paranormal-or-skeptic-ISI-p.../main.py
2021-05-29 14:30:20 +00:00

90 lines
2.6 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
class NetworkModel(torch.nn.Module):
def __init__(self):
dim = 200
super(NeuralNetworkModel, self).__init__()
self.fc1 = torch.nn.Linear(dim, 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
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]
print(data)
data = [word2vecOnDoc(document) for document in data]
return data
def trainModel(trainFileIn, trainFileExpected):
with open(trainFileExpected, 'r') as f:
expectedData = f.readlines()
with open(trainFileIn, 'r') as f:
inData = f.readlines()
expectedData = prepareData(expectedData)
inData = prepareData(inData)
# networkModel = NetworkModel(300, 300, 1)
# criterion = torch.nn.BCELoss()
# optim = torch.optim.SGD(network.parameters(), lr=0.02)
# epochs = 1
# batchSize = 2
# for _ in range(epochs):
# network.train()
# for i in range(0, inData.shape[0], batchSize):
# x = inData[i : i + batchSize]
# x = torch.tensor(x)
# y = expectedData[i : i + batchSize]
# y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1, 1)
# outputs = network(x.float())
# loss = criterion(outputs, y)
# print(loss)
# optim.zero_grad()
# loss.backward()
# optim.step()
# return networkModel
def evaluateModel(model, inFile, outFile):
with open(inFile, 'r') as f:
inData = f.readlines()
inData = prepareData(inData)
pred = []
with torch.no_grad():
for i in range(0, len(inData), batch_size):
x = inData[i : i + batch_size]
x = torch.tensor(x)
outputs = model(x.float())
prediction = outputs >= 0.5
pred += prediction.tolist()
numpy.asarray(pred, dtype=numpyp.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")