MNIST challenge for EvalAI data preparation

preparation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(42000, 785)\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "\n",
    "train = pd.read_csv(\"Data/train.csv\")\n",
    "print(train.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = train.loc[:, train.columns != 'label']\n",
    "Y = train.loc[:, train.columns == 'label']\n",
    "X = X.as_matrix()\n",
    "Y = Y.as_matrix()\n",
    "from sklearn.model_selection import train_test_split\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.30, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(29400, 784) (12600, 784) (29400, 1) (12600, 1)\n"
     ]
    }
   ],
   "source": [
    "print(X_train.shape,X_test.shape,y_train.shape,y_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "z = pd.DataFrame(X_train)\n",
    "z['label'] = y_train\n",
    "z = z.set_index('label').reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "z.to_csv(\"Data/training.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "zt = pd.DataFrame(X_test)\n",
    "zt2 = pd.DataFrame(y_test)\n",
    "zt3 = zt2.sample(frac=1)\n",
    "zt3.reset_index(inplace=True)\n",
    "zt3.drop(\"index\",axis=1,inplace=True)\n",
    "zt3 = zt3.rename(index=str, columns={0: \"label\"})\n",
    "zt2 = zt2.rename(index=str, columns={0: \"label\"})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "zt3.to_csv(\"Data/submission.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "zt2.to_csv(\"Data/answers.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "zt.to_csv(\"Data/testing.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "virtualenvironment3",
   "language": "python",
   "name": "virtualenvironment3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}