{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib as mpl\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Let's read in the data file\n",
    "df = pd.read_excel('../data/mdcps/DADE_SchoolGrades17.xls', header = None)\n",
    "# df.set_index(df.iloc[3])\n",
    "df = df[4:]\n",
    "df.columns = df.iloc[0]\n",
    "df = df[1:]\n",
    "# df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "df2 = pd.DataFrame(df, columns = ['District Number', 'District Name', 'School Number', 'School Name',\n",
    "       'English Language Arts Achievement',\n",
    "       'English Language Arts Learning Gains',\n",
    "       'English Language Arts Learning Gains of the Lowest 25%',\n",
    "       'Mathematics Achievement', 'Mathematics Learning Gains',\n",
    "       'Mathematics Learning Gains of the Lowest 25%', 'Science Achievement',\n",
    "       'Social Studies Achievement', 'Middle School Acceleration',\n",
    "       'Graduation Rate 2015-16', 'College and Career Acceleration 2015-16',\n",
    "       'Total Points Earned', 'Total Components',\n",
    "       'Percent of Total Possible Points', 'Percent Tested', 'Grade 2017',\n",
    "       'Grade 2016', 'Informational Baseline Grade 2015', 'Grade 2014',\n",
    "       'Grade 2013', 'Grade 2012', 'Grade 2011', 'Grade 2010', 'Grade 2009',\n",
    "       'Grade 2008', 'Grade 2007', 'Grade 2006', 'Grade 2005', 'Grade 2004',\n",
    "       'Grade 2003', 'Grade 2002', 'Grade 2001', 'Grade 2000', 'Grade 1999',\n",
    "       'Was the collocated rule used?', 'Collocated Number', 'Charter School',\n",
    "       'Title I', 'Alternative/ESE Center School', 'School Type',\n",
    "       'Percent of Minority Students',\n",
    "       'Percent of Economically Disadvantaged Students', 'Region'])\n",
    "# df2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "x = np.array(df2['English Language Arts Achievement'])\n",
    "y = np.array(df2['Social Studies Achievement'])\n",
    "z = np.array(df2['Mathematics Achievement'])\n",
    "w= np.array(df2['Science Achievement'])\n",
    "colors = ['green']*(len(x)-1)\n",
    "# colors.append('red')\n",
    "\n",
    "plt.figure()\n",
    "plt.scatter(z, w, s=100, c=colors) # Math & Science"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.scatter(x, y, s=100, c=colors) # English & Social Studies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.scatter(x, z, s=100, c=colors) # English & Math"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.scatter(y, w, s=100, c=colors) # Science & Social Studies"
   ]
  },
  {
   "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": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}