114 lines
3.5 KiB
Python
Executable File
114 lines
3.5 KiB
Python
Executable File
#!/usr/bin/env python
|
|
# coding: utf-8
|
|
import lzma
|
|
from gensim.models import Word2Vec
|
|
import gensim.downloader
|
|
import numpy as np
|
|
import pandas as pd
|
|
import torch
|
|
|
|
X_train = lzma.open("train/in.tsv.xz", mode='rt', encoding='utf-8').readlines()
|
|
y_train = np.array(open('train/expected.tsv').readlines())
|
|
X_dev0 = lzma.open("dev-0/in.tsv.xz", mode='rt', encoding='utf-8').readlines()
|
|
y_expected_dev0 = np.array(open("dev-0/expected.tsv", "r").readlines())
|
|
X_test = lzma.open("test-A/in.tsv.xz", mode='rt', encoding='utf-8').readlines()
|
|
|
|
X_train = [line.split() for line in X_train]
|
|
X_dev0 = [line.split() for line in X_dev0]
|
|
X_test = [line.split() for line in X_test]
|
|
|
|
model_w2v = Word2Vec(X_train, vector_size=100, window=5, min_count=1, workers=4)
|
|
|
|
def vectorize(model, data):
|
|
return np.array([np.mean([model.wv[word] if word in model.wv.key_to_index else np.zeros(100, dtype=float) for word in doc], axis=0) for doc in data])
|
|
|
|
|
|
X_train_w2v = vectorize(model_w2v, X_train)
|
|
X_dev0_w2v = vectorize(model_w2v, X_dev0)
|
|
X_test_w2v = vectorize(model_w2v, X_test)
|
|
|
|
|
|
FEATURES = 100
|
|
|
|
class NeuralNetworkModel(torch.nn.Module):
|
|
|
|
def __init__(self):
|
|
super(NeuralNetworkModel, self).__init__()
|
|
self.fc1 = torch.nn.Linear(FEATURES,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 = 42
|
|
criterion = torch.nn.BCELoss()
|
|
optimizer = torch.optim.SGD(nn_model.parameters(), lr = 0.1)
|
|
|
|
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 = np.array(X_dataset[i:i+BATCH_SIZE]).astype(np.float32)
|
|
X = torch.tensor(X)
|
|
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)
|
|
|
|
def predict(model, data):
|
|
model.eval()
|
|
predictions = []
|
|
for x in data:
|
|
X = torch.tensor(np.array(x).astype(np.float32))
|
|
Y_predictions = model(X)
|
|
if Y_predictions[0] > 0.5:
|
|
predictions.append("1")
|
|
else:
|
|
predictions.append("0")
|
|
return predictions
|
|
|
|
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_w2v[i:i+BATCH_SIZE]
|
|
X = torch.tensor(X)
|
|
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]
|
|
|
|
display(epoch)
|
|
display(get_loss_acc(nn_model, X_train_w2v, y_train))
|
|
display(get_loss_acc(nn_model, X_dev0_w2v, y_expected_dev0))
|
|
|
|
|
|
y_pred_dev0 = predict(nn_model, X_dev0_w2v)
|
|
y_pred_test = predict(nn_model, X_test_w2v)
|
|
|
|
open('dev-0/out.tsv', 'w').writelines([i+'\n' for i in y_pred_dev0])
|
|
open('test-A/out.tsv', 'w').writelines([i+'\n' for i in y_pred_test]) |