85 lines
2.6 KiB
Python
85 lines
2.6 KiB
Python
|
import gensim.downloader as gensim
|
||
|
|
import numpy as np
|
||
|
|
import pandas as pd
|
||
|
|
import torch
|
||
|
|
from nltk.tokenize import word_tokenize
|
||
|
|
|
||
|
|
|
||
|
|
class NeuralNetworkModel(torch.nn.Module):
|
||
|
|
def __init__(self):
|
||
|
|
super(NeuralNetworkModel, self).__init__()
|
||
|
|
self.l01 = torch.nn.Linear(300, 300)
|
||
|
|
self.l02 = torch.nn.Linear(300, 1)
|
||
|
|
|
||
|
|
def forward(self, x):
|
||
|
|
x = self.l01(x)
|
||
|
|
x = torch.relu(x)
|
||
|
|
x = self.l02(x)
|
||
|
|
x = torch.sigmoid(x)
|
||
|
|
return x
|
||
|
|
|
||
|
|
|
||
|
|
def d2v(doc):
|
||
|
|
return np.mean([word2vec[word] for word in doc if word in word2vec] or [np.zeros(300)], axis=0)
|
||
|
|
|
||
|
|
|
||
|
|
x_train = pd.read_table('train/in.tsv.xz', compression='xz', sep='\t', header=None, error_bad_lines=False, quoting=3)
|
||
|
|
y_train = pd.read_table('train/expected.tsv', sep='\t', header=None, quoting=3)
|
||
|
|
y_train = y_train[0]
|
||
|
|
x_dev = pd.read_table('dev-0/in.tsv.xz', compression='xz', sep='\t', header=None, quoting=3)
|
||
|
|
x_test = pd.read_table('test-A/in.tsv.xz', compression='xz', sep='\t', header=None, quoting=3)
|
||
|
|
x_train = x_train[0].str.lower()
|
||
|
|
x_dev = x_dev[0].str.lower()
|
||
|
|
x_test = x_test[0].str.lower()
|
||
|
|
x_train = [word_tokenize(x) for x in x_train]
|
||
|
|
x_dev = [word_tokenize(x) for x in x_dev]
|
||
|
|
x_test = [word_tokenize(x) for x in x_test]
|
||
|
|
word2vec = gensim.load('word2vec-google-news-300')
|
||
|
|
x_train = [d2v(doc) for doc in x_train]
|
||
|
|
x_dev = [d2v(doc) for doc in x_dev]
|
||
|
|
x_test = [d2v(doc) for doc in x_test]
|
||
|
|
|
||
|
|
model = NeuralNetworkModel()
|
||
|
|
BATCH_SIZE = 5
|
||
|
|
criterion = torch.nn.BCELoss()
|
||
|
|
optimizer = torch.optim.Adam(model.parameters())
|
||
|
|
|
||
|
|
for epoch in range(5):
|
||
|
|
model.train()
|
||
|
|
for i in range(0, y_train.shape[0], BATCH_SIZE):
|
||
|
|
X = x_train[i:i + BATCH_SIZE]
|
||
|
|
X = torch.tensor(X)
|
||
|
|
y = y_train[i:i + BATCH_SIZE]
|
||
|
|
y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
|
||
|
|
optimizer.zero_grad()
|
||
|
|
outputs = model(X.float())
|
||
|
|
loss = criterion(outputs, y)
|
||
|
|
loss.backward()
|
||
|
|
optimizer.step()
|
||
|
|
|
||
|
|
y_dev = []
|
||
|
|
y_test = []
|
||
|
|
model.eval()
|
||
|
|
|
||
|
|
with torch.no_grad():
|
||
|
|
for i in range(0, len(x_dev), BATCH_SIZE):
|
||
|
|
X = x_dev[i:i + BATCH_SIZE]
|
||
|
|
X = torch.tensor(X)
|
||
|
|
outputs = model(X.float())
|
||
|
|
y = (outputs > 0.5)
|
||
|
|
y_dev.extend(y)
|
||
|
|
|
||
|
|
for i in range(0, len(x_test), BATCH_SIZE):
|
||
|
|
X = x_test[i:i + BATCH_SIZE]
|
||
|
|
X = torch.tensor(X)
|
||
|
|
outputs = model(X.float())
|
||
|
|
y = (outputs >= 0.5)
|
||
|
|
y_test.extend(y)
|
||
|
|
|
||
|
|
y_dev = np.asarray(y_dev, dtype=np.int32)
|
||
|
|
y_test = np.asarray(y_test, dtype=np.int32)
|
||
|
|
Y_dev = pd.DataFrame({'label': y_dev})
|
||
|
|
Y_test = pd.DataFrame({'label': y_test})
|
||
|
|
Y_dev.to_csv(r'dev-0/out.tsv', sep='\t', index=False, header=False)
|
||
|
|
Y_test.to_csv(r'test-A/out.tsv', sep='\t', index=False, header=False)
|