jacKlinc

[
  {
    "publish_date": "2014-07-31",
    "title": "Did Coulson\u2019s News of the World Incite Others to Commit Crimes and Cause Unsafe Convictions?",
    "url": "https://www.bellingcat.com/news/uk-and-europe/2014/07/31/did-coulsons-news-of-the-world-incite-others-to-commit-crimes-and-cause-unsafe-convictions/",
    "articles_text": "\n\nMore on the Fake Sheikh, the Police, and News of the World by occasional blogger @jpublik.\n\nAndy Coulson\u2018s News of the World sent a man to jail after luring him to sell them drugs he was terrified of carrying by promising him a job. He was sentenced to four years in prison before his conviction was quashed \u2013 after he\u2019d already served his time.\n\nIn a case which has hardly received any publicity, according to high court documents, Albanian Besnik Qema was asked to supply News of the World cocaine and a passport on a promise of job as security for a wealthy Arab family.\n\nThe High Court documents detail how in January 2005, Mazher Mahmood had asked Florim 

jacKlinc

year,month,url,path,articles_text,publish_date,title
2014,7,https://www.bellingcat.com/news/uk-and-europe/2014/07/31/did-coulsons-news-of-the-world-incite-others-to-commit-crimes-and-cause-unsafe-convictions/,/news/uk-and-europe/2014/07/31/did-coulsons-news-of-the-world-incite-others-to-commit-crimes-and-cause-unsafe-convictions/,"

More on the Fake Sheikh, the Police, and News of the World by occasional blogger @jpublik.

Andy Coulson‘s News of the World sent a man to jail after luring him to sell them drugs he was terrified of carrying by promising him a job. He was sentenced to four years in prison before his conviction was quashed – after he’d already served his time.

In a case which has hardly received any publicity, according to high court documents, Albanian Besnik Qema was asked to supply News of the World cocaine and a passport on a promise of job as security for a wealthy Arab family.

The High Court documents detail how in January 2005, Mazher Mahmood had asked Florim Gashi, a contact of his who h

jacKlinc

jacKlinc

import requests
from functools import reduce
from dataclasses import dataclass

from bs4 import BeautifulSoup
from newspaper import Article
import pandas as pd

BASE_URL = "https://www.bellingcat.com"
BELLINGCAT_START_YEAR = 2014  # earliest article on site

jacKlinc

class LanguageModelMulti(Module):
  """
  Deepening the model with the built-in RNN class for more accuracy
  """
  def __init__(self, vocab_sz, n_hidden, n_layers):
    self.i_h = nn.Embedding(vocab_sz, n_hidden)
    # Creates an RNN within
    self.rnn = nn.RNN(n_hidden, n_hidden, n_layers, batch_first=True)
    self.h_o = nn.Linear(n_hidden, vocab_sz)
    # Creates zeros for all layers

jacKlinc

class LanguageModelRecurrentState(Module):
  """
  State is saved by moving the reset to the init method

  Gradients are detached for all but 3 layers
  """
  def __init__(self, vocab_sz, n_hidden):
    self.i_h = nn.Embedding(vocab_sz, n_hidden)
    self.h_h = nn.Linear(n_hidden, n_hidden)
    self.h_o = nn.Linear(n_hidden, vocab_sz)

jacKlinc

class LanguageModel(Module):
  """
  Takes three words as input and returns a probability for the next
  The 1st layer will use the first word's embedding
  The 2nd layer will use the 2nd word's embedding and the 1st word's output activations
  The 3rd layer will use the 3rd word's embedding plus the 2nd word's output activations
  """
  def __init__(self, vocab_sz, n_hidden):
    self.i_h = nn.Embedding(vocab_sz, n_hidden) # Converts the indices to a vector
    self.h_h = nn.Linear(n_hidden, n_hidden) # Creates the activations for the successive word

jacKlinc

welcome back here we go again great to

see you and congratulations

thank you you will never forget what is

going on in the world when you think

about when your child is born you will

jacKlinc

from sklearn.feature_extraction.text import CountVectorizer

def parse_txt(txt_file):
    """
    Pass text file location and returns n list elements for each line in the file
    """
    with open(txt_file, "r") as f:
        # Reads files, removes new lines and appends to list
        words = f.read().splitlines()
        # Removes None elements

jacKlinc

from fastai import *
from fastbook import *

def create_params(size):
    """
      Pass tensor shape
      Returns normalised model parameters
    """
    return nn.Parameter(torch.zeros(*size).normal_(0, 0.01))