def Predict(self, test_generator):
metrics = Metrics()
valid_loss_x, valid_loss_y, valid_loss_z, valid_loss_phi, y_pred, gt_labels = self.ValidateSingleEpoch(
test_generator)
gt_labels = torch.tensor(gt_labels, dtype=torch.float32)
y_pred = torch.tensor(y_pred, dtype=torch.float32)
MSE, MAE, r2_score = metrics.Update(y_pred, gt_labels,
[0, 0, 0, 0],
[valid_loss_x, valid_loss_y, valid_loss_z, valid_loss_phi])
y_pred_viz = metrics.GetPred()
gt_labels_viz = metrics.GetLabels()
DataVisualization.desc = "Test_"
DataVisualization.PlotGTandEstimationVsTime(gt_labels_viz, y_pred_viz)
DataVisualization.PlotGTVsEstimation(gt_labels_viz, y_pred_viz)
DataVisualization.DisplayPlots()
logging.info('Test MSE: {}'.format(MSE))
logging.info('Test MAE: {}'.format(MAE))
logging.info('Test r2_score: {}'.format(r2_score))
return y_pred
def Predict(self, test_generator):
metrics = Metrics()
valid_loss_x, valid_loss_y, valid_loss_z, valid_loss_phi, y_pred, gt_labels = self.ValidateSingleEpoch(
test_generator)
gt_labels = torch.tensor(gt_labels, dtype=torch.float32)
y_pred = torch.tensor(y_pred, dtype=torch.float32)
MSE, MAE, r2_score = metrics.Update(y_pred, gt_labels,
[0, 0, 0, 0],
[valid_loss_x, valid_loss_y, valid_loss_z, valid_loss_phi])
y_pred_viz = metrics.GetPred()
gt_labels_viz = metrics.GetLabels()
DataVisualization.desc = "Test_"
DataVisualization.PlotGTandEstimationVsTime(gt_labels_viz, y_pred_viz)
DataVisualization.PlotGTVsEstimation(gt_labels_viz, y_pred_viz)
DataVisualization.DisplayPlots()
logging.info('[ModelTrainer] Test MSE: [{0:.4f}, {1:.4f}, {2:.4f}, {3:.4f}]'.format(MSE[0], MSE[1], MSE[2], MSE[3]))
logging.info('[ModelTrainer] Test MAE: [{0:.4f}, {1:.4f}, {2:.4f}, {3:.4f}]'.format(MAE[0], MAE[1], MAE[2], MAE[3]))
logging.info('[ModelTrainer] Test r2_score: [{0:.4f}, {1:.4f}, {2:.4f}, {3:.4f}]'.format(r2_score[0], r2_score[1], r2_score[2],
r2_score[3]))
def __init__(self,inputFile = None, reference=None):
"""
Inputs
• inputFile: Name of the input file. Default value is None
• reference: Name of the reference column. Default value is None.
Local variables set:
• dataDict
• header
• reference
• stats
• visualize
Outputs: None
"""
# Check if inputFile is None
if inputFile == None:
# Initialize all the variables to None
self.dataDict = None
self.reference = None
self.header = None
self.numColumns = None
self.numRows = None
self.inputFile = None
else:
# else call the load function
self.load(inputFile,reference)
# initialize DataStatistics and DataVisualization objects
self.visualize = DataVisualization(self)
def Train(self, training_generator, validation_generator):
metrics = Metrics()
early_stopping = EarlyStopping(patience=10, verbose=True)
scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(self.optimizer, mode='min', factor=np.sqrt(0.1),
patience=5, verbose=False,
threshold=0.0001, threshold_mode='rel', cooldown=0,
min_lr=0.1e-6, eps=1e-08)
loss_epoch_m1 = 1e3
for epoch in range(1, self.args.epochs + 1):
logging.info("[ModelTrainer] Starting Epoch {}".format(epoch))
change_prec = False
ended = False
# if self.args.quantize:
# change_prec, ended = self.relax.step(loss_epoch_m1, epoch, None)
# if ended:
# break
train_loss_x, train_loss_y, train_loss_z, train_loss_phi = self.TrainSingleEpoch(training_generator)
valid_loss_x, valid_loss_y, valid_loss_z, valid_loss_phi, y_pred, gt_labels = self.ValidateSingleEpoch(
validation_generator)
valid_loss = valid_loss_x + valid_loss_y + valid_loss_z + valid_loss_phi
scheduler.step(valid_loss)
gt_labels = torch.tensor(gt_labels, dtype=torch.float32)
y_pred = torch.tensor(y_pred, dtype=torch.float32)
MSE, MAE, r_score = metrics.Update(y_pred, gt_labels,
[train_loss_x, train_loss_y, train_loss_z, train_loss_phi],
[valid_loss_x, valid_loss_y, valid_loss_z, valid_loss_phi])
logging.info('[ModelTrainer] Validation MSE: {}'.format(MSE))
logging.info('[ModelTrainer] Validation MAE: {}'.format(MAE))
logging.info('[ModelTrainer] Validation r_score: {}'.format(r_score))
checkpoint_filename = self.folderPath + self.model.name + '-{:03d}.pt'.format(epoch)
early_stopping(valid_loss, self.model, epoch, checkpoint_filename)
if early_stopping.early_stop:
logging.info("[ModelTrainer] Early stopping")
break
MSEs = metrics.GetMSE()
MAEs = metrics.GetMAE()
r_score = metrics.Getr2_score()
y_pred_viz = metrics.GetPred()
gt_labels_viz = metrics.GetLabels()
train_losses_x, train_losses_y, train_losses_z, train_losses_phi, valid_losses_x, valid_losses_y, valid_losses_z, valid_losses_phi = metrics.GetLosses()
DataVisualization.desc = "Train_"
DataVisualization.PlotLoss(train_losses_x, train_losses_y, train_losses_z, train_losses_phi , valid_losses_x, valid_losses_y, valid_losses_z, valid_losses_phi)
DataVisualization.PlotMSE(MSEs)
DataVisualization.PlotMAE(MAEs)
DataVisualization.PlotR2Score(r_score)
DataVisualization.PlotGTandEstimationVsTime(gt_labels_viz, y_pred_viz)
DataVisualization.PlotGTVsEstimation(gt_labels_viz, y_pred_viz)
DataVisualization.DisplayPlots()
new_time_series = fe.execute_feature_engineering(time_series)
# new_time_series = dp.delete_column(time_series, ['Confirmed Cases', 'Deaths', 'Recovered Cases', 'Active Cases'])
# Truncate zero values from the time series
# new_time_series = dp.truncate_time_series(new_time_series, '26/02/2020')
# Preliminary Analysis: Stationarity Check
pa = PreliminaryAnalysis()
pa.execute_preliminary_analysis(new_time_series)
# Data Visualization Phase
log.info(Constants.DATA_VISUALIZATION_MSG)
dv = DataVisualization()
# original time series data
dv.plot_data_structure(time_series)
# new time series data
dv.plot_data_structure(new_time_series)
# plots of all cases
dv.plot_data_structure(new_time_series['New Confirmed Cases'])
dv.plot_data_structure(new_time_series['New Deaths'])
dv.plot_data_structure(new_time_series['New Recovered Cases'])
dv.plot_data_structure(new_time_series['New Active Cases'])
# Decomposition plots for:
# Confirmed Cases
x = new_time_series['New Confirmed Cases'].resample('D').mean()