training.python.datascience/workshop/pandas-shoes/performance-test.ipynb

{
 "cells": [
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": [
    "# Test de performance Dask\n",
    "\n",
    "Test d'un tri sur un `DateFrame` de 10 000 lignes et 34 colonnes."
   ],
   "id": "b623744e3d523007"
  },
  {
   "cell_type": "code",
   "id": "initial_id",
   "metadata": {
    "collapsed": true,
    "ExecuteTime": {
     "end_time": "2024-06-30T14:02:48.704914Z",
     "start_time": "2024-06-30T14:02:45.257624Z"
    }
   },
   "source": [
    "from contexttimer import Timer\n",
    "from dask import dataframe as dd\n",
    "\n",
    "\n",
    "loops: int = 10\n",
    "df: dd.DataFrame = dd.read_csv(\"data/womens-shoes.csv.xz\", low_memory=False, dtype={\"asins\": \"object\", \"prices.offer\": \"object\", \"upc\": \"object\", \"weight\": \"object\"})\n",
    "\n",
    "# Dask Dataframe (±4800ms)\n",
    "with Timer() as timer:\n",
    "    for i in range(loops):\n",
    "        df2 = df.sort_values(\"prices.amountMin\", ascending=bool(i % 2)).compute()\n",
    "print(f\"Dask Dataframe: {timer.elapsed:.4f} seconds\")\n"
   ],
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dask Dataframe: 3.4439 seconds\n"
     ]
    }
   ],
   "execution_count": 8
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": [
    "# Test de performance Pandas\n",
    "\n",
    "Test d'un tri sur un `DateFrame` de 10 000 lignes et 34 colonnes :\n",
    "\n",
    "- Avec des types `numpy`\n",
    "- Avec des types `pyarrow`"
   ],
   "id": "2d1c8a87edd35ebd"
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-06-30T15:55:33.485090Z",
     "start_time": "2024-06-30T15:55:32.684991Z"
    }
   },
   "cell_type": "code",
   "source": [
    "from contexttimer import Timer\n",
    "import pandas as pd\n",
    "\n",
    "loops: int = 10\n",
    "pf = pd.read_csv(\"data/womens-shoes.csv.xz\")\n",
    "af = pd.read_csv(\"data/womens-shoes.csv.xz\", engine=\"pyarrow\")\n",
    "\n",
    "# Pandas Dataframe (±35ms)\n",
    "with Timer() as timer:\n",
    "    for i in range(loops):\n",
    "        df2 = pf.sort_values(\"prices.amountMin\", ascending=bool(i % 2))\n",
    "print(f\"Pandas Dataframe: {timer.elapsed:.4f} seconds\")\n",
    "\n",
    "# Pandas PyArrow Dataframe (±29ms)\n",
    "with Timer() as timer:\n",
    "    for i in range(loops):\n",
    "        df2 = af.sort_values(\"prices.amountMin\", ascending=bool(i % 2))\n",
    "print(f\"Pandas PyArrow Dataframe: {timer.elapsed:.4f} seconds\")\n",
    "\n",
    "\n"
   ],
   "id": "53cce38938154ec2",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pandas Dataframe: 0.0489 seconds\n",
      "Pandas PyArrow Dataframe: 0.0401 seconds\n"
     ]
    }
   ],
   "execution_count": 11
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": [
    "# Test de performance Polars\n",
    "\n",
    "Test d'un tri sur un `DateFrame` de 10 000 lignes et 34 colonnes "
   ],
   "id": "c9fb11f939e169b7"
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-06-30T15:55:16.739324Z",
     "start_time": "2024-06-30T15:55:16.185126Z"
    }
   },
   "cell_type": "code",
   "source": [
    "import polars as pl\n",
    "from contexttimer import Timer\n",
    "\n",
    "\n",
    "loops: int = 10\n",
    "pf = pl.read_csv(\"data/womens-shoes.csv\", infer_schema_length=2 ** 30)\n",
    "\n",
    "# Polars Dataframe (±9ms)\n",
    "with Timer() as timer:\n",
    "    for i in range(loops):\n",
    "        df2 = pf.sort(\"prices.amountMin\", descending=bool(i % 2))\n",
    "print(f\"Polars Dataframe: {timer.elapsed:.4f} seconds\")\n",
    "\n"
   ],
   "id": "58d61771c0970c52",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Polars Dataframe: 0.0092 seconds\n"
     ]
    }
   ],
   "execution_count": 9
  },
  {
   "metadata": {},
   "cell_type": "markdown",
   "source": [
    "# Test de performance DuckDB\n",
    "\n",
    "Test d'un tri sur un `DateFrame` de 10 000 lignes et 34 colonnes "
   ],
   "id": "7a152865db550d98"
  },
  {
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-06-30T15:54:26.130463Z",
     "start_time": "2024-06-30T15:54:24.404916Z"
    }
   },
   "cell_type": "code",
   "source": [
    "import pandas as pd\n",
    "import duckdb as duck\n",
    "from contexttimer import Timer\n",
    "\n",
    "\n",
    "loops: int = 10\n",
    "df = pd.read_csv(\"data/womens-shoes.csv\")\n",
    "\n",
    "# DuckDB Dataframe (±1000ms)\n",
    "with Timer() as timer:\n",
    "    for i in range(loops):\n",
    "        asc = \"ASC\" if i % 2 == 0 else \"DESC\"\n",
    "        df2 = duck.query(f\"\"\"SELECT * FROM df ORDER BY \"prices.amountMin\" {asc}\"\"\").to_df()\n",
    "print(f\"DuckDB on Pandas Dataframe: {timer.elapsed:.4f} seconds\")\n"
   ],
   "id": "1f92c50608a41220",
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DuckDB on Pandas Dataframe: 1.2534 seconds\n"
     ]
    }
   ],
   "execution_count": 2
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}