Upload files to ''

This commit is contained in:
Kacper Dudzic 2022-05-24 23:38:18 +02:00
parent 78d8d6bb37
commit e0386bbcc2
2 changed files with 119 additions and 0 deletions

59
predict.py Normal file
View File

@ -0,0 +1,59 @@
import numpy as np
import torch
from gensim import downloader
import gensim
class NeuralNetworkModel(torch.nn.Module):
def __init__(self):
super(NeuralNetworkModel, self).__init__()
self.fc1 = torch.nn.Linear(100, 500)
self.fc2 = torch.nn.Linear(500, 1)
def forward(self, x):
x = self.fc1(x)
x = torch.relu(x)
x = self.fc2(x)
x = torch.sigmoid(x)
return x
BATCH_SIZE = 5
PATH = "new_model_full.pt"
model = torch.load(PATH)
model.eval()
glove_vectors = downloader.load("glove-wiki-gigaword-100")
with open(r"C:\Users\Kacper Dudzic\Desktop\paranormal-or-skeptic\dev-0\in.tsv", "r", encoding="utf-8") as dev_in, \
open(r"C:\Users\Kacper Dudzic\Desktop\paranormal-or-skeptic\test-A\in.tsv", "r", encoding="utf-8") as test_in:
X_dev = [line for line in dev_in.readlines()]
X_dev = [np.mean([glove_vectors[tk] for tk in gensim.utils.tokenize(text, lowercase=True) if tk in glove_vectors] or
[np.zeros(100)], axis=0) for text in X_dev]
X_test = [line for line in test_in.readlines()]
X_test = [np.mean([glove_vectors[tk] for tk in gensim.utils.tokenize(text, lowercase=True) if tk in glove_vectors] or
[np.zeros(100)], axis=0) for text in X_test]
with open('dev_out.tsv', 'w', encoding='utf-8') as dev_out, open('test_out.tsv', 'w', encoding='utf-8') as test_out:
dev_predictions = []
test_predictions = []
for i in range(0, len(X_dev), BATCH_SIZE):
X = X_dev[i:i + BATCH_SIZE]
X = torch.tensor(np.array(X).astype(np.float32))
Y_predictions = (model(X) > 0.5)
dev_predictions.extend(Y_predictions)
for i in range(0, len(X_test), BATCH_SIZE):
X = X_test[i:i + BATCH_SIZE]
X = torch.tensor(np.array(X).astype(np.float32))
Y_predictions = (model(X) > 0.5)
test_predictions.extend(Y_predictions)
for pred in dev_predictions:
dev_out.write(str(pred.int()[0].item()) + '\n')
for pred in test_predictions:
test_out.write(str(pred.int()[0].item()) + '\n')

60
train.py Normal file
View File

@ -0,0 +1,60 @@
import numpy as np
import torch
from gensim import downloader
import gensim
with open(r"C:\Users\Kacper Dudzic\Desktop\paranormal-or-skeptic\train\in.tsv", "r", encoding="utf-8") as f:
X_train = [line.strip() for line in f.readlines()]
with open(r"C:\Users\Kacper Dudzic\Desktop\paranormal-or-skeptic\train\expected.tsv", "r", encoding="utf-8") as f:
Y_train = np.array([int(line.strip()) for line in f.readlines()])
glove_vectors = downloader.load("glove-wiki-gigaword-100")
X_train = [np.mean([glove_vectors[tk] for tk in gensim.utils.tokenize(text, lowercase=True) if tk in glove_vectors] or
[np.zeros(100)], axis=0) for text in X_train]
class NeuralNetworkModel(torch.nn.Module):
def __init__(self):
super(NeuralNetworkModel, self).__init__()
self.fc1 = torch.nn.Linear(100, 500)
self.fc2 = torch.nn.Linear(500, 1)
def forward(self, x):
x = self.fc1(x)
x = torch.relu(x)
x = self.fc2(x)
x = torch.sigmoid(x)
return x
nn_model = NeuralNetworkModel()
criterion = torch.nn.BCELoss()
optimizer = torch.optim.Adam(nn_model.parameters())
BATCH_SIZE = 5
for epoch in range(5):
loss_score = 0
acc_score = 0
items_total = 0
nn_model.train()
for i in range(0, Y_train.shape[0], BATCH_SIZE):
X = X_train[i:i + BATCH_SIZE]
X = torch.tensor(np.array(X).astype(np.float32))
Y = Y_train[i:i + BATCH_SIZE]
Y = torch.tensor(Y.astype(np.float32)).reshape(-1, 1)
Y_predictions = nn_model(X)
acc_score += torch.sum((Y_predictions > 0.5) == Y).item()
items_total += Y.shape[0]
optimizer.zero_grad()
loss = criterion(Y_predictions, Y)
loss.backward()
optimizer.step()
loss_score += loss.item() * Y.shape[0]
print(epoch)
print((loss_score / items_total), (acc_score / items_total))
PATH = "new_model_full.pt"
torch.save(nn_model, PATH)