afparsons

"""
A quick excerpt demonstrating usage of a custom `RegularExpressionMatcher` for spaCy 3.
This is from one of my personal projects (HaleyNLP/Irnerius). Module-level imports and other code blocks have been elided.
"""

class ComponentExtractionBibliographer(
    AbstractComponentMatcher,
    matcher=RegularExpressionMatcher,
):
    """

afparsons

"""
A quick excerpt demonstrating usage of a custom `RegularExpressionMatcher` for spaCy 3.
This is from one of my personal projects (HaleyNLP/Irnerius). Module-level imports and other code blocks have been elided.
"""

class RegularExpressionMatcher:
    """
    Akin to spaCy's Token Matcher, although this runs regular expressions
    on the entire doc text.

afparsons

"""
A quick excerpt demonstrating usage of a custom `RegularExpressionMatcher` for spaCy 3.
This is from one of my personal projects (HaleyNLP/Irnerius). Module-level imports and other code blocks have been elided.
"""

@registry.misc('haleynlp.common.extraction.handler.on_match.bibliography._european_union_ecli')
def _european_union_ecli(
    span: Span,
    match: re.Match,
) -> None:

afparsons

SELECT ?cur ?curLabel ?code ?char ?symbol ?endTime ?countryLabel ?altLabel
WHERE 
{
  ?sign wdt:P31 wd:Q308229.
  ?sign wdt:P487 ?char .
  ?cur wdt:P489 ?sign .
  ?cur wdt:P31 wd:Q8142 .
  ?cur wdt:P498 ?code .
  OPTIONAL { ?cur wdt:P5061 ?symbol . }
  ?cur wdt:P17 ?country .

afparsons

"""
Adpated from: https://stackoverflow.com/a/14822210/4189676
"""

from math import floor, log

def bytes_to_human_readable(number_of_bytes: int) -> str:
    magnitude: int = int(floor(log(number_of_bytes, 1024)))
    value: float = number_of_bytes / pow(1024, magnitude)
    if magnitude > 3:

afparsons

from typing import List, Set, Tuple, Type
from taggit.models import Tag, TaggedItem
from django.db.models import Model, QuerySet
from django.contrib.contenttypes.models import ContentType


class TagAdder:
    """
    An object which adds specific tags to given Django Model objects in bulk.
    """

afparsons

from typing import Dict
from pandas import DataFrame
from taggit.models import TaggedItem
from django.db.models import Q, Count


def get_tag_counts() -> DataFrame:
    """
    Returns a DataFrame with the counts of django-taggit TaggedItems by
    Tag name and ContentType model name.

afparsons

# standard library imports
from operator import attrgetter
from typing import Union, Generator

# third-party library imports
from pandas import DataFrame
from spacy.tokens import Token, Span, Doc


def analyze_tokens(

afparsons

# Enhanced Django QuerySet printing using PrettyPrinter
# Example usage: dropped into and employed within an IPython notebook.

# --- PRETTYPRINT -------------------------------------------------------------
# A PrettyPrinter object contains a _dispatch dictionary.
# This lookup table contains (key, value) pairs wherein the key corresponds to
# an object's __repr__ method, and the value is a special _pprint_<OBJECT>
# method. The PrettyPrint method pprint() queries the dictionary to call the
# appropriate object printer.

afparsons