arhouati

from torch.utils.data import Dataset
import pandas as pd
from .review_vectorizer import ReviewVectorizer


class ReviewDataset(Dataset):

    def __init__(self, review_df, vectorizer):
        """
        Args:

arhouati

import collections
import re

import pandas as pd
import numpy as np
import argparse


# set up arguments
parser = argparse.ArgumentParser(description='Split DataSet Arguments.')

arhouati

import torch
import torch.nn as nn

class Perceptron(nn.Module):
    """ A perceptron is one linear Layer"""
    def __init__(self, input_dim: int):
        """

        :param input_dim (int): size of inputs features
        """

arhouati

class Aljazeera():

    url = 'https://www.aljazeera.net/aljazeerarss/a7c186be-1baa-4bd4-9d80-a84db769f779/73d0e1b4-532f-45ef-b135-bfdff8b8cab9'
    url_base = 'https://www.aljazeera.net'
    name = 'aljazeera.net'
    ua = {
        'use-agent': "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36"}
    feed = None
    articles = []

arhouati

import xmltodict
from urllib.request import urlopen

class RssFeed(threading.Thread):

    def __init__(self, url):
        threading.Thread.__init__(self)
        self.url = url

    name = "undefined"

arhouati

import regex as re
from langdetect import detect
import logging
import os

dir_base = os.path.dirname(os.path.abspath(__file__))

logging.basicConfig(filename=dir_base + '/../logs/ArabicTextCleaner.log', filemode='w', format='%(name)s - %(levelname)s - %(message)s')