Youssef-Harby

import pyarrow as pa
import pyarrow.parquet as pq
from pathlib import Path
import json
import pandas as pd


def process_parquet_file(parquet_path):
    # Read the Parquet file into a PyArrow Table
    table = pq.read_table(parquet_path)

Youssef-Harby

import httpx
import datetime
import hashlib
import hmac

# AWS credentials
access_key = "secret"
secret_key = "secret"
region = "eu-central-1"  # e.g. 'us-west-1'
bucket = "bucket-name"

Youssef-Harby

# dataset ref : https://www.kaggle.com/datasets/max-mind/world-cities-database/code
# pip install duckdb

import duckdb

con = duckdb.connect()

data = """
-- Environment setup
SET enable_progress_bar = true;

Youssef-Harby

import duckdb

con = duckdb.connect('./duckdb.duckdb')
data = """
SET memory_limit = '32GB';
SET threads TO 16;
SET enable_progress_bar = true;
SET enable_progress_bar_print = true;
INSTALL httpfs;
INSTALL spatial;

Youssef-Harby

import csv
import re


def extract_lat_long(csv_file, url_column):
    pattern = r".+!3d(-?\d+\.\d+)!4d(-?\d+\.\d+).+"
    data = []

    # Read the CSV file and extract latitude and longitude values
    with open(csv_file, 'r') as f:

Youssef-Harby

Keybase proof

I hereby claim:

• I am youssef-harby on github.
• I am yharby (https://keybase.io/yharby) on keybase.
• I have a public key ASBmkyd87Ju7hwN_Uej1lBn8r2SbYZsl12bXghbTDcxPNwo

To claim this, I am signing this object: