108 lines
3.1 KiB
Python
108 lines
3.1 KiB
Python
import numpy
|
|
from sklearn.preprocessing import LabelEncoder
|
|
from sklearn.naive_bayes import GaussianNB, MultinomialNB
|
|
from sklearn.pipeline import Pipeline
|
|
from sklearn.feature_extraction.text import TfidfVectorizer
|
|
import torch
|
|
from gensim import downloader
|
|
from nltk.tokenize import word_tokenize
|
|
import pandas as pd
|
|
|
|
class NetworkModel(torch.nn.Module):
|
|
|
|
def __init__(self, input_size, hidden_size, num_classes):
|
|
super(NetworkModel, self).__init__()
|
|
self.fc1 = torch.nn.Linear(input_size, hidden_size)
|
|
self.fc2 = torch.nn.Linear(hidden_size, num_classes)
|
|
|
|
def forward(self, x):
|
|
x = self.fc1(x)
|
|
x = torch.relu(x)
|
|
x = self.fc2(x)
|
|
x = torch.sigmoid(x)
|
|
return x
|
|
|
|
word2vec = downloader.load("word2vec-google-news-300")
|
|
|
|
def word2vecOnDoc(document):
|
|
return numpy.mean(
|
|
[word2vec[token] for token in document if token in word2vec] or [numpy.zeros(300)],
|
|
axis=0,
|
|
)
|
|
|
|
def prepareData(data):
|
|
data = [word_tokenize(row) for row in data.content.str.lower()]
|
|
data = [word2vecOnDoc(document) for document in data]
|
|
return data
|
|
|
|
def trainModel(trainFileIn, trainFileExpected):
|
|
inData = pd.read_table(
|
|
trainFileIn,
|
|
error_bad_lines=False,
|
|
header=None,
|
|
quoting=3,
|
|
usecols=["content"],
|
|
names=["content", "id"],
|
|
nrows=225000,
|
|
)
|
|
expectedData = pd.read_table(
|
|
trainFileExpected,
|
|
error_bad_lines=False,
|
|
header=None,
|
|
quoting=3,
|
|
usecols=["label"],
|
|
names=["label"],
|
|
nrows=225000,
|
|
)
|
|
|
|
# expectedData = prepareData(expectedData)
|
|
inData = prepareData(inData)
|
|
networkModel = NetworkModel(300, 300, 1)
|
|
criterion = torch.nn.BCELoss()
|
|
optim = torch.optim.SGD(networkModel.parameters(), lr=0.02)
|
|
epochs = 1
|
|
batchSize = 2
|
|
|
|
for _ in range(epochs):
|
|
networkModel.train()
|
|
for i in range(0, expectedData.shape[0], batchSize):
|
|
x = inData[i : i + batchSize]
|
|
x = torch.tensor(x)
|
|
y = expectedData[i : i + batchSize]
|
|
y = torch.tensor(y.astype(numpy.float32).to_numpy()).reshape(-1, 1)
|
|
outputs = networkModel(x.float())
|
|
loss = criterion(outputs, y)
|
|
# print(loss)
|
|
optim.zero_grad()
|
|
loss.backward()
|
|
optim.step()
|
|
return networkModel
|
|
|
|
def evaluateModel(model, inFile, outFile):
|
|
inData = pd.read_table(
|
|
inFile,
|
|
error_bad_lines=False,
|
|
header=None,
|
|
quoting=3,
|
|
usecols=["content"],
|
|
names=["content", "id"],
|
|
)
|
|
|
|
inData = prepareData(inData)
|
|
batchSize = 2
|
|
pred = []
|
|
with torch.no_grad():
|
|
for i in range(0, len(inData), batchSize):
|
|
x = inData[i : i + batchSize]
|
|
x = torch.tensor(x)
|
|
outputs = model(x.float())
|
|
prediction = outputs >= 0.5
|
|
pred += prediction.tolist()
|
|
numpy.asarray(pred, dtype=numpy.int32).tofile(outFile, sep="\n")
|
|
|
|
model = trainModel("train/in.tsv", "train/expected.tsv")
|
|
evaluateModel(model, "dev-0/in.tsv", "dev-0/out.tsv")
|
|
evaluateModel(model, "test-A/in.tsv", "test-A/out.tsv")
|
|
|
|
|