Sorting pairs.gz files

merge_sort_oi_2parquet_GSOC.ipynb

merge_sort_oi_GSOC.ipynb

pairs_to_parquet(DuckDB)_GSOC.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import duckdb\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "con = duckdb.connect(\":memory:\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<duckdb.duckdb.DuckDBPyConnection at 0x2b1e4a25d5f0>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "con.execute(\"PRAGMA temp_directory='/users/slavska.olesia/scratch/slavska.olesia';\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<duckdb.duckdb.DuckDBPyConnection at 0x2b1e4a25d5f0>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "con.execute(\"PRAGMA memory_limit='55GB';\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<duckdb.duckdb.DuckDBPyConnection at 0x2b1e4a25d5f0>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "con.execute(\"SET enable_progress_bar = true;\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 257 ms, sys: 66.2 ms, total: 323 ms\n",
      "Wall time: 354 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "\n",
    "input_file = '/users/slavska.olesia/projects/lesia/Micro-C_RAD21_IAA_rep4.mm10.dups.pairs.gz'\n",
    "\n",
    "pairs = con.read_csv(\n",
    "    input_file, \n",
    "    sep=\"\\t\", \n",
    "    header=False, \n",
    "    parallel=True, \n",
    "    skiprows=500,\n",
    "    names=[\"read_id\", \"chrom1\", \"pos1\", \"chrom2\", \"pos2\", \"strand1\", \"strand2\", \"pair_type\", \"mapq1\", \"mapq2\"]\n",
    ")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b7424b19220a429d81f988a52a355ea1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "FloatProgress(value=0.0, layout=Layout(width='auto'), style=ProgressStyle(bar_color='black'))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 7min 25s, sys: 2min 15s, total: 9min 41s\n",
      "Wall time: 1min 44s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "pairs.write_parquet(\"test.pq\", row_group_size=1_000_000, compression=\"zstd\")"
   ]
  }
 ],
 "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(DaskVersion)_GSOC.ipynb

parquet_sort(DuckDB)_GSOC.ipynb

parquet_sort(PolarsVersion2)_GSOC.ipynb