uk_deaths.md

   1 ---
   2 jupyter:
   3   jupytext:
   4     formats: ipynb,md
   5     text_representation:
   6       extension: .md
   7       format_name: markdown
   8       format_version: '1.2'
   9       jupytext_version: 1.3.4
  10   kernelspec:
  11     display_name: Python 3
  12     language: python
  13     name: python3
  14 ---
  15
  16 Data from:
  17
  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.
  21
  22
  23 ```python
  24 import itertools
  25 import collections
  26 import pandas as pd
  27 import numpy as np
  28 from scipy.stats import gmean
  29
  30 import matplotlib as mpl
  31 import matplotlib.pyplot as plt
  32 %matplotlib inline
  33 ```
  34
  35 ```python
  36 !ls uk-deaths-data
  37 ```
  38
  39 ```python
  40 raw_data_2015 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2015.csv',
  41                        parse_dates=[1, 2], dayfirst=True,
  42                       index_col=0,
  43                       header=[0, 1]
  44                            )
  45 dh15i = raw_data_2015.iloc[:, [2]]
  46 dh15i.columns = ['total_2015']
  47 # dh15i.head()
  48 ```
  49
  50 ```python
  51 raw_data_2016 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2016.csv',
  52                         parse_dates=[1, 2], dayfirst=True,
  53                       index_col=0,
  54                       header=[0, 1]
  55                            )
  56 dh16i = raw_data_2016.iloc[:, [2]]
  57 dh16i.columns = ['total_2016']
  58 # dh16i.head()
  59 ```
  60
  61 ```python
  62 raw_data_2017 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2017.csv',
  63                         parse_dates=[1, 2], dayfirst=True,
  64                       index_col=0,
  65                       header=[0, 1]
  66                            )
  67 dh17i = raw_data_2017.iloc[:, [2]]
  68 dh17i.columns = ['total_2017']
  69 # dh17i.head()
  70 ```
  71
  72 ```python
  73 raw_data_2018 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2018.csv',
  74                         parse_dates=[1, 2], dayfirst=True,
  75                       index_col=0,
  76                       header=[0, 1]
  77                            )
  78 dh18i = raw_data_2018.iloc[:, [2]]
  79 dh18i.columns = ['total_2018']
  80 # dh18i.head()
  81 ```
  82
  83 ```python
  84 raw_data_2019 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2019.csv',
  85                         parse_dates=[1, 2], dayfirst=True,
  86                       index_col=0,
  87                       header=[0, 1]
  88                            )
  89 dh19i = raw_data_2019.iloc[:, [2]]
  90 dh19i.columns = ['total_2019']
  91 # dh19i.head()
  92 ```
  93
  94 ```python
  95 raw_data_2020_i = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2020.csv',
  96                         parse_dates=[1], dayfirst=True,
  97                       index_col=0,
  98                       header=[0, 1]
  99                            )
 100 deaths_headlines_i = raw_data_2020_i.iloc[:, [1]]
 101 deaths_headlines_i.columns = ['total_2020']
 102 deaths_headlines_i.head()
 103 ```
 104
 105 ```python
 106
 107 ```
 108
 109 ```python
 110
 111 ```
 112
 113 ```python
 114 raw_data_s = pd.read_csv('uk-deaths-data/weekly-deaths-april-20-scotland.csv',
 115                       index_col=0,
 116                       header=0,
 117                         skiprows=2
 118                            )
 119 # raw_data_s
 120 ```
 121
 122 ```python
 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
 127 deaths_headlines_s
 128 ```
 129
 130 ```python
 131
 132 ```
 133
 134 ```python
 135
 136 ```
 137
 138 ```python
 139
 140 ```
 141
 142 ```python
 143
 144 ```
 145
 146 ```python
 147
 148 ```
 149
 150 ```python
 151 raw_data_2020 = pd.read_csv('uk-deaths-data/publishedweek182020.csv',
 152                        parse_dates=[1], dayfirst=True,
 153                       index_col=0,
 154                       header=[0, 1])
 155 ```
 156
 157 ```python
 158 # raw_data_2020.head()
 159 ```
 160
 161 ```python
 162 raw_data_2020['W92000004', 'Wales']
 163 ```
 164
 165 ```python
 166 raw_data_2019 = pd.read_csv('uk-deaths-data/publishedweek522019.csv',
 167                        parse_dates=[1], dayfirst=True,
 168                       index_col=0,
 169                       header=[0, 1])
 170 # raw_data_2019.head()
 171 ```
 172
 173 ```python
 174 raw_data_2018 = pd.read_csv('uk-deaths-data/publishedweek522018.csv',
 175                        parse_dates=[1], dayfirst=True,
 176                       index_col=0,
 177                       header=[0, 1])
 178 # raw_data_2018.head()
 179 ```
 180
 181 ```python
 182 raw_data_2017 = pd.read_csv('uk-deaths-data/publishedweek522017.csv',
 183                        parse_dates=[1], dayfirst=True,
 184                       index_col=0,
 185                       header=[0, 1])
 186 # raw_data_2017.head()
 187 ```
 188
 189 ```python
 190 raw_data_2016 = pd.read_csv('uk-deaths-data/publishedweek522016.csv',
 191                        parse_dates=[1], dayfirst=True,
 192                       index_col=0,
 193                       header=[0, 1])
 194 # raw_data_2016.head()
 195 ```
 196
 197 ```python
 198 raw_data_2015 = pd.read_csv('uk-deaths-data/publishedweek2015.csv',
 199                        parse_dates=[1], dayfirst=True,
 200                       index_col=0,
 201                       header=[0, 1])
 202 # raw_data_2015.head()
 203 ```
 204
 205 ```python
 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()
 213 deaths_headlines_e
 214 ```
 215
 216 ```python
 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
 222 dh19e.head()
 223 ```
 224
 225 ```python
 226 dh19w.head()
 227 ```
 228
 229 ```python
 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
 235 # dh18e.head()
 236 ```
 237
 238 ```python
 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
 244 # dh17e.head()
 245 ```
 246
 247 ```python
 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
 253 # dh16e.head()
 254 ```
 255
 256 ```python
 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
 262 # dh15e.head()
 263 ```
 264
 265 ```python
 266 # dh18 = raw_data_2018.iloc[:, [1, 2]]
 267 # dh18.columns = ['total_2018', 'total_previous']
 268 # # dh18.head()
 269 ```
 270
 271 ```python
 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)
 278 deaths_headlines_e
 279 ```
 280
 281 ```python
 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
 286 deaths_headlines_s
 287 ```
 288
 289 ```python
 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)
 296 deaths_headlines_w
 297 ```
 298
 299 ```python
 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)
 305 deaths_headlines_i
 306 ```
 307
 308 ```python
 309 deaths_headlines = deaths_headlines_e + deaths_headlines_w + deaths_headlines_i + deaths_headlines_s
 310 deaths_headlines
 311 ```
 312
 313 ```python
 314 deaths_headlines['previous_mean'] = deaths_headlines['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)
 315 deaths_headlines
 316 ```
 317
 318 ```python
 319 deaths_headlines['total_2020 total_2019 total_2018 total_2017 total_2016 total_2015'.split()].plot(figsize=(10, 8))
 320 ```
 321
 322 ```python
 323 fig = plt.figure(figsize=(10, 10))
 324 ax = fig.add_subplot(111, projection="polar")
 325
 326 theta = np.roll(
 327     np.flip(
 328         np.arange(len(deaths_headlines))/float(len(deaths_headlines))*2.*np.pi),
 329     14)
 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
 340
 341 lmean, = ax.plot(theta, deaths_headlines['previous_mean'], color="black", linestyle='dashed', label="mean")
 342
 343 l20, = ax.plot(theta, deaths_headlines['total_2020'], color="red", label="2020")
 344
 345 # deaths_headlines.total_2019.plot(ax=ax)
 346
 347 def _closeline(line):
 348     x, y = line.get_data()
 349     x = np.concatenate((x, [x[0]]))
 350     y = np.concatenate((y, [y[0]]))
 351     line.set_data(x, y)
 352
 353 [_closeline(l) for l in [l19, l18, l17, l16, l15, lmean]]
 354
 355
 356 ax.set_xticks(theta)
 357 ax.set_xticklabels(deaths_headlines.index)
 358 plt.legend()
 359 plt.title("Deaths by week over years, all UK")
 360 plt.savefig('deaths-radar.png')
 361 plt.show()
 362 ```
 363
 364 ```python
 365 (deaths_headlines.loc[12:].total_2020 - deaths_headlines.loc[12:].previous_mean).sum()
 366 ```
 367
 368 ```python
 369
 370 ```