ines

function venv {
    default_envdir=".env"
    envdir=${1:-$default_envdir}

    if [ ! -d $envdir ]; then
        python -m venv $envdir
        pip install ipython black flake8
        echo -e "\x1b[38;5;2m✔ Created virtualenv $envdir\x1b[0m"
    fi
    source $envdir/bin/activate

ines

"""
Example of a Streamlit app for an interactive Prodigy dataset viewer that also lets you
run simple training experiments for NER and text classification.

Requires the Prodigy annotation tool to be installed: https://prodi.gy
See here for details on Streamlit: https://streamlit.io.
"""
import streamlit as st
from prodigy.components.db import connect
from prodigy.models.ner import EntityRecognizer, merge_spans, guess_batch_size

ines

pip install streamlit
pip install spacy
python -m spacy download en_core_web_sm
python -m spacy download en_core_web_md
python -m spacy download de_core_news_sm

ines

import difflib
import wasabi

def diff_strings(a, b):
    output = []
    matcher = difflib.SequenceMatcher(None, a, b)
    for opcode, a0, a1, b0, b1 in matcher.get_opcodes():
        if opcode == "equal":
            output.append(a[a0:a1])
        elif opcode == "insert":

ines

# Using spaCy & NLP to create variations of "those generously buttered noodles"
# See here: https://twitter.com/ArielDumas/status/1086294656957272065
#
# Disclaimer 1: This is a quick, simplified example focusing on one particular
# sentence. There are obviously many more different constructions and
# different types of dependencies you want to cover. Some aspects also become
# significantly more difficult if you're working with, say, German instead of
# English.
#
# Disclaimer 2: Creating spam comments is a very bad use case for NLP and

ines

# coding: utf8
from __future__ import unicode_literals

from spacy.lang.en import English
from spacy.tokens import Token

# Example of using spaCy v2.0's custom attribute extensions to get and set
# character spans of a token text as token attributes.
# Discussion: https://twitter.com/DavidWell/status/920245066404450304

ines

import spacy

nlp = spacy.load('🦄')
doc = nlp(u'Wow, my model is named 🦄 !')

for word in doc:
    print(word.text, word.tag_, word.dep_, word.head.text)

ines

//- Usage: +displacy({ arcs: [...], words: [...] })

//- Blog post for more info: https://explosion.ai/blog/displacy-js-nlp-visualizer
//- spaCy REST service to generate JSON markup: https://github.com/explosion/spacy-services

- var distance = 200
- var offsetX = 50
- var arrowSpacing = 20
- var arrowWidth = 10
- var arrowStroke = 2