91 lines
2.8 KiB
Python
91 lines
2.8 KiB
Python
|
import numpy as np
|
||
|
|
import torch
|
||
|
|
from nltk.tokenize import word_tokenize
|
||
|
|
import nltk
|
||
|
|
from gensim import models
|
||
|
|
from pandas import DataFrame
|
||
|
|
import csv
|
||
|
|
|
||
|
|
eph = 5
|
||
|
|
BATCH_SIZE = 1
|
||
|
|
|
||
|
|
class MyNeuralnn_model(torch.nn.Module):
|
||
|
|
def __init__(self):
|
||
|
|
super(MyNeuralnn_model, self).__init__()
|
||
|
|
self.fc1 = torch.nn.Linear(300, 600)
|
||
|
|
self.fc2 = torch.nn.Linear(600, 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 = MyNeuralnn_model()
|
||
|
|
criterion = torch.nn.BCELoss()
|
||
|
|
optimizer = torch.optim.SGD(nn_model.parameters(), lr=0.01)
|
||
|
|
word2vec = models.KeyedVectors.load_word2vec_format(r"GoogleNews-vectors-negative300.bin.gz", binary=True, limit = 100000)
|
||
|
|
|
||
|
|
def vectorize(document):
|
||
|
|
return np.mean([word2vec[word] for word in document if word in word2vec] or [np.zeros(300)], axis=0)
|
||
|
|
|
||
|
|
Xtrain = []
|
||
|
|
with open("train/in.tsv", 'r', encoding="utf-8") as train:
|
||
|
|
for line in csv.reader(train, delimiter="\t"):
|
||
|
|
Xtrain.append(line[0].lower())
|
||
|
|
Xtrain = [word_tokenize(x) for x in Xtrain]
|
||
|
|
Xtrain = [vectorize(document) for document in Xtrain]
|
||
|
|
|
||
|
|
Ytrain = []
|
||
|
|
with open("train/expected.tsv", 'r', encoding="utf-8") as train:
|
||
|
|
for line in csv.reader(train, delimiter="\t"):
|
||
|
|
Ytrain.append(line[0].lower())
|
||
|
|
Ytrain = DataFrame(Ytrain)
|
||
|
|
|
||
|
|
Xdev = []
|
||
|
|
with open("dev-0/in.tsv", 'r', encoding="utf-8") as train:
|
||
|
|
for line in csv.reader(train, delimiter="\t"):
|
||
|
|
Xdev.append(line[0].lower())
|
||
|
|
Xdev = [word_tokenize(x) for x in Xdev]
|
||
|
|
Xdev = [vectorize(x) for x in Xdev]
|
||
|
|
|
||
|
|
Xtest = []
|
||
|
|
with open("test-A/in.tsv", 'r', encoding="utf-8") as train:
|
||
|
|
for line in csv.reader(train, delimiter="\t"):
|
||
|
|
Xtest.append(line[0].lower())
|
||
|
|
Xtest = [word_tokenize(x) for x in Xtest]
|
||
|
|
Xtest = [vectorize(x) for x in Xtest]
|
||
|
|
|
||
|
|
|
||
|
|
for epoch in range(eph):
|
||
|
|
nn_model.train()
|
||
|
|
for i in range(0, Ytrain.shape[0], BATCH_SIZE):
|
||
|
|
x = Xtrain[i :i + BATCH_SIZE]
|
||
|
|
x = torch.tensor(x).float()
|
||
|
|
y = Ytrain[i :i + BATCH_SIZE]
|
||
|
|
y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1,1)
|
||
|
|
y_predictions = nn_model(x)
|
||
|
|
|
||
|
|
loss = criterion(y_predictions, y)
|
||
|
|
optimizer.zero_grad()
|
||
|
|
loss.backward()
|
||
|
|
optimizer.step()
|
||
|
|
|
||
|
|
with torch.no_grad():
|
||
|
|
# Predykcja dla Dev
|
||
|
|
with open('dev-0/out.tsv', 'w', encoding="utf-8") as dev_out:
|
||
|
|
for i in range(0, len(Xdev), BATCH_SIZE):
|
||
|
|
x = Xdev[i :i + BATCH_SIZE]
|
||
|
|
x = torch.tensor(x).float()
|
||
|
|
predict = nn_model(x) > 0.5
|
||
|
|
dev_out.write(str(predict.to(torch.int32)[0].item()) + '\n')
|
||
|
|
# Predykcja dla test
|
||
|
|
with open('test-A/out.tsv', 'w', encoding="utf-8") as test_A:
|
||
|
|
for i in range(0, len(Xtest), BATCH_SIZE):
|
||
|
|
x = Xtest[i :i + BATCH_SIZE]
|
||
|
|
x = torch.tensor(x).float()
|
||
|
|
predict = nn_model(x) > 0.5
|
||
|
|
test_A.write(str(predict.to(torch.int32)[0].item()) + '\n')
|
||
|
|
|