sport-text-classification-ball-ISI-public/sport text classification.ipynb

import pandas as pd
import numpy as np
from gensim.test.utils import common_texts
from gensim.models import FastText
import os.path
import gzip
import shutil
import torch
import torch.optim as optim

features = 100
batch_size = 16
criterion = torch.nn.BCELoss()

with gzip.open('train/train.tsv.gz', 'rb') as f_in:
    with open('train/train.tsv', 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out)

data = pd.read_csv('train/train.tsv', sep='\t', names=["Ball","Text"])
data["Text"] = data["Text"].str.lower().str.split()
data["Text"]

0        [mindaugas, budzinauskas, wierzy, w, odbudowę,...
1        [przyjmujący, reprezentacji, polski, wrócił, d...
2        [fen, 9:, zapowiedź, walki, róża, gumienna, vs...
3        [aleksander, filipiak:, czuję, się, dobrze, w,...
4        [victoria, carl, i, aleksiej, czerwotkin, mist...
                               ...                        
98127    [kamil, syprzak, zaczyna, kolekcjonować, trofe...
98128    [holandia:, dwa, gole, piotra, parzyszka, piot...
98129    [sparingowo:, korona, gorsza, od, stali., lett...
98130    [vive, -, wisła., ośmiu, debiutantów, w, tegor...
98131    [wta, miami:, timea, bacsinszky, pokonana,, sw...
Name: Text, Length: 98132, dtype: object

ft_model = None
if not os.path.isfile('fasttext.model'):
    ft_model = FastText(size=features, window=3, min_count=1)
    ft_model.build_vocab(sentences=data["Text"])
    ft_model.train(data["Text"], total_examples=len(data["Text"]), epochs=10)
    ft_model.save("fasttext.model")
else:
    ft_model = FastText.load("fasttext.model")
    
def document_vector(doc):
    result = ft_model.wv[doc]
    return np.max(result, axis=0)

X = [document_vector(x) for x in data["Text"]]
Y = data["Ball"]

class NeuralNetworkModel(torch.nn.Module):
    def __init__(self):
        super(NeuralNetworkModel, self).__init__()
        self.fc1 = torch.nn.Linear(features,200)
        self.fc2 = torch.nn.Linear(200,150)
        self.fc3 = torch.nn.Linear(150,1)

    def forward(self, x):
        x = self.fc1(x)
        x = torch.relu(x)
        x = self.fc2(x)
        x = torch.sigmoid(x)
        x = self.fc3(x)
        x = torch.sigmoid(x)
        return x

    
def get_loss_acc(model, X_dataset, Y_dataset):
    loss_score = 0
    acc_score = 0
    items_total = 0
    model.eval()
    for i in range(0, Y_dataset.shape[0], batch_size):
        x = X_dataset[i:i+batch_size]
        x = torch.tensor(x)
        y = Y_dataset[i:i+batch_size]
        y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1,1)
        y_predictions = model(x)
        acc_score += torch.sum((y_predictions >= 0.5) == y).item()
        items_total += y.shape[0] 

        loss = criterion(y_predictions, y)

        loss_score += loss.item() * y.shape[0] 
    return (loss_score / items_total), (acc_score / items_total)

model_path = 'nn.model'
nn_model = NeuralNetworkModel()
    
if not os.path.isfile(model_path):
    optimizer = optim.SGD(nn_model.parameters(), lr=0.1)

    display(get_loss_acc(nn_model, X, Y))
    for epoch in range(5):
        nn_model.train()
        for i in range(0, len(X), batch_size):
            x = X[i:i+batch_size]
            x = torch.tensor(x)

            y = Y[i:i+batch_size]
            y = torch.tensor(y.astype(np.float32).to_numpy()).reshape(-1,1)

            y_predictions = nn_model(x)
            loss = criterion(y_predictions, y)

            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
        display(get_loss_acc(nn_model, X, Y))
    torch.save(nn_model.state_dict(), model_path)
else:
    nn_model.load_state_dict(torch.load(model_path))

x_dev = pd.read_csv('dev-0/in.tsv', sep='\t', names=["Text"])["Text"]
y_dev = pd.read_csv('dev-0/expected.tsv', sep='\t', names=["Ball"])["Ball"]
x_dev = [document_vector(x) for x in x_dev.str.lower().str.split()]

get_loss_acc(nn_model, x_dev, y_dev)

(0.45761072419184756, 0.7694424064563463)

y_dev_prediction = nn_model(torch.tensor(x_dev))
y_dev_prediction = np.array([round(y) for y in y_dev_prediction.flatten().tolist()])
np.savetxt("dev-0/out.tsv", y_dev_prediction,  fmt='%d')

x_test = pd.read_csv('test-A/in.tsv', sep='\t', names=["Text"])["Text"]
x_test = [document_vector(x) for x in x_test.str.lower().str.split()]
y_test_prediction = nn_model(torch.tensor(x_test))
y_test_prediction = np.array([round(y) for y in y_test_prediction.flatten().tolist()])
np.savetxt("test-A/out.tsv", y_test_prediction,  fmt='%d')