173 lines
4.5 KiB
Python
173 lines
4.5 KiB
Python
![]() |
import lzma
|
||
|
import gensim.downloader
|
||
|
import numpy as np
|
||
|
import torch
|
||
|
|
||
|
FEAUTERES = 100
|
||
|
|
||
|
def predict(data):
|
||
|
nn_model.eval()
|
||
|
predictions = []
|
||
|
for i in range(len(data)):
|
||
|
X = data[i]
|
||
|
X = torch.tensor(X.astype(np.float32))
|
||
|
Y_predictions = nn_model(X)
|
||
|
if Y_predictions[0] > 0.5:
|
||
|
predictions.append("1")
|
||
|
else:
|
||
|
predictions.append("0")
|
||
|
return predictions
|
||
|
|
||
|
def vectorize(data):
|
||
|
vectorized_data = np.array([np.array([word2vec_model.wv[i] for i in ls if i in words]) for ls in data])
|
||
|
avarage_vector = []
|
||
|
for vector in vectorized_data:
|
||
|
if vector.size:
|
||
|
avarage_vector.append(vector.mean(axis=0))
|
||
|
else:
|
||
|
avarage_vector.append(np.zeros(100, dtype=float))
|
||
|
return avarage_vector
|
||
|
|
||
|
|
||
|
def generate_out(folder_path):
|
||
|
print('Generating out')
|
||
|
X_dev = []
|
||
|
with lzma.open(f"{folder_path}/in.tsv.xz", 'r') as file:
|
||
|
for line in file:
|
||
|
line = line.strip()
|
||
|
line = line.decode("utf-8")
|
||
|
tabs = line.rsplit('\t')
|
||
|
content = tabs[0]
|
||
|
pre_processed = gensim.utils.simple_preprocess(content)
|
||
|
X_dev.append(pre_processed)
|
||
|
|
||
|
print("step 5")
|
||
|
X_dev = vectorize(X_dev)
|
||
|
prediction = predict(X_dev)
|
||
|
|
||
|
print("step 6")
|
||
|
f = open(f"{folder_path}/out.tsv", "a")
|
||
|
for p in prediction:
|
||
|
f.write(str(p) + '\n')
|
||
|
f.close()
|
||
|
|
||
|
|
||
|
def get_loss_acc(model, X_dataset, Y_dataset):
|
||
|
loss_score = 0
|
||
|
acc_score = 0
|
||
|
items_total = 0
|
||
|
model.eval()
|
||
|
for i in range(0, Y_dataset.shape[0], BATCH_SIZE):
|
||
|
X = X_dataset[i:i+BATCH_SIZE]
|
||
|
X = torch.tensor(X.astype(np.float32))
|
||
|
Y = Y_dataset[i:i+BATCH_SIZE]
|
||
|
Y = torch.tensor(Y.astype(np.float32)).reshape(-1,1)
|
||
|
Y_predictions = model(X)
|
||
|
acc_score += torch.sum((Y_predictions > 0.5) == Y).item()
|
||
|
items_total += Y.shape[0]
|
||
|
|
||
|
loss = criterion(Y_predictions, Y)
|
||
|
|
||
|
loss_score += loss.item() * Y.shape[0]
|
||
|
return (loss_score / items_total), (acc_score / items_total)
|
||
|
|
||
|
|
||
|
class NeuralNetworkModel(torch.nn.Module):
|
||
|
|
||
|
def __init__(self):
|
||
|
super(NeuralNetworkModel, self).__init__()
|
||
|
self.fc1 = torch.nn.Linear(FEAUTERES,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
|
||
|
|
||
|
|
||
|
|
||
|
if __name__ == "__main__":
|
||
|
X = []
|
||
|
Y = []
|
||
|
with lzma.open('train/in.tsv.xz', 'r') as file:
|
||
|
for line in file:
|
||
|
line = line.strip()
|
||
|
line = line.decode("utf-8")
|
||
|
tabs = line.rsplit('\t')
|
||
|
content = tabs[0]
|
||
|
pre_processed = gensim.utils.simple_preprocess(content)
|
||
|
X.append(pre_processed)
|
||
|
print("step 1")
|
||
|
with open('train/expected.tsv', 'r') as file:
|
||
|
for line in file:
|
||
|
line = line.strip()
|
||
|
Y.append(int(line))
|
||
|
|
||
|
X_train = X
|
||
|
Y_train = Y
|
||
|
print("step 2")
|
||
|
|
||
|
|
||
|
print('Word to vec start')
|
||
|
|
||
|
word2vec_model = gensim.models.Word2Vec(X_train, vector_size=100, window=5, min_count=2)
|
||
|
print('Created model')
|
||
|
words = set(word2vec_model.wv.index_to_key)
|
||
|
print('Created set of worlds')
|
||
|
|
||
|
X_train = vectorize(X_train)
|
||
|
X_train = np.array(X_train)
|
||
|
Y_train = np.array(Y_train)
|
||
|
print('Vectorized data')
|
||
|
|
||
|
|
||
|
print('Word to vec ended')
|
||
|
print("step 3")
|
||
|
# model = LogisticRegression()
|
||
|
# model.fit(X_vectorized, Y)
|
||
|
nn_model = NeuralNetworkModel()
|
||
|
BATCH_SIZE = 5
|
||
|
criterion = torch.nn.BCELoss()
|
||
|
optimizer = torch.optim.SGD(nn_model.parameters(), lr = 0.1)
|
||
|
|
||
|
for epoch in range(7):
|
||
|
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(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('Printing')
|
||
|
print(epoch)
|
||
|
print(get_loss_acc(nn_model, X_train, Y_train))
|
||
|
|
||
|
# display(get_loss_acc(nn_model, X_dev, Y_dev))
|
||
|
|
||
|
print("step 4")
|
||
|
generate_out('dev-0')
|
||
|
# generate_out('dev-1')
|
||
|
generate_out('test-A')
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|
||
|
|