Sorting pairs.gz files

merge_sort_oi_2parquet_GSOC.ipynb

merge_sort_oi_GSOC.ipynb

pairs_to_parquet(DuckDB)_GSOC.ipynb

parquet_sort(DaskVersion)_GSOC.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import dask.dataframe as dd\n",
    "import dask.array as da"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = dd.read_parquet('test.pq', chunksize=\"100MB\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.partitions[1:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "sorted_df = df.sort_values(by=[\"chrom1\", \"chrom2\", \"pos1\", \"pos2\", \"strand1\", \"strand2\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 8min 13s, sys: 6min 25s, total: 14min 38s\n",
      "Wall time: 11min 12s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "sorted_df.to_parquet('dask.parquet', write_index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%time\n",
    "\n",
    "sorted_df.compute()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "main",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}

parquet_sort(DuckDB)_GSOC.ipynb

parquet_sort(PolarsVersion2)_GSOC.ipynb