koaning

import timeit
import requests

import html_text
import justext 
from selectolax.parser import HTMLParser

# There's a difference between these two
html_long = requests.get("http://planet.python.org/").content.decode("utf-8")
html_short = "<p><b>This</b> is just a small example.</p>"

koaning

import spacy
from spacy import displacy


def show_results(text, patterns):
    nlp = spacy.blank("en")
    ruler = nlp.add_pipe("entity_ruler")

    ruler.add_patterns(patterns)
    doc = nlp(text)

koaning

"""
This script combines two datasets to generate a file with all found patterns. 
"""

import srsly 
from prodigy.components.db import connect
import spacy 

nlp = spacy.blank("en")

koaning

import time
from typing import List

from rich import box
from rich.table import Table
from rich.console import Console

import prodigy
from prodigy.components.loaders import CSV

koaning

import base64
import pathlib
from jinja2 import Environment, FileSystemLoader, select_autoescape

env = Environment(
    loader=FileSystemLoader("images"),
    autoescape=select_autoescape()
)

template = env.get_template("instructions.template")

koaning

import pyphen

import prodigy
from prodigy.components.loaders import JSONL
from prodigy.components.db import connect

hyphenator = pyphen.Pyphen(lang="en_US")

def construct_html(text):
    hyphend = hyphenator.inserted(text)

koaning

koaning

koaning

{
  "$schema": "https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json",
  "basics": {
    "name": "Vincent D. Warmerdam",
    "label": "Senior Data Professional & Research Advocate",
    "image": "",
    "email": "[email protected]",
    "url": "https://koaning.io",
    "summary": "",
    "location": {

koaning