9 jupytext_version: 1.3.4
11 display_name: Python 3
18 * [Office of National Statistics](https://www.ons.gov.uk/peoplepopulationandcommunity/birthsdeathsandmarriages/deaths/datasets/weeklyprovisionalfiguresondeathsregisteredinenglandandwales) (Endland and Wales) Weeks start on a Saturday.
19 * [Northern Ireland Statistics and Research Agency](https://www.nisra.gov.uk/publications/weekly-deaths) (Northern Ireland). Weeks start on a Saturday. Note that the week numbers don't match the England and Wales data.
20 * [National Records of Scotland](https://www.nrscotland.gov.uk/statistics-and-data/statistics/statistics-by-theme/vital-events/general-publications/weekly-and-monthly-data-on-births-and-deaths/weekly-data-on-births-and-deaths) (Scotland). Note that Scotland uses ISO8601 week numbers, which start on a Monday.
28 from scipy.stats import gmean
30 import matplotlib as mpl
31 import matplotlib.pyplot as plt
40 raw_data_2015 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2015.csv',
41 parse_dates=[1, 2], dayfirst=True,
45 dh15i = raw_data_2015.iloc[:, [2]]
46 dh15i.columns = ['total_2015']
51 raw_data_2016 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2016.csv',
52 parse_dates=[1, 2], dayfirst=True,
56 dh16i = raw_data_2016.iloc[:, [2]]
57 dh16i.columns = ['total_2016']
62 raw_data_2017 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2017.csv',
63 parse_dates=[1, 2], dayfirst=True,
67 dh17i = raw_data_2017.iloc[:, [2]]
68 dh17i.columns = ['total_2017']
73 raw_data_2018 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2018.csv',
74 parse_dates=[1, 2], dayfirst=True,
78 dh18i = raw_data_2018.iloc[:, [2]]
79 dh18i.columns = ['total_2018']
84 raw_data_2019 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2019.csv',
85 parse_dates=[1, 2], dayfirst=True,
89 dh19i = raw_data_2019.iloc[:, [2]]
90 dh19i.columns = ['total_2019']
95 raw_data_2020_i = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2020.csv',
96 parse_dates=[1], dayfirst=True,
100 deaths_headlines_i = raw_data_2020_i.iloc[:, [1]]
101 deaths_headlines_i.columns = ['total_2020']
102 deaths_headlines_i.head()
114 raw_data_s = pd.read_csv('uk-deaths-data/weekly-deaths-april-20-scotland.csv',
123 deaths_headlines_s = raw_data_s[reversed('2015 2016 2017 2018 2019 2020'.split())]
124 deaths_headlines_s.columns = ['total_' + c for c in deaths_headlines_s.columns]
125 deaths_headlines_s.reset_index(drop=True, inplace=True)
126 deaths_headlines_s.index = deaths_headlines_s.index + 1
151 raw_data_2020 = pd.read_csv('uk-deaths-data/publishedweek182020.csv',
152 parse_dates=[1], dayfirst=True,
158 # raw_data_2020.head()
162 raw_data_2020['W92000004', 'Wales']
166 raw_data_2019 = pd.read_csv('uk-deaths-data/publishedweek522019.csv',
167 parse_dates=[1], dayfirst=True,
170 # raw_data_2019.head()
174 raw_data_2018 = pd.read_csv('uk-deaths-data/publishedweek522018.csv',
175 parse_dates=[1], dayfirst=True,
178 # raw_data_2018.head()
182 raw_data_2017 = pd.read_csv('uk-deaths-data/publishedweek522017.csv',
183 parse_dates=[1], dayfirst=True,
186 # raw_data_2017.head()
190 raw_data_2016 = pd.read_csv('uk-deaths-data/publishedweek522016.csv',
191 parse_dates=[1], dayfirst=True,
194 # raw_data_2016.head()
198 raw_data_2015 = pd.read_csv('uk-deaths-data/publishedweek2015.csv',
199 parse_dates=[1], dayfirst=True,
202 # raw_data_2015.head()
206 deaths_headlines_e = raw_data_2020.iloc[:, [1]]
207 deaths_headlines_e.columns = ['total_2020']
208 deaths_headlines_w = raw_data_2020['W92000004']
209 deaths_headlines_e.columns = ['total_2020']
210 deaths_headlines_w.columns = ['total_2020']
211 deaths_headlines_e.total_2020 -= deaths_headlines_w.total_2020
212 deaths_headlines_e.head()
217 dh19e = raw_data_2019.iloc[:, [1]]
218 dh19w = raw_data_2019['W92000004']
219 dh19e.columns = ['total_2019']
220 dh19w.columns = ['total_2019']
221 dh19e.total_2019 -= dh19w.total_2019
230 dh18e = raw_data_2018.iloc[:, [1]]
231 dh18w = raw_data_2018['W92000004']
232 dh18e.columns = ['total_2018']
233 dh18w.columns = ['total_2018']
234 dh18e.total_2018 -= dh18w.total_2018
239 dh17e = raw_data_2017.iloc[:, [1]]
240 dh17w = raw_data_2017['W92000004']
241 dh17e.columns = ['total_2017']
242 dh17w.columns = ['total_2017']
243 dh17e.total_2017 -= dh17w.total_2017
248 dh16e = raw_data_2016.iloc[:, [1]]
249 dh16w = raw_data_2016['W92000004']
250 dh16e.columns = ['total_2016']
251 dh16w.columns = ['total_2016']
252 dh16e.total_2016 -= dh16w.total_2016
257 dh15e = raw_data_2015.iloc[:, [1]]
258 dh15w = raw_data_2015['W92000004']
259 dh15e.columns = ['total_2015']
260 dh15w.columns = ['total_2015']
261 dh15e.total_2015 -= dh15w.total_2015
266 # dh18 = raw_data_2018.iloc[:, [1, 2]]
267 # dh18.columns = ['total_2018', 'total_previous']
272 deaths_headlines_e = deaths_headlines_e.merge(dh19e['total_2019'], how='outer', left_index=True, right_index=True)
273 deaths_headlines_e = deaths_headlines_e.merge(dh18e['total_2018'], how='outer', left_index=True, right_index=True)
274 deaths_headlines_e = deaths_headlines_e.merge(dh17e['total_2017'], how='outer', left_index=True, right_index=True)
275 deaths_headlines_e = deaths_headlines_e.merge(dh16e['total_2016'], how='outer', left_index=True, right_index=True)
276 # deaths_headlines = deaths_headlines.merge(dh15['total_2015'], how='outer', left_index=True, right_index=True)
277 deaths_headlines_e = deaths_headlines_e.merge(dh15e['total_2015'], how='left', left_index=True, right_index=True)
282 deaths_headlines_s = raw_data_s[reversed('2015 2016 2017 2018 2019 2020'.split())]
283 deaths_headlines_s.columns = ['total_' + c for c in deaths_headlines_s.columns]
284 deaths_headlines_s.reset_index(drop=True, inplace=True)
285 deaths_headlines_s.index = deaths_headlines_s.index + 1
290 deaths_headlines_w = deaths_headlines_w.merge(dh19w['total_2019'], how='outer', left_index=True, right_index=True)
291 deaths_headlines_w = deaths_headlines_w.merge(dh18w['total_2018'], how='outer', left_index=True, right_index=True)
292 deaths_headlines_w = deaths_headlines_w.merge(dh17w['total_2017'], how='outer', left_index=True, right_index=True)
293 deaths_headlines_w = deaths_headlines_w.merge(dh16w['total_2016'], how='outer', left_index=True, right_index=True)
294 # deaths_headlines = deaths_headlines.merge(dh15['total_2015'], how='outer', left_index=True, right_index=True)
295 deaths_headlines_w = deaths_headlines_w.merge(dh15w['total_2015'], how='left', left_index=True, right_index=True)
300 deaths_headlines_i = deaths_headlines_i.merge(dh19i['total_2019'], how='outer', left_index=True, right_index=True)
301 deaths_headlines_i = deaths_headlines_i.merge(dh18i['total_2018'], how='outer', left_index=True, right_index=True)
302 deaths_headlines_i = deaths_headlines_i.merge(dh17i['total_2017'], how='outer', left_index=True, right_index=True)
303 deaths_headlines_i = deaths_headlines_i.merge(dh16i['total_2016'], how='outer', left_index=True, right_index=True)
304 deaths_headlines_i = deaths_headlines_i.merge(dh15i['total_2015'], how='left', left_index=True, right_index=True)
309 deaths_headlines = deaths_headlines_e + deaths_headlines_w + deaths_headlines_i + deaths_headlines_s
314 deaths_headlines['previous_mean'] = deaths_headlines['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)
319 deaths_headlines['total_2020 total_2019 total_2018 total_2017 total_2016 total_2015'.split()].plot(figsize=(10, 8))
323 fig = plt.figure(figsize=(10, 10))
324 ax = fig.add_subplot(111, projection="polar")
328 np.arange(len(deaths_headlines))/float(len(deaths_headlines))*2.*np.pi),
330 # l15, = ax.plot(theta, deaths_headlines['total_2015'], color="#b56363", label="2015") # 0
331 # l16, = ax.plot(theta, deaths_headlines['total_2016'], color="#a4b563", label="2016") # 72
332 # l17, = ax.plot(theta, deaths_headlines['total_2017'], color="#63b584", label="2017") # 144
333 # l18, = ax.plot(theta, deaths_headlines['total_2018'], color="#6384b5", label="2018") # 216
334 # l19, = ax.plot(theta, deaths_headlines['total_2019'], color="#a4635b", label="2019") # 288
335 l15, = ax.plot(theta, deaths_headlines['total_2015'], color="#e47d7d", label="2015") # 0
336 l16, = ax.plot(theta, deaths_headlines['total_2016'], color="#afc169", label="2016") # 72 , d0e47d
337 l17, = ax.plot(theta, deaths_headlines['total_2017'], color="#7de4a6", label="2017") # 144
338 l18, = ax.plot(theta, deaths_headlines['total_2018'], color="#7da6e4", label="2018") # 216
339 l19, = ax.plot(theta, deaths_headlines['total_2019'], color="#d07de4", label="2019") # 288
341 lmean, = ax.plot(theta, deaths_headlines['previous_mean'], color="black", linestyle='dashed', label="mean")
343 l20, = ax.plot(theta, deaths_headlines['total_2020'], color="red", label="2020")
345 # deaths_headlines.total_2019.plot(ax=ax)
347 def _closeline(line):
348 x, y = line.get_data()
349 x = np.concatenate((x, [x[0]]))
350 y = np.concatenate((y, [y[0]]))
353 [_closeline(l) for l in [l19, l18, l17, l16, l15, lmean]]
357 ax.set_xticklabels(deaths_headlines.index)
359 plt.title("Deaths by week over years, all UK")
360 plt.savefig('deaths-radar.png')
365 (deaths_headlines.loc[12:].total_2020 - deaths_headlines.loc[12:].previous_mean).sum()