deanm0000

def pl_cal_sheet(
    wb: CalamineWorkbook,
    sheet: str,
    header_rows: int | None = None,
    header_merge_char: str = "_",
    skip_rows: int = 0,
    infer_schema_length: int = 1000,
    infer_schema_minrow: int = 10,
    column_dupe_name_seperator: str = "_",
) -> pl.DataFrame:

deanm0000

import polars as pl
import numpy as np
from itertools import product
import time
from datetime import datetime
import json


def gen_long_string(str_len=10, n_rows=10_000_000):
    rng = np.random.default_rng()

deanm0000

from pathlib import Path
import re

rootpath = Path("./polars/crates")

for p in rootpath.rglob("*.rs"):
    with p.open() as f:
        filestr = f.read()
    if filestr.find("fn") == -1:
        continue

deanm0000

def parse_dtypes(df, exclude=[]):
    str_cols = [x for x, y in df.schema.items() if y == pl.String and x not in exclude]
    try_casts = df.select(
        pl.struct(pl.all()).alias("original"),
        pl.struct(
            pl.coalesce(
                pl.col(col).str.strptime(pl.Datetime, x, strict=False)
                for x in ["%Y-%m-%dT%H:%M:%S", "%Y-%m-%d %H:%M:%S"]
            )
            for col in str_cols

deanm0000

import httpx
import asyncio
from bs4 import BeautifulSoup
import os
import geopandas as gpd
import pandas as pd
from pathlib import Path
from geoarrow.rust.core import (
    GeoTable,
    write_parquet,