anapaulagomes

srun --gres=local:50 --job-name "notebook"  --mem 20GB --time 2:00:00 --pty bash -i

uv run marimo edit notebooks/ --port 8885 --headless --host 0.0.0.0

anapaulagomes

import os
from pathlib import Path
from typing import Optional

from huggingface_hub import snapshot_download

"""
Mandatory: downloading HugginFace Hub CLI https://huggingface.co/docs/huggingface_hub/v0.19.1/en/guides/cli
Usage: hf download <wanted model>

anapaulagomes

# 100% stacked bar of null vs not-null values
_proportion = []
for _col, _valid, _nulls in zip(raw_df.columns, raw_df.count(), raw_df.null_count()):
    _total = _valid[0] + _nulls[0]
    _not_null = _valid[0]/_total
    _nulls = _nulls[0]/_total
    _proportion.append({"column": _col, "status": "not-null", "proportion": _not_null})
    _proportion.append({"column": _col, "status": "null", "proportion": _nulls})
    print(f"{_col} not-null {_not_null:.2f}% null {_nulls:.2f}%")

anapaulagomes

alias nbib2bib='f(){ nbib2xml "$1" | xml2bib -b; unset -f f; }; f'

anapaulagomes

Source: https://stackoverflow.com/a/72778999


    python -m venv venv
    source venv/bin/activate
    ipython kernel install --user --name=venv
    jupyter notebook
    go to kernel-->change kernel-->choose the venv from the dropdown

anapaulagomes

# https://gitlab.mister-muffin.de/josch/img2pdf
ls *.jpg | sort -n | tr '\n' ' ' | xargs img2pdf -o ebook.pdf

anapaulagomes

from dataclasses import asdict
import json


json.dump(asdict(my_object), open("my_object.json", "w"))

anapaulagomes

import json
import requests


def retrieve_errors(issue_id):
  issue_id = ""  # FIXME
  endpoint = f"https://sentry.io/api/0/issues/{issue_id}/events/?full=True"
  token = ""  # FIXME
  headers = {"Authorization": f"Bearer {token}"}

anapaulagomes

anapaulagomes

import scrapy


class ImprensaOficialSpider(scrapy.Spider):
    start_urls = ["http://www.imprensaoficial.org/acesso.htm"]
    # example http://pmameliarodriguesba.imprensaoficial.org/
    name = "imprensa_oficial"
    TERRITORY_ID = None
    handle_httpstatus_list = [301]