csv_to_python_code.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:681e72a21fa977c3ce344c0a3832c28951a4a3244d830457e2f130383b733e33"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Convert A CSV Into Python Code To Recreate It\n",
      "\n",
      "This snippit was written by [Chris R. Albon](http://www.chrisralbon.com/) and is part of his collection of [well-documented Python snippits](https://github.com/chrisalbon/code_py). All code is written in Python 3 in iPython notebook and offered under the [Creative Commons Attribution-ShareAlike 4.0 International License](http://creativecommons.org/licenses/by-sa/4.0/\"><img alt=\"Creative Commons License).\n",
      "\n",
      "This might seem like a strange bit of code, but it serves a very valuable (though niche) function. As a rule, I like all the snippits in my [well-documented Python snippits series](https://github.com/chrisalbon/code_py) to not rely on outside data to run. That is, the data is created within the script itself, rather than requiring loading an data from a csv file. Obviously this is not reasonable for real analyses, but for snippits it just makes everything simpler and easier.\n",
      "\n",
      "However, this preference to embed the generation of data in the snippits themselves becomes a problem when I want to use data found in existing datasets. So, **I created this script to complete one simple task: To take a dataset and generate the python code required to recreate it.**"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Preliminaries"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Import the pandas package\n",
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Load the external dataset"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Load the csv file as a pandas dataframe\n",
      "df_original = pd.read_csv('http://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv')\n",
      "df = pd.read_csv('http://vincentarelbundock.github.io/Rdatasets/csv/datasets/iris.csv')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Print the code required to create that dataset"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Print the code to create the dataframe\n",
      "print('==============================')\n",
      "print('RUN THE CODE BELOW THIS LINE')\n",
      "print('==============================')\n",
      "print('raw_data =', df.to_dict(outtype='list'))\n",
      "print('df = pd.DataFrame(raw_data, columns = ' + str(list(df_original)) + ')')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "==============================\n",
        "RUN THE CODE BELOW THIS LINE\n",
        "==============================\n",
        "raw_data = {'Unnamed: 0': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150], 'Sepal.Length': [5.0999999999999996, 4.9000000000000004, 4.7000000000000002, 4.5999999999999996, 5.0, 5.4000000000000004, 4.5999999999999996, 5.0, 4.4000000000000004, 4.9000000000000004, 5.4000000000000004, 4.7999999999999998, 4.7999999999999998, 4.2999999999999998, 5.7999999999999998, 5.7000000000000002, 5.4000000000000004, 5.0999999999999996, 5.7000000000000002, 5.0999999999999996, 5.4000000000000004, 5.0999999999999996, 4.5999999999999996, 5.0999999999999996, 4.7999999999999998, 5.0, 5.0, 5.2000000000000002, 5.2000000000000002, 4.7000000000000002, 4.7999999999999998, 5.4000000000000004, 5.2000000000000002, 5.5, 4.9000000000000004, 5.0, 5.5, 4.9000000000000004, 4.4000000000000004, 5.0999999999999996, 5.0, 4.5, 4.4000000000000004, 5.0, 5.0999999999999996, 4.7999999999999998, 5.0999999999999996, 4.5999999999999996, 5.2999999999999998, 5.0, 7.0, 6.4000000000000004, 6.9000000000000004, 5.5, 6.5, 5.7000000000000002, 6.2999999999999998, 4.9000000000000004, 6.5999999999999996, 5.2000000000000002, 5.0, 5.9000000000000004, 6.0, 6.0999999999999996, 5.5999999999999996, 6.7000000000000002, 5.5999999999999996, 5.7999999999999998, 6.2000000000000002, 5.5999999999999996, 5.9000000000000004, 6.0999999999999996, 6.2999999999999998, 6.0999999999999996, 6.4000000000000004, 6.5999999999999996, 6.7999999999999998, 6.7000000000000002, 6.0, 5.7000000000000002, 5.5, 5.5, 5.7999999999999998, 6.0, 5.4000000000000004, 6.0, 6.7000000000000002, 6.2999999999999998, 5.5999999999999996, 5.5, 5.5, 6.0999999999999996, 5.7999999999999998, 5.0, 5.5999999999999996, 5.7000000000000002, 5.7000000000000002, 6.2000000000000002, 5.0999999999999996, 5.7000000000000002, 6.2999999999999998, 5.7999999999999998, 7.0999999999999996, 6.2999999999999998, 6.5, 7.5999999999999996, 4.9000000000000004, 7.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.5, 6.4000000000000004, 6.7999999999999998, 5.7000000000000002, 5.7999999999999998, 6.4000000000000004, 6.5, 7.7000000000000002, 7.7000000000000002, 6.0, 6.9000000000000004, 5.5999999999999996, 7.7000000000000002, 6.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.2000000000000002, 6.0999999999999996, 6.4000000000000004, 7.2000000000000002, 7.4000000000000004, 7.9000000000000004, 6.4000000000000004, 6.2999999999999998, 6.0999999999999996, 7.7000000000000002, 6.2999999999999998, 6.4000000000000004, 6.0, 6.9000000000000004, 6.7000000000000002, 6.9000000000000004, 5.7999999999999998, 6.7999999999999998, 6.7000000000000002, 6.7000000000000002, 6.2999999999999998, 6.5, 6.2000000000000002, 5.9000000000000004], 'Petal.Length': [1.3999999999999999, 1.3999999999999999, 1.3, 1.5, 1.3999999999999999, 1.7, 1.3999999999999999, 1.5, 1.3999999999999999, 1.5, 1.5, 1.6000000000000001, 1.3999999999999999, 1.1000000000000001, 1.2, 1.5, 1.3, 1.3999999999999999, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.8999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.3999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.5, 1.3999999999999999, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6000000000000001, 1.8999999999999999, 1.3999999999999999, 1.6000000000000001, 1.3999999999999999, 1.5, 1.3999999999999999, 4.7000000000000002, 4.5, 4.9000000000000004, 4.0, 4.5999999999999996, 4.5, 4.7000000000000002, 3.2999999999999998, 4.5999999999999996, 3.8999999999999999, 3.5, 4.2000000000000002, 4.0, 4.7000000000000002, 3.6000000000000001, 4.4000000000000004, 4.5, 4.0999999999999996, 4.5, 3.8999999999999999, 4.7999999999999998, 4.0, 4.9000000000000004, 4.7000000000000002, 4.2999999999999998, 4.4000000000000004, 4.7999999999999998, 5.0, 4.5, 3.5, 3.7999999999999998, 3.7000000000000002, 3.8999999999999999, 5.0999999999999996, 4.5, 4.5, 4.7000000000000002, 4.4000000000000004, 4.0999999999999996, 4.0, 4.4000000000000004, 4.5999999999999996, 4.0, 3.2999999999999998, 4.2000000000000002, 4.2000000000000002, 4.2000000000000002, 4.2999999999999998, 3.0, 4.0999999999999996, 6.0, 5.0999999999999996, 5.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.5999999999999996, 4.5, 6.2999999999999998, 5.7999999999999998, 6.0999999999999996, 5.0999999999999996, 5.2999999999999998, 5.5, 5.0, 5.0999999999999996, 5.2999999999999998, 5.5, 6.7000000000000002, 6.9000000000000004, 5.0, 5.7000000000000002, 4.9000000000000004, 6.7000000000000002, 4.9000000000000004, 5.7000000000000002, 6.0, 4.7999999999999998, 4.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.0999999999999996, 6.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.5999999999999996, 6.0999999999999996, 5.5999999999999996, 5.5, 4.7999999999999998, 5.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.0999999999999996, 5.9000000000000004, 5.7000000000000002, 5.2000000000000002, 5.0, 5.2000000000000002, 5.4000000000000004, 5.0999999999999996], 'Petal.Width': [0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.10000000000000001, 0.20000000000000001, 0.40000000000000002, 0.40000000000000002, 0.29999999999999999, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.5, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.59999999999999998, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 1.3999999999999999, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6000000000000001, 1.0, 1.3, 1.3999999999999999, 1.0, 1.5, 1.0, 1.3999999999999999, 1.3, 1.3999999999999999, 1.5, 1.0, 1.5, 1.1000000000000001, 1.8, 1.3, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3999999999999999, 1.7, 1.5, 1.0, 1.1000000000000001, 1.0, 1.2, 1.6000000000000001, 1.5, 1.6000000000000001, 1.5, 1.3, 1.3, 1.3, 1.2, 1.3999999999999999, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1000000000000001, 1.3, 2.5, 1.8999999999999999, 2.1000000000000001, 1.8, 2.2000000000000002, 2.1000000000000001, 1.7, 1.8, 1.8, 2.5, 2.0, 1.8999999999999999, 2.1000000000000001, 2.0, 2.3999999999999999, 2.2999999999999998, 1.8, 2.2000000000000002, 2.2999999999999998, 1.5, 2.2999999999999998, 2.0, 2.0, 1.8, 2.1000000000000001, 1.8, 1.8, 1.8, 2.1000000000000001, 1.6000000000000001, 1.8999999999999999, 2.0, 2.2000000000000002, 1.5, 1.3999999999999999, 2.2999999999999998, 2.3999999999999999, 1.8, 1.8, 2.1000000000000001, 2.3999999999999999, 2.2999999999999998, 1.8999999999999999, 2.2999999999999998, 2.5, 2.2999999999999998, 1.8999999999999999, 2.0, 2.2999999999999998, 1.8], 'Sepal.Width': [3.5, 3.0, 3.2000000000000002, 3.1000000000000001, 3.6000000000000001, 3.8999999999999999, 3.3999999999999999, 3.3999999999999999, 2.8999999999999999, 3.1000000000000001, 3.7000000000000002, 3.3999999999999999, 3.0, 3.0, 4.0, 4.4000000000000004, 3.8999999999999999, 3.5, 3.7999999999999998, 3.7999999999999998, 3.3999999999999999, 3.7000000000000002, 3.6000000000000001, 3.2999999999999998, 3.3999999999999999, 3.0, 3.3999999999999999, 3.5, 3.3999999999999999, 3.2000000000000002, 3.1000000000000001, 3.3999999999999999, 4.0999999999999996, 4.2000000000000002, 3.1000000000000001, 3.2000000000000002, 3.5, 3.6000000000000001, 3.0, 3.3999999999999999, 3.5, 2.2999999999999998, 3.2000000000000002, 3.5, 3.7999999999999998, 3.0, 3.7999999999999998, 3.2000000000000002, 3.7000000000000002, 3.2999999999999998, 3.2000000000000002, 3.2000000000000002, 3.1000000000000001, 2.2999999999999998, 2.7999999999999998, 2.7999999999999998, 3.2999999999999998, 2.3999999999999999, 2.8999999999999999, 2.7000000000000002, 2.0, 3.0, 2.2000000000000002, 2.8999999999999999, 2.8999999999999999, 3.1000000000000001, 3.0, 2.7000000000000002, 2.2000000000000002, 2.5, 3.2000000000000002, 2.7999999999999998, 2.5, 2.7999999999999998, 2.8999999999999999, 3.0, 2.7999999999999998, 3.0, 2.8999999999999999, 2.6000000000000001, 2.3999999999999999, 2.3999999999999999, 2.7000000000000002, 2.7000000000000002, 3.0, 3.3999999999999999, 3.1000000000000001, 2.2999999999999998, 3.0, 2.5, 2.6000000000000001, 3.0, 2.6000000000000001, 2.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 2.8999999999999999, 2.5, 2.7999999999999998, 3.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 3.0, 3.0, 2.5, 2.8999999999999999, 2.5, 3.6000000000000001, 3.2000000000000002, 2.7000000000000002, 3.0, 2.5, 2.7999999999999998, 3.2000000000000002, 3.0, 3.7999999999999998, 2.6000000000000001, 2.2000000000000002, 3.2000000000000002, 2.7999999999999998, 2.7999999999999998, 2.7000000000000002, 3.2999999999999998, 3.2000000000000002, 2.7999999999999998, 3.0, 2.7999999999999998, 3.0, 2.7999999999999998, 3.7999999999999998, 2.7999999999999998, 2.7999999999999998, 2.6000000000000001, 3.0, 3.3999999999999999, 3.1000000000000001, 3.0, 3.1000000000000001, 3.1000000000000001, 3.1000000000000001, 2.7000000000000002, 3.2000000000000002, 3.2999999999999998, 3.0, 2.5, 3.0, 3.3999999999999999, 3.0], 'Species': ['setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica']}\n",
        "df = pd.DataFrame(raw_data, columns = ['Unnamed: 0', 'Sepal.Length', 'Sepal.Width', 'Petal.Length', 'Petal.Width', 'Species'])\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stderr",
       "text": [
        "/Users/chrisralbon/anaconda/envs/py3k/lib/python3.3/site-packages/pandas/util/decorators.py:81: FutureWarning: the 'outtype' keyword is deprecated, use 'orient' instead\n",
        "  warnings.warn(msg, FutureWarning)\n"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## If you want to check the results...\n",
      "\n",
      "### 1. Enter the code produced from the cell above in this cell"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "raw_data = {'Petal.Width': [0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.10000000000000001, 0.20000000000000001, 0.40000000000000002, 0.40000000000000002, 0.29999999999999999, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.5, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.40000000000000002, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.10000000000000001, 0.20000000000000001, 0.20000000000000001, 0.29999999999999999, 0.29999999999999999, 0.20000000000000001, 0.59999999999999998, 0.40000000000000002, 0.29999999999999999, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 0.20000000000000001, 1.3999999999999999, 1.5, 1.5, 1.3, 1.5, 1.3, 1.6000000000000001, 1.0, 1.3, 1.3999999999999999, 1.0, 1.5, 1.0, 1.3999999999999999, 1.3, 1.3999999999999999, 1.5, 1.0, 1.5, 1.1000000000000001, 1.8, 1.3, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3999999999999999, 1.7, 1.5, 1.0, 1.1000000000000001, 1.0, 1.2, 1.6000000000000001, 1.5, 1.6000000000000001, 1.5, 1.3, 1.3, 1.3, 1.2, 1.3999999999999999, 1.2, 1.0, 1.3, 1.2, 1.3, 1.3, 1.1000000000000001, 1.3, 2.5, 1.8999999999999999, 2.1000000000000001, 1.8, 2.2000000000000002, 2.1000000000000001, 1.7, 1.8, 1.8, 2.5, 2.0, 1.8999999999999999, 2.1000000000000001, 2.0, 2.3999999999999999, 2.2999999999999998, 1.8, 2.2000000000000002, 2.2999999999999998, 1.5, 2.2999999999999998, 2.0, 2.0, 1.8, 2.1000000000000001, 1.8, 1.8, 1.8, 2.1000000000000001, 1.6000000000000001, 1.8999999999999999, 2.0, 2.2000000000000002, 1.5, 1.3999999999999999, 2.2999999999999998, 2.3999999999999999, 1.8, 1.8, 2.1000000000000001, 2.3999999999999999, 2.2999999999999998, 1.8999999999999999, 2.2999999999999998, 2.5, 2.2999999999999998, 1.8999999999999999, 2.0, 2.2999999999999998, 1.8], 'Sepal.Width': [3.5, 3.0, 3.2000000000000002, 3.1000000000000001, 3.6000000000000001, 3.8999999999999999, 3.3999999999999999, 3.3999999999999999, 2.8999999999999999, 3.1000000000000001, 3.7000000000000002, 3.3999999999999999, 3.0, 3.0, 4.0, 4.4000000000000004, 3.8999999999999999, 3.5, 3.7999999999999998, 3.7999999999999998, 3.3999999999999999, 3.7000000000000002, 3.6000000000000001, 3.2999999999999998, 3.3999999999999999, 3.0, 3.3999999999999999, 3.5, 3.3999999999999999, 3.2000000000000002, 3.1000000000000001, 3.3999999999999999, 4.0999999999999996, 4.2000000000000002, 3.1000000000000001, 3.2000000000000002, 3.5, 3.6000000000000001, 3.0, 3.3999999999999999, 3.5, 2.2999999999999998, 3.2000000000000002, 3.5, 3.7999999999999998, 3.0, 3.7999999999999998, 3.2000000000000002, 3.7000000000000002, 3.2999999999999998, 3.2000000000000002, 3.2000000000000002, 3.1000000000000001, 2.2999999999999998, 2.7999999999999998, 2.7999999999999998, 3.2999999999999998, 2.3999999999999999, 2.8999999999999999, 2.7000000000000002, 2.0, 3.0, 2.2000000000000002, 2.8999999999999999, 2.8999999999999999, 3.1000000000000001, 3.0, 2.7000000000000002, 2.2000000000000002, 2.5, 3.2000000000000002, 2.7999999999999998, 2.5, 2.7999999999999998, 2.8999999999999999, 3.0, 2.7999999999999998, 3.0, 2.8999999999999999, 2.6000000000000001, 2.3999999999999999, 2.3999999999999999, 2.7000000000000002, 2.7000000000000002, 3.0, 3.3999999999999999, 3.1000000000000001, 2.2999999999999998, 3.0, 2.5, 2.6000000000000001, 3.0, 2.6000000000000001, 2.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 2.8999999999999999, 2.5, 2.7999999999999998, 3.2999999999999998, 2.7000000000000002, 3.0, 2.8999999999999999, 3.0, 3.0, 2.5, 2.8999999999999999, 2.5, 3.6000000000000001, 3.2000000000000002, 2.7000000000000002, 3.0, 2.5, 2.7999999999999998, 3.2000000000000002, 3.0, 3.7999999999999998, 2.6000000000000001, 2.2000000000000002, 3.2000000000000002, 2.7999999999999998, 2.7999999999999998, 2.7000000000000002, 3.2999999999999998, 3.2000000000000002, 2.7999999999999998, 3.0, 2.7999999999999998, 3.0, 2.7999999999999998, 3.7999999999999998, 2.7999999999999998, 2.7999999999999998, 2.6000000000000001, 3.0, 3.3999999999999999, 3.1000000000000001, 3.0, 3.1000000000000001, 3.1000000000000001, 3.1000000000000001, 2.7000000000000002, 3.2000000000000002, 3.2999999999999998, 3.0, 2.5, 3.0, 3.3999999999999999, 3.0], 'Species': ['setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'setosa', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'versicolor', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica', 'virginica'], 'Unnamed: 0': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150], 'Sepal.Length': [5.0999999999999996, 4.9000000000000004, 4.7000000000000002, 4.5999999999999996, 5.0, 5.4000000000000004, 4.5999999999999996, 5.0, 4.4000000000000004, 4.9000000000000004, 5.4000000000000004, 4.7999999999999998, 4.7999999999999998, 4.2999999999999998, 5.7999999999999998, 5.7000000000000002, 5.4000000000000004, 5.0999999999999996, 5.7000000000000002, 5.0999999999999996, 5.4000000000000004, 5.0999999999999996, 4.5999999999999996, 5.0999999999999996, 4.7999999999999998, 5.0, 5.0, 5.2000000000000002, 5.2000000000000002, 4.7000000000000002, 4.7999999999999998, 5.4000000000000004, 5.2000000000000002, 5.5, 4.9000000000000004, 5.0, 5.5, 4.9000000000000004, 4.4000000000000004, 5.0999999999999996, 5.0, 4.5, 4.4000000000000004, 5.0, 5.0999999999999996, 4.7999999999999998, 5.0999999999999996, 4.5999999999999996, 5.2999999999999998, 5.0, 7.0, 6.4000000000000004, 6.9000000000000004, 5.5, 6.5, 5.7000000000000002, 6.2999999999999998, 4.9000000000000004, 6.5999999999999996, 5.2000000000000002, 5.0, 5.9000000000000004, 6.0, 6.0999999999999996, 5.5999999999999996, 6.7000000000000002, 5.5999999999999996, 5.7999999999999998, 6.2000000000000002, 5.5999999999999996, 5.9000000000000004, 6.0999999999999996, 6.2999999999999998, 6.0999999999999996, 6.4000000000000004, 6.5999999999999996, 6.7999999999999998, 6.7000000000000002, 6.0, 5.7000000000000002, 5.5, 5.5, 5.7999999999999998, 6.0, 5.4000000000000004, 6.0, 6.7000000000000002, 6.2999999999999998, 5.5999999999999996, 5.5, 5.5, 6.0999999999999996, 5.7999999999999998, 5.0, 5.5999999999999996, 5.7000000000000002, 5.7000000000000002, 6.2000000000000002, 5.0999999999999996, 5.7000000000000002, 6.2999999999999998, 5.7999999999999998, 7.0999999999999996, 6.2999999999999998, 6.5, 7.5999999999999996, 4.9000000000000004, 7.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.5, 6.4000000000000004, 6.7999999999999998, 5.7000000000000002, 5.7999999999999998, 6.4000000000000004, 6.5, 7.7000000000000002, 7.7000000000000002, 6.0, 6.9000000000000004, 5.5999999999999996, 7.7000000000000002, 6.2999999999999998, 6.7000000000000002, 7.2000000000000002, 6.2000000000000002, 6.0999999999999996, 6.4000000000000004, 7.2000000000000002, 7.4000000000000004, 7.9000000000000004, 6.4000000000000004, 6.2999999999999998, 6.0999999999999996, 7.7000000000000002, 6.2999999999999998, 6.4000000000000004, 6.0, 6.9000000000000004, 6.7000000000000002, 6.9000000000000004, 5.7999999999999998, 6.7999999999999998, 6.7000000000000002, 6.7000000000000002, 6.2999999999999998, 6.5, 6.2000000000000002, 5.9000000000000004], 'Petal.Length': [1.3999999999999999, 1.3999999999999999, 1.3, 1.5, 1.3999999999999999, 1.7, 1.3999999999999999, 1.5, 1.3999999999999999, 1.5, 1.5, 1.6000000000000001, 1.3999999999999999, 1.1000000000000001, 1.2, 1.5, 1.3, 1.3999999999999999, 1.7, 1.5, 1.7, 1.5, 1.0, 1.7, 1.8999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.3999999999999999, 1.6000000000000001, 1.6000000000000001, 1.5, 1.5, 1.3999999999999999, 1.5, 1.2, 1.3, 1.3999999999999999, 1.3, 1.5, 1.3, 1.3, 1.3, 1.6000000000000001, 1.8999999999999999, 1.3999999999999999, 1.6000000000000001, 1.3999999999999999, 1.5, 1.3999999999999999, 4.7000000000000002, 4.5, 4.9000000000000004, 4.0, 4.5999999999999996, 4.5, 4.7000000000000002, 3.2999999999999998, 4.5999999999999996, 3.8999999999999999, 3.5, 4.2000000000000002, 4.0, 4.7000000000000002, 3.6000000000000001, 4.4000000000000004, 4.5, 4.0999999999999996, 4.5, 3.8999999999999999, 4.7999999999999998, 4.0, 4.9000000000000004, 4.7000000000000002, 4.2999999999999998, 4.4000000000000004, 4.7999999999999998, 5.0, 4.5, 3.5, 3.7999999999999998, 3.7000000000000002, 3.8999999999999999, 5.0999999999999996, 4.5, 4.5, 4.7000000000000002, 4.4000000000000004, 4.0999999999999996, 4.0, 4.4000000000000004, 4.5999999999999996, 4.0, 3.2999999999999998, 4.2000000000000002, 4.2000000000000002, 4.2000000000000002, 4.2999999999999998, 3.0, 4.0999999999999996, 6.0, 5.0999999999999996, 5.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.5999999999999996, 4.5, 6.2999999999999998, 5.7999999999999998, 6.0999999999999996, 5.0999999999999996, 5.2999999999999998, 5.5, 5.0, 5.0999999999999996, 5.2999999999999998, 5.5, 6.7000000000000002, 6.9000000000000004, 5.0, 5.7000000000000002, 4.9000000000000004, 6.7000000000000002, 4.9000000000000004, 5.7000000000000002, 6.0, 4.7999999999999998, 4.9000000000000004, 5.5999999999999996, 5.7999999999999998, 6.0999999999999996, 6.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.5999999999999996, 6.0999999999999996, 5.5999999999999996, 5.5, 4.7999999999999998, 5.4000000000000004, 5.5999999999999996, 5.0999999999999996, 5.0999999999999996, 5.9000000000000004, 5.7000000000000002, 5.2000000000000002, 5.0, 5.2000000000000002, 5.4000000000000004, 5.0999999999999996]}\n",
      "df = pd.DataFrame(raw_data, columns = ['Unnamed: 0', 'Sepal.Length', 'Sepal.Width', 'Petal.Length', 'Petal.Width', 'Species'])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "### 2. Compare the original and recreated dataframes"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Look at the top few rows of the original dataframe\n",
      "df.head()"
     ],
     "language": "python",
     "metadata": {},
     "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>Unnamed: 0</th>\n",
        "      <th>Sepal.Length</th>\n",
        "      <th>Sepal.Width</th>\n",
        "      <th>Petal.Length</th>\n",
        "      <th>Petal.Width</th>\n",
        "      <th>Species</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1</td>\n",
        "      <td> 5.1</td>\n",
        "      <td> 3.5</td>\n",
        "      <td> 1.4</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 2</td>\n",
        "      <td> 4.9</td>\n",
        "      <td> 3.0</td>\n",
        "      <td> 1.4</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4.7</td>\n",
        "      <td> 3.2</td>\n",
        "      <td> 1.3</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 4</td>\n",
        "      <td> 4.6</td>\n",
        "      <td> 3.1</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 5</td>\n",
        "      <td> 5.0</td>\n",
        "      <td> 3.6</td>\n",
        "      <td> 1.4</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "   Unnamed: 0  Sepal.Length  Sepal.Width  Petal.Length  Petal.Width Species\n",
        "0           1           5.1          3.5           1.4          0.2  setosa\n",
        "1           2           4.9          3.0           1.4          0.2  setosa\n",
        "2           3           4.7          3.2           1.3          0.2  setosa\n",
        "3           4           4.6          3.1           1.5          0.2  setosa\n",
        "4           5           5.0          3.6           1.4          0.2  setosa"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Look at the top few rows of the dataframe created with our code\n",
      "df_original.head()"
     ],
     "language": "python",
     "metadata": {},
     "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>Unnamed: 0</th>\n",
        "      <th>Sepal.Length</th>\n",
        "      <th>Sepal.Width</th>\n",
        "      <th>Petal.Length</th>\n",
        "      <th>Petal.Width</th>\n",
        "      <th>Species</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> 1</td>\n",
        "      <td> 5.1</td>\n",
        "      <td> 3.5</td>\n",
        "      <td> 1.4</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> 2</td>\n",
        "      <td> 4.9</td>\n",
        "      <td> 3.0</td>\n",
        "      <td> 1.4</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> 3</td>\n",
        "      <td> 4.7</td>\n",
        "      <td> 3.2</td>\n",
        "      <td> 1.3</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 4</td>\n",
        "      <td> 4.6</td>\n",
        "      <td> 3.1</td>\n",
        "      <td> 1.5</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> 5</td>\n",
        "      <td> 5.0</td>\n",
        "      <td> 3.6</td>\n",
        "      <td> 1.4</td>\n",
        "      <td> 0.2</td>\n",
        "      <td> setosa</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "   Unnamed: 0  Sepal.Length  Sepal.Width  Petal.Length  Petal.Width Species\n",
        "0           1           5.1          3.5           1.4          0.2  setosa\n",
        "1           2           4.9          3.0           1.4          0.2  setosa\n",
        "2           3           4.7          3.2           1.3          0.2  setosa\n",
        "3           4           4.6          3.1           1.5          0.2  setosa\n",
        "4           5           5.0          3.6           1.4          0.2  setosa"
       ]
      }
     ],
     "prompt_number": 9
    }
   ],
   "metadata": {}
  }
 ]
}