainY, epoch, batchSize)
t2 = time.time() - t1
print("train time is", t2)
# forecasting
trainPred = MLP_model.predict(trainX)
testPred = MLP_model.predict(testX)
# reverse the time series
trainPred = scaler.inverse_transform(trainPred)
trainY = scaler.inverse_transform(trainY)
testPred = scaler.inverse_transform(testPred)
testY = scaler.inverse_transform(testY)
# evaluate
MAE = eval.calcMAE(testY, testPred)
print("test MAE", MAE)
MRSE = eval.calcRMSE(testY, testPred)
print("test RMSE", MRSE)
SMAPE = eval.calcSMAPE(testY, testPred)
print("test SMAPE", SMAPE)
if plot_flag:
util.plot(trainPred, trainY, testPred, testY)
return trainPred, testPred, MAE, MRSE, SMAPE
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 run(data, lookBack, train_lookAhead, test_lookAhead, epoch, lr, batchSize,
method, modelPath):
# 归一化数据
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(data)
# 分割训练测试样本
trainData, testData = divideTrainTest(dataset)
# 分割序列为样本, 支持RNN或者普通样本形式
flag = True
trainX, trainY = createSamples(trainData,
lookBack=lookBack,
lookAhead=train_lookAhead,
RNN=flag)
testX, testY = createSamples(testData,
lookBack=lookBack,
lookAhead=test_lookAhead,
RNN=flag)
print("testX shape:", testX.shape)
print("testy shape:", testY.shape)
print("trainX shape:", trainX.shape)
print("trainy shape:", trainY.shape)
train(trainX,
trainY,
epoch=epoch,
lr=lr,
batchSize=batchSize,
modelPath=modelPath,
lookBack=lookBack,
lookAhead=train_lookAhead,
method=method)
# testPred = predict(testX, MODEL_PATH)
testPred = predict_iteration(testX, test_lookAhead, MODEL_PATH)
print("testPred shape:", testPred.shape)
# trainPred = predict(trainX, MODEL_PATH)
# print("trainPred shape:", trainPred.shape)
testPred = scaler.inverse_transform(testPred)
testY = scaler.inverse_transform(testY)
MAE = eval.calcMAE(testY, testPred)
print("test MAE", MAE)
MRSE = eval.calcRMSE(testY, testPred)
print("test RMSE", MRSE)
SMAPE = eval.calcSMAPE(testY, testPred)
print("test SMAPE", SMAPE)
return testPred, MAE, MRSE, SMAPE
def SVRforecasting(dataset, lookBack):
# 归一化数
#dataset = dataset.reshape(-1, 1)
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# 分割序列为样本,此处不整理成RNN形式，采用标准形式
train, test = util.divideTrainTest(dataset)
trainX, trainY = util.createSamples(train, lookBack, RNN=False)
testX, testY = util.createSamples(test, lookBack, RNN=False)
# 构建模型并训练
SVRModel = SVR.SVRModel(C=2, epsilon=0.01)
SVRModel.train(trainX, trainY)
# 预测
trainPred = SVRModel.predict(trainX)
testPred = SVRModel.predict(testX)
# 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 SMAPE", SMAPE)
#util.plot(trainPred,trainY,testPred,testY)
return trainPred, testPred, MAE, MRSE, SMAPE
def SVR_forecasting(dataset, lookBack, C=2.0, epsilon=0.01, plot_flag=False):
# normalize time series
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# divide the series into training/testing samples
# NOTE: Not RNN format
train, test = util.divideTrainTest(dataset)
trainX, trainY = util.createSamples(train, lookBack, RNN=False)
testX, testY = util.createSamples(test, lookBack, RNN=False)
print("trainX shape is", trainX.shape)
print("trainY shape is", trainY.shape)
print("testX shape is", testX.shape)
print("testY shape is", testY.shape)
# buil model and train
SVRModel = SVR.SVRModel(C=C, epsilon=epsilon)
SVRModel.train(trainX, trainY)
# forecasting
trainPred = SVRModel.predict(trainX).reshape(-1, 1)
testPred = SVRModel.predict(testX).reshape(-1, 1)
# reverse the time series
trainPred = scaler.inverse_transform(trainPred)
trainY = scaler.inverse_transform(trainY)
testPred = scaler.inverse_transform(testPred)
testY = scaler.inverse_transform(testY)
# evaluate
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)
if plot_flag:
util.plot(trainPred, trainY, testPred, testY)
return trainPred, testPred, MAE, MRSE, SMAPE
def run_aram(data, maxar, maxma):
train, test = util.divideTrainTest(data)
print("train shape is", train.shape)
print("test shape is", test.shape)
diffn = 0
if stationarity(train) < 0.01:
print('平稳，不需要差分')
else:
diffn = best_diff(train, maxdiff=8)
# train = produce_diffed_timeseries(train, diffn)
print('差分阶数为' + str(diffn))
print('开始进行ARMA拟合')
order = choose_order(train, maxar, maxma)
print('模型的阶数为：' + str(order))
diffn = 1
_ar = order[0]
_ma = order[1]
train = train.flatten()
model = pf.ARIMA(data=train,
ar=_ar,
ma=_ma,
integ=diffn,
family=pf.Normal())
model.fit("MLE")
testPred = model.predict(len(test))
# testPred = predict_recover(test_predict, train, diffn)
# 评估指标
MAE = eval.calcMAE(test, testPred)
print("test MAE", MAE)
MRSE = eval.calcRMSE(test, testPred)
print("test RMSE", MRSE)
MAPE = eval.calcMAPE(test, testPred)
print("test MAPE", MAPE)
SMAPE = eval.calcSMAPE(test, testPred)
print("test SMAPE", 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
if __name__ == '__main__':
p = 6
q = 4
h_test = 1
lag = 24
ts, data = util.load_data("./data/NSW2013.csv", columnName="TOTALDEMAND")
# ts, data = util.load_data("./data/bike_hour.csv", columnName="cnt")
# ts, data = util.load_data("./data/TAS2016.csv", columnName="TOTALDEMAND")
# ts, data = util.load_data("./data/traffic_data_in_bits.csv", columnName="value")
# ts, data = util.load_data("./data/beijing_pm25.csv", columnName="pm2.5")
# ts, data = util.load_data("./data/pollution.csv", columnName="Ozone")
train, test = util.divideTrainTest(data)
testX, testY = util.createSamples(test, lookBack=24, RNN=False)
testX = testX[:3]
print("train shape is", train.shape)
print("test shape is", test.shape)
train_data = [x[0] for x in train]
predictions = []
realTestY = []
for t in range(len(testX)):
add_test = [x for x in testX[t]]
raw_train_data = train_data
train_data.extend(add_test)
model = pf.ARIMA(data=np.array(train_data),
ar=p,