GuyAglionby

import json
import sqlite3
from time import sleep

SCHEMA = """CREATE TABLE IF NOT EXISTS planes (
    hex TEXT NOT NULL,
    unix_time INT NOT NULL,
    flight TEXT,
    category TEXT);

GuyAglionby

import glob
import itertools

from lxml import etree
from networkx.utils import UnionFind
from tqdm import tqdm


def elems_same(elem1, elem2):
    return elem1.attrib == elem2.attrib

GuyAglionby

import pandas as pd
import re
from datetime import datetime
from collections import defaultdict, OrderedDict
import yaml

re_session_extract = re.compile(r'\w+ (\w+) (\d+), (\d+) (\d+\w) ([\w\d\s:\-.,()]+-\d+) (\d+):(\d\d) UTC(.*)')


def extract_date(x):

GuyAglionby

UID,title,authors,abstract,keywords,session
1,Learning to Understand Child-directed and Adult-directed Speech,Lieke Gelderloos|Grzegorz Chrupała|Afra Alishahi,"Speech directed to children differs from adult-directed speech in linguistic aspects such as repetition, word choice, and sentence length, as well as in aspects of the speech signal itself, such as prosodic and phonemic variation. Human language acquisition research indicates that child-directed speech helps language learners. This study explores the effect of child-directed speech when learning to extract semantic information from speech directly. We compare the task performance of models trained on adult-directed speech (ADS) and child-directed speech (CDS). We find indications that CDS helps in the initial stages of learning, but eventually, models trained on ADS reach comparable task performance, and generalize better. The results suggest that this is at least partially due to linguistic rather than acoustic properties of the two registers, as we s

GuyAglionby

import pandas as pd
import re
from typing import List

re_author_split = re.compile(' and |, ')
re_curly_brace = re.compile('{([A-Za-z0-9 ]+)}')

acceptable_chars = '[\'`\/:\-()?\w\s\d.,]+'
re_newline = re.compile('[ ]*\n[ ]*')
re_inline_italics = re.compile(r'{\\(?:em|it) (' + acceptable_chars + ')}')

GuyAglionby

import pdfquery
import re
from lxml import etree as ET
import urllib.request
import urllib.error
from collections import Counter
import random
import numpy as np
import fileinput
import multiprocessing

GuyAglionby

import pdfquery
import re
from lxml import etree as ET
import urllib.request
import urllib.error

# https://raw.githubusercontent.com/dwyl/english-words/master/words_alpha.txt
with open('words_alpha.txt', 'r') as f:
    words = set([x.strip() for x in f])
    words.add('embeddings')