60 lines
2.1 KiB
Python
60 lines
2.1 KiB
Python
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')
|