chore: adjust limits for ecdc notebook

c7a2b7bb · Rok Roškar · e8987d80 · c7a2b7bb
Unverified Commit c7a2b7bb authored 3 years ago by Rok Roškar
--- a/notebooks/covid-19-ecdc.ipynb
+++ b/notebooks/covid-19-ecdc.ipynb
@@ -90,7 +90,7 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "nthresh=3000\n",
+    "nthresh=4000\n",
    "country_max_ser = df.set_index(['country_label', 'date'])['positive_100k'].groupby(level='country_label').max()\n",
    "countries_over_thresh = country_max_ser[country_max_ser>nthresh].index\n",
    "countries_over_thresh = [c for c in countries_over_thresh if c not in set(['Andorra', 'Iceland', 'San Marino'])]\n",
@@ -193,7 +193,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.7.3"
+   "version": "3.9.6"
  },
  "mimetype": "text/x-python",
  "name": "python",

 %% Cell type:code id: tags:

 ``` python
 %load_ext autoreload
 %autoreload 2
 ```

 %% Cell type:code id: tags:

 ``` python
 from datetime import datetime

 import altair as alt
 import pandas as pd

 from IPython.display import display, HTML

 from covid_19_utils import helper, plotting
 from covid_19_utils.converters import CaseConverter
 ```

 %% Cell type:markdown id: tags:

 # Covid-19 Global Data from ECDC

 This dataset is collected by the European Center for Disease Prevention and Control and can be found [here](https://www.ecdc.europa.eu/en/publications-data/download-todays-data-geographic-distribution-covid-19-cases-worldwide).

 %% Cell type:code id: tags:

 ``` python
 html_credits=HTML('''
 <p style="font-size: smaller">Data Sources:
  <a href="https://www.ecdc.europa.eu/en/publications-data/download-todays-data-geographic-distribution-covid-19-cases-worldwide">ECDC</a>
  <br>
 Analysis and Visualization:
  <a href="https://renkulab.io/projects/covid-19/covid-19-public-data">Covid-19 Public Data Collaboration Project @ renkulab.io</a>
 </p>''')
 ```

 %% Cell type:code id: tags:parameters

 ``` python
 data_path = '../data/covid-19-ecdc'
 atlas_path = '../data/atlas'
 ```

 %% Cell type:code id: tags:

 ``` python
 converter = CaseConverter(atlas_path)
 df = converter.read_convert(data_path)
 ```

 %% Cell type:code id: tags:

 ``` python
 df.columns
 ```

 %% Cell type:code id: tags:

 ``` python
-nthresh=3000
+nthresh=4000
 country_max_ser = df.set_index(['country_label', 'date'])['positive_100k'].groupby(level='country_label').max()
 countries_over_thresh = country_max_ser[country_max_ser>nthresh].index
 countries_over_thresh = [c for c in countries_over_thresh if c not in set(['Andorra', 'Iceland', 'San Marino'])]

 start_date = datetime.fromisoformat('2020-08-01')
 thresh_df = df.loc[(df.date > start_date) & (df.country_label.isin(countries_over_thresh))]
 ```

 %% Cell type:code id: tags:

 ``` python
 df.columns
 ```

 %% Cell type:markdown id: tags:

 ## Daily deaths globally

 %% Cell type:markdown id: tags:

 The chart below shows the total number of covid-19 related deaths reported worldwide since February 1st, 2020.

 %% Cell type:code id: tags:

 ``` python
 chart = alt.Chart(
    df.loc[df.date > start_date].groupby('date')['deceased_daily'].sum().reset_index()
 ).mark_line().encode(
    x=alt.X('date', title='Date'),
    y=alt.Y('deceased_daily', title='Daily deaths')
 )
 display(chart)
 display(html_credits)
 ```

 %% Cell type:markdown id: tags:

 Deaths in countries with over 300,000 cases, ordered by total number of deaths.

 %% Cell type:code id: tags:

 ``` python
 order = thresh_df.groupby(['country_label'])['deceased'].max().sort_values(ascending=False).index.tolist()

 base = alt.Chart(thresh_df)
 chart = base.mark_line().encode(
    x=alt.X('date', title='Date'),
    y=alt.Y('deceased_daily', title='Daily deaths'),
    facet=alt.Facet('country_label', sort=alt.SortArray(order), columns=5, title='')
 ).properties(
    height=150,
    width=150
 )
 chart.resolve_scale(y='independent')
 display(chart)
 display(html_credits)
 ```

 %% Cell type:code id: tags:

 ``` python
 ```