Dashboard.run.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "papermill": {
     "duration": 0.609203,
     "end_time": "2020-03-21T08:21:34.856967",
     "exception": false,
     "start_time": "2020-03-21T08:21:34.247764",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os\n",
    "from IPython.display import display, HTML, Markdown\n",
    "import covid_19_dashboard as helper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "papermill": {
     "duration": 0.022235,
     "end_time": "2020-03-21T08:21:34.894425",
     "exception": false,
     "start_time": "2020-03-21T08:21:34.872190",
     "status": "completed"
    },
    "tags": [
     "parameters"
    ]
   },
   "outputs": [],
   "source": [
    "ts_folder = \"../data/covid-19_jhu-csse/\"\n",
    "rates_folder = \"../data/covid-19_rates/\"\n",
    "geodata_path = \"../data/geodata/geo_data.csv\"\n",
    "out_folder = None\n",
    "PAPERMILL_OUTPUT_PATH = None"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "papermill": {
     "duration": 0.022115,
     "end_time": "2020-03-21T08:21:34.927671",
     "exception": false,
     "start_time": "2020-03-21T08:21:34.905556",
     "status": "completed"
    },
    "tags": [
     "injected-parameters"
    ]
   },
   "outputs": [],
   "source": [
    "# Parameters\n",
    "PAPERMILL_INPUT_PATH = \"/tmp/t7uqe0kc/notebooks/Dashboard.ipynb\"\n",
    "PAPERMILL_OUTPUT_PATH = \"runs/Dashboard.run.ipynb\"\n",
    "ts_folder = \"/tmp/t7uqe0kc/data/covid-19_jhu-csse\"\n",
    "rates_folder = \"/tmp/t7uqe0kc/data/covid-19_rates\"\n",
    "geodata_path = \"/tmp/t7uqe0kc/data/geodata/geo_data.csv\"\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "papermill": {
     "duration": 0.023145,
     "end_time": "2020-03-21T08:21:34.964505",
     "exception": false,
     "start_time": "2020-03-21T08:21:34.941360",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Read in the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "papermill": {
     "duration": 0.267358,
     "end_time": "2020-03-21T08:21:35.246180",
     "exception": false,
     "start_time": "2020-03-21T08:21:34.978822",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "jhu_frames_map = helper.read_jhu_frames_map(ts_folder)\n",
    "rates_frames_map = helper.read_rates_frames_map(rates_folder)\n",
    "geodata_df = helper.read_geodata(geodata_path)\n",
    "\n",
    "# Identify countries with 100 or more cases\n",
    "countries_over_thresh = helper.countries_with_number_of_cases(jhu_frames_map, 'confirmed', 100)\n",
    "# Filter out some countries with very high case/population ratio\n",
    "countries_over_thresh = [c for c in countries_over_thresh if c not in set(['San Marino', 'Iceland'])]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.012804,
     "end_time": "2020-03-21T08:21:35.273057",
     "exception": false,
     "start_time": "2020-03-21T08:21:35.260253",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Questions About COVID-19 and Its Spread\n",
    "\n",
    "Understanding the spread, distribution, and deadliness of COVID-19 is difficult, despite the data available about it. Differences in rates of testing, quality of data, demographics, etc. make it difficult to compare data between countries. \n",
    "\n",
    "All this needs to be considered when looking at the plots below. But despite those caveats, I found it helpful to plot the raw data, even though direct comparisons between countries might not be inaccurate."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "papermill": {
     "duration": 0.035757,
     "end_time": "2020-03-21T08:21:35.321446",
     "exception": false,
     "start_time": "2020-03-21T08:21:35.285689",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<em>Data up to Mar 20 2020; countries with 100 or more confirmed cases.</em>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "data_ts = jhu_frames_map['confirmed'].iloc[:,-1].name.strftime(\"%b %d %Y\")\n",
    "display(HTML(f\"<em>Data up to {data_ts}; countries with 100 or more confirmed cases.</em>\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "papermill": {
     "duration": 0.012885,
     "end_time": "2020-03-21T08:21:35.350882",
     "exception": false,
     "start_time": "2020-03-21T08:21:35.337997",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "## How are cases per 100,000 distributed geographically?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "papermill": {
     "duration": 0.023769,
     "end_time": "2020-03-21T08:21:35.387608",
     "exception": false,
     "start_time": "2020-03-21T08:21:35.363839",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "import altair as alt"