style: fixed a comment to be clearer

7c83554c · Chandrasekhar Ramakrishnan · 9435b564 · 7c83554c
Commit 7c83554c authored 5 years ago by Chandrasekhar Ramakrishnan
--- a/notebooks/Dashboard.ipynb
+++ b/notebooks/Dashboard.ipynb
@@ -51,7 +51,7 @@
    "\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 very small countries\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:code id: tags:

 ``` python
 import pandas as pd
 import numpy as np
 import os
 from IPython.display import display, HTML, Markdown
 import covid_19_dashboard as helper
 ```

 %% Cell type:code id: tags:parameters

 ``` python
 ts_folder = "../data/covid-19_jhu-csse/"
 rates_folder = "../data/covid-19_rates/"
 geodata_path = "../data/geodata/geo_data.csv"
 out_folder = None
 PAPERMILL_OUTPUT_PATH = None
 ```

 %% Cell type:code id: tags:

 ``` python
 # Read in the data
 ```

 %% Cell type:code id: tags:

 ``` python
 jhu_frames_map = helper.read_jhu_frames_map(ts_folder)
 rates_frames_map = helper.read_rates_frames_map(rates_folder)
 geodata_df = helper.read_geodata(geodata_path)

 # Identify countries with 100 or more cases
 countries_over_thresh = helper.countries_with_number_of_cases(jhu_frames_map, 'confirmed', 100)
-# Filter out some very small countries
+# Filter out some countries with very high case/population ratio
 countries_over_thresh = [c for c in countries_over_thresh if c not in set(['San Marino', 'Iceland'])]
 ```

 %% Cell type:markdown id: tags:

 # Questions About COVID-19 and Its Spread

 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.

 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 id: tags:

 ``` python
 data_ts = jhu_frames_map['confirmed'].iloc[:,-1].name.strftime("%b %d %Y")
 display(HTML(f"<em>Data up to {data_ts}; countries with 100 or more confirmed cases.</em>"))
 ```

 %% Cell type:markdown id: tags:

 ## How are cases per 100,000 distributed geographically?

 %% Cell type:code id: tags:

 ``` python
 import altair as alt
 ```

 %% Cell type:code id: tags:

 ``` python
 map_df = helper.compute_map_df(rates_frames_map, jhu_frames_map, geodata_df, countries_over_thresh)
 ```

 %% Cell type:code id: tags:

 ``` python
 display(helper.map_of_variable(map_df, 'Confirmed/100k', 'Confirmed'))
 display(HTML('''
 <p style="font-size: smaller">Data Sources:
  <a href="https://github.com/CSSEGISandData/COVID-19">JHU CSSE</a>,
  <a href="https://data.worldbank.org/indicator/SP.POP.TOTL">World Bank</a>,
  <a href="https://worldmap.harvard.edu/data/geonode:country_centroids_az8">Harvard Worldmap</a>
 </p>'''))
 ```

 %% Cell type:code id: tags:

 ``` python
 bars = alt.Chart(map_df).mark_bar().encode(
    x='Confirmed/100k:Q',
    y=alt.Y("Country/Region:N", sort='-x'),
    tooltip=["Country/Region:N",
         "Confirmed:Q", "Deaths:Q", "Recovered:Q",
         "Confirmed/100k:Q", "Deaths/100k:Q", "Recovered/100k:Q"]
 )

 text = bars.mark_text(
    align='left',
    baseline='middle',
    dx=3  # Nudges text to right so it doesn't appear on top of the bar
 ).encode(
    text=alt.Text('Confirmed/100k:Q', format=".3")
 )

 chart = (bars + text).properties(height=900, title=f"Confirmed cases per 100k inhabitants")
 display(chart)
 display(HTML('''
 <p style="font-size: smaller">Data Sources:
  <a href="https://github.com/CSSEGISandData/COVID-19">JHU CSSE</a>,
  <a href="https://data.worldbank.org/indicator/SP.POP.TOTL">World Bank</a>,
  <a href="https://worldmap.harvard.edu/data/geonode:country_centroids_az8">Harvard Worldmap</a>
 </p>'''))
 ```

 %% Cell type:markdown id: tags:

 ## How have cases been growing?

 %% Cell type:code id: tags:

 ``` python
 confirmed_rate_df = helper.growth_df(rates_frames_map, geodata_df, 'confirmed', countries_over_thresh, 2)
 latest_confirmed_ser = confirmed_rate_df.set_index(
    ['Country/Region', 'Geo Region', 'Date']).drop(
    ['Longitude', 'Latitude'], axis=1).unstack().iloc[:,-1]
 sort_order = latest_confirmed_ser.groupby('Geo Region').mean().sort_values(ascending=False).index.tolist()
 ```

 %% Cell type:code id: tags:

 ``` python
 base = alt.Chart(confirmed_rate_df).properties(
    width=300, height=200, title="Countries with 2 or more cases per 100k")
 line = base.mark_line().encode(
    x='Date',
    y='Confirmed/100k',
    color='Country/Region',
    facet=alt.Facet('Geo Region:N', columns=1, sort=alt.SortArray(sort_order), title='Geographic Region'),
    tooltip=["Country/Region:N", "Date:T", "Confirmed/100k:Q"]
 )
 line
 display(line)
 display(HTML('''
 <p style="font-size: smaller">Data Sources:
  <a href="https://github.com/CSSEGISandData/COVID-19">JHU CSSE</a>,
  <a href="https://data.worldbank.org/indicator/SP.POP.TOTL">World Bank</a>,
  <a href="https://worldmap.harvard.edu/data/geonode:country_centroids_az8">Harvard Worldmap</a>
 </p>'''))
 ```

 %% Cell type:code id: tags:

 ``` python
 def country_increase_df(c, df_nominal, growth_in_rate_df):
    over_100 = df_nominal[df_nominal['Confirmed'] >= 100]
    tdf = (over_100[['Date', 'Confirmed']] - over_100.iloc[0][['Date', 'Confirmed']]).reset_index()
    tdfr = growth_in_rate_df[(growth_in_rate_df['Date'] >= over_100.iloc[0]['Date']) &
                             (growth_in_rate_df['Country/Region'] == c)].reset_index()
    tdf['Confirmed/100k'] = tdfr['Confirmed/100k']
    tdf['Country/Region'] = c
    tdf['Days'] = (tdf['Date'] / np.timedelta64(1, 'D')).astype(int)
    return tdf[['Country/Region', 'Days', 'Confirmed', 'Confirmed/100k']]


 growth_in_rate_df = helper.growth_df(rates_frames_map, geodata_df, 'confirmed', countries_over_thresh, 0)
 frame_map = {'confirmed': jhu_frames_map['confirmed'].groupby(level='Country/Region').sum()}
 growth_in_value_df = helper.growth_df(frame_map, geodata_df, 'confirmed', countries_over_thresh, 1000)
 growth_in_value_df = growth_in_value_df.rename({'Confirmed/100k':'Confirmed'}, axis=1)
 increase_df = pd.concat([country_increase_df(c, df_nominal, growth_in_rate_df) for
                         c, df_nominal in growth_in_value_df.groupby('Country/Region')])
 ```

 %% Cell type:code id: tags:

 ``` python
 def facetted_growth_plot(df, variable, sort_order, ref_country, title):
    base = alt.Chart(df).properties(
        width=250, height=150)
    line = base.mark_line().encode(
        x='Days',
        y=variable,
        color='Country/Region',
        tooltip=["Country/Region:N", "Days:Q", f"{variable}:Q"]
    )
    label_loc = increase_df[increase_df['Country/Region'] == ref_country]['Days'].iloc[-2]
    ref = base.mark_line(opacity=0.3).encode(
        x='Days',
        y=variable,
        color=alt.ColorValue('steelblue'),
    ).transform_filter(f"datum['Country/Region'] == '{ref_country}'")
    ref += ref.mark_text().encode(text='Country/Region:N').transform_filter(f"datum['Days'] == {label_loc}")
    charts = []
    # make our small multiples
    for country in sort_order:
        smallm = line.transform_filter(f"datum['Country/Region'] == '{country}'").properties(
            title=country)
        smallm += ref
        charts.append(smallm)

    # group the small multiples into 3 horizontal charts
    groups = []
    c = None
    for i, chart in enumerate(charts):
        if not i%3:
            if c != None:
                groups.append(c)
            c = alt.hconcat()
        c |= chart
    # vertically combine the horizontal charts
    chart = alt.vconcat(title=title)
    for c in groups:
        chart &= c
    return chart
 ```

 %% Cell type:code id: tags:

 ``` python
 sort_order = growth_in_value_df.groupby(
    'Country/Region').max().sort_values(
    'Confirmed', ascending=False).index.tolist()
 # Exclude China in this plot because its numbers are far greater then everywhere else
 sort_order = [o for o in sort_order if o != 'China']
 chart = facetted_growth_plot(increase_df[increase_df['Country/Region'] != 'China'],
                             'Confirmed',
                             sort_order,
                             'Italy',
                             "Growth of cases from case 100, compared to Italy")
 display(chart)
 display(HTML('''
 <p style="font-size: smaller">Data Sources:
  <a href="https://github.com/CSSEGISandData/COVID-19">JHU CSSE</a>,
  <a href="https://data.worldbank.org/indicator/SP.POP.TOTL">World Bank</a>,
  <a href="https://worldmap.harvard.edu/data/geonode:country_centroids_az8">Harvard Worldmap</a>
 </p>
 <p style="font-size: smaller">Inspired by <a href="https://covid19dashboards.com/growth-analysis/">Thomas Wiecki</a>'''))
 ```

 %% Cell type:code id: tags:

 ``` python
 sort_order = growth_in_value_df.groupby(
    'Country/Region').max().sort_values(
    'Confirmed', ascending=False).index.tolist()
 chart = facetted_growth_plot(increase_df,
                             'Confirmed/100k',
                             sort_order,
                             'Italy',
                             "Growth of cases/100k from case 100, compared to Italy")
 display(chart)
 display(HTML('''
 <p style="font-size: smaller">Data Sources:
  <a href="https://github.com/CSSEGISandData/COVID-19">JHU CSSE</a>,
  <a href="https://data.worldbank.org/indicator/SP.POP.TOTL">World Bank</a>,
  <a href="https://worldmap.harvard.edu/data/geonode:country_centroids_az8">Harvard Worldmap</a>
 </p>'''))
 ```