From db521fa7912e960c02fb9aa2f053150b24c5874b Mon Sep 17 00:00:00 2001
From: Chandrasekhar Ramakrishnan <cramakri@ethz.ch>
Date: Sun, 15 Mar 2020 16:33:38 +0000
Subject: [PATCH] fix: Use geodata for centroids in Dashboard
---
notebooks/Dashboard.ipynb | 76 +++++++++++++++++++++++----------------
1 file changed, 46 insertions(+), 30 deletions(-)
diff --git a/notebooks/Dashboard.ipynb b/notebooks/Dashboard.ipynb
index b7f64b2b..695dac12 100644
--- a/notebooks/Dashboard.ipynb
+++ b/notebooks/Dashboard.ipynb
@@ -23,6 +23,7 @@
"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"
]
@@ -84,18 +85,10 @@
"metadata": {},
"outputs": [],
"source": [
- "# Compile data needed for the visualizations"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Compute geospatial coordinates\n",
- "country_coords_df = jhu_frames_map['confirmed'].reset_index([2,3])[['Lat', 'Long']]\n",
- "country_coords_df = country_coords_df.groupby(level='Country/Region').mean()"
+ "geodata_df = pd.read_csv(geodata_path)\n",
+ "geodata_df = geodata_df.drop('Unnamed: 0', axis=1)\n",
+ "geodata_df = geodata_df.rename({'name_jhu':'Country/Region'}, axis=1)\n",
+ "geodata_df = geodata_df.set_index('Country/Region')"
]
},
{
@@ -105,7 +98,11 @@
"outputs": [],
"source": [
"# Identify countries with 100 or more cases\n",
- "case_count_ser = jhu_frames_map['confirmed'].iloc[:,-1].groupby(level='Country/Region').sum()\n",
+ "def latest_jhu_country_ser(name):\n",
+ " return jhu_frames_map[name].iloc[:,-1].groupby(level='Country/Region').sum()\n",
+ "\n",
+ "\n",
+ "case_count_ser = latest_jhu_country_ser('confirmed')\n",
"countries_over_thresh = case_count_ser[case_count_ser > 99].index"
]
},
@@ -115,7 +112,9 @@
"source": [
"# Questions About COVID-19 and Its Spread\n",
"\n",
- "These plots should be taken with a large grain of salt. I am not an epidemiologist, so the analyses shown here are completely naive. There are large discrepencies in the data from different countries for a variety of reasons (rates of testing, demographics, etc.) so that make direct comparisons inaccurate. Nonetheless, I think there is a lot of interesting information in this data."
+ "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."
]
},
{
@@ -125,7 +124,7 @@
"outputs": [],
"source": [
"data_ts = jhu_frames_map['confirmed'].iloc[:,-1].name.strftime(\"%b %d %Y\")\n",
- "display(HTML(f\"<em>Data up to {data_ts}</em>\"))"
+ "display(HTML(f\"<em>Data up to {data_ts}; countries with 100 or more confirmed cases.</em>\"))"
]
},
{
@@ -151,16 +150,27 @@
"metadata": {},
"outputs": [],
"source": [
+ "def latest_rates_ser(name):\n",
+ " return rates_frames_map[name].iloc[:,-1]\n",
+ "\n",
+ "\n",
"# Compile the basic df\n",
"map_df = pd.concat([\n",
- " rates_frames_map['confirmed'].iloc[:,-1],\n",
- " rates_frames_map['deaths'].iloc[:,-1],\n",
- " rates_frames_map['recovered'].iloc[:,-1],\n",
- " country_coords_df], axis=1)\n",
+ " latest_rates_ser('confirmed'),\n",
+ " latest_rates_ser('deaths'),\n",
+ " latest_rates_ser('recovered')], axis=1)\n",
+ "nominal_df = pd.concat([\n",
+ " latest_jhu_country_ser('confirmed'),\n",
+ " latest_jhu_country_ser('deaths'),\n",
+ " latest_jhu_country_ser('recovered')], axis=1)\n",
+ "map_df = pd.concat([map_df, nominal_df, geodata_df[['Longitude', 'Latitude']]], axis=1)\n",
"# Restrict to countries with 100 or more cases\n",
"map_df = map_df.loc[countries_over_thresh].dropna()\n",
"map_df = map_df.reset_index()\n",
- "map_df.columns = ['Country/Region', 'Confirmed', 'Deaths', 'Recovered', 'Lat', 'Long']"
+ "map_df.columns = ['Country/Region', \n",
+ " 'Confirmed/100k', 'Deaths/100k', 'Recovered/100k', \n",
+ " 'Confirmed', 'Deaths', 'Recovered',\n",
+ " 'Long', 'Lat']"
]
},
{
@@ -169,7 +179,7 @@
"metadata": {},
"outputs": [],
"source": [
- "def map_of_variable(map_df, variable):\n",
+ "def map_of_variable(map_df, variable, title):\n",
" # Data generators for the background\n",
" sphere = alt.sphere()\n",
" graticule = alt.graticule()\n",
@@ -187,11 +197,13 @@
" latitude='Lat:Q',\n",
" size=alt.Size(f'{variable}:Q', title=\"Cases\"),\n",
" color=alt.value('steelblue'),\n",
- " tooltip=[\"Country/Region:N\", \"Confirmed:Q\", \"Deaths:Q\", \"Recovered:Q\"]\n",
+ " tooltip=[\"Country/Region:N\", \n",
+ " \"Confirmed:Q\", \"Deaths:Q\", \"Recovered:Q\",\n",
+ " \"Confirmed/100k:Q\", \"Deaths/100k:Q\", \"Recovered/100k:Q\"]\n",
" )\n",
" ).project(\n",
" 'naturalEarth1'\n",
- " ).properties(width=600, height=400, title=f\"{variable} cases per 100,000\"\n",
+ " ).properties(width=600, height=400, title=f\"{title} cases per 100k inhabitants\"\n",
" ).configure_view(stroke=None)\n",
" return p"
]
@@ -202,11 +214,12 @@
"metadata": {},
"outputs": [],
"source": [
- "display(map_of_variable(map_df, 'Confirmed'))\n",
+ "display(map_of_variable(map_df, 'Confirmed/100k', 'Confirmed'))\n",
"display(HTML('''\n",
- "<p style=\"font-size: smaller\">Data Source: \n",
- " <a href=\"https://github.com/CSSEGISandData/COVID-19\">JHU CSSE</a> and\n",
- " <a href=\"https://data.worldbank.org/indicator/SP.POP.TOTL\">World Bank</a>\n",
+ "<p style=\"font-size: smaller\">Data Sources: \n",
+ " <a href=\"https://github.com/CSSEGISandData/COVID-19\">JHU CSSE</a>,\n",
+ " <a href=\"https://data.worldbank.org/indicator/SP.POP.TOTL\">World Bank</a>,\n",
+ " <a href=\"https://worldmap.harvard.edu/data/geonode:country_centroids_az8\">Harvard Worldmap</a>\n",
"</p>'''))"
]
},
@@ -217,8 +230,11 @@
"outputs": [],
"source": [
"bars = alt.Chart(map_df).mark_bar().encode(\n",
- " x='Confirmed:Q',\n",
- " y=alt.Y(\"Country/Region:N\", sort='-x')\n",
+ " x='Confirmed/100k:Q',\n",
+ " y=alt.Y(\"Country/Region:N\", sort='-x'),\n",
+ " tooltip=[\"Country/Region:N\", \n",
+ " \"Confirmed:Q\", \"Deaths:Q\", \"Recovered:Q\",\n",
+ " \"Confirmed/100k:Q\", \"Deaths/100k:Q\", \"Recovered/100k:Q\"]\n",
")\n",
"\n",
"text = bars.mark_text(\n",
@@ -226,7 +242,7 @@
" baseline='middle',\n",
" dx=3 # Nudges text to right so it doesn't appear on top of the bar\n",
").encode(\n",
- " text=alt.Text('Confirmed:Q', format=\".3\")\n",
+ " text=alt.Text('Confirmed/100k:Q', format=\".3\")\n",
")\n",
"\n",
"(bars + text).properties(height=900)"
--
GitLab