04_Mixing_sklearn_and_keras.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Keras's sklearn wrappers\n",
    "\n",
    "We will build now a keras classifier that you could use in your standard sklearn pipeline. Let's say we have a SVM classifier (sklearn.svm.LinearSVC) and we want compare its performance with a Neural net: we want to build, train, and compare the two classifiers.\n",
    "\n",
    "The object we will need is [this](https://keras.io/scikit-learn-api/):\n",
    "\n",
    "`keras.wrappers.scikit_learn.KerasClassifier(build_fn=None, **sk_params)`\n",
    "\n",
    "where `build_fn` should be a function building, compiling and returning a Keras Sequential() model. `**sk_params` can be both model paramters, and fit parameters (like `epochs=`)\n",
    "\n",
    "Let's perform the following steps:\n",
    "- download and preprocess the MNIST data\n",
    "- train a SVM classifier\n",
    "- build and train a Sequential() classifier\n",
    "- compare"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 1 - Download and preprocess MNIST"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "# reshape to 1D data\n",
    "\n",
    "# normalize\n",
    "\n",
    "# make a categorical representation for the NN\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 2 - train a SVM classifier"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 2 - train a SVM classifier\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 3 - build and train a Sequential model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### 4 - Compare the results "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}