68 lines
1.8 KiB
Python
68 lines
1.8 KiB
Python
import numpy as np
|
|
import torch
|
|
import gensim
|
|
from sklearn import preprocessing
|
|
import pandas as pd
|
|
from gensim.test.utils import common_texts
|
|
from gensim.models import Word2Vec
|
|
|
|
with open("train/in.tsv") as f:
|
|
X_train = f.readlines()
|
|
with open("train/expected.tsv") as ff:
|
|
Y_train = ff.readlines()
|
|
with open("test-A/in.tsv") as d:
|
|
X = d.readlines()
|
|
|
|
model = Word2Vec(X_train, min_count=1,size= 50,workers=3, window =3, sg = 1)
|
|
X_train=model[X_train]
|
|
X=model[X]
|
|
FEAUTERES=1000
|
|
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
|
|
|
|
nn_model = NeuralNetworkModel()
|
|
|
|
BATCH_SIZE = 5
|
|
|
|
criterion = torch.nn.BCELoss()
|
|
|
|
optimizer = torch.optim.SGD(nn_model.parameters(), lr = 0.1)
|
|
|
|
for epoch in range(10):
|
|
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).todense())
|
|
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]
|
|
with open('test-A/out.tsv', 'w') as file:
|
|
for e in Y_predictions:
|
|
file.write("%f\n" % e)
|
|
|
|
|