2024-heraklion-data/exercises/.ipynb_checkpoints/slow_when_slicing_wrongly-checkpoint.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "af52b0cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "198afa0e",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_slice_and_perform_something(x, axis):\n",
    "    idx = 75\n",
    "    if axis == 0:\n",
    "        slice_ = x[idx, :]\n",
    "    else:\n",
    "        slice_ =  x[:, idx]\n",
    "    # Here I divide by two but any other operation will do, \n",
    "    # we just want to simulate the fact that we actually need to read the memory\n",
    "    return slice_ // 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "15900a3c",
   "metadata": {},
   "outputs": [],
   "source": [
    "page_size = 4096\n",
    "n = 100\n",
    "x = np.empty((page_size * n, page_size * n), dtype='int8')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "c182d3d3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(409600, 409600)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "86a3e63f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "28.2 µs ± 1.22 µs per loop (mean ± std. dev. of 7 runs, 10,000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit get_slice_and_perform_something(x, axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "8b2a96c2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The slowest run took 5.29 times longer than the fastest. This could mean that an intermediate result is being cached.\n",
      "886 ms ± 337 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%timeit get_slice_and_perform_something(x, axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a8f67b13",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "32218.18181818182"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "886000 / 27.5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "17a65d38",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}