Auto-saving for plamennavenkova on branch master from commit 09d70f57

e221712e · Plamenna Venkova-Marchevska · 09d70f57 · e221712e · e221712e · e221712e
Commit e221712e authored May 07, 2020 by Plamenna Venkova-Marchevska
--- a/notebooks/openzh-covid-19.ipynb
+++ b/notebooks/openzh-covid-19.ipynb
 %% Cell type:code id: tags:

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

 %% Cell type:code id: tags:

 ``` python
 from pathlib import Path

 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:code id: tags:parameters

 ``` python
 save_figures = False
 data_path = '../data/openzh-covid-19'
 atlas_path = '../data/atlas'
 ```

 %% Cell type:code id: tags:

 ``` python
 html_credits=HTML('''
 <p style="font-size: smaller">Data Sources:
  <a href="https://github.com/openZH/covid_19">OpenData Zuerich</a>,
  <a href="https://www.bfs.admin.ch">Federal Statistical Office</a>
 <br>
 Analysis:
  <a href="https://renkulab.io/projects/covid-19/covid-19-public-data">Covid-19 Public Data Collaboration Project</a>
 </p>''')
 ```

+%%%% Output: error
+
+    ---------------------------------------------------------------------------
+    NameError                                 Traceback (most recent call last)
+    <ipython-input-2-4f8381516fe8> in <module>
+    ----> 1 html_credits=HTML('''
+          2 <p style="font-size: smaller">Data Sources:
+          3   <a href="https://github.com/openZH/covid_19">OpenData Zuerich</a>,
+          4   <a href="https://www.bfs.admin.ch">Federal Statistical Office</a>
+          5 <br>
+    NameError: name 'HTML' is not defined
+
 %% Cell type:markdown id: tags:

 ## Summary data for Covid-19 cases in Switzerland

 The data for Switzerland comes from the effort initiated by [OpenData Zürich](https://github.com/openZH/covid_19) and collected during the [Case data #covid19mon hackathon challenge](https://db.schoolofdata.ch/project/73).

 Below we make plots of total cases, total cases per 10k population and total deaths. You can click on the canton abbreviations in the legend to highlight individual lines.

 %% Cell type:code id: tags:

 ``` python
 # read in cantonal data and produce one dataframe
 converter = CaseConverter(atlas_path)
 df = converter.read_convert(data_path)
 df["canton"] = df.apply(lambda row: row["region_iso"][3:], axis=1)
 ```

+%%%% Output: error
+
+    ---------------------------------------------------------------------------
+    NameError                                 Traceback (most recent call last)
+    <ipython-input-3-88cb7f8fc4d7> in <module>
+          1 # read in cantonal data and produce one dataframe
+    ----> 2 converter = CaseConverter(atlas_path)
+          3 df = converter.read_convert(data_path)
+          4 df["canton"] = df.apply(lambda row: row["region_iso"][3:], axis=1)
+    NameError: name 'CaseConverter' is not defined
+
 %% Cell type:markdown id: tags:

 ### Total cases

 %% Cell type:code id: tags:

 ``` python
 base = alt.Chart(df)
 base.configure_header(titleFontSize=25)
 base.configure_axis(labelFontSize=15, titleFontSize=15)

 # cumul = generate_canton_chart(base, 'positive', 'Cases', 'Cases')
 cumul = plotting.generate_region_chart(
    base,
    column='positive',
    region_column='canton',
    ytitle='Cases',
    legend_title='Canton',
    tooltip_title='Cases')
 cumul_100k = plotting.generate_region_chart(
    base,
    column='positive_100k',
    region_column='canton',
    ytitle='Cases per 100k population',
    legend_title='Canton',
    tooltip_title='Cases/100k')

 chart = alt.hconcat(
    cumul, cumul_100k, title='Covid-19 cases in Switzerland by Canton'
 ).configure_title(
    anchor='middle'
 )

 display(chart)
 if save_figures:
    chart.save(str(Path(figures_path) / 'switzerland-cases-by-canton.html'))

 display(html_credits)
 ```

 %% Cell type:markdown id: tags:

 ### Deaths

 %% Cell type:code id: tags:

 ``` python
 base = alt.Chart(df)
 base.configure_header(titleFontSize=25)
 base.configure_axis(labelFontSize=15, titleFontSize=15)

 deaths = plotting.generate_region_chart(
    base,
    column='deceased',
    region_column='canton',
    ytitle='Deaths',
    tooltip_title='Deaths',
    legend_title='Canton'
 )
 deaths_10k = plotting.generate_region_chart(
    base,
    column='deceased_100k',
    region_column='canton',
    ytitle='Deaths per 100k population',
    tooltip_title='Deaths/100k',
    legend_title='Canton'
 )

 chart = alt.hconcat(
    deaths, deaths_10k, title='Covid-19 deaths in Switzerland by Canton'
 ).configure_title(
    anchor='middle'
 )
 display(chart)
 display(html_credits)

 if save_figures:
    chart.save(str(Path(figures_path) / 'switzerland-deaths-by-canton.html'))
 ```

 %% Cell type:code id: tags:

 ``` python
 since_100th_case = helper.make_since_df(df, 'positive', 'canton')

 base = alt.Chart(since_100th_case, title="Switzerland: total cases since 100th case").encode(alt.Y(scale=alt.Scale(type='log')))

 lineChart = plotting.make_region_since_chart(
    base,
    'positive',
    'sinceDay0',
    'canton',
    'Days since 100th case',
    'Cumulative positive cases',
    'Cases',
    'Canton'
 ).properties(
    width=450,
    height=450
 )

 rule_chart = plotting.make_rule_chart(max_days=max(since_100th_case['sinceDay0']), pos_day=(9,5000), pos_3days=(19,8000))

 lineChart + rule_chart
 ```

 %% Cell type:code id: tags:

 ``` python
 ```

--- a/notebooks/process/download-covidtracking-data.ipynb
+++ b/notebooks/process/download-covidtracking-data.ipynb
@@ -128,7 +128,7 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.7.6"
+   "version": "3.7.3"
  }
 },
 "nbformat": 4,

--- a/notebooks/process/wikidata-pop-data.ipynb
+++ b/notebooks/process/wikidata-pop-data.ipynb
 %% Cell type:markdown id: tags:

 # Gather Population Data from Wikidata

 %% Cell type:code id: tags:

 ``` python
 import os
 import pandas as pd

 from covid_19_utils import helper
 ```

 %% Cell type:code id: tags:parameters

 ``` python
 out_folder = '../../data/atlas/wikidata'
 PAPERMILL_OUTPUT_PATH = None
 ```

 %% Cell type:code id: tags:

 ``` python
 def write_population_data(iso_code, df):
    if PAPERMILL_OUTPUT_PATH is None:
        return
    out_path = os.path.join(out_folder, f"{iso_code.lower()}-population.csv")
    print(f"Writing {len(df)} rows to {out_path}")
    df.to_csv(out_path)
 ```

 %% Cell type:markdown id: tags:

 ## Italy

 %% Cell type:code id: tags:

 ``` python
 iso_code = "ITA"
 pops = helper.get_region_populations(
    iso_code,
    additional_fields="?istatid",
    additional_query="?region wdt:P635 ?istatid .",
 )
 df = pd.DataFrame(pops)
 write_population_data(iso_code, df)
 df.head(2)
 ```

 %%%% Output: execute_result

-  region_iso region_label country_label istatid population
-0      IT-34       Veneto         Italy      05    4926818
-1      IT-25     Lombardy         Italy      03   10067494
+      region_iso region_label country_label istatid population
+    0      IT-34       Veneto         Italy      05    4926818
+    1      IT-25     Lombardy         Italy      03   10067494

 %% Cell type:markdown id: tags:

 ## Switzerland

 %% Cell type:code id: tags:

 ``` python
 iso_code = "CHE"
 pops = helper.get_region_populations(iso_code)
 df = pd.DataFrame(pops)
 write_population_data(iso_code, df)
 df.head(2)
 ```

 %%%% Output: execute_result

-  region_iso      region_label country_label population
-0      CH-GE  Canton of Geneva   Switzerland     499480
-1      CH-JU    Canton of Jura   Switzerland      73419
+      region_iso      region_label country_label population
+    0      CH-GE  Canton of Geneva   Switzerland     499480
+    1      CH-JU    Canton of Jura   Switzerland      73419

 %% Cell type:markdown id: tags:

 ## United States

 %% Cell type:code id: tags:

 ``` python
 iso_code = "USA"
 pops = helper.get_region_populations(iso_code)
 df = pd.DataFrame(pops)
 write_population_data(iso_code, df)
 df.head(2)
 ```

 %%%% Output: execute_result

-  region_iso region_label             country_label population
-0      US-DE     Delaware  United States of America     945934
-1      US-OR       Oregon  United States of America    4028977
+      region_iso region_label             country_label population
+    0      US-DE     Delaware  United States of America     945934
+    1      US-OR       Oregon  United States of America    4028977

 %% Cell type:code id: tags:

 ``` python
 ```