paranormal-or-skeptic-ISI-p.../program.py
Jan Przybylski caa65adce5 up
2021-05-10 23:26:41 +02:00

71 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= 500,workers=3, window =3, sg = 1)
model1 = Word2Vec(X, min_count=1,size= 500,workers=3, window =3, sg = 1)
X_train=model.wv
X=model1.wv
FEAUTERES=500
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)