Marcin Kostrzewski
d794e390aa
Some checks failed
s444409-training/pipeline/head There was a failure building this commit
145 lines
3.5 KiB
Python
145 lines
3.5 KiB
Python
import argparse
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
import torch
|
|
from sacred.observers import FileStorageObserver
|
|
from torch import nn
|
|
from torch.utils.data import DataLoader, Dataset
|
|
from sacred import Experiment
|
|
|
|
default_batch_size = 64
|
|
default_epochs = 5
|
|
|
|
device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
|
|
|
|
def hour_to_int(text: str):
|
|
return float(text.replace(':', ''))
|
|
|
|
|
|
def int_to_hour(num: int):
|
|
return str(num)
|
|
|
|
|
|
class PlantsDataset(Dataset):
|
|
def __init__(self, file_name):
|
|
df = pd.read_csv(file_name)
|
|
|
|
x = np.array([x[0].split(' ')[1] for x in df.iloc[:, 0:1].values])
|
|
y = df.iloc[:, 3].values
|
|
|
|
x_processed = np.array([hour_to_int(h) for h in x], dtype='float32')
|
|
|
|
self.x_train = torch.from_numpy(x_processed)
|
|
self.y_train = torch.from_numpy(y)
|
|
self.x_train.type(torch.LongTensor)
|
|
|
|
def __len__(self):
|
|
return len(self.y_train)
|
|
|
|
def __getitem__(self, idx):
|
|
return self.x_train[idx].float(), self.y_train[idx].float()
|
|
|
|
|
|
class MLP(nn.Module):
|
|
def __init__(self):
|
|
super().__init__()
|
|
self.layers = nn.Sequential(
|
|
nn.Linear(1, 64),
|
|
nn.ReLU(),
|
|
nn.Linear(64, 32),
|
|
nn.ReLU(),
|
|
nn.Linear(32, 1),
|
|
)
|
|
|
|
def forward(self, x):
|
|
x = x.view(x.size(0), -1)
|
|
return self.layers(x)
|
|
|
|
|
|
def train(dataloader, model, loss_fn, optimizer):
|
|
size = len(dataloader.dataset)
|
|
model.train()
|
|
for batch, (X, y) in enumerate(dataloader):
|
|
X, y = X.to(device), y.to(device)
|
|
|
|
# Compute prediction error
|
|
pred = model(X)
|
|
loss = loss_fn(pred, y)
|
|
|
|
# Backpropagation
|
|
optimizer.zero_grad()
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
if batch % 100 == 0:
|
|
loss, current = loss.item(), batch * len(X)
|
|
print(f"loss: {loss:>7f} [{current:>5d}/{size:>5d}]")
|
|
|
|
|
|
def test(dataloader, model, loss_fn):
|
|
num_batches = len(dataloader)
|
|
model.eval()
|
|
test_loss, correct = 0, 0
|
|
with torch.no_grad():
|
|
for X, y in dataloader:
|
|
X, y = X.to(device), y.to(device)
|
|
pred = model(X)
|
|
test_loss += loss_fn(pred, y).item()
|
|
test_loss /= num_batches
|
|
print(f"Avg loss (using {loss_fn}): {test_loss:>8f} \n")
|
|
return test_loss
|
|
|
|
|
|
def main(batch_size, epochs):
|
|
print(f"Using {device} device")
|
|
|
|
plant_test = PlantsDataset('data/Plant_1_Generation_Data.csv.test')
|
|
plant_train = PlantsDataset('data/Plant_1_Generation_Data.csv.train')
|
|
|
|
train_dataloader = DataLoader(plant_train, batch_size=batch_size)
|
|
test_dataloader = DataLoader(plant_test, batch_size=batch_size)
|
|
|
|
for i, (data, labels) in enumerate(train_dataloader):
|
|
print(data.shape, labels.shape)
|
|
print(data, labels)
|
|
break
|
|
|
|
model = MLP()
|
|
print(model)
|
|
|
|
loss_fn = nn.MSELoss()
|
|
optimizer = torch.optim.Adam(model.parameters(), lr=1e-3)
|
|
for t in range(epochs):
|
|
print(f"Epoch {t + 1}\n-------------------------------")
|
|
train(train_dataloader, model, loss_fn, optimizer)
|
|
test(test_dataloader, model, loss_fn)
|
|
print("Done!")
|
|
|
|
torch.save(model.state_dict(), './model_out')
|
|
print("Model saved in ./model_out file.")
|
|
|
|
|
|
def setup_experiment():
|
|
ex = Experiment('Predict power output for a given time')
|
|
ex.observers.append(FileStorageObserver('sacred_runs'))
|
|
return ex
|
|
|
|
|
|
ex = setup_experiment()
|
|
|
|
|
|
@ex.config
|
|
def experiment_config():
|
|
batch_size = 64
|
|
epochs = 5
|
|
|
|
|
|
@ex.automain
|
|
def run(batch_size, epochs):
|
|
main(batch_size, epochs)
|
|
|
|
|
|
ex.add_artifact('model_out')
|