VictorMylle/Thesis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Updated training scripts

Browse Source
This commit is contained in:
Victor Mylle
2024-03-18 12:15:06 +01:00
parent 34335cd9fe
commit 1a8e735cbc
10 changed files with 487 additions and 308 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
src/training_scripts/autoregressive_quantiles.py
View File

@@ -2,9 +2,7 @@ from src.utils.clearml import ClearMLHelper
#### ClearML ####
clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
task = clearml_helper.get_task(
task_name="Non Autoregressive Quantile Regression: Non Linear"
)
task = clearml_helper.get_task(task_name="AQR: Non Linear")
task.execute_remotely(queue_name="default", exit_process=True)
from src.policies.PolicyEvaluator import PolicyEvaluator
@@ -60,16 +58,16 @@ if quantiles is None:
quantiles = [0.01, 0.05, 0.1, 0.15, 0.3, 0.4, 0.5, 0.6, 0.7, 0.85, 0.9, 0.95, 0.99]
task.set_parameter("general/quantiles", quantiles)
else:
# if string, convert to list "[0.01, 0.05, 0.1, 0.15, 0.3, 0.4, 0.5, 0.6, 0.7, 0.85, 0.9, 0.95, 0.99]""
# if string, convert to list "[0.01, 0.05, 0.1, 0.15, 0.3, 0.4, 0.5, 0.6, 0.7, 0.85, 0.9, 0.95, 0.99]"
if isinstance(quantiles, str):
quantiles = eval(quantiles)
model_parameters = {
"learning_rate": 0.0001,
"hidden_size": 256,
"num_layers": 4,
"hidden_size": 512,
"num_layers": 5,
"dropout": 0.2,
"time_feature_embedding": 16,
"time_feature_embedding": 8,
}
model_parameters = task.connect(model_parameters, name="model_parameters")
@@ -77,7 +75,14 @@ model_parameters = task.connect(model_parameters, name="model_parameters")
time_embedding = TimeEmbedding(
data_processor.get_time_feature_size(), model_parameters["time_feature_embedding"]
)
# lstm_model = GRUModel(time_embedding.output_dim(inputDim), len(quantiles), hidden_size=model_parameters["hidden_size"], num_layers=model_parameters["num_layers"], dropout=model_parameters["dropout"])
# lstm_model = GRUModel(
# time_embedding.output_dim(inputDim),
# len(quantiles),
# hidden_size=model_parameters["hidden_size"],
# num_layers=model_parameters["num_layers"],
# dropout=model_parameters["dropout"],
# )
non_linear_model = NonLinearRegression(
time_embedding.output_dim(inputDim),
len(quantiles),
@@ -85,10 +90,11 @@ non_linear_model = NonLinearRegression(
numLayers=model_parameters["num_layers"],
dropout=model_parameters["dropout"],
)
# linear_model = LinearRegression(time_embedding.output_dim(inputDim), len(quantiles))
model = nn.Sequential(time_embedding, non_linear_model)
model.output_size = 96
model.output_size = 1
optimizer = torch.optim.Adam(model.parameters(), lr=model_parameters["learning_rate"])
### Policy Evaluator ###
@@ -122,18 +128,37 @@ trainer = AutoRegressiveQuantileTrainer(
trainer.add_metrics_to_track(
[PinballLoss(quantiles), MSELoss(), L1Loss(), CRPSLoss(quantiles)]
)
trainer.early_stopping(patience=30)
trainer.early_stopping(patience=10)
trainer.plot_every(5)
trainer.train(task=task, epochs=epochs, remotely=True)
### Policy Evaluation ###
idx_samples = trainer.test_set_samples
_, test_loader = trainer.data_processor.get_dataloaders(
predict_sequence_length=trainer.model.output_size, full_day_skip=True
predict_sequence_length=trainer.model.output_size, full_day_skip=False
)
policy_evaluator.evaluate_test_set(idx_samples, test_loader)
policy_evaluator.plot_profits_table()
policy_evaluator.plot_thresholds_per_day()
# policy_evaluator.evaluate_test_set(idx_samples, test_loader)
# policy_evaluator.plot_profits_table()
# policy_evaluator.plot_thresholds_per_day()
optimal_penalty, profit, charge_cycles = (
policy_evaluator.optimize_penalty_for_target_charge_cycles(
idx_samples=idx_samples,
test_loader=test_loader,
initial_penalty=1000,
target_charge_cycles=283,
learning_rate=15,
max_iterations=150,
tolerance=1,
)
)
print(
f"Optimal Penalty: {optimal_penalty}, Profit: {profit}, Charge Cycles: {charge_cycles}"
)
task.get_logger().report_single_value(name="Optimal Penalty", value=optimal_penalty)
task.get_logger().report_single_value(name="Optimal Profit", value=profit)
task.get_logger().report_single_value(name="Optimal Charge Cycles", value=charge_cycles)
task.close()