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

Policy evaluation during training

Browse Source
This commit is contained in:
Victor Mylle
2024-02-25 22:13:00 +01:00
parent 90751866a4
commit f1b54df2c9
5 changed files with 450 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/training_scripts/autoregressive_quantiles.py
View File

@@ -1,3 +1,12 @@
from src.utils.clearml import ClearMLHelper
#### ClearML ####
clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
task = clearml_helper.get_task(
task_name="Autoregressive Quantile Regression: Non Linear"
)
task.execute_remotely(queue_name="default", exit_process=True)
from src.policies.PolicyEvaluator import PolicyEvaluator
from src.policies.simple_baseline import BaselinePolicy, Battery
from src.models.lstm_model import GRUModel
@@ -13,11 +22,6 @@ import torch.nn as nn
from src.models.time_embedding_layer import TimeEmbedding
#### ClearML ####
clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
task = clearml_helper.get_task(task_name="Autoregressive Quantile Regression: Non Linear")
#### Data Processor ####
data_config = DataConfig()
@@ -34,7 +38,6 @@ data_config.DAY_OF_WEEK = True
data_config.NOMINAL_NET_POSITION = True
data_config = task.connect(data_config, name="data_features")
data_processor = DataProcessor(data_config, path="", lstm=False)
@@ -68,9 +71,17 @@ model_parameters = {
model_parameters = task.connect(model_parameters, name="model_parameters")
time_embedding = TimeEmbedding(data_processor.get_time_feature_size(), model_parameters["time_feature_embedding"])
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"])
non_linear_model = NonLinearRegression(time_embedding.output_dim(inputDim), len(quantiles), hiddenSize=model_parameters["hidden_size"], numLayers=model_parameters["num_layers"], dropout=model_parameters["dropout"])
non_linear_model = NonLinearRegression(
time_embedding.output_dim(inputDim),
len(quantiles),
hiddenSize=model_parameters["hidden_size"],
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)
@@ -103,10 +114,11 @@ 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)
predict_sequence_length=trainer.model.output_size, full_day_skip=True
)
policy_evaluator.evaluate_test_set(idx_samples, test_loader)
policy_evaluator.plot_profits_table()
policy_evaluator.plot_thresholds_per_day()
task.close()
task.close()

44
src/training_scripts/diffusion_training.py
View File

@@ -1,25 +1,17 @@
from clearml import Task
from src.data import DataProcessor, DataConfig
from src.trainers.trainer import Trainer
from src.utils.clearml import ClearMLHelper
from src.models import *
from src.losses import *
import torch
import numpy as np
from torch.nn import MSELoss, L1Loss
from datetime import datetime
import torch.nn as nn
from src.models.time_embedding_layer import TimeEmbedding
from src.models.diffusion_model import GRUDiffusionModel, SimpleDiffusionModel
from src.trainers.diffusion_trainer import DiffusionTrainer
clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
task = clearml_helper.get_task(task_name="Diffusion Training")
# execute remotely
task.execute_remotely(queue_name="default", exit_process=True)
print("Running remotely")
from src.models import *
from src.losses import *
from src.models.time_embedding_layer import TimeEmbedding
from src.models.diffusion_model import GRUDiffusionModel, SimpleDiffusionModel
from src.trainers.diffusion_trainer import DiffusionTrainer
from src.data import DataProcessor, DataConfig
from src.policies.simple_baseline import BaselinePolicy, Battery
from src.policies.PolicyEvaluator import PolicyEvaluator
#### Data Processor ####
data_config = DataConfig()
@@ -54,11 +46,21 @@ model_parameters = {
model_parameters = task.connect(model_parameters, name="model_parameters")
#### Model ####
model = SimpleDiffusionModel(96, model_parameters["hidden_sizes"], other_inputs_dim=inputDim[1], time_dim=model_parameters["time_dim"])
model = SimpleDiffusionModel(
96,
model_parameters["hidden_sizes"],
other_inputs_dim=inputDim[1],
time_dim=model_parameters["time_dim"],
)
# model = GRUDiffusionModel(96, model_parameters["hidden_sizes"], other_inputs_dim=inputDim[2], time_dim=model_parameters["time_dim"], gru_hidden_size=128)
print("Starting training ...")
### Policy Evaluator ###
battery = Battery(2, 1)
baseline_policy = BaselinePolicy(battery, data_path="")
policy_evaluator = PolicyEvaluator(baseline_policy, task)
#### Trainer ####
trainer = DiffusionTrainer(model, data_processor, "cuda")
trainer.train(model_parameters["epochs"], model_parameters["learning_rate"], task)
trainer = DiffusionTrainer(
model, data_processor, "cuda", policy_evaluator=policy_evaluator
)
trainer.train(model_parameters["epochs"], model_parameters["learning_rate"], task)