You'll need ripgrep and pandoc to get started. You can read more about ripgrep here and pandoc here. I use both of these frequently and they're quite helpful.
You can install them both with homebrew:
brew install pandoc ripgrep
Peter Baumgartner pmbaumgartner
pmbaumgartner
/ docx-cli-search.md
Created
July 19, 2021 15:17
Search the contents of Word docs via CLI
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #cloud-config | |
| package_upgrade: true | |
| ssh_authorized_keys: | |
| - <your key> | |
| packages: | |
| - apt-transport-https | |
| - ca-certificates | |
| - curl |
pmbaumgartner
/ softie.py
Last active
July 12, 2024 13:50
Create a soft label classifier from any scikit-learn regressor object
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from sklearn.base import BaseEstimator, ClassifierMixin | |
| from scipy.special import expit, logit | |
| class SoftLabelClassifier(BaseEstimator, ClassifierMixin): | |
| def __init__(self, regressor, eps=0.001): | |
| self.regressor = regressor | |
| self.eps = eps | |
| def fit(self, X, y=None): |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import dash | |
| from dash import dcc | |
| from dash import html | |
| from dash.dependencies import Input, Output | |
| import json | |
| clicked = [] | |
| external_stylesheets = ["https://codepen.io/chriddyp/pen/bWLwgP.css"] | |
| app = dash.Dash(external_stylesheets=external_stylesheets) |
pmbaumgartner
/ overlap_lines_buffer.py
Created
December 28, 2021 12:23
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import random | |
| from typing import List, Union | |
| import shapely.geometry as geo | |
| from tqdm import tqdm | |
| MultiLineStringType = Union[List[geo.LineString], geo.MultiLineString] | |
| def overlap_lines( |
pmbaumgartner
/ spacy_colab_gpu.py
Last active
January 7, 2022 00:52
Install spaCy with correct cuda version on Colab with GPU
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # SETUP | |
| cuda_version = !nvcc --version | grep -Po '^.*release \K([0-9]+\.[0-9])' | sed 's/\.//g' | |
| # REQUIREMENTS | |
| from pathlib import Path | |
| reqs = f""" | |
| spacy[cuda{cuda_version.s},transformers,lookups]==3.2.1 | |
| """ | |
| Path("requirements.txt").write_text(reqs) | |
| !pip install --quiet -r requirements.txt |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from spacy.tokenizer import Tokenizer | |
| class CTLTokenizer(Tokenizer): | |
| # https://stackoverflow.com/a/58718664 | |
| def __call__(self, string) -> spacy.tokens.Doc: | |
| string = self.clean_string(string) | |
| doc = super().__call__(string) | |
| return doc | |
| def clean_string(self, string: str) -> str: |
pmbaumgartner
/ digit_ngram_suggester.py
Last active
July 1, 2024 16:08
A span candidate suggester function for spaCy that suggests spans containing a digit.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from typing import Optional, Iterable, cast, List | |
| from thinc.api import get_current_ops, Ops | |
| from thinc.types import Ragged, Ints1d | |
| from spacy.pipeline.spancat import Suggester | |
| from spacy.tokens import Doc | |
| from spacy.util import registry | |
| @registry.misc("ngram_digits_suggester.v1") |
pmbaumgartner
/ getiosevka.sh
Last active
September 22, 2025 10:29
Iosevka Ubuntu Install - edited from https://blog.programster.org/install-iosevka-fonts
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| RELEASE="15.2.0" | |
| mkdir /tmp/iosevka-font/v$RELEASE | |
| cd /tmp/iosevka-font/v$RELEASE | |
| wget https://github.com/be5invis/Iosevka/releases/download/v$RELEASE/ttf-iosevka-$RELEASE.zip | |
| wget https://github.com/be5invis/Iosevka/releases/download/v$RELEASE/ttf-iosevka-aile-$RELEASE.zip | |
| wget https://github.com/be5invis/Iosevka/releases/download/v$RELEASE/ttf-iosevka-curly-$RELEASE.zip | |
| wget https://github.com/be5invis/Iosevka/releases/download/v$RELEASE/ttf-iosevka-curly-slab-$RELEASE.zip | |
| wget https://github.com/be5invis/Iosevka/releases/download/v$RELEASE/ttf-iosevka-etoile-$RELEASE.zip | |
| wget https://github.com/be5invis/Iosevka/releases/download/v$RELEASE/ttf-iosevka-fixed-$RELEASE.zip |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from spacy import displacy | |
| from spacy.tokens import Doc | |
| from spacy.util import get_lang_class | |
| from pathlib import Path | |
| words = ["The", "quick", "brown", "fox", "jumped", "over", "the", "lazy", "fox"] | |
| heads = [3, 3, 3, 4, 4, 4, 8, 8, 5] | |
| deps = ["det", "amod", "amod", "nsubj", "ROOT", "prep", "pobj", "det", "amod"] | |
| doc = Doc(get_lang_class("en")().vocab, words=words, heads=heads, deps=deps) |