do-me

import re

# Default replaces white spaces, tabs, line breaks etc.
def replace_multiple_whitespaces(text):
    return re.sub(r'\s+', ' ', text) # use re.sub(r'[ \t]+', ' ', text) if line breaks should be preserved

# Use this function if you want to preserve exactly one line break and remove the rest like above
def replace_multiple_whitespaces_keep_one_linebreak(text):
    text = re.sub(r'[ \t]*\r?\n[ \t\r\n]*', '\n', text)
    # Replace one or more spaces or tabs with a single space (for remaining white spaces)

do-me

• gdf.to_json("temp.json")
• tippecanoe --no-feature-limit --no-tile-size-limit --no-tile-compression -s EPSG:4326 --output-to-directory tilesDirectory --force temp.json as tippecanoe unfortunately does not support geoparquet yet
• then host the tiles with npx http-server --cors (note that --cors is not needed for QGIS but for static sites like Leaflet or similar running on localhost)
•  use http://localhost:8080/tilesDirectory/{z}/{x}/{y}.pbf in a map framework of your choice

Works like a charm for me. (From: geopandas/geopandas#2295 (comment))

do-me

import numpy as np
from tqdm import tqdm
tqdm.pandas()

def chunk_text(text, max_words=100):
    words = text.split()
    chunks = [' '.join(words[i:i + max_words]) for i in range(0, len(words), max_words)]
    
    # Convert the list of embeddings to a NumPy array and change its dtype to float32
    embeddings_array = np.array(model.encode(chunks)).astype('float32')

do-me

function exportTableToCSV(filename) {
    var csv = [];
    var rows = document.querySelectorAll('table tr');
    
    for (var i = 0; i < rows.length; i++) {
        var row = [], cols = rows[i].querySelectorAll('td, th');
        
        for (var j = 0; j < cols.length; j++) {
            var cellText = cols[j].textContent.trim();
            var link = cols[j].querySelector('a');

do-me

import subprocess

def run_shell_command(command):
    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, shell=True)
    output, error = process.communicate()
    
    if process.returncode != 0:
        print(f"Error executing command: {command}")
        print(f"Error message: {error.decode('utf-8')}")
    else:

do-me

import numpy as np

# takes an arbitrary number of vectors/weights as input 
def weighted_mean_embedding(vectors, weights):
    if len(vectors) != len(weights):
        raise ValueError("Number of vectors must be equal to the number of weights")

    # Convert lists to NumPy arrays and cast to float
    vectors = [np.array(vector, dtype=float) for vector in vectors]

do-me

import zipfile
import pandas as pd
from io import TextIOWrapper

# Specify the path to your zip file
zip_file_path = 'zipfile.zip'

# Create empty lists to store filename and content
filenames = []
contents = []

do-me

import os

# Assuming you're in the "docs" dir

output_file_path = "mkdocs_material_docs_31_12_2023.md"

max_depth = 10  # Set the maximum depth of subdirectories to include
md_files = [os.path.join(root, file) for root, dirs, files in 
            os.walk(".", topdown=True) for file in files if
            file.endswith('.md') and root.count(os.path.sep) - ".".count(os.path.sep) < max_depth]

do-me

import requests
from requests.auth import HTTPBasicAuth

base_url = "https://photon.yourserver.de"

# Create an HTTP session with basic authentication
username = "username"
password = "password"
session = requests.Session()
session.auth = HTTPBasicAuth(username, password)

do-me

from collections import Counter
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from tqdm import tqdm 
import pandas as pd
import string

# Download NLTK stopwords
import nltk
nltk.download('stopwords')