Skip to content
Snippets Groups Projects
download-covidtracking-data.ipynb 2.97 KiB
Newer Older
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import os\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": [
     "parameters"
    ]
   },
   "outputs": [],
   "source": [
    "out_folder = \"../data/covidtracking/\"\n",
    "PAPERMILL_OUTPUT_PATH = None"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Download state metadata\n",
    "\n",
    "Download a dataset of URLs for data for each US state and several territories. See [Google Doc](https://docs.google.com/spreadsheets/d/18oVRrHj3c183mHmq3m89_163yuYltLNlOmPerQ18E8w/htmlview?sle=true)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = 'http://covidtracking.com/api/states/info'\n",
    "r = requests.get(url, allow_redirects=True)\n",
    "states_metadata_json = r.content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# save the result\n",
    "if PAPERMILL_OUTPUT_PATH:\n",
    "    out_path = os.path.join(out_folder, 'states-metadata.json')\n",
    "    with open(out_path, 'wb') as f:\n",
    "        f.write(states_metadata_json)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "metadata_df = pd.read_json(states_metadata_json)\n",
    "print(len(metadata_df), \"states and territories have metadata\")\n",
    "metadata_df.head(2)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Download daily state data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = 'https://covidtracking.com/api/states/daily'\n",
    "r = requests.get(url, allow_redirects=True)\n",
    "states_daily_json = r.content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# save the result\n",
    "if PAPERMILL_OUTPUT_PATH:\n",
    "    out_path = os.path.join(out_folder, 'states-daily.json')\n",
    "    with open(out_path, 'wb') as f:\n",
    "        f.write(states_daily_json)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_df = pd.read_json(states_daily_json)\n",
    "print(len(data_df), \"data points\")\n",
    "data_df.head(2)"
   ]
  }
 ],
 "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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}