diff --git a/INSTALL.md b/INSTALL.md
index c231d0f1bcfcf3a9b476efb17e84a20229466dd2..42aa887c51283b74ba9b966d7c2b8ce739ca6052 100644
--- a/INSTALL.md
+++ b/INSTALL.md
@@ -8,7 +8,7 @@ packages installed.
Linux
-----
-We assume Ubuntu (12.04 Quantal Quetzal or later) or Debian Linux (7.0 Wheezy
+We assume Ubuntu (12.10 Quantal Quetzal or later) or Debian Linux (7.0 Wheezy
or later), but if you manage to install everything on a different flavour
that's also fine.
@@ -56,11 +56,13 @@ Install some of the other package we'll use:
pip install numpy
pip install matplotlib
pip install biopython
+ pip install pandas==0.14.0
+ pip install openpyxl==2.0.4
Define a default matplotlib backend:
- mkdir -p ~/.matplotlib
- echo "backend : GTKCairo" >> ~/.matplotlib/matplotlibrc
+ mkdir -p ~/.config/matplotlib
+ echo "backend : GTKCairo" >> ~/.config/matplotlib/matplotlibrc
Mac OSX Mountain Lion
@@ -109,4 +111,7 @@ Install some of the other package we'll use:
pip install pyzmq tornado jinja2 pygments sphinx markdown nose
pip install numpy
pip install matplotlib
- pip install biopython
\ No newline at end of file
+ pip install biopython
+ pip install pandas==0.14.0
+ pip install openpyxl==2.0.4
+
diff --git a/PaintingPandas.ipynb b/PaintingPandas.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..f3924a2ef3be1fb893f692cad72c5b0ec018594e
--- /dev/null
+++ b/PaintingPandas.ipynb
@@ -0,0 +1,808 @@
+{
+ "metadata": {
+ "name": "",
+ "signature": "sha256:f4bfd304820a6c792a65b971256ff4c1e3c8c0b9201520c8d5bb56942f3b771f"
+ },
+ "nbformat": 3,
+ "nbformat_minor": 0,
+ "worksheets": [
+ {
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "source": [
+ "\n",
+ "More on IPython and Python libraries making science peanuts..\n",
+ "===\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "source": [
+ "First of all, I would like to guide you through this lecture interactively.. so first syncronize our directories to:\n",
+ " \n",
+ " cd ~/programming-course/day03/paintingpandas\n",
+ " workon programming-course\n",
+ " ipython notebook"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "source": [
+ "Pandas\n",
+ "===\n",
+ "\n",
+ "* The ultimate carpenters toolkit for bio-informaticians\n",
+ "* Functional programming for science\n",
+ "* ***Easy*** statistical analyses using Python\n",
+ "* Intuitive data mangling\n",
+ "\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "# Enable inline plotting\n",
+ "%matplotlib inline\n",
+ "%pylab inline\n",
+ "\n",
+ "from pandas import DataFrame, read_csv\n",
+ "import matplotlib.pyplot as plt\n"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "output_type": "stream",
+ "stream": "stdout",
+ "text": [
+ "Populating the interactive namespace from numpy and matplotlib\n"
+ ]
+ }
+ ],
+ "prompt_number": 2
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "source": [
+ "Learn by example\n",
+ "===\n",
+ "\n",
+ "Live demo,"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "# Sample dataset\n",
+ "participants = ['Anthony', 'Berend', 'Christine', 'Don', 'Esther', \n",
+ " 'Fer', 'Ginny', 'Hendrik', 'Ivo', 'John', 'Karl', \n",
+ " 'Lotte', 'Marjolijn', 'Nanda']\n",
+ "grades = [70, 65, 81, 73, 85, 45, 70, 60, 14, 64, 72, 75, 92, 84]\n",
+ "sex = ['M','M','F','M','F','M','F','M','M','M','M', 'F', 'F', 'F']\n",
+ "university = ['AU', 'NL', 'NL', 'AU', 'DE', 'DE', 'NL', 'NL', 'NL', 'AU', 'DE', 'NL', 'NL', 'AU']\n",
+ "\n",
+ "\n",
+ "courseResults = zip(participants, grades)\n",
+ "partipants_info = zip(participants, grades, sex, university)"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "outputs": [],
+ "prompt_number": 158
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "courseResults"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 159,
+ "text": [
+ "[('Anthony', 70),\n",
+ " ('Berend', 65),\n",
+ " ('Christine', 81),\n",
+ " ('Don', 73),\n",
+ " ('Esther', 85),\n",
+ " ('Fer', 45),\n",
+ " ('Ginny', 70),\n",
+ " ('Hendrik', 60),\n",
+ " ('Ivo', 14),\n",
+ " ('John', 64),\n",
+ " ('Karl', 72),\n",
+ " ('Lotte', 75),\n",
+ " ('Marjolijn', 92),\n",
+ " ('Nanda', 84)]"
+ ]
+ }
+ ],
+ "prompt_number": 159
+ },
+ {
+ "cell_type": "code",
+ "collapsed": true,
+ "input": [
+ "partipants_info"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 160,
+ "text": [
+ "[('Anthony', 70, 'M', 'AU'),\n",
+ " ('Berend', 65, 'M', 'NL'),\n",
+ " ('Christine', 81, 'F', 'NL'),\n",
+ " ('Don', 73, 'M', 'AU'),\n",
+ " ('Esther', 85, 'F', 'DE'),\n",
+ " ('Fer', 45, 'M', 'DE'),\n",
+ " ('Ginny', 70, 'F', 'NL'),\n",
+ " ('Hendrik', 60, 'M', 'NL'),\n",
+ " ('Ivo', 14, 'M', 'NL'),\n",
+ " ('John', 64, 'M', 'AU'),\n",
+ " ('Karl', 72, 'M', 'DE'),\n",
+ " ('Lotte', 75, 'F', 'NL'),\n",
+ " ('Marjolijn', 92, 'F', 'NL'),\n",
+ " ('Nanda', 84, 'F', 'AU')]"
+ ]
+ }
+ ],
+ "prompt_number": 160
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "df = DataFrame(zip(grades,sex,university), index=participants, columns=['Grade','Sex', 'University' ])\n",
+ "df"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "outputs": [
+ {
+ "html": [
+ "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Grade</th>\n",
+ " <th>Sex</th>\n",
+ " <th>University</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Anthony</th>\n",
+ " <td> 70</td>\n",
+ " <td> M</td>\n",
+ " <td> AU</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Berend</th>\n",
+ " <td> 65</td>\n",
+ " <td> M</td>\n",
+ " <td> NL</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Christine</th>\n",
+ " <td> 81</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Don</th>\n",
+ " <td> 73</td>\n",
+ " <td> M</td>\n",
+ " <td> AU</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Esther</th>\n",
+ " <td> 85</td>\n",
+ " <td> F</td>\n",
+ " <td> DE</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Fer</th>\n",
+ " <td> 45</td>\n",
+ " <td> M</td>\n",
+ " <td> DE</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Ginny</th>\n",
+ " <td> 70</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Hendrik</th>\n",
+ " <td> 60</td>\n",
+ " <td> M</td>\n",
+ " <td> NL</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Ivo</th>\n",
+ " <td> 14</td>\n",
+ " <td> M</td>\n",
+ " <td> NL</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>John</th>\n",
+ " <td> 64</td>\n",
+ " <td> M</td>\n",
+ " <td> AU</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Karl</th>\n",
+ " <td> 72</td>\n",
+ " <td> M</td>\n",
+ " <td> DE</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Lotte</th>\n",
+ " <td> 75</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Marjolijn</th>\n",
+ " <td> 92</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Nanda</th>\n",
+ " <td> 84</td>\n",
+ " <td> F</td>\n",
+ " <td> AU</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 161,
+ "text": [
+ " Grade Sex University\n",
+ "Anthony 70 M AU\n",
+ "Berend 65 M NL\n",
+ "Christine 81 F NL\n",
+ "Don 73 M AU\n",
+ "Esther 85 F DE\n",
+ "Fer 45 M DE\n",
+ "Ginny 70 F NL\n",
+ "Hendrik 60 M NL\n",
+ "Ivo 14 M NL\n",
+ "John 64 M AU\n",
+ "Karl 72 M DE\n",
+ "Lotte 75 F NL\n",
+ "Marjolijn 92 F NL\n",
+ "Nanda 84 F AU"
+ ]
+ }
+ ],
+ "prompt_number": 161
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "# Here for some reason we would like to know what is the average scoring in this class\n",
+ "df.plot(style='o')\n",
+ "summary = df.describe()\n",
+ "summary"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "outputs": [
+ {
+ "html": [
+ "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Grade</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td> 14.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td> 67.857143</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td> 19.457477</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td> 14.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td> 64.250000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td> 71.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td> 79.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td> 92.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 162,
+ "text": [
+ " Grade\n",
+ "count 14.000000\n",
+ "mean 67.857143\n",
+ "std 19.457477\n",
+ "min 14.000000\n",
+ "25% 64.250000\n",
+ "50% 71.000000\n",
+ "75% 79.500000\n",
+ "max 92.000000"
+ ]
+ },
+ {
+ "metadata": {},
+ "output_type": "display_data",
+ "png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAEACAYAAACuzv3DAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3X+cVPV97/EXgiwBMcuiXeEKjp0WTVLjmlwVo4GJkR0N\nihhbapJ62dzGlqvdxd62EYEN5AH4q9dcYfuISZMmuzb+psYQ9haX4A5r1GqNEo2GmGyllSCr8sP6\nowsK5/7xPWfnx87s/J7vfGffz8djHjvnzJkz7z1z5jvnfM53zgERERERERERERERERERERERERER\nkZL6HjAAvJAwrgHYCrwM9AD1CY/dCPwa2Ak0VyijiIiM4NPAWSQ35LcBX/Xv3wDc4t//KLADOBYI\nAb8BjqlIShERGVGI5IZ8J9Do3z/JHwazNX5DwnRbgNnlDiciMtoVssXciCm34P8NGvXpwO6E6XYD\n/63waCIikotiSx+efxvpcRERKaNxBTxnAFNS2QtMA173x/8WmJEw3cn+uCTTp0/39uzZU8DLioiM\nav3A76V7oJAt8k3AYv/+YuDhhPFXAeOBU4HfB55OffKePXvwPM/Z26pVq6xnUH77OZTfvZvL2T3P\nAwhnapSzbZHfC8wFTgBeBb6G6aXyAPCnwC5gkT/tS/74l4APgGupwdLKrl27bEcoivLbpfz2uJw9\nm2wN+RcyjL8ow/ib/JuIiFSI+nnnqaWlxXaEoii/Xcpvj8vZsxlj4TU9v94jIiI5GjNmDGRos6tm\ni7yhoYExY8boVsCtoaEh5+Uci8XK9yZWgPLb5XJ+l7NnU0j3w7I4cOAA2lIvjP9NLSKjVNWUVsaM\nGaOGvEBadiK1z4nSioiIFEYN+Sjjep1Q+e1yOb/L2bNRQ15FQqEQ27Ztsx1DRByjhjwP9913H+ee\ney7HHXccjY2NzJ49mzvvvLNk8w96oZRTJBIp6/zLTfntcjm/y9mzcaIh7+7uIxpdSSSymmh0Jd3d\nfRWfx+23387111/PDTfcwMDAAAMDA3zrW9/i8ccf5/Dhw8OmP3r0aN4ZRURc4aWTafzmzdu9cHi5\nB97QLRxe7m3evD3t9OWYx8GDB71JkyZ5Dz30UMZpFi9e7C1ZssS75JJLvEmTJnnbtm3zNm/e7DU1\nNXnHH3+8N2PGDG/16tVJz7nrrru8mTNnelOnTvXWrVvnhUIhb9u2bZ7ned7Ro0e9m2++2QuHw97U\nqVO9RYsWefv370/72pmWXTq9vb05T1uNlN8ul/O7nN3zvBFPGV71W+QbNvTQ378uaVx//zo6OrZW\nbB5PPvkkhw4d4vLLLx9xunvvvZf29nbeeecdzj//fI477jh+8IMf8NZbb9Hd3c2dd97Jj370IwBe\neuklrr32Wu6++2727NnDvn372L07fl2ODRs2sGnTJvr6+njttdeYMmUK1113Xc7/s4iMHlXfkB86\nlP43S4ODYys2jzfffJMTTjiBY46JL65PfepTTJkyhYkTJ/LYY48xZswYFi5cyHnnnQdAXV0dc+fO\n5WMf+xgAZ5xxBldddRXbt28HYOPGjVx22WVccMEFjB8/njVr1iTN/9vf/jZr165l+vTpHHvssaxa\ntYqNGzcWXbJxvU6o/Ha5mD8oq65eHSu4NFvtquaXnZnU1X2QdvyECUcqNo+pU6fy5ptvcvTo0aHG\n9oknngBgxowZQ43rySefnPS8p556imXLlvHiiy9y+PBhDh06xKJF5qy/e/bsSZp+4sSJTJ06dWh4\n165dXHHFFUmN+7hx4xgYGGDatGk55RYZ7bq7+1i69JGkPfL+/hUAzJ8/x1askqv6LfK2tmbC4RVJ\n48Lh5bS2zqvYPM477zzq6up4+OGHR5wutcfJF7/4RRYuXMju3bs5ePAgS5YsGfoF5vTp03n11VeH\npn3vvffYt2/f0PDMmTPZsmULBw4cGLq99957RTfirvelVX67XMufXFaNAfmXZl1Q9VvkwbdmR0c7\ng4NjmTDhCK2tF+f1bVrsPOrr61m1ahXXXnstnufR3NzMpEmTeP7553n33XczPu+dd95hypQpjB8/\nnqeffpp77rmHaDQKwJVXXsns2bN5/PHHOfvss/na176WVDZZsmQJy5cvp6uri5kzZ/LGG2/w5JNP\nsmDBgpz/b5HRrhSl2Vq3FHgB+IV/H6AB2Aq8DPQA9Wmel/GIbLW7++67vXPOOcebOHGid+KJJ3rn\nnnuu953vfMc7fPiw19LS4rW3tydNv3HjRu+UU07xJk+e7F166aVea2urd/XVVw893tXVldRr5dRT\nT03qtfKNb3zDO+2007zJkyd74XDYW7FiRdpcLiw7ERuam1ck9VYLbtHoStvR8sYIvVYK/fXJH2Au\nA3c28D6wBVgC/DnwJnAbcAMwBViWpiEfHkQnfiqYlp1Ieulq5OHwctavz2+vvhqU46RZpwNPAYPA\nEWA7cCWwAOjyp+kCFhY4fykT12qcqZTfLtfyz58/h/Xro0Sj7Zx5ZgvRaLuTjXg2hdbIfwGsw5RS\nBoHPAc8AjcCAP82APywiYs38+XOYP38OsVjMye6TuSi0Id8J3Iqpg78L7MBsmSfKWNNpaWkhFAoB\n5kBiU1NTgTEkVbDFFKywqcPBuEyPV/uw8it/ocORSKSq8mQbjsVidHZ2Agy1l5mU6gxN64DdmIOe\nEWAvMA3oxZRhEqlGXmJadiK1r1wXlvgd/+9M4PPAPcAmYLE/fjEwcsdrqTjXapyplN8ul/O7nD2b\nYvqRbwSmYnqtXAu8BdwCPAD8KbALWFRkPhERyaJqrtnZ0NDAgQMHLMRx35QpU9i/f7/tGCJSRiOV\nVqqmIRcRkcx08eUScr3Opvx2Kb89LmfPRg25iIjjVFoREXGASisiIjVMDXmeXK2zBVdJaWpqcfoq\nKa4u/4Dy2+Ny9myq/nzkUrzkM8DFgEhNXiVFZLRSjXwUiEZX0tOzNs34drZsWWMhkUjt6O7uY8OG\nHg4dGkdd3Qe0tTWXZQNppBq5tshHAV0lRaQ8quWaoKqR58nFOlvyxadjQ/fyuYB1tXBx+SdSfnvK\nkT35mqCGjWuCqiEfBUpxAWsRGa5a9nZVIx8lurv76OjYmnDx6Xk60ClSpEoef9K5VkREyqCS1wTV\nD4JKyOUaISi/bcpvTzmyJ14TdO7c1dauCapeKyIiRQiuCWqTSis5qlRfURGRdMrVj/xG4E+Ao8AL\nwJeBScD9wCnErxB0sIjXqArV0ldURCSdQmvkIeAa4BPAGcBY4CpgGbAVmAVs84edl9xXNAbY6Sta\nCi7XOEH5bXM5v8vZsym0If9PzLU6J2K26icCe4AFQJc/TRewsNiA1aBa+oqKiKRTaEO+H7gd+A9M\nA34QsyXeCAz40wz4w85L/mVkZOiei7+MjEQitiMURfntcjm/y9mzKbRGHgaux5RY3gIexNTLE3n+\nbZiWlhZCoRAA9fX1NDU1DS3kYPenmoYjkRPp71+RcPZACId7aG29uCryaVjDGq694VgsRmdnJ8BQ\ne5lJob1W/hiYB3zFH74amA1cCHwG2AtMA3qB01Oe62yvlY6Orezd+yonnTTD2V9GxmKxoZXGRcpv\nl8v5Xc4O5em1shNoBz4EDAIXAU8D7wKLgVv9vw8XOP+qE/QVdX1lEJHaU0w/8q9iGuujwLOYrfPJ\nwAPATDJ3P3Ryi1xExCada0VExHE610oJBQcjXKX8dim/PS5nz0YNuYiI41RaERFxgEorIiI1TA15\nnlyvsym/Xcpvj8vZs9H5yEXEOp0mujiqkYuIVekvl7aC9eujaswTqEYuIlUr+TTRhqunibZFDXme\nXK+zKb9dyj9cpU4T7fqyH4kachGxKvk00XEunibaFtXIq4QO9sholb5GvtzK1eirWbmu2SklomuC\nymgWrOMdHe0MDo5lwoQjtLaqEa92nst6e3tLPs/m5hUeeMNu0ejKkr9WOfJXkvLbsXnzdq+5eYV3\n5pmLvebmFd7mzdttR8qbq8s+QIYL9YC2yKuCrgkq1Sx5jzEGRLTHWGV0sDNP5bioRCUP9rh+UQzl\nr7zk7oERwM3ugS4u+1ypIa8CbW3NhMMrksaFw8tpbZ1nKZFInPYYq1+hDflpwHMJt7eANqAB2Aq8\nDPQA9SXIWFXK0Rd1/vw5rF8fJRptZ+7c1USj7WU7Yu96X1rlr7zkPcbY0D3Xuge6uOxzVWiN/FfA\nWf79Y4DfAj8ElmEa8tuAG/zhZalPjkZXqntdiuCaoJJe0D1zYGA3jY0/0fpTQW1tzfT3rxjWPbC1\n9WKLqSRRKfqRN2MuxPxpzEWZ5wIDwEmYr+/TU6b3wNO5FCRnOheHfd3dfXR0bE3oHjhPy77Cyn3N\nzu8BzwDfBA4AUxLmvT9hOOAFvWii0Xa2bFlTgghSy6LRlfT0rE0zXuuPjB7l/EHQeOAyTBkl1Qj9\nHluAEDt3PsYdd9xBU1PT0BHloI5VrcOu5a2F/AMDu4m7A2gCIgwOjq2KfPkMu7j8ayV/cL9a8uSS\nt7OzE4BQKEQ5XQ5sSRjeiSmpAEzzh1OV9Qcv5eb6jwpczJ/8g6lerT8WuZzf5eyeN/IPgootrdwH\n/DPQ5Q/fBuwDbsUc5Kxn+MFOv0aucylIbnQuDpHy1cgnAf8OnAq87Y9rAB4AZgK7gEXAwZTnedHo\nSh0skbzoYJuMduU+2Jkvfy/BTbFYbKie5SLlt0v57XE5O+gKQSIiNU1b5CIiDtAWuYhIDVNDnqfE\nvqguUn67lN8el7NnUzPnI9el0kRktKqJGrnOxSEita7ma+TJJ743XDzxvYhIIWqiIa/kie9dr7Mp\nv13lyt/d3Uc0upJIZDXR6Eq6u/vK8jouL3+Xs2dTEzXySl4qTaTapCst6pqao0sN18h1Lg4ZHXSa\n39GhnKexrQpBY93R0Z5wLg414jI66JqaUhM1cjCN+ZYta4jFVrNly5qyNeKu19mU365y5K9kadHl\n5e9y9mxqpiEXGa3a2poJh1ckjTPX1JxnKZFUWk3UyEVGO53mt/bpNLYiIo4r1w+C6oGNwC+Bl4Bz\nMReW2Aq8DPT409QU1+tsym+X8tvjcvZsimnI1wP/D/gI8HHM9TmXYRryWcA2hl/mTURESqzQ0sqH\ngeeA300ZvxOYCwxgLsIcA05PmUalFak6OumaVLty9CM/FXgD+D5wJvAz4HqgEdOI4/9tLHD+IhWj\nX0aK6wotrYwDPgF80//7LsPLKJ5/qymu19mUf7hKnnRNy98el7NnU+gW+W7/9q/+8EbgRmAvpqSy\nF5gGvJ7uyS0tLYRCIQDq6+tpamoauihqsLCrdXjHjh1VlUf5i5//wMBu4mL+3wiDg2OdyF/JYdfz\nuzQci8Xo7OwEGGovMymm+2Ef8BVMD5XVwER//D7gVswWej1pttRVI5dqonOViAvK1f2wFbgb+Dmm\n18o64BZgHqZxv9AfFqlq+mWkuE4/CMpTLBYb2g1ykfKnV6lfRmr52+NydhgFZz8UKdb8+XPUQ0Wc\npS1yEREH1Pw1O0VERjM15HkKuge5SvntUn57XM6ejRpyERHHqUYuIuIA1chFRGqYGvI8uV5nU367\nlN8el7Nno4ZcRMRxqpGLiDhANXIRkRqmhjxPrtfZlN8u5bfH5ezZqCEXEXGcauQiIg5QjVxEpIap\nIc+T63U25bdL+e1xOXs2xZyPfBfwn8AR4H3gHKABuB84xX98EXCwqIQiIjKiYmrkrwCfBPYnjLsN\neNP/ewMwBV2zU0SkaOWskafOdAHQ5d/vAhYWOX8REcmimIbcA34CPANc449rBAb8+wP+cE1xvc6m\n/HYpvz0uZ8+mmBr5+cBrwInAVmBnyuOefxMRkTIqpiF/zf/7BvBDzMHOAeAkYC8wDXg93RNbWloI\nhUIA1NfX09TUNHR16+Bbs1qHg3HVkkf5qyuf8lfvcCQSqao82YZjsRidnZ0AQ+1lJoUe7JwIjAXe\nBiYBPcDXgYuAfcCtmIOc9ehgp4hI0cpxsLMReAzYATwFbMY05rcA84CXgQv94ZoSfGO6SvntUn57\nXM6eTaGllVeApjTj92O2ykVEpEJ0rhUREQfoXCsiIjVMDXmeXK+zKb9dym+Py9mzUUMuIuI41chF\nRBwwUo28mB8EiQzp7u5jw4YeDh0aR13dB7S1NTN//hzbsURGBZVW8uR6na0c+bu7+1i69BF6etay\nfftqenrWsnTpI3R395X8tbT87XI5v8vZs1FDLkXbsKGH/v51SeP6+9fR0bHVUiKR0UU1cilaJLKa\n7dtXDxs/d+5qYrHh40Ukf+pHLmVVV/dB2vETJhypcBKR0UkNeZ5cr7OVI39bWzPh8IqkceHwclpb\n55X8tbT87XI5v8vZs1GvFSla0Dulo6OdwcGxTJhwhNbWi9VrRaRCVCMXEXGAauQiIjVMDXmeXK+z\nKb9dym+Py9mzUUMuIuK4YmvkY4FngN3AZUADcD9wCrALWAQcTHmOauQiInkqZ418KfASELTMy4Ct\nwCxgG8Ov1ykiIiVWTEN+MvA54LvEvyUWAF3+/S5gYRHzr0qu19mU3y7lt8fl7NkU05D/X+BvgKMJ\n4xqBAf/+gD8sIiJlVOgPgi4FXgeeAyIZpvGIl1yStLS0EAqFAKivr6epqYlIxMwm+Nas1uFgXLXk\nUf7qyqf81TsciUSqKk+24VgsRmdnJ8BQe5lJoQc7bwKuBj4AJgDHAw8BZ2Ma9r3ANKAXOD3luTrY\nKSKSp3Ic7FwOzABOBa4CHsU07JuAxf40i4GHC5x/1Qq+MV2l/HYpvz0uZ8+mVP3Ig03sW4B5wMvA\nhf6wiIiUkc61IiLiAJ1rRUSkhqkhz5PrdTblt0v57XE5ezZqyEVEHKcauYiIA1QjFxGpYWrI8+R6\nnU357VJ+e1zOno0achERx6lGLiLiANXIRURqmBryPLleZ1N+u5TfHpezZ6OGXETEcaqRi4g4QDVy\nEZEapoY8T67X2ZTfLuW3x+Xs2aghFxFxnGrkIiIOKEeNfALwFLADeAm42R/fAGzFXCGoB6gvcP4i\nIpKjQhvyQeAzQBPwcf/+BcAyTEM+C9jmD9cU1+tsym+X8tvjcvZsiqmRv+f/HQ+MBQ4AC4Auf3wX\nsLCI+YuISA6KqZEfAzwLhIE7ga9iGvMpCfPenzAcUI1cRCRPI9XIxxUx36OY0sqHgUcw5ZVEnn8b\npqWlhVAoBEB9fT1NTU1EIhEgvvujYQ1rWMOjeTgWi9HZ2Qkw1F5mUqpeK+3AfwFfASLAXmAa0Auc\nnjKt01vksVhsaKG7SPntUn57XM4O5em1cgLxHikfAuYBzwGbgMX++MXAwwXOX0REclToFvkZmIOZ\nx/i3fwT+FtP98AFgJrALWAQcTHmu01vkIiI2jLRFrh8EiYg4QCfNKqHgYISrlN8u5bfH5ezZqCEX\nEXGcSisiIg5QaUVEpIapIc+T63U25bdL+e1xOXs2ashFRBynGrmIiANUIxcRqWFqyPPkep1N+e1S\nfntczp6NGnIREcepRi4i4gDVyEVEapga8jy5XmdTfruU3x6Xs2ejhlxExHGqkYuIOEA1chGRGlZo\nQz4Dcz3OF4FfAG3++AZgK/Ay0EP8cnA1w/U6m/Lbpfz2uJw9m0Ib8veBvwQ+BswGrgM+AizDNOSz\ngG3+sIiIlFGpauQPA3/n3+YCA8BJQAw4PWVa1chFRPJU7hp5CDgLeApoxDTi+H8bSzB/EREZwbgi\nn38c8E/AUuDtlMc8/zZMS0sLoVAIgPr6epqamohEIkC8jlWtw3fccYdTeZW/uoaV395wcL9a8uSS\nt7OzE2CovSyHY4FHgOsTxu3ElFQApvnDqTyX9fb22o5QFOW3S/ntcTm753kZN4yh8Br5GKAL2Ic5\n6Bm4zR93K+ZAZz3DD3j6mUREJFcj1cgLbcgvAPqA54l/S9wIPA08AMwEdgGLgIMpz1VDLiKSp3Ic\n7Pyp/9wmzIHOs4AtwH7gIkz3w2aGN+LOS6yzuUj57VJ+e1zOno1+2Ski4jida0VExAE614qISA1T\nQ54n1+tsym+X8tvjcvZs1JCLiDhONXIREQeoRi4iUsPUkOfJ9Tqb8tvR3d1HNLqSpqYWotGVdHf3\n2Y5UEFeXP7idPZtiT5olIll0d/exdOkj9Pevw5zZOUJ//woA5s+fYzOa1AjVyEXKLBpdSU/P2jTj\n29myZY2FROIi1chFLDp0KP2O7+Dg2AonkVqlhjxPrtfZlL/y6uo+SBiKDd2bMOFIxbMUy8XlH3A5\nezZqyEXKrK2tmXB4RdK4cHg5ra3zLCWSWqMauUgFdHf30dGxlcHBsUyYcITW1nk60Cl5Kcf5yIuh\nhlxEJE/lOtj5PcwFll9IGNcAbAVeBnowVwiqKa7X2ZTfLuW3x+Xs2RTTkH8fuDhl3DJMQz4L2Mbw\ny7w5b8eOHbYjFEX57VJ+e1zOnk0xDfljwIGUcQsw1/LE/7uwiPlXpYMH3b7okfLbpfz2uJw9m1L3\nWmnElFvw/zaWeP4iIpKinN0PPeIXZq4Zu3btsh2hKMpvl/Lb43L2bIrttRICfgyc4Q/vBCLAXmAa\n0AucnvKc3wDhIl9XRGS06Qd+L90DpT5p1iZgMXCr//fhNNOkDSIiIpV3L7AHOAy8CnwZ0/3wJ9Rw\n90MREREREWsWAkeB03KY9nrgQwnD75QlUXYnAfdh6vLPAN3ANZi6fi6+Dnx2hMcvBz6Sx/SlcgR4\nLuH21RGmTc0YAz5ZtmT5aQTuwdT+ngGewKxnnwTWW8xVLFvre7ESc38O+BUwI4/ntwAdJcxzFPjH\nhOFxwBvk/vkNTAcezDJNJGG+lwE3+Pf/HLg6z9eravdjauCrc5j2FWBqwvDb5QiUxRjgSeDPEsZ9\nHFhJbitCLj16OoEr805WvHyWZyfJGXspvCEv5TGVdO/PTOAvSvgatthY30shyP1Z4NfAqXk8dxzm\nuFgpG/K3gWeBCf7wJZgNl0155spFhPy/IJxzHLAL80H7pT8ugtm6e9Af9wN/fBtwCHge8+tOMG/I\nWmAH5sP7O/74EPAo8HNMbT349u/EbJE9jtlaCxqiLswWZuBuzI+Q0rkQ2J5m/FxMY5aaG/9/vAX4\nGfDHJDeCtwAv+ln/FjgP2Af8G2Zl+92U6XdhvvR+hlkWwZ7MJMzpDZ7yn5cp/0gyNRS5ZOz1p3sK\ns8V1gf/csf5znvafHzSwEcyPv37kT18qnyXxnK7JIsQ/VKsxy6sXsy60+uNDmPfv74FfAI9gPvBh\nzDIP/H7KcCUE7899mC3bQCfweaAO88vo5zHvS6SC2UbyNjAHs5xnJYy/BrNe7AA2Et/b7gS+BfwL\ncDvlacjXEv9M3YXZ+wzWjXMwe3HPYtqKIHMLprHfhllvTsGsI2DWkXTLPpIw35aE/2M18Ff+/Rjp\nPzvO+BLmDQPoAz6B+ccPYnZbxmAW6Kf8aV7BHPgMHAXm+/dvBYJzev6Y+G7Ll4Ef+vc7MXsAYMoC\nv/bvz0mY5sOYBirTlnMb8I0047Pl/uuEab+P+eBNxXStDByf8njq9MG8rvPv/y/gO/79mzDLE8zB\n4F8BEzP8D5l8QHJp5Y/yyNiLabDBbOFs9e//GfH3pQ74V0xjGcHscp+SZ8ZsMr0/MLwh/ylwLOZ/\nfBPzpRMC3sfsZYFZX4Ll+ihwpn//JuLvQ6UEDflCzLoMMB74D8yy/Svgu/7404B/9x+37X3MF/8f\npIxP/CyvIb7X1IlpMINuzOVoyM/AbHTVYdb1ucTXjcmYdQHgIsyXDJiG+FXinS1CxM8JlW7Z15G5\nIV8F/G//fqbPjnW5/iDoC8RrTA/6wx7mW3qPf38HZoGlcxhTnwazdRRMNxtTIwWzZRx8w3nEuy7+\nkvgvRPswW1gn+Bk2Yr4k0hnpx0gj5b4/zfQHgUHgH4ArgP9KeGykvvgP+X+fTXiNZsw5aJ7DrBh1\n5FeHxH/9sxJuD+aZMVOu/+Hn+hfMhzfoKvo0ZoUvpdT35+8w78XTKY95mHUnaGReJ74+vILZsoLk\n9eq7mA2DY4BFxNexStsCfAbTSF+C2UM8BJxPfE/wV5hlm8uxp3I7jNmy/UrK+DMwe2XPY74sP+qP\n9zDrXjl/+PcC5n39AvE2JFCPaQNewGwUfDThsR7MZyJVumU/K810maT77FiXS0PegFkZ/wHzwfkb\nzIdjDGalDBwhcz3q/YT7R1Omy9QQHs4wzV2YrfgWzC53Ji+SuRY8Uu53U6Yd409zDmaluRTzAQ2M\ntBIHr5P6Gp8n3giHKE3JIp+MmXL9RUKuMKbcBcOXSSm8iNmzS3ztzwInppk2cV1IzJzpfXwI03Be\nijmImnpOoEoZxOyORzGfmcSNhNT1vhp+BX0Uk/Mc4MaE8Z3AtZi9n6+T3JHhvQrk2gT8H0yX58Tl\ntgZTPjkDc4Ay11zFLPtMnx2rcmnI/xDTeIYwBz9mYhr0kc6K/zbxXfuRPAFc5d//EmaLO5tOTK8Y\nj+RSQqpHMVu71ySM+zjw6RxeI9UkzLf/P2N2s4Ld9lz/z0SPYMoKgbMKyJNOsRkfwXxYg5VzFvmX\nfPLxKKZeuSRh3KQ00xXy6+NBzP9zJ6a0ZNP9wP/ErHfBl+tjxMtAszCfqVIefyjGIKYM+iVMbjDH\nyPZiylt/QuaGr1zXN/gepsT2Ysr44zF71mD2wHJRzcu+YLk05FcRr0sH/skfn+kN/XvMShsc7Ezd\nVQ6GWzFvwM8xC3dpynTp7r8OvERuH9ArMLWz32AOdqwDXhshdzoephb3Yz/nY8Bf+o/dh9lD+Rnm\nQOJI8whecw3mA/G8n+nreWQJfIjkGvlNRWQMcn0Xs1yfxeyq3olp1Mt5zpyFmJrnv2EOIHUS70rp\nJfzN9Pqp4xOH78FsYfaUImieEnP0YDZ6tmKObQB8E/PZex7z/iwmea/VliD3AcwpqlditnTbMe/P\nT4l3dkh9TnC/lOtKMK/fYkpvqa9xG3AzZp0dy8jrTDCcadl7Izw/1/VP8jAR0zBPth1EqtpfU9iX\npNSeT5K5h1Q2HZjGXkroIky3vrYs08no9kPMgdOGbBNKzfvvmNJJIddGWIM58D+lpIlERERERERE\nREREREQD2gK7AAAAD0lEQVREREREREREROz7/+r8tTaVYXH8AAAAAElFTkSuQmCC\n",
+ "text": [
+ "<matplotlib.figure.Figure at 0x749f350>"
+ ]
+ }
+ ],
+ "prompt_number": 162
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "groupGrades = df.groupby('University')"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "outputs": [],
+ "prompt_number": 163
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "df['Lower'] = groupGrades['Grade'].transform( lambda x: x.quantile(q=.25) - (1.2*x.quantile(q=.75)-x.quantile(q=.25)) )\n",
+ "df['Upper'] = groupGrades['Grade'].transform( lambda x: x.quantile(q=.75) + (1.2*x.quantile(q=.75)-x.quantile(q=.25)) )\n",
+ "df['Outlier'] = (df['Grade'] < df['Lower']) | (df['Grade'] > df['Upper']) \n",
+ "df\n"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "html": [
+ "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Grade</th>\n",
+ " <th>Sex</th>\n",
+ " <th>University</th>\n",
+ " <th>Lower</th>\n",
+ " <th>Upper</th>\n",
+ " <th>Outlier</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Anthony</th>\n",
+ " <td> 70</td>\n",
+ " <td> M</td>\n",
+ " <td> AU</td>\n",
+ " <td> 46.1</td>\n",
+ " <td> 98.15</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Berend</th>\n",
+ " <td> 65</td>\n",
+ " <td> M</td>\n",
+ " <td> NL</td>\n",
+ " <td> 31.4</td>\n",
+ " <td> 109.10</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Christine</th>\n",
+ " <td> 81</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " <td> 31.4</td>\n",
+ " <td> 109.10</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Don</th>\n",
+ " <td> 73</td>\n",
+ " <td> M</td>\n",
+ " <td> AU</td>\n",
+ " <td> 46.1</td>\n",
+ " <td> 98.15</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Esther</th>\n",
+ " <td> 85</td>\n",
+ " <td> F</td>\n",
+ " <td> DE</td>\n",
+ " <td> 22.8</td>\n",
+ " <td> 114.20</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Fer</th>\n",
+ " <td> 45</td>\n",
+ " <td> M</td>\n",
+ " <td> DE</td>\n",
+ " <td> 22.8</td>\n",
+ " <td> 114.20</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Ginny</th>\n",
+ " <td> 70</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " <td> 31.4</td>\n",
+ " <td> 109.10</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Hendrik</th>\n",
+ " <td> 60</td>\n",
+ " <td> M</td>\n",
+ " <td> NL</td>\n",
+ " <td> 31.4</td>\n",
+ " <td> 109.10</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Ivo</th>\n",
+ " <td> 14</td>\n",
+ " <td> M</td>\n",
+ " <td> NL</td>\n",
+ " <td> 31.4</td>\n",
+ " <td> 109.10</td>\n",
+ " <td> True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>John</th>\n",
+ " <td> 64</td>\n",
+ " <td> M</td>\n",
+ " <td> AU</td>\n",
+ " <td> 46.1</td>\n",
+ " <td> 98.15</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Karl</th>\n",
+ " <td> 72</td>\n",
+ " <td> M</td>\n",
+ " <td> DE</td>\n",
+ " <td> 22.8</td>\n",
+ " <td> 114.20</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Lotte</th>\n",
+ " <td> 75</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " <td> 31.4</td>\n",
+ " <td> 109.10</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Marjolijn</th>\n",
+ " <td> 92</td>\n",
+ " <td> F</td>\n",
+ " <td> NL</td>\n",
+ " <td> 31.4</td>\n",
+ " <td> 109.10</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Nanda</th>\n",
+ " <td> 84</td>\n",
+ " <td> F</td>\n",
+ " <td> AU</td>\n",
+ " <td> 46.1</td>\n",
+ " <td> 98.15</td>\n",
+ " <td> False</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 164,
+ "text": [
+ " Grade Sex University Lower Upper Outlier\n",
+ "Anthony 70 M AU 46.1 98.15 False\n",
+ "Berend 65 M NL 31.4 109.10 False\n",
+ "Christine 81 F NL 31.4 109.10 False\n",
+ "Don 73 M AU 46.1 98.15 False\n",
+ "Esther 85 F DE 22.8 114.20 False\n",
+ "Fer 45 M DE 22.8 114.20 False\n",
+ "Ginny 70 F NL 31.4 109.10 False\n",
+ "Hendrik 60 M NL 31.4 109.10 False\n",
+ "Ivo 14 M NL 31.4 109.10 True\n",
+ "John 64 M AU 46.1 98.15 False\n",
+ "Karl 72 M DE 22.8 114.20 False\n",
+ "Lotte 75 F NL 31.4 109.10 False\n",
+ "Marjolijn 92 F NL 31.4 109.10 False\n",
+ "Nanda 84 F AU 46.1 98.15 False"
+ ]
+ }
+ ],
+ "prompt_number": 164
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "df.plot(style='-')"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 165,
+ "text": [
+ "<matplotlib.axes.AxesSubplot at 0xb1b24d0>"
+ ]
+ },
+ {
+ "metadata": {},
+ "output_type": "display_data",
+ "png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAEACAYAAACuzv3DAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njUaj0Wg0Go1Go9EEGv8HwuXnWj8AmAoAAAAASUVORK5CYII=\n",
+ "text": [
+ "<matplotlib.figure.Figure at 0xaa14a50>"
+ ]
+ }
+ ],
+ "prompt_number": 165
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "source": [
+ "So, what does this mean?\n",
+ "===\n",
+ "\n",
+ "Let's grind the dataset a little bit more..."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "df.boxplot(column=['Grade'], by=['University'])"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 166,
+ "text": [
+ "<matplotlib.axes.AxesSubplot at 0xb194750>"
+ ]
+ },
+ {
+ "metadata": {},
+ "output_type": "display_data",
+ "png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEaCAYAAAD9iIezAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nIOQAAAAASUVORK5CYII=\n",
+ "text": [
+ "<matplotlib.figure.Figure at 0xac5c150>"
+ ]
+ }
+ ],
+ "prompt_number": 166
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "df.boxplot(column=['Grade'], by=['Sex'])"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 167,
+ "text": [
+ "<matplotlib.axes.AxesSubplot at 0xb5a9590>"
+ ]
+ },
+ {
+ "metadata": {},
+ "output_type": "display_data",
+ "png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAEaCAYAAAD9iIezAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nR9MY/ilJkiRJkiRJkiRJkiRJUvL/ia8+8LiPvcIAAAAASUVORK5CYII=\n",
+ "text": [
+ "<matplotlib.figure.Figure at 0xb5acd10>"
+ ]
+ }
+ ],
+ "prompt_number": 167
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "\n",
+ "type(groupGrades)"
+ ],
+ "language": "python",
+ "metadata": {},
+ "outputs": [
+ {
+ "metadata": {},
+ "output_type": "pyout",
+ "prompt_number": 209,
+ "text": [
+ "pandas.core.groupby.DataFrameGroupBy"
+ ]
+ }
+ ],
+ "prompt_number": 209
+ },
+ {
+ "cell_type": "code",
+ "collapsed": false,
+ "input": [
+ "\n",
+ "for group, data in groupGrades:\n",
+ " fig, ax = plt.subplots(1, 1)\n",
+ " ax.get_xaxis().set_visible(False) # hide ticks\n",
+ " data.plot( style='-', table=True, ax = ax, secondary_y=['Outlier'], mark_right=False)"
+ ],
+ "language": "python",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "subslide"
+ }
+ },
+ "outputs": [
+ {
+ "metadata": {},
+ "output_type": "display_data",
+ "png": "iVBORw0KGgoAAAANSUhEUgAAAaYAAAEuCAYAAADFkra2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\niIiIiIiIiIiIiIiIiIiIuMv/B/aqTY+jz+aEAAAAAElFTkSuQmCC\n",
+ "text": [
+ "<matplotlib.figure.Figure at 0x163a33d0>"
+ ]
+ },
+ {
+ "metadata": {},
+ "output_type": "display_data",
+ "png": "iVBORw0KGgoAAAANSUhEUgAAAaYAAAEuCAYAAADFkra2AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
+ "text": [
+ "<matplotlib.figure.Figure at 0x163a32d0>"
+ ]
+ },
+ {
+ "metadata": {},
+ "output_type": "display_data",
+ "png": "iVBORw0KGgoAAAANSUhEUgAAAZgAAAEuCAYAAACzqAQ9AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nEEIIIYQQQgghhBBCiP+zfwAWi45j3oS4wAAAAABJRU5ErkJggg==\n",
+ "text": [
+ "<matplotlib.figure.Figure at 0x15989390>"
+ ]
+ }
+ ],
+ "prompt_number": 229
+ }
+ ],
+ "metadata": {}
+ }
+ ]
+}
\ No newline at end of file
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000000000000000000000000000000000000..31383d6e3092fc22a0776900d35a641d4ead7eaa
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,14 @@
+ipython==2.1.0
+pyzmq==14.3.1
+tornado==3.2.2
+Jinja2==2.7.3
+Pygments==1.6
+Sphinx==1.2.2
+Markdown==2.4.1
+nose==1.3.3
+numpy==1.8.1
+matplotlib==1.3.1
+biopython==1.64
+pandas==0.14.0
+openpyxl==2.0.4
+