def run(self, period, mlName):
print("starting prediction for "+period+" days"+ " with "+mlName)
dataFrame = getDatafromDb(period)
print(dataFrame)
myframe = dataFrame.copy()
dataFrame = processDbDataForLrTestInput(dataFrame)
X_test, y_test = prepareData(dataFrame[['CpuUsage']], lag_start=3, lag_end=25)
print("y_test")
print(y_test)
#print(y_test.timebucket)
if(mlName == "LR"):
predictedData = linearRegression(X_test)
elif(mlName == "RF"):
predictedData = randomForest(X_test)
elif (mlName == "ARIMA"):
dataFrame = getDatafromDb(-1)
dataFrame = processDbDataForLrTestInput(dataFrame)
X_train, y_train = prepareData(dataFrame[['CpuUsage']], lag_start=3, lag_end=25)
history = [x for x in y_train]
predictedData = arimaPrediction(y_test, history)
else:
print("Invalid Model"+ mlName)
return
# write into promql
writeDataToDb(mlName, myframe['timebucket'], myframe['CpuUsage'], predictedData)
print("predicted")
print(predictedData)
print(mlName + " Model completed prediction for "+ period)
def buildRandomForestMNodel():
dataFrame = getDatafromDb(-1)
dataFrame = processDbDataForLrTestInput(dataFrame)
X_train, y_train = prepareData(dataFrame[['CpuUsage']],
lag_start=3,
lag_end=25)
model = RandomForestRegressor()
model.fit(X_train, y_train)
return model
def buildLinearRegressionModel():
dataFrame = getDatafromDb(-1)
dataFrame = processDbDataForLrTestInput(dataFrame)
X_train, y_train = prepareData(dataFrame[['CpuUsage']],
lag_start=3,
lag_end=25)
model = LinearRegression()
model.fit(X_train, y_train)
return model
def buildArimaModel():
dataFrame = getDatafromDb(-1)
dataFrame = processDbDataForLrTestInput(dataFrame)
X_train, y_train = prepareData(dataFrame[['CpuUsage']],
lag_start=3,
lag_end=25)
history = [x for x in y_train]
model = ARIMA(history, order=(5, 1, 0))
#for t in range(len(y_train)):
# model = ARIMA(history, order=(5, 1, 0))
# model_fit = model.fit(disp=0)
# output = model_fit.forecast()
# yhat = output[0]
# predictions.append(yhat[0])
# obs = y_train[t]
# history.append(obs)
# print('predicted=%f, expected=%f' % (yhat, obs))
return model
def randomForest(xtest):
pickleModel = settings.ML_RF_MODEL
pickle_in = open(pickleModel, "rb")
loadData = pickle.load(pickle_in)
dataset = loadData.predict(xtest)
return dataset
def arimaPrediction(ytest, history):
pickleModel = settings.ML_ARIMA_MODEL
pickle_in = open(pickleModel, "rb")
loadData = pickle.load(pickle_in)
print(loadData)
predictions = list()
print(len(history))
for t in range(len(ytest)):
model = ARIMA(history, order=(5,1,0))
model_fit = model.fit(disp=0)
output = model_fit.forecast()
yhat = output[0]
predictions.append(yhat[0])
obs = ytest[t]
history.append(obs)
print('predicted=%f, expected=%f' % (yhat, obs))
return predictions
if __name__ == "__main__":
dataFrame = getDatafromDb()
#predicted_data = linearRegression(xtest)
print(dataFrame)