X-Git-Url: https://git.njae.me.uk/?p=covid19.git;a=blobdiff_plain;f=international_comparison.py;fp=international_comparison.py;h=213560930552e1ba777f427035050c1c57d16b44;hp=0000000000000000000000000000000000000000;hb=5afedd66506be7575034ae6deebcfaa7c2ced978;hpb=4abff18d7988bdea04a267a08a0792ba570fe0bd

diff --git a/international_comparison.py b/international_comparison.py
new file mode 100644
index 0000000..2135609
--- /dev/null
+++ b/international_comparison.py
@@ -0,0 +1,102 @@
+#!/usr/bin/env python
+# coding: utf-8
+# %%
+# Data from [European Centre for Disease Prevention and Control](https://www.ecdc.europa.eu/en/publications-data/download-todays-data-geographic-distribution-covid-19-cases-worldwide)
+
+# %%
+import itertools
+import collections
+import json
+import pandas as pd
+import numpy as np
+from scipy.stats import gmean
+import datetime
+
+from sqlalchemy.types import Integer, Text, String, DateTime, Date, Float
+from sqlalchemy import create_engine
+
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+plt.ioff()
+
+
+# %%
+connection_string = 'postgresql://covid:3NbjJTkT63@localhost/covid'
+
+
+# %%
+engine = create_engine(connection_string)
+
+
+# %%
+DEATH_COUNT_THRESHOLD = 10
+COUNTRIES_CORE = tuple(sorted('IT DE UK ES IE FR BE'.split()))
+COUNTRIES_NORDIC = tuple('SE NO DK FI UK'.split())
+COUNTRIES_FRIENDS = tuple('IT UK ES BE SI MX'.split())
+# COUNTRIES_FRIENDS = 'IT UK ES BE SI PT'.split()
+
+COUNTRIES_AMERICAS = ('AG', 'AR', 'AW', 'BS', 'BB', 'BZ', 'BM', 'BO', 'BR', 'VG', 'KY', # excluding Canada and USA
+       'CL', 'CO', 'CR', 'CU', 'CW', 'DM', 'DO', 'EC', 'SV', 'GL', 'GD', 'GT',
+       'GY', 'HT', 'HN', 'JM', 'MX', 'MS', 'NI', 'PA', 'PY', 'PE', 'PR', 'KN',
+       'LC', 'VC', 'SX', 'SR', 'TT', 'TC', 'VI', 'UY', 'VE')
+COUNTRIES_OF_INTEREST = tuple(set(COUNTRIES_CORE + COUNTRIES_FRIENDS))
+COUNTRIES_ALL = tuple(set(COUNTRIES_CORE + COUNTRIES_FRIENDS + COUNTRIES_NORDIC + COUNTRIES_AMERICAS))
+
+
+# %%
+query_string = f'''select report_date, geo_id, deaths_weekly, culm_deaths 
+from weekly_cases 
+where geo_id in {COUNTRIES_CORE} 
+order by report_date, geo_id'''
+
+country_data = pd.read_sql_query(query_string,
+                  engine,
+                  index_col = 'report_date',
+                  parse_dates = ['report_date']
+                 )
+
+
+# %%
+deaths_culm = country_data.pivot(columns='geo_id', values='culm_deaths')
+
+
+# %%
+ax = deaths_culm.loc['2020-03-15':].plot(figsize=(10, 6), title="Total deaths, linear")
+ax.set_xlabel(f"Date")
+for c in COUNTRIES_CORE:
+    lvi = deaths_culm[c].last_valid_index()
+    ax.text(x = lvi + pd.Timedelta(days=1), y = deaths_culm[c][lvi], s = f"{c}: {deaths_culm[c][lvi]:.0f}")
+plt.savefig('covid_deaths_total_linear.png')    
+
+
+# %%
+deaths_weekly = country_data.pivot(columns='geo_id', values='deaths_weekly')
+
+
+# %%
+ax = deaths_weekly.loc['2020-03-01':, COUNTRIES_CORE].plot(figsize=(10, 6), title="Deaths per week")
+ax.set_xlabel('Date')
+for c in COUNTRIES_CORE:
+    lvi = deaths_weekly[c].last_valid_index()
+    ax.text(x = lvi + pd.Timedelta(days=1), y = deaths_weekly[c][lvi], s = c)
+plt.savefig('covid_deaths_per_week.png') 
+
+
+# %%
+ax = deaths_weekly.iloc[-6:].plot(figsize=(10, 6), title="Deaths per week")#, ylim=(-10, 100))
+ax.set_xlabel("Date")
+
+text_x_pos = deaths_weekly.last_valid_index() + pd.Timedelta(days=0.5)
+
+for c in COUNTRIES_CORE:
+    lvi = deaths_weekly[c].last_valid_index()
+#     if c != 'ES':
+    ax.text(x = text_x_pos, y = deaths_weekly[c][lvi], s = f"{c}: {deaths_weekly[c][lvi]:.0f}")
+plt.savefig('deaths_by_date_last_6_weeks.png') 
+
+
+# %%
+
+
+
+