scripts/nn/examples/Example - MNIST Softmax Classifier deprecated.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Quick Setup - Warning: Deprecated"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "# Create a SystemDS MLContext object\n",
    "from systemds import MLContext, dml\n",
    "ml = MLContext(sc)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download Data - MNIST"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The MNIST dataset contains labeled images of handwritten digits, where each example is a 28x28 pixel image of grayscale values in the range [0,255] stretched out as 784 pixels, and each label is one of 10 possible digits in [0,9].  Here, we download 60,000 training examples, and 10,000 test examples, where the format is \"label, pixel_1, pixel_2, ..., pixel_n\"."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%%sh\n",
    "mkdir -p data/mnist/\n",
    "cd data/mnist/\n",
    "curl -O https://pjreddie.com/media/files/mnist_train.csv\n",
    "curl -O https://pjreddie.com/media/files/mnist_test.csv"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## SystemDS Softmax Model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1. Train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "training = \"\"\"\n",
    "source(\"nn/examples/mnist_softmax.dml\") as mnist_softmax\n",
    "\n",
    "# Read training data\n",
    "data = read($data, format=\"csv\")\n",
    "n = nrow(data)\n",
    "\n",
    "# Extract images and labels\n",
    "images = data[,2:ncol(data)]\n",
    "labels = data[,1]\n",
    "\n",
    "# Scale images to [0,1], and one-hot encode the labels\n",
    "images = images / 255.0\n",
    "labels = table(seq(1, n), labels+1, n, 10)\n",
    "\n",
    "# Split into training (55,000 examples) and validation (5,000 examples)\n",
    "X = images[5001:nrow(images),]\n",
    "X_val = images[1:5000,]\n",
    "y = labels[5001:nrow(images),]\n",
    "y_val = labels[1:5000,]\n",
    "\n",
    "# Train\n",
    "epochs = 1\n",
    "[W, b] = mnist_softmax::train(X, y, X_val, y_val, epochs)\n",
    "\"\"\"\n",
    "script = dml(training).input(\"$data\", \"data/mnist/mnist_train.csv\").output(\"W\", \"b\")\n",
    "W, b = ml.execute(script).get(\"W\", \"b\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 2. Compute Test Accuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "testing = \"\"\"\n",
    "source(\"nn/examples/mnist_softmax.dml\") as mnist_softmax\n",
    "\n",
    "# Read test data\n",
    "data = read($data, format=\"csv\")\n",
    "n = nrow(data)\n",
    "\n",
    "# Extract images and labels\n",
    "X_test = data[,2:ncol(data)]\n",
    "y_test = data[,1]\n",
    "\n",
    "# Scale images to [0,1], and one-hot encode the labels\n",
    "X_test = X_test / 255.0\n",
    "y_test = table(seq(1, n), y_test+1, n, 10)\n",
    "\n",
    "# Eval on test set\n",
    "probs = mnist_softmax::predict(X_test, W, b)\n",
    "[loss, accuracy] = mnist_softmax::eval(probs, y_test)\n",
    "\n",
    "print(\"Test Accuracy: \" + accuracy)\n",
    "\"\"\"\n",
    "script = dml(testing).input(\"$data\", \"data/mnist/mnist_test.csv\", W=W, b=b)\n",
    "ml.execute(script)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 3. Extract Model Into Spark DataFrames For Future Use"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "W_df = W.toDF()\n",
    "b_df = b.toDF()\n",
    "W_df, b_df"
   ]
  }
 ],
 "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": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}