#4.1-Comparison_of_speeds_of_DataFrame_and_svmlight.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Comparison of speeds of DataFrame and svmlight files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "sys.version_info(major=3, minor=6, micro=2, releaselevel='final', serial=0)\n",
      "sklearn version = 0.20.0\n"
     ]
    }
   ],
   "source": [
    "from itertools import product\n",
    "from pathlib import Path\n",
    "import sys\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "import sklearn\n",
    "from sklearn.datasets import dump_svmlight_file, load_svmlight_file\n",
    "\n",
    "\n",
    "%matplotlib inline\n",
    "\n",
    "print(sys.version_info)\n",
    "print(f'sklearn version = {sklearn.__version__}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "def make_dataset(num_samples, num_bits, on_bit_ratio):\n",
    "    np.random.seed(20181021)\n",
    "\n",
    "    X = np.random.binomial(1, on_bit_ratio, size=(num_samples, num_bits))\n",
    "    X = pd.DataFrame(X)\n",
    "    y = np.random.rand(num_samples).round(3)    \n",
    "    return X, y"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Make dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Make dataset directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "p = Path('./dataset')\n",
    "p.mkdir(parents=True, exist_ok=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Make dataset parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "num_sample_set = (1000, 2000, 4000, 8000)\n",
    "num_bit_set  = (256, 512, 1024, 2048, 4096)\n",
    "on_bit_ratios = (.1, .3, .5, .7, .9)\n",
    "random_seeds = (0, 1, 2, 3, 4)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Make dataset in dataset directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "for num_samples, num_bits, on_bit_ratio, random_seed in product(num_sample_set, \n",
    "                                                                             num_bit_set, on_bit_ratios, random_seeds):\n",
    "    # Make dataset\n",
    "    X, y = make_dataset(num_samples, num_bits, on_bit_ratio)\n",
    "    file_name = f'{num_samples}_{num_bits}_{int(on_bit_ratio*100)}_{random_seed}.csv'\n",
    "\n",
    "    # Save X and y as svmlight data\n",
    "    dump_svmlight_file(X, y, f'dataset/svmlight_{file_name}')\n",
    "\n",
    "    # Save X and y as dataframe\n",
    "    X.insert(loc=0, column='y', value=y)\n",
    "    X.to_csv(f'dataset/dataframe_{file_name}', index=False, header=False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# EOF"
   ]
  }
 ],
 "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": "3.6.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}