{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "# *Data Analysis and Machine Learning Applications for Physicists*"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "notes"
    }
   },
   "source": [
    "*Material for a* [*University of Illinois*](http://illinois.edu) *course offered by the* [*Physics Department*](https://physics.illinois.edu). *This content is maintained on* [*GitHub*](https://github.com/illinois-mla) *and is distributed under a* [*BSD3 license*](https://opensource.org/licenses/BSD-3-Clause).\n",
    "\n",
    "[Table of contents](Contents.ipynb)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "## Welcome!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "fragment"
    }
   },
   "source": [
    "![Einstein-as-a-data-scientist](./img/Intro/pynstein.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "**ACTIVITY:** Discuss these questions:\n",
    "1. What is *Data Science*? *Machine Learning / Artifical Intelligence*? *Statistics / Data Analysis*? How are these related?\n",
    "2. What distinguishes *Data* from *Models* from *Parameters* and their estimation?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "![Data-models-statistics triangle](./img/Intro/MLS-triangle.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "Further reading:\n",
    "- [Data mining and statistics: what's the connection?](statweb.stanford.edu/~jhf/ftp/dm-stat.pdf)\n",
    "- [The rise of the \"data engineer\"](https://medium.com/@maximebeauchemin/the-rise-of-the-data-engineer-91be18f1e603)\n",
    "- [Humorous contrasts between ML and Stats](http://statweb.stanford.edu/~tibs/stat315a/glossary.pdf)\n",
    "    - python$\\leftrightarrow$ R\n",
    "    - conference talk$\\leftrightarrow$ journal article"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "![AI-Circle](./img/Intro/AI-Circle.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### How will this course be different from a CS class?\n",
    "\n",
    "Physics and astronomy students have different preparation:\n",
    "- Strong background and experience with mathematical tools (linear algebra, multivariate calculus) needed for rigorous discussion of statistics.\n",
    "- Weak / varied background in traditional CS core topics of fundamental algorithms, databases, etc\n",
    "\n",
    "Physics and astronomy research also has different needs:\n",
    "- Our data and models are often fundamentally different from those in typical CS contexts.\n",
    "- We ask different types of questions about our data, sometimes requiring new methods.\n",
    "- We have different priorities for judging a \"good\" method: interpretability, error estimates, etc."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### What is Data?\n",
    "\n",
    "Data are a finite set of measurements:\n",
    "- Usually viewed as a 2D table e.g., spreadsheet, [FITS table](http://docs.astropy.org/en/stable/io/fits/usage/table.html), [ROOT tree](https://root.cern.ch/root/html/guides/users-guide/Trees.html#trees), [Pandas dataframe](https://pandas.pydata.org/pandas-docs/stable/generated/pandas.DataFrame.html)...\n",
    "- **colums = features**: numeric / categorical?\n",
    "- **rows = samples**: ordered? independent?\n",
    "- measurement errors?\n",
    "- binned / un-binned?\n",
    "- similarity measure on samples?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "**ACTIVITY:** Pick one of these ML problems and describe the rows (samples) and columns (features) of the data you might use to solve the problem.\n",
    "1. Learn a fast approximation to a slow exact calculation.\n",
    "2. Learn to identify Higgs particle decays from LHC event data.\n",
    "3. Learn to estimate the distance to a quasar using optical images."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### What is a Model?\n",
    "\n",
    "Models specify the probabilities of possible measurements:\n",
    "- Explicit: probability density function.\n",
    "- Implicit: algorithm to generate random outcomes (forward / generative model).\n",
    "- Usually wrong (except \"Toy MC\")\n",
    "- Observables (latent variables):\n",
    "  - integrability: required to calculate normalized probabilities.\n",
    "- Parameters (and hyper-parameters):\n",
    "  - differentiability: required to find most probable (uphill) direction.\n",
    "- Variance - bias tradeoffs (regularization)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "slideshow": {
     "slide_type": "slide"
    }
   },
   "source": [
    "### What is special about ML in physics and astronomy?\n",
    "\n",
    "- We are data **producers**, not (only) data consumers:\n",
    "  - Experiment / survey design.\n",
    "  - Optimization of statistical errors.\n",
    "  - Control of systematic errors.\n",
    "- Our data represent measurements of physical processes:\n",
    "  - Measurements often reduce to counting photons, etc, with known a-priori random errors.\n",
    "  - Dimensions and units are important.\n",
    "- Our models are usually traceable to an underlying physical theory:\n",
    "  - Models constrained by theory and previous observations.\n",
    "  - Parameter values often intrinsically interesting.\n",
    "- A parameter error estimate is just as important as its value:\n",
    "  - Prefer methods that handle input data errors (weights) and provide output parameter error estimates.\n",
    "- In some experiments and scientific domains, the data sets are *huge* --> \"Big Data\"\n",
    "  - See one of my [recent talks](https://absuploads.aps.org/presentation.cfm?pid=14316)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "\n",
    "**Postprocessing for html export of notebook**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "Python postamble (do not edit):"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install jupyter_contrib_nbextensions >/dev/null\n",
    "!jupyter nbconvert *.ipynb --to html_embed"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "Please see the full instructions at\n",
    "\n",
    "https://illinois-mla.github.io/syllabus/assets/html-embed-export-tutorial.pdf\n",
    "\n",
    "for what to do after this cell executes to obtain a pdf of your notebook."
   ]
  }
 ],
 "metadata": {
  "celltoolbar": "Slideshow",
  "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": "3.9.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}