README.md

Refined Code for Bryan's blog post

one_hot.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:08.183114Z",
     "start_time": "2018-03-11T08:58:08.091062Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:08.755589Z",
     "start_time": "2018-03-11T08:58:08.751011Z"
    }
   },
   "outputs": [],
   "source": [
    "y = np.random.randint(0, 100, 10000)[None,:]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:09.404976Z",
     "start_time": "2018-03-11T08:58:09.394362Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(1, 10000)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:10.481452Z",
     "start_time": "2018-03-11T08:58:10.477342Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10000"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.size"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:11.110602Z",
     "start_time": "2018-03-11T08:58:11.105840Z"
    }
   },
   "outputs": [],
   "source": [
    "def one_hot(y):\n",
    "    y_one_hot = np.zeros([y.size, np.amax(y)+1])\n",
    "    y_one_hot[np.arange(y.size), y.ravel()]  = 1\n",
    "    return y_one_hot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:12.151425Z",
     "start_time": "2018-03-11T08:58:12.141216Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "one_hot(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:30.348374Z",
     "start_time": "2018-03-11T08:58:13.989049Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.64 ms ± 41.1 µs per loop (mean ± std. dev. of 10 runs, 1000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 1000 -r 10 one_hot(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:31.599221Z",
     "start_time": "2018-03-11T08:58:31.595080Z"
    }
   },
   "outputs": [],
   "source": [
    "def one_hot2(y):\n",
    "    max_v = y.max()\n",
    "    e = np.eye(max_v+1)\n",
    "    return e[y.ravel(), :]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:32.232390Z",
     "start_time": "2018-03-11T08:58:32.224439Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.],\n",
       "       [0., 0., 0., ..., 0., 0., 0.]])"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "one_hot2(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2018-03-11T08:58:47.933443Z",
     "start_time": "2018-03-11T08:58:34.568948Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.34 ms ± 19.2 µs per loop (mean ± std. dev. of 10 runs, 1000 loops each)\n"
     ]
    }
   ],
   "source": [
    "%timeit -n 1000 -r 10 one_hot2(y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.4"
  },
  "toc": {
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": "block",
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}