ml-arithmetic/Data Generator.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "from PIL import Image, ImageDraw, ImageFont\n",
    "from random import randint\n",
    "import os\n",
    "import uuid"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_img(top,bottom,operand,mode):\n",
    "    img = Image.new('1', (128,128), color = (1))\n",
    "    fnt = ImageFont.truetype('arial.ttf', 50)\n",
    "    d = ImageDraw.Draw(img)\n",
    "    answer = get_answer(top,bottom,operand)\n",
    "    my_string = str(str(top) + '\\n' + operand + str(bottom))\n",
    "    d.multiline_text((30,5), my_string, font=fnt, align='right')\n",
    "    d.line([(30,110),(115,110)], width=3)\n",
    "    if not os.path.exists('./data/{}/{}'.format(mode,answer)):\n",
    "        os.makedirs('./data/{}/{}'.format(mode,answer))\n",
    "    img.save('./data/{}/{}/{}.png'.format(mode,answer,uuid.uuid4().hex))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "operators = ['x','+', '-']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_answer(top, bottom, operand):\n",
    "    if(operand == 'x'):\n",
    "        return top * bottom\n",
    "    elif(operand == '+'):\n",
    "        return top + bottom\n",
    "    else:\n",
    "        return top - bottom "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(1000):\n",
    "    int_one = randint(0,10)\n",
    "    int_two = randint(0,10)\n",
    "    if(i/1000 < .6):\n",
    "        mode = 'train'\n",
    "    elif(i/1000 >= .6 and i/1000 < .8):\n",
    "        mode = 'validate'\n",
    "    else:\n",
    "        mode = 'test'\n",
    "    if(int_one > int_two):\n",
    "        make_img(int_one,int_two, operators[randint(0,2)],mode)\n",
    "    else:\n",
    "        make_img(int_two,int_one, operators[randint(0,2)],mode)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "my_set = []\n",
    "for i in range(11):\n",
    "    for j in range(11):\n",
    "        my_set.append(i+j)\n",
    "        my_set.append(i*j)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "242"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(my_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0,\n",
       " 1,\n",
       " 2,\n",
       " 3,\n",
       " 4,\n",
       " 5,\n",
       " 6,\n",
       " 7,\n",
       " 8,\n",
       " 9,\n",
       " 10,\n",
       " 11,\n",
       " 12,\n",
       " 13,\n",
       " 14,\n",
       " 15,\n",
       " 16,\n",
       " 17,\n",
       " 18,\n",
       " 19,\n",
       " 20,\n",
       " 21,\n",
       " 24,\n",
       " 25,\n",
       " 27,\n",
       " 28,\n",
       " 30,\n",
       " 32,\n",
       " 35,\n",
       " 36,\n",
       " 40,\n",
       " 42,\n",
       " 45,\n",
       " 48,\n",
       " 49,\n",
       " 50,\n",
       " 54,\n",
       " 56,\n",
       " 60,\n",
       " 63,\n",
       " 64,\n",
       " 70,\n",
       " 72,\n",
       " 80,\n",
       " 81,\n",
       " 90,\n",
       " 100}"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "my_set = set(my_set)\n",
    "my_set"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "my_list = list(my_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "63"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "my_list[39]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "img = Image.new('1', (128,128), color = (1))\n",
    "fnt = ImageFont.truetype('arial.ttf', 50)\n",
    "d = ImageDraw.Draw(img)\n",
    "top = 10\n",
    "bottom = 10\n",
    "operand = 'x'\n",
    "answer = get_answer(top,bottom,operand)\n",
    "my_string = str(str(top) + '\\n' + operand + str(bottom))\n",
    "d.multiline_text((30,5), my_string, font=fnt, align='right')\n",
    "d.line([(30,110),(115,110)], width=3)\n",
    "img.save('./human/test.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "for answer in range(100):\n",
    "    for mode in ['train','validate','test']:\n",
    "        if not os.path.exists('./data/{}/{}'.format(mode,answer)):\n",
    "            os.makedirs('./data/{}/{}'.format(mode,answer))"
   ]
  },
  {
   "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}