apcamargo

"""
Find correspondences between groups belonging to different partitions of the
same fixed collection of elements.

Design choices implemented here:
  * strict one-to-one correspondences (no splits / merges)
  * deterministic tie-breaking -> one canonical answer, always
  * multiple partitions are aligned against a single reference partition
  * optional weighting, at two independent levels (see below)

apcamargo

#!/usr/bin/env python

# https://adamj.eu/tech/2025/07/20/python-fix-brokenpipeerror/

import os
import sys
from contextlib import contextmanager
from typing import Generator

apcamargo

#!/usr/bin/env python

import argparse
from pathlib import Path


def main():
    parser = argparse.ArgumentParser(
        description="Renumber taxids in taxdumps."
    )

apcamargo

from bisect import bisect_left, bisect_right
from collections import defaultdict
from math import floor, sqrt


def iter_similar_sets(a, b, metric="jaccard", min_similarity=0.0):
    """
    Yield pairs of dictionary keys whose set similarity meets a threshold.

    Parameters

apcamargo

#!/usr/bin/env python


import argparse
import math
import sys
from dataclasses import dataclass
from pathlib import Path

ANY_BACK = 1e-5

apcamargo

#!/usr/bin/env python

import shutil
from pathlib import Path
from typing import Literal

import pyarrow as pa
import pyarrow.parquet as pq

apcamargo

from typing import Sequence
import math


def find_cutoff(values: Sequence[float]) -> float:
    """
    Determine the cutoff point in a biphasic distribution curve by identifying
    the "bending point" where the curve transitions from slowly growing values 
    to rapidly growing values, using the maximum perpendicular distance method.

apcamargo

duckdb -c "
INSTALL httpfs;
LOAD httpfs;
INSTALL parquet;
LOAD parquet;
COPY (
  SELECT *
  FROM read_parquet('s3://sra-pub-metadata-us-east-1/sra/metadata/*')
) TO STDOUT WITH (FORMAT CSV, DELIMITER E'\t', HEADER);"

apcamargo

#!/usr/bin/env python

import json
import re
import sys
from typing import Generator, Dict, Any, Optional

import requests
from tqdm import tqdm

apcamargo

from pathlib import Path
from typing import Iterator, Optional, Union

import polars as pl
from needletail import parse_fastx_file
from polars.io.plugins import register_io_source


def scan_fastx(fastx_file: Union[str, Path]) -> pl.LazyFrame:
    schema = pl.Schema(