import os
import torch.optim
from data_loader import LabelledTextDS
from models import FastText
from plotting import *
from training import train_model
import pandas as pd
num_epochs = 50
num_hidden = 40 # Number of hidden neurons in model
dev = 'cuda' if torch.cuda.is_available(
) else 'cpu' # If you have a GPU installed, use that, otherwise CPU
dataset = LabelledTextDS(os.path.join('data', 'labelled_movie_reviews.csv'),
dev=dev)
imdb_data = pd.read_csv('data/labelled_movie_reviews.csv')
model = FastText(
len(dataset.token_to_id) + 2, num_hidden, len(dataset.class_to_id)).to(dev)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
losses, accuracies = train_model(dataset, model, optimizer, num_epochs)
torch.save(model, os.path.join('saved_models', 'classifier.pth'))
print('')
print_accuracies(accuracies)
plot_losses(losses)
import os
from sklearn.linear_model import LogisticRegression
from data_loader import LabelledTextDS
from plotting import *
dataset = LabelledTextDS(os.path.join('data', 'labelled_movie_reviews.csv'))
train, valid, test = dataset.get_vector_representation()
model = LogisticRegression(
) # You can change the hyper-parameters of the model by passing args here
model.fit(train[0], train[1])
train_accuracy = (model.predict(train[0]) == train[1]).astype(float).mean()
valid_accuracy = (model.predict(valid[0]) == valid[1]).astype(float).mean()
test_accuracy = (model.predict(test[0]) == test[1]).astype(float).mean()
print_accuracies((train_accuracy, valid_accuracy, test_accuracy))