113 lines
3.5 KiB
Python
113 lines
3.5 KiB
Python
import pandas as pd
|
|
import numpy as np
|
|
import csv
|
|
import torch
|
|
from nltk.tokenize import word_tokenize
|
|
from gensim import downloader
|
|
|
|
FEATURES = ['content', 'id', 'label']
|
|
PATHS = ['train/in.tsv', 'train/expected.tsv', 'dev-0/in.tsv', './dev-0/out.tsv']
|
|
PRE_TRAINED = 'word2vec-google-news-300'
|
|
|
|
class NeuralNetwork(torch.nn.Module):
|
|
def __init__(self, INPUT_DIM):
|
|
super(NeuralNetwork, self).__init__()
|
|
self.l1 = torch.nn.Linear(INPUT_DIM, 500)
|
|
self.l2 = torch.nn.Linear(500, 1)
|
|
|
|
def forward(self, x):
|
|
x = self.l1(x)
|
|
x = torch.relu(x)
|
|
x = self.l2(x)
|
|
x = torch.sigmoid(x)
|
|
return x
|
|
|
|
def get_data(FEATURES, PATHS):
|
|
x_train = pd.read_table(PATHS[0], error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = FEATURES[:2])
|
|
y_train = pd.read_table(PATHS[1], error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = FEATURES[2:])
|
|
x_dev = pd.read_table(PATHS[2], error_bad_lines = False, header = None, quoting = csv.QUOTE_NONE, names = FEATURES[:2])
|
|
|
|
return x_train, y_train, x_dev
|
|
|
|
def preprocess(x_train, y_train, x_dev):
|
|
x_train = x_train[FEATURES[0]].str.lower()
|
|
x_dev = x_dev[FEATURES[0]].str.lower()
|
|
y_train = y_train[FEATURES[2]]
|
|
|
|
return x_train, y_train, x_dev
|
|
|
|
def tokenize(x_train, x_dev):
|
|
x_train = [word_tokenize(i) for i in x_train]
|
|
x_dev = [word_tokenize(i) for i in x_dev]
|
|
|
|
return x_train, x_dev
|
|
|
|
def use_word2vec():
|
|
w2v = downloader.load(PRE_TRAINED)
|
|
|
|
return w2v
|
|
|
|
def document_vector(w2v, x_train, x_dev):
|
|
x_train = [np.mean([w2v[word] for word in doc if word in w2v] or [np.zeros(300)], axis = 0) for doc in x_train]
|
|
x_dev = [np.mean([w2v[word] for word in doc if word in w2v] or [np.zeros(300)], axis = 0) for doc in x_dev]
|
|
|
|
return x_train, x_dev
|
|
|
|
def basic_config():
|
|
INPUT_DIM = 300
|
|
BATCH_SIZE = 5
|
|
|
|
return INPUT_DIM, BATCH_SIZE
|
|
|
|
def init_model(INPUT_DIM):
|
|
nn_model = NeuralNetwork(INPUT_DIM)
|
|
criterion = torch.nn.BCELoss()
|
|
optimizer = torch.optim.SGD(nn_model.parameters(), lr = 0.1)
|
|
|
|
return nn_model, optimizer, criterion
|
|
|
|
def train(nn_model, BATCH_SIZE, criterion, optimizer, x_train, y_train):
|
|
for epoch in range(5):
|
|
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)
|
|
y = y_train[i:i+BATCH_SIZE]
|
|
y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
|
|
outputs = nn_model(X.float())
|
|
loss = criterion(outputs, y)
|
|
optimizer.zero_grad()
|
|
loss.backward()
|
|
optimizer.step()
|
|
|
|
def prediction(nn_model, BATCH_SIZE, x_dev):
|
|
y_dev = []
|
|
nn_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 = nn_model(X.float())
|
|
prediction = (outputs > 0.5)
|
|
y_dev += prediction.tolist()
|
|
|
|
return y_dev
|
|
|
|
def get_result(y_dev):
|
|
np.asarray(y_dev, dtype = np.int32).tofile(PATHS[3], sep='\n')
|
|
|
|
def main():
|
|
x_train, y_train, x_dev = get_data(FEATURES, PATHS)
|
|
x_train, y_train, x_dev = preprocess(x_train, y_train, x_dev)
|
|
x_train, x_dev = tokenize(x_train, x_dev)
|
|
w2v = use_word2vec()
|
|
x_train, x_dev = document_vector(w2v, x_train, x_dev)
|
|
INPUT_DIM, BATCH_SIZE = basic_config()
|
|
nn_model, optimizer, criterion = init_model(INPUT_DIM)
|
|
train(nn_model, BATCH_SIZE, criterion, optimizer, x_train, y_train)
|
|
y_dev = prediction(nn_model, BATCH_SIZE, x_dev)
|
|
get_result(y_dev)
|
|
|
|
if _name_ == '_main_':
|
|
main()
|