From c42bb0d66367b642bb59c864f0416ac338955a12 Mon Sep 17 00:00:00 2001
From: Chandrasekhar Ramakrishnan <cramakri@ethz.ch>
Date: Wed, 18 Mar 2020 21:52:40 +0000
Subject: [PATCH] feat: example for working with covidtracking data
---
.../examples/covidtracking-example.ipynb | 1058 +++++++++++++++++
1 file changed, 1058 insertions(+)
create mode 100644 notebooks/examples/covidtracking-example.ipynb
diff --git a/notebooks/examples/covidtracking-example.ipynb b/notebooks/examples/covidtracking-example.ipynb
new file mode 100644
index 000000000..89fa1b8dc
--- /dev/null
+++ b/notebooks/examples/covidtracking-example.ipynb
@@ -0,0 +1,1058 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import altair as alt"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Look at the metadata"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "metadata_df = pd.read_json('../../data/covidtracking/states-metadata.json')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>state</th>\n",
+ " <th>dataSite</th>\n",
+ " <th>covid19Site</th>\n",
+ " <th>twitter</th>\n",
+ " <th>pui</th>\n",
+ " <th>pum</th>\n",
+ " <th>notes</th>\n",
+ " <th>name</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>AK</td>\n",
+ " <td>http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...</td>\n",
+ " <td>http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-...</td>\n",
+ " <td>@Alaska_DHSS</td>\n",
+ " <td>All data</td>\n",
+ " <td>False</td>\n",
+ " <td>Unclear if their reported number means \"person...</td>\n",
+ " <td>Alaska</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>AL</td>\n",
+ " <td>http://www.alabamapublichealth.gov/infectiousd...</td>\n",
+ " <td>http://www.alabamapublichealth.gov/infectiousd...</td>\n",
+ " <td>@alpublichealth</td>\n",
+ " <td>No data</td>\n",
+ " <td>False</td>\n",
+ " <td>Last negative count from 3/16.</td>\n",
+ " <td>Alabama</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>AR</td>\n",
+ " <td>https://www.healthy.arkansas.gov/programs-serv...</td>\n",
+ " <td>https://www.healthy.arkansas.gov/programs-serv...</td>\n",
+ " <td>@adhpio</td>\n",
+ " <td>All data</td>\n",
+ " <td>True</td>\n",
+ " <td>Pending = \"PUIs\"</td>\n",
+ " <td>Arkansas</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>AZ</td>\n",
+ " <td>https://www.azdhs.gov/preparedness/epidemiolog...</td>\n",
+ " <td>https://www.azdhs.gov/preparedness/epidemiolog...</td>\n",
+ " <td>@azdhs</td>\n",
+ " <td>All data</td>\n",
+ " <td>False</td>\n",
+ " <td>Negative = “Ruled Outâ€. Our total is slightly ...</td>\n",
+ " <td>Arizona</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>CA</td>\n",
+ " <td>https://www.cdph.ca.gov/Programs/CID/DCDC/Page...</td>\n",
+ " <td>https://www.cdph.ca.gov/Programs/CID/DCDC/Page...</td>\n",
+ " <td>@CAPublicHealth</td>\n",
+ " <td>Only positives</td>\n",
+ " <td>False</td>\n",
+ " <td>Only positives reported regularly. Add deaths ...</td>\n",
+ " <td>California</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " state dataSite \\\n",
+ "0 AK http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-... \n",
+ "1 AL http://www.alabamapublichealth.gov/infectiousd... \n",
+ "2 AR https://www.healthy.arkansas.gov/programs-serv... \n",
+ "3 AZ https://www.azdhs.gov/preparedness/epidemiolog... \n",
+ "4 CA https://www.cdph.ca.gov/Programs/CID/DCDC/Page... \n",
+ "\n",
+ " covid19Site twitter \\\n",
+ "0 http://dhss.alaska.gov/dph/Epi/id/Pages/COVID-... @Alaska_DHSS \n",
+ "1 http://www.alabamapublichealth.gov/infectiousd... @alpublichealth \n",
+ "2 https://www.healthy.arkansas.gov/programs-serv... @adhpio \n",
+ "3 https://www.azdhs.gov/preparedness/epidemiolog... @azdhs \n",
+ "4 https://www.cdph.ca.gov/Programs/CID/DCDC/Page... @CAPublicHealth \n",
+ "\n",
+ " pui pum notes \\\n",
+ "0 All data False Unclear if their reported number means \"person... \n",
+ "1 No data False Last negative count from 3/16. \n",
+ "2 All data True Pending = \"PUIs\" \n",
+ "3 All data False Negative = “Ruled Outâ€. Our total is slightly ... \n",
+ "4 Only positives False Only positives reported regularly. Add deaths ... \n",
+ "\n",
+ " name \n",
+ "0 Alaska \n",
+ "1 Alabama \n",
+ "2 Arkansas \n",
+ "3 Arizona \n",
+ "4 California "
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "metadata_df.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Look at the data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data_df = pd.read_json('../../data/covidtracking/states-daily.json')\n",
+ "data_df['date'] = pd.to_datetime(data_df['date'], format=\"%Y%m%d\")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>date</th>\n",
+ " <th>state</th>\n",
+ " <th>positive</th>\n",
+ " <th>negative</th>\n",
+ " <th>pending</th>\n",
+ " <th>death</th>\n",
+ " <th>total</th>\n",
+ " <th>dateChecked</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>2020-03-18</td>\n",
+ " <td>AK</td>\n",
+ " <td>6.0</td>\n",
+ " <td>406.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>412.0</td>\n",
+ " <td>2020-03-18T20:00:00Z</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2020-03-18</td>\n",
+ " <td>AL</td>\n",
+ " <td>46.0</td>\n",
+ " <td>28.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>74.0</td>\n",
+ " <td>2020-03-18T20:00:00Z</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>2020-03-18</td>\n",
+ " <td>AR</td>\n",
+ " <td>33.0</td>\n",
+ " <td>236.0</td>\n",
+ " <td>50.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>319.0</td>\n",
+ " <td>2020-03-18T20:00:00Z</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>2020-03-18</td>\n",
+ " <td>AZ</td>\n",
+ " <td>28.0</td>\n",
+ " <td>148.0</td>\n",
+ " <td>102.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>278.0</td>\n",
+ " <td>2020-03-18T20:00:00Z</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>2020-03-18</td>\n",
+ " <td>CA</td>\n",
+ " <td>611.0</td>\n",
+ " <td>7981.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>13.0</td>\n",
+ " <td>8592.0</td>\n",
+ " <td>2020-03-18T20:00:00Z</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " date state positive negative pending death total \\\n",
+ "0 2020-03-18 AK 6.0 406.0 NaN NaN 412.0 \n",
+ "1 2020-03-18 AL 46.0 28.0 NaN 0.0 74.0 \n",
+ "2 2020-03-18 AR 33.0 236.0 50.0 NaN 319.0 \n",
+ "3 2020-03-18 AZ 28.0 148.0 102.0 0.0 278.0 \n",
+ "4 2020-03-18 CA 611.0 7981.0 NaN 13.0 8592.0 \n",
+ "\n",
+ " dateChecked \n",
+ "0 2020-03-18T20:00:00Z \n",
+ "1 2020-03-18T20:00:00Z \n",
+ "2 2020-03-18T20:00:00Z \n",
+ "3 2020-03-18T20:00:00Z \n",
+ "4 2020-03-18T20:00:00Z "
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data_df.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## How many data points per state?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>state</th>\n",
+ " <th>date</th>\n",
+ " <th>positive</th>\n",
+ " <th>negative</th>\n",
+ " <th>pending</th>\n",
+ " <th>death</th>\n",
+ " <th>total</th>\n",
+ " <th>dateChecked</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>AZ</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>6</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>CA</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>0</td>\n",
+ " <td>7</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>FL</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>14</td>\n",
+ " <td>8</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>GA</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>6</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>16</th>\n",
+ " <td>IL</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>12</td>\n",
+ " <td>2</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>21</th>\n",
+ " <td>MA</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>6</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>14</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30</th>\n",
+ " <td>NC</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>7</td>\n",
+ " <td>2</td>\n",
+ " <td>3</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>33</th>\n",
+ " <td>NH</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>0</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>37</th>\n",
+ " <td>NY</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>13</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40</th>\n",
+ " <td>OR</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>1</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44</th>\n",
+ " <td>SC</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>47</th>\n",
+ " <td>TX</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>2</td>\n",
+ " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>52</th>\n",
+ " <td>WA</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>13</td>\n",
+ " <td>2</td>\n",
+ " <td>8</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>53</th>\n",
+ " <td>WI</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " <td>5</td>\n",
+ " <td>0</td>\n",
+ " <td>15</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>CO</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>4</td>\n",
+ " <td>5</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>DC</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>12</td>\n",
+ " <td>0</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>22</th>\n",
+ " <td>MD</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>2</td>\n",
+ " <td>0</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>24</th>\n",
+ " <td>MI</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>12</td>\n",
+ " <td>0</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>32</th>\n",
+ " <td>NE</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>11</td>\n",
+ " <td>0</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>34</th>\n",
+ " <td>NJ</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>9</td>\n",
+ " <td>12</td>\n",
+ " <td>8</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>36</th>\n",
+ " <td>NV</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>38</th>\n",
+ " <td>OH</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>12</td>\n",
+ " <td>0</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46</th>\n",
+ " <td>TN</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>8</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>49</th>\n",
+ " <td>VA</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>14</td>\n",
+ " <td>5</td>\n",
+ " <td>4</td>\n",
+ " <td>13</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>AK</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>7</td>\n",
+ " <td>0</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>AR</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>0</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>DE</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>11</td>\n",
+ " <td>0</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>IA</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>8</td>\n",
+ " <td>0</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17</th>\n",
+ " <td>IN</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>9</td>\n",
+ " <td>0</td>\n",
+ " <td>5</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18</th>\n",
+ " <td>KS</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>5</td>\n",
+ " <td>5</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>19</th>\n",
+ " <td>KY</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25</th>\n",
+ " <td>MN</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>35</th>\n",
+ " <td>NM</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>4</td>\n",
+ " <td>0</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41</th>\n",
+ " <td>PA</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>8</td>\n",
+ " <td>5</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51</th>\n",
+ " <td>VT</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>54</th>\n",
+ " <td>WV</td>\n",
+ " <td>13</td>\n",
+ " <td>12</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " <td>4</td>\n",
+ " <td>13</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>AL</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " <td>9</td>\n",
+ " <td>4</td>\n",
+ " <td>4</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>CT</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " <td>11</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>HI</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>1</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>15</th>\n",
+ " <td>ID</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>20</th>\n",
+ " <td>LA</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " <td>0</td>\n",
+ " <td>4</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>23</th>\n",
+ " <td>ME</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>6</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26</th>\n",
+ " <td>MO</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>7</td>\n",
+ " <td>0</td>\n",
+ " <td>5</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>28</th>\n",
+ " <td>MS</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>8</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29</th>\n",
+ " <td>MT</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>5</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>31</th>\n",
+ " <td>ND</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " <td>12</td>\n",
+ " <td>8</td>\n",
+ " <td>6</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>39</th>\n",
+ " <td>OK</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " <td>11</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43</th>\n",
+ " <td>RI</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " <td>11</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45</th>\n",
+ " <td>SD</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>1</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>48</th>\n",
+ " <td>UT</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>7</td>\n",
+ " <td>0</td>\n",
+ " <td>4</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>55</th>\n",
+ " <td>WY</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " <td>3</td>\n",
+ " <td>1</td>\n",
+ " <td>0</td>\n",
+ " <td>12</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>AS</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>GU</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>27</th>\n",
+ " <td>MP</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42</th>\n",
+ " <td>PR</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>2</td>\n",
+ " <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50</th>\n",
+ " <td>VI</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>1</td>\n",
+ " <td>3</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " state date positive negative pending death total dateChecked\n",
+ "4 AZ 15 15 15 15 6 15 15\n",
+ "5 CA 15 15 15 0 7 15 15\n",
+ "10 FL 15 15 15 14 8 15 15\n",
+ "11 GA 15 15 1 0 6 15 15\n",
+ "16 IL 15 15 15 12 2 15 15\n",
+ "21 MA 15 15 6 0 0 14 15\n",
+ "30 NC 15 15 7 2 3 15 15\n",
+ "33 NH 15 15 15 15 0 15 15\n",
+ "37 NY 15 15 13 4 4 15 15\n",
+ "40 OR 15 15 15 15 1 15 15\n",
+ "44 SC 15 15 15 3 3 15 15\n",
+ "47 TX 15 15 2 0 2 15 15\n",
+ "52 WA 15 15 13 2 8 15 15\n",
+ "53 WI 15 15 15 5 0 15 15\n",
+ "6 CO 14 14 14 4 5 14 14\n",
+ "8 DC 14 14 14 12 0 14 14\n",
+ "22 MD 14 14 14 2 0 14 14\n",
+ "24 MI 14 14 14 12 0 14 14\n",
+ "32 NE 14 14 14 11 0 14 14\n",
+ "34 NJ 14 14 9 12 8 14 14\n",
+ "36 NV 14 14 14 1 3 14 14\n",
+ "38 OH 14 14 14 12 0 14 14\n",
+ "46 TN 14 14 8 0 0 14 14\n",
+ "49 VA 14 14 14 5 4 13 14\n",
+ "0 AK 13 13 13 7 0 13 13\n",
+ "2 AR 13 13 13 13 0 13 13\n",
+ "9 DE 13 13 13 11 0 13 13\n",
+ "14 IA 13 13 13 8 0 13 13\n",
+ "17 IN 13 13 9 0 5 13 13\n",
+ "18 KS 13 13 13 5 5 13 13\n",
+ "19 KY 13 13 13 1 3 13 13\n",
+ "25 MN 13 13 13 0 0 13 13\n",
+ "35 NM 13 13 13 4 0 13 13\n",
+ "41 PA 13 13 8 5 0 12 13\n",
+ "51 VT 13 13 13 0 0 13 13\n",
+ "54 WV 13 12 13 13 4 13 13\n",
+ "1 AL 12 11 9 4 4 12 12\n",
+ "7 CT 12 11 11 1 0 12 12\n",
+ "13 HI 12 12 1 1 0 12 12\n",
+ "15 ID 12 12 12 0 0 12 12\n",
+ "20 LA 12 12 11 0 4 12 12\n",
+ "23 ME 12 12 12 6 0 12 12\n",
+ "26 MO 12 12 7 0 5 12 12\n",
+ "28 MS 12 12 8 0 0 12 12\n",
+ "29 MT 12 12 12 5 0 12 12\n",
+ "31 ND 12 11 12 8 6 12 12\n",
+ "39 OK 12 12 11 11 0 12 12\n",
+ "43 RI 12 12 11 11 0 12 12\n",
+ "45 SD 12 12 12 12 1 12 12\n",
+ "48 UT 12 12 7 0 4 12 12\n",
+ "55 WY 12 12 3 1 0 12 12\n",
+ "3 AS 3 3 0 0 1 3 3\n",
+ "12 GU 3 3 3 0 0 3 3\n",
+ "27 MP 3 3 0 0 1 3 3\n",
+ "42 PR 3 3 3 2 0 3 3\n",
+ "50 VI 3 3 0 0 1 3 3"
+ ]
+ },
+ "execution_count": 16,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "summary_df = data_df.groupby('state').count()\n",
+ "summary_df.reset_index().sort_values(['date', 'state'], ascending=[False, True])"
+ ]
+ }
+ ],
+ "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
+}
--
GitLab