matrix_creattion_routines.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create a one hot encoded vector to demostrate matrix building perfomance."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "shape = (1000,200)\n",
    "seed = np.random.randint(0,shape[1], shape[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_mat_prealloc(seed, shape):\n",
    "    \"\"\" Creates matrix preallocating\"\"\"\n",
    "    \n",
    "    mat = np.zeros(shape)\n",
    "    for i, n in enumerate(seed):\n",
    "        mat[i, n] = 1\n",
    "    return mat\n",
    "\n",
    "def make_mat_rbr(seed, shape):\n",
    "    \"\"\"What we do. Creates matrix row by row\"\"\"\n",
    "    \n",
    "    for i, n in enumerate(seed):\n",
    "        # init matrix for first row\n",
    "        if i == 0:\n",
    "            mat = np.zeros(shape[1])\n",
    "            mat[n] = 1\n",
    "            \n",
    "        # create and stack other rows\n",
    "        else:\n",
    "            mat_i = np.zeros(shape[1])\n",
    "            mat_i[n] = 1\n",
    "            mat = np.vstack((mat, mat_i))\n",
    "    return mat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "mat1 = make_mat_prealloc(seed, shape)\n",
    "mat2 = make_mat_rbr(seed, shape)\n",
    "\n",
    "assert np.isclose(mat1,mat2).all()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "769 µs ± 24.9 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit make_mat_prealloc(seed, shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "248 ms ± 17.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)\n"
     ]
    }
   ],
   "source": [
    "%timeit make_mat_rbr(seed, shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Not only is orders of magnitude faster, it's **cleaner** and the canonical way to create matrices when one knows the shape "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python [default]",
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}