{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Change this to the title of your project"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "*by Chuck Anderson, October, 2023* \n",
    "\n",
    "Change the above line to be your name and date.  Include names of all team members, if this is a team project."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Please follow the structure of this example proposal.  For the proposal, change all text except the headings.\n",
    "\n",
    "At the end is a code cell that counts words for you.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Introduction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Summarize the machine learning concepts, algorithms, and data that interest you.  Describe why you are interested in these.  \n",
    "\n",
    "Very briefy describe your planned methods."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Methods"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Describe in some detail the algorithms and data you will use.  In your final report cite articles and github cites like this [Goodfellow, et al., 2016].\n",
    "\n",
    "In your proposal, make a table here with at least 5 milestones for your project with expected dates.\n",
    "\n",
    "REQUIRED: If this is a team project, clearly describe in detail what each team member will do."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the proposal, summarize what you expect your results to be.  \n",
    "\n",
    "In the final report, show all results.  Intermediate results might be shown in above Methods section.  Plots, tables, whatever is needed to tell your story."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Conclusions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In your proposal, describe what you expect to learn and what you expect will be most difficult.\n",
    "\n",
    "In your project report, describe what you learned, and what was most difficult.  Summarize any surprises you encontered."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### References"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* [Goodfellow, et al., 2016] Ian Goodfellow and Yoshua Bengio and Aaron Courville, [Deep Learning](http://www.deeplearningbook.org), MIT Press. 2014."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "There is no word count expectations for your proposal.\n",
    "\n",
    "Your final report should contain 2,000 to 3,000 words, times the number of team members.  Projects with two people, for example, should contain 4,000 to 6,000 words.\n",
    "\n",
    "Count words by running the following python code in your report directory.  Do this before you check-in this notebook so the word count appears as the output of the following code cell."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-10-16T19:01:45.609927Z",
     "start_time": "2023-10-16T19:01:45.450944Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Word count for file Project Proposal and Report Example.ipynb is 314\n"
     ]
    }
   ],
   "source": [
    "import io\n",
    "import nbformat\n",
    "import glob\n",
    "nbfile = glob.glob('Project Proposal and Report Example.ipynb')\n",
    "if len(nbfile) > 1:\n",
    "    print('More than one ipynb file. Using the first one.  nbfile=', nbfile)\n",
    "with io.open(nbfile[0], 'r', encoding='utf-8') as f:\n",
    "    nb = nbformat.read(f, nbformat.NO_CONVERT)\n",
    "word_count = 0\n",
    "for cell in nb.cells:\n",
    "    if cell.cell_type == \"markdown\":\n",
    "        word_count += len(cell['source'].replace('#', '').lstrip().split(' '))\n",
    "print('Word count for file', nbfile[0], 'is', word_count)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.10.13"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}