parks.ipynb

parks.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "parks.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "metadata": {
        "id": "CeoMKry-IWzB",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO import numpy and pandas, show pandas version\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "print(pd.__version__)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "Fx4hUgMhIfzA",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#read the dataset about national parks from 1904-2016 and get its summary statistics\n",
        "df = pd.read_csv('National Parks Ranked by Total Visitation 1904-2016 and by Year.csv')\n",
        "df.describe()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "UNPGw0fRJtuc",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO: review dataframe types\n",
        "df.dtypes"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "SJWg6sMqiSBI",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO: Notice the issue with the visitors column name\n",
        "df.columns"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "jTp_ECWMiYrl",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO: Make sure that the columns are properly named\n",
        "df.rename(str.strip, axis='columns', inplace=True)\n",
        "df.columns"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "KHR30Abpjr2c",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO: convert Year values that are not \"Total\" to int\n",
        "df = df[~df.YearRaw.isin([\"Total\"])]\n",
        "df.YearRaw = df.YearRaw.astype(int)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "2NUZ5uMS9mpz",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO clean up visitors string values and return as int\n",
        "df.Visitors = df.Visitors.apply(lambda s: int(s.strip().replace(',', '').replace('-', '0'))).astype(int)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "BBYqxvB2IjUp",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO: create a pivot table showing park attendance in each park in each state from 2010-2016\n",
        "df_pivot = df.pivot_table(index=[\"State\",\"Unit Name\"], columns=[\"YearRaw\"], values='Visitors', aggfunc=np.sum)\n",
        "df_2010_2016 = df_pivot.loc[:, 2010:2016] \n",
        "df_2010_2016"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "prJcmO7s8ZWt",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO: show total park attendance in every state from 2010-2016\n",
        "df_2010_2016 = df_2010_2016.groupby(\"State\").agg(np.sum)\n",
        "df_2010_2016[\"Total\"] = df_2010_2016.sum(axis=1)\n",
        "df_2010_2016"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "iJ-WfqfmAAPM",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "#TODO: show the top 5 most visited parks from 2010-2016\n",
        "df_2010_2016.nlargest(5, columns=[\"Total\"])"
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}