dash-example-src.ipynb

dash-example-src.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "dash-example-src.ipynb",
      "private_outputs": true,
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyOMO/+1NsOStjfVLuIulkC6",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/Caellwyn/add34fef7ddf61b4472ad78461729d72/dash-example-src.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Z5j43XRVwvRi"
      },
      "source": [
        "import pandas as pd\r\n",
        "from statsmodels.tsa.statespace.sarimax import SARIMAX\r\n",
        "from numpy import cbrt\r\n",
        "from plotly import graph_objects as go\r\n",
        "\r\n",
        "def get_covid_data():\r\n",
        "    \"\"\"\r\n",
        "    Download latest covid data.\r\n",
        "    \"\"\"\r\n",
        "    DATA_URL = 'https://raw.githubusercontent.com/OxCGRT/covid-policy-tracker/master/data/OxCGRT_latest.csv'\r\n",
        "    full_df = pd.read_csv(DATA_URL,\r\n",
        "                        parse_dates=['Date'],\r\n",
        "                        encoding=\"ISO-8859-1\",\r\n",
        "                        dtype={\"RegionName\": str,\r\n",
        "                                \"RegionCode\": str,\r\n",
        "                                \"CountryName\": str,\r\n",
        "                                \"CountryCode\": str},\r\n",
        "                            usecols = ['Date','CountryName','RegionName',\r\n",
        "                                    'ConfirmedCases','ConfirmedDeaths','Jurisdiction'],\r\n",
        "                        error_bad_lines=False)\r\n",
        "    full_df = full_df.set_index('Date', drop=True)\r\n",
        "    new_cols = {'ConfirmedCases':'Cumulative Cases','ConfirmedDeaths':'Cumulative Deaths'}\r\n",
        "    full_df = full_df.rename(columns = new_cols)\r\n",
        "    return full_df\r\n",
        "\r\n",
        "def get_graph(df, state, country, stats):\r\n",
        "    \"\"\"\r\n",
        "    get_graph(df, state, country, stats)\r\n",
        "    ---\r\n",
        "    Helper function for graph_stat to create and return plotly figure of chosen statistics.\r\n",
        "    ---\r\n",
        "    \"\"\"\r\n",
        "\r\n",
        "    if state != 'None':\r\n",
        "        title = f'COVID-19 in {state}, {country}'\r\n",
        "    else:\r\n",
        "        title = f'COVID-19 in {country}'\r\n",
        "    \r\n",
        "    fig = go.Figure(layout_title_text = title)\r\n",
        "    for stat in stats:\r\n",
        "        fig.add_trace(go.Scatter(x=df.index, y=df[stat], name=stat))\r\n",
        "    fig.update_layout(showlegend=True)\r\n",
        "\r\n",
        "    return fig\r\n",
        "\r\n",
        "def graph_stat(full_df, country='United States',\r\n",
        "                    state=None, stats=['Cumulative Cases']):\r\n",
        "    \"\"\"\r\n",
        "    graph_stat(full_df, country='United States',\r\n",
        "                    state=None, stat='Cumulative Cases')\r\n",
        "    ---\r\n",
        "    Graphs chosen statistic(s)\r\n",
        "    full_df should be a Pandas DataFrame with a time series index.  \r\n",
        "    Function subsets full_df in respect to state and/or country. \r\n",
        "    Uses a SARIMA model to graph up to date COVID cases or deaths.\r\n",
        "    Returns a plotly figure of deaths or cases\r\n",
        "    ---\r\n",
        "    \"\"\"\r\n",
        "    if not stats:\r\n",
        "        stats = ['Cumulative Cases']\r\n",
        "\r\n",
        "    if state in full_df['RegionName'].dropna().unique():\r\n",
        "        df = full_df[(full_df['Jurisdiction'] == 'STATE_TOTAL') \r\n",
        "                    & (full_df['RegionName'] == state)][:-1]\r\n",
        "    else: \r\n",
        "        df = full_df[(full_df['Jurisdiction'] == 'NAT_TOTAL') \r\n",
        "                    & (full_df['CountryName'] == country)][:-1]\r\n",
        "\r\n",
        "    df = df.interpolate(method='time', limit_direction='forward', \r\n",
        "                        limit_area='inside', downcast='infer')\r\n",
        "    df['Daily Cases'] = df['Cumulative Cases'].diff()\r\n",
        "    df['Daily Deaths'] = df['Cumulative Deaths'].diff()\r\n",
        "    df = df[stats]\r\n",
        "\r\n",
        "    df = df.dropna()\r\n",
        "    \r\n",
        "    fig = get_graph(df, state, country, stats)\r\n",
        "\r\n",
        "    return fig"
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}