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: 1.9.1
  10   kernelspec:
  11     display_name: Python 3
  12     language: python
  13     name: python3
  14 ---
  15
  16 <!-- #region Collapsed="false" -->
  17 Data from:
  18
  19 * [Office of National Statistics](https://www.ons.gov.uk/peoplepopulationandcommunity/birthsdeathsandmarriages/deaths/datasets/weeklyprovisionalfiguresondeathsregisteredinenglandandwales) (Endland and Wales) Weeks start on a Saturday.
  20 * [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.
  21 * [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.
  22
  23 <!-- #endregion -->
  24
  25 ```python Collapsed="false"
  26 import itertools
  27 import collections
  28 import json
  29 import pandas as pd
  30 import numpy as np
  31 from scipy.stats import gmean
  32
  33 import matplotlib as mpl
  34 import matplotlib.pyplot as plt
  35 %matplotlib inline
  36 ```
  37
  38 ```python Collapsed="false"
  39 england_wales_filename = 'uk-deaths-data/publishedweek532020.xlsx'
  40 ```
  41
  42 ```python Collapsed="false"
  43 raw_data_2015 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2015.csv',
  44                        parse_dates=[1, 2], dayfirst=True,
  45                       index_col=0,
  46                       header=[0, 1]
  47                            )
  48 dh15i = raw_data_2015.iloc[:, [2]]
  49 dh15i.columns = ['total_2015']
  50 # dh15i.head()
  51 ```
  52
  53 ```python Collapsed="false"
  54 raw_data_2016 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2016.csv',
  55                         parse_dates=[1, 2], dayfirst=True,
  56                       index_col=0,
  57                       header=[0, 1]
  58                            )
  59 dh16i = raw_data_2016.iloc[:, [2]]
  60 dh16i.columns = ['total_2016']
  61 # dh16i.head()
  62 ```
  63
  64 ```python Collapsed="false"
  65 raw_data_2017 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2017.csv',
  66                         parse_dates=[1, 2], dayfirst=True,
  67                       index_col=0,
  68                       header=[0, 1]
  69                            )
  70 dh17i = raw_data_2017.iloc[:, [2]]
  71 dh17i.columns = ['total_2017']
  72 # dh17i.head()
  73 ```
  74
  75 ```python Collapsed="false"
  76 raw_data_2018 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2018.csv',
  77                         parse_dates=[1, 2], dayfirst=True,
  78                       index_col=0,
  79                       header=[0, 1]
  80                            )
  81 dh18i = raw_data_2018.iloc[:, [2]]
  82 dh18i.columns = ['total_2018']
  83 # dh18i.head()
  84 ```
  85
  86 ```python Collapsed="false"
  87 raw_data_2019 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2019.csv',
  88                         parse_dates=[1, 2], dayfirst=True,
  89                       index_col=0,
  90                       header=[0, 1]
  91                            )
  92 dh19i = raw_data_2019.iloc[:, [2]]
  93 dh19i.columns = ['total_2019']
  94 # dh19i.head()
  95 ```
  96
  97 ```python Collapsed="false"
  98 raw_data_2020_i = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2020.csv',
  99                         parse_dates=[1], dayfirst=True,
 100                       index_col=0,
 101                       header=[0, 1]
 102                            )
 103 deaths_headlines_i = raw_data_2020_i.iloc[:, [1]]
 104 deaths_headlines_i.columns = ['total_2020']
 105 deaths_headlines_i.tail()
 106 ```
 107
 108 ```python Collapsed="false"
 109 raw_data_2019
 110 ```
 111
 112 ```python Collapsed="false"
 113
 114 ```
 115
 116 ```python Collapsed="false"
 117 raw_data_s = pd.read_csv('uk-deaths-data/weekly-deaths-scotland.csv',
 118                       index_col=0,
 119                       header=0,
 120                         skiprows=2
 121                            )
 122 # raw_data_s
 123 ```
 124
 125 ```python Collapsed="false"
 126 deaths_headlines_s = raw_data_s[reversed('2015 2016 2017 2018 2019 2020'.split())]
 127 deaths_headlines_s.columns = ['total_' + c for c in deaths_headlines_s.columns]
 128 deaths_headlines_s.reset_index(drop=True, inplace=True)
 129 deaths_headlines_s.index = deaths_headlines_s.index + 1
 130 deaths_headlines_s
 131 ```
 132
 133 ```python Collapsed="false"
 134
 135 ```
 136
 137 ```python Collapsed="false"
 138 eng_xls = pd.read_excel(england_wales_filename,
 139                         sheet_name="Weekly figures 2020",
 140                         skiprows=[0, 1, 2, 3],
 141                         header=0,
 142                         index_col=[1]
 143                        ).iloc[:91].T
 144 eng_xls
 145 ```
 146
 147 ```python Collapsed="false"
 148 # eng_xls_columns
 149 ```
 150
 151 ```python Collapsed="false"
 152 eng_xls_columns = list(eng_xls.columns)
 153
 154 for i, c in enumerate(eng_xls_columns):
 155 #     print(i, c, type(c), isinstance(c, float))
 156     if isinstance(c, float) and np.isnan(c):
 157         if eng_xls.iloc[0].iloc[i] is not pd.NaT:
 158             eng_xls_columns[i] = eng_xls.iloc[0].iloc[i]
 159
 160 # np.isnan(eng_xls_columns[0])
 161 # eng_xls_columns
 162
 163 eng_xls.columns = eng_xls_columns
 164 # eng_xls.columns
 165 ```
 166
 167 ```python Collapsed="false"
 168 eng_xls['Total deaths, all ages']
 169 ```
 170
 171 ```python Collapsed="false"
 172 eng_xls['Wales'].iloc[1:]
 173 ```
 174
 175 ```python Collapsed="false"
 176 # raw_data_2020 = pd.read_csv('uk-deaths-data/publishedweek272020.csv',
 177 #                        parse_dates=[1], dayfirst=True,
 178 #                       index_col=0,
 179 #                       header=[0, 1])
 180 ```
 181
 182 ```python Collapsed="false"
 183
 184 ```
 185
 186 ```python Collapsed="false"
 187 # raw_data_2020.head()
 188 ```
 189
 190 ```python Collapsed="false"
 191 # raw_data_2020['W92000004', 'Wales']
 192 ```
 193
 194 ```python Collapsed="false"
 195 raw_data_2019 = pd.read_csv('uk-deaths-data/publishedweek522019.csv',
 196                        parse_dates=[1], dayfirst=True,
 197                       index_col=0,
 198                       header=[0, 1])
 199 # raw_data_2019.head()
 200 ```
 201
 202 ```python Collapsed="false"
 203 raw_data_2018 = pd.read_csv('uk-deaths-data/publishedweek522018.csv',
 204                        parse_dates=[1], dayfirst=True,
 205                       index_col=0,
 206                       header=[0, 1])
 207 # raw_data_2018.head()
 208 ```
 209
 210 ```python Collapsed="false"
 211 raw_data_2017 = pd.read_csv('uk-deaths-data/publishedweek522017.csv',
 212                        parse_dates=[1], dayfirst=True,
 213                       index_col=0,
 214                       header=[0, 1])
 215 # raw_data_2017.head()
 216 ```
 217
 218 ```python Collapsed="false"
 219 raw_data_2016 = pd.read_csv('uk-deaths-data/publishedweek522016.csv',
 220                        parse_dates=[1], dayfirst=True,
 221                       index_col=0,
 222                       header=[0, 1])
 223 # raw_data_2016.head()
 224 ```
 225
 226 ```python Collapsed="false"
 227 raw_data_2015 = pd.read_csv('uk-deaths-data/publishedweek2015.csv',
 228                        parse_dates=[1], dayfirst=True,
 229                       index_col=0,
 230                       header=[0, 1])
 231 # raw_data_2015.head()
 232 ```
 233
 234 ```python Collapsed="false"
 235 dhw = eng_xls['Wales'].iloc[1:]
 236 dhe = eng_xls['Total deaths, all ages'].iloc[1:] - dhw
 237 deaths_headlines_e = pd.DataFrame({'total_2020': dhe.dropna()})
 238 deaths_headlines_w = pd.DataFrame({'total_2020': dhw.dropna()})
 239 ```
 240
 241 ```python Collapsed="false"
 242 # deaths_headlines_e = raw_data_2020.iloc[:, [1]].copy()
 243 # deaths_headlines_e.columns = ['total_2020']
 244 # deaths_headlines_w = raw_data_2020['W92000004'].copy()
 245 # deaths_headlines_e.columns = ['total_2020']
 246 # deaths_headlines_w.columns = ['total_2020']
 247 # deaths_headlines_e.total_2020 -= deaths_headlines_w.total_2020
 248 # deaths_headlines_e.head()
 249 # deaths_headlines_e
 250 ```
 251
 252 ```python Collapsed="false"
 253 dh19e = raw_data_2019.iloc[:, [1]]
 254 dh19w = raw_data_2019['W92000004']
 255 dh19e.columns = ['total_2019']
 256 dh19w.columns = ['total_2019']
 257 dh19e.total_2019 -= dh19w.total_2019
 258 dh19e.tail()
 259 ```
 260
 261 ```python Collapsed="false"
 262 dh19w.head()
 263 ```
 264
 265 ```python Collapsed="false"
 266 dh18e = raw_data_2018.iloc[:, [1]]
 267 dh18w = raw_data_2018['W92000004']
 268 dh18e.columns = ['total_2018']
 269 dh18w.columns = ['total_2018']
 270 dh18e.total_2018 -= dh18w.total_2018
 271 # dh18e.head()
 272 ```
 273
 274 ```python Collapsed="false"
 275 dh17e = raw_data_2017.iloc[:, [1]]
 276 dh17w = raw_data_2017['W92000004']
 277 dh17e.columns = ['total_2017']
 278 dh17w.columns = ['total_2017']
 279 dh17e.total_2017 -= dh17w.total_2017
 280 # dh17e.head()
 281 ```
 282
 283 ```python Collapsed="false"
 284 dh16e = raw_data_2016.iloc[:, [1]]
 285 dh16w = raw_data_2016['W92000004']
 286 dh16e.columns = ['total_2016']
 287 dh16w.columns = ['total_2016']
 288 dh16e.total_2016 -= dh16w.total_2016
 289 # dh16e.head()
 290 ```
 291
 292 ```python Collapsed="false"
 293 dh15e = raw_data_2015.iloc[:, [1]]
 294 dh15w = raw_data_2015['W92000004']
 295 dh15e.columns = ['total_2015']
 296 dh15w.columns = ['total_2015']
 297 dh15e.total_2015 -= dh15w.total_2015
 298 # dh15e.head()
 299 ```
 300
 301 ```python Collapsed="false"
 302 # dh18 = raw_data_2018.iloc[:, [1, 2]]
 303 # dh18.columns = ['total_2018', 'total_previous']
 304 # # dh18.head()
 305 ```
 306
 307 ```python Collapsed="false"
 308 deaths_headlines_e = deaths_headlines_e.merge(dh19e['total_2019'], how='outer', left_index=True, right_index=True)
 309 deaths_headlines_e = deaths_headlines_e.merge(dh18e['total_2018'], how='outer', left_index=True, right_index=True)
 310 deaths_headlines_e = deaths_headlines_e.merge(dh17e['total_2017'], how='outer', left_index=True, right_index=True)
 311 deaths_headlines_e = deaths_headlines_e.merge(dh16e['total_2016'], how='outer', left_index=True, right_index=True)
 312 # deaths_headlines = deaths_headlines.merge(dh15['total_2015'], how='outer', left_index=True, right_index=True)
 313 deaths_headlines_e = deaths_headlines_e.merge(dh15e['total_2015'], how='left', left_index=True, right_index=True)
 314 deaths_headlines_e
 315 ```
 316
 317 ```python Collapsed="false"
 318 deaths_headlines_s = raw_data_s[reversed('2015 2016 2017 2018 2019 2020'.split())]
 319 deaths_headlines_s.columns = ['total_' + c for c in deaths_headlines_s.columns]
 320 deaths_headlines_s.reset_index(drop=True, inplace=True)
 321 deaths_headlines_s.index = deaths_headlines_s.index + 1
 322 deaths_headlines_s = deaths_headlines_s.loc[1:52]
 323 deaths_headlines_s
 324 ```
 325
 326 <!-- #region Collapsed="false" -->
 327 # Correction for missing data
 328 <!-- #endregion -->
 329
 330 ```python Collapsed="false"
 331 # deaths_headlines_s.loc[20, 'total_2020'] = 1000
 332 # deaths_headlines_s
 333 ```
 334
 335 ```python Collapsed="false"
 336 deaths_headlines_w = deaths_headlines_w.merge(dh19w['total_2019'], how='outer', left_index=True, right_index=True)
 337 deaths_headlines_w = deaths_headlines_w.merge(dh18w['total_2018'], how='outer', left_index=True, right_index=True)
 338 deaths_headlines_w = deaths_headlines_w.merge(dh17w['total_2017'], how='outer', left_index=True, right_index=True)
 339 deaths_headlines_w = deaths_headlines_w.merge(dh16w['total_2016'], how='outer', left_index=True, right_index=True)
 340 # deaths_headlines = deaths_headlines.merge(dh15['total_2015'], how='outer', left_index=True, right_index=True)
 341 deaths_headlines_w = deaths_headlines_w.merge(dh15w['total_2015'], how='left', left_index=True, right_index=True)
 342 deaths_headlines_w
 343 ```
 344
 345 ```python Collapsed="false"
 346 deaths_headlines_i = deaths_headlines_i.merge(dh19i['total_2019'], how='outer', left_index=True, right_index=True)
 347 deaths_headlines_i = deaths_headlines_i.merge(dh18i['total_2018'], how='outer', left_index=True, right_index=True)
 348 deaths_headlines_i = deaths_headlines_i.merge(dh17i['total_2017'], how='outer', left_index=True, right_index=True)
 349 deaths_headlines_i = deaths_headlines_i.merge(dh16i['total_2016'], how='outer', left_index=True, right_index=True)
 350 deaths_headlines_i = deaths_headlines_i.merge(dh15i['total_2015'], how='left', left_index=True, right_index=True)
 351 deaths_headlines_i
 352 ```
 353
 354 ```python Collapsed="false"
 355 deaths_headlines_s
 356 ```
 357
 358 ```python Collapsed="false"
 359 deaths_headlines = deaths_headlines_e + deaths_headlines_w + deaths_headlines_i + deaths_headlines_s
 360 deaths_headlines
 361 ```
 362
 363 ```python Collapsed="false"
 364 deaths_headlines_e['previous_mean'] = deaths_headlines_e['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)
 365 deaths_headlines_w['previous_mean'] = deaths_headlines_w['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)
 366 deaths_headlines_s['previous_mean'] = deaths_headlines_s['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)
 367 deaths_headlines_i['previous_mean'] = deaths_headlines_i['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)
 368 deaths_headlines['previous_mean'] = deaths_headlines['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)
 369 deaths_headlines
 370 ```
 371
 372 ```python Collapsed="false"
 373 deaths_headlines['total_2020 total_2019 total_2018 total_2017 total_2016 total_2015'.split()].plot(figsize=(14, 8))
 374 ```
 375
 376 ```python Collapsed="false"
 377 deaths_headlines[['total_2020', 'previous_mean']].plot(figsize=(10, 8))
 378 ```
 379
 380 ```python Collapsed="false"
 381 deaths_headlines_i.plot()
 382 ```
 383
 384 ```python Collapsed="false"
 385 # Radar plot code taken from example at https://stackoverflow.com/questions/42878485/getting-matplotlib-radar-plot-with-pandas#
 386
 387 dhna = deaths_headlines.dropna()
 388
 389 fig = plt.figure(figsize=(10, 10))
 390 ax = fig.add_subplot(111, projection="polar")
 391
 392 theta = np.roll(
 393     np.flip(
 394         np.arange(len(dhna))/float(len(dhna))*2.*np.pi),
 395     14)
 396 # l15, = ax.plot(theta, deaths_headlines['total_2015'], color="#b56363", label="2015") # 0
 397 # l16, = ax.plot(theta, deaths_headlines['total_2016'], color="#a4b563", label="2016") # 72
 398 # l17, = ax.plot(theta, deaths_headlines['total_2017'], color="#63b584", label="2017") # 144
 399 # l18, = ax.plot(theta, deaths_headlines['total_2018'], color="#6384b5", label="2018") # 216
 400 # l19, = ax.plot(theta, deaths_headlines['total_2019'], color="#a4635b", label="2019") # 288
 401 l15, = ax.plot(theta, dhna['total_2015'], color="#e47d7d", label="2015") # 0
 402 l16, = ax.plot(theta, dhna['total_2016'], color="#afc169", label="2016") # 72 , d0e47d
 403 l17, = ax.plot(theta, dhna['total_2017'], color="#7de4a6", label="2017") # 144
 404 l18, = ax.plot(theta, dhna['total_2018'], color="#7da6e4", label="2018") # 216
 405 l19, = ax.plot(theta, dhna['total_2019'], color="#d07de4", label="2019") # 288
 406
 407 lmean, = ax.plot(theta, dhna['previous_mean'], color="black", linestyle='dashed', label="mean")
 408
 409 l20, = ax.plot(theta, dhna['total_2020'], color="red", label="2020")
 410
 411 # deaths_headlines.total_2019.plot(ax=ax)
 412
 413 def _closeline(line):
 414     x, y = line.get_data()
 415     x = np.concatenate((x, [x[0]]))
 416     y = np.concatenate((y, [y[0]]))
 417     line.set_data(x, y)
 418
 419 [_closeline(l) for l in [l19, l18, l17, l16, l15, lmean]]
 420
 421
 422 ax.set_xticks(theta)
 423 ax.set_xticklabels(dhna.index)
 424 plt.legend()
 425 plt.title("Deaths by week over years, all UK")
 426 plt.savefig('deaths-radar.png')
 427 plt.show()
 428 ```
 429
 430 <!-- #region Collapsed="false" -->
 431 # Excess deaths calculation
 432 <!-- #endregion -->
 433
 434 ```python Collapsed="false"
 435 # raw_data_2020.loc[12, 'Week ended']
 436 ```
 437
 438 ```python Collapsed="false"
 439 eng_xls.loc[12, 'Week ended']
 440 ```
 441
 442 ```python Collapsed="false"
 443 # raw_data_2020.iloc[-1]['Week ended']
 444 ```
 445
 446 ```python Collapsed="false"
 447 deaths_headlines_e.total_2020.dropna().last_valid_index()
 448 ```
 449
 450 ```python Collapsed="false"
 451 eng_xls.loc[deaths_headlines_e.total_2020.dropna().last_valid_index(), 'Week ended']
 452 ```
 453
 454 ```python Collapsed="false"
 455 eng_xls.loc[27, 'Week ended']
 456 ```
 457
 458 ```python Collapsed="false"
 459 # raw_data_2020.loc[12].droplevel(1)['Week ended']
 460 ```
 461
 462 ```python Collapsed="false"
 463 # raw_data_2020.iloc[-1].droplevel(1)['Week ended']
 464 ```
 465
 466 ```python Collapsed="false"
 467 (deaths_headlines.loc[12:].total_2020 - deaths_headlines.loc[12:].previous_mean).sum()
 468 ```
 469
 470 ```python Collapsed="false"
 471 (deaths_headlines.loc[12:27].total_2020 - deaths_headlines.loc[12:27].previous_mean).sum()
 472 ```
 473
 474 ```python Collapsed="false"
 475 deaths_headlines.previous_mean.sum()
 476 ```
 477
 478 ```python Collapsed="false"
 479 # excess_death_data = {
 480 #     'start_date': str(eng_xls.loc[12, 'Week ended']),
 481 #     'end_date': str(eng_xls.loc[deaths_headlines_e.total_2020.dropna().last_valid_index(), 'Week ended']),
 482 #     'excess_deaths': (deaths_headlines.loc[12:].total_2020 - deaths_headlines.loc[12:].previous_mean).sum()
 483 # }
 484
 485 # with open('excess_deaths.json', 'w') as f:
 486 #     json.dump(excess_death_data, f)
 487 ```
 488
 489 ```python Collapsed="false"
 490 # excess_death_data = {
 491 #     'start_date': str(eng_xls.loc[12, 'Week ended']),
 492 #     'end_date': str(eng_xls.loc[27, 'Week ended']),
 493 #     'excess_deaths': (deaths_headlines.loc[12:27].total_2020 - deaths_headlines.loc[12:27].previous_mean).sum()
 494 # }
 495
 496 # with open('excess_deaths.json', 'w') as f:
 497 #     json.dump(excess_death_data, f)
 498 ```
 499
 500 ```python Collapsed="false"
 501 # excess_death_data = {
 502 #     'start_date': str(raw_data_2020.loc[12].droplevel(1)['Week ended']),
 503 #     'end_date': str(raw_data_2020.iloc[-1].droplevel(1)['Week ended']),
 504 #     'excess_deaths': (deaths_headlines.loc[12:].total_2020 - deaths_headlines.loc[12:].previous_mean).sum()
 505 # }
 506
 507 # with open('excess_deaths.json', 'w') as f:
 508 #     json.dump(excess_death_data, f)
 509 ```
 510
 511 ```python Collapsed="false"
 512 eng_xls['Week ended']
 513 ```
 514
 515 ```python Collapsed="false"
 516 # raw_data_2020.droplevel(1, axis='columns')['Week ended']
 517 ```
 518
 519 ```python Collapsed="false"
 520 deaths_by_week = deaths_headlines.merge(eng_xls['Week ended'], left_index=True, right_index=True)
 521 deaths_by_week.rename(columns={'Week ended': 'week_ended'}, inplace=True)
 522 deaths_by_week.to_csv('deaths_by_week.csv', header=True, index=False)
 523 ```
 524
 525 ```python Collapsed="false"
 526 # deaths_by_week = deaths_headlines.merge(raw_data_2020.droplevel(1, axis='columns')['Week ended'], left_index=True, right_index=True)
 527 # deaths_by_week.rename(columns={'Week ended': 'week_ended'}, inplace=True)
 528 # deaths_by_week.to_csv('deaths_by_week.csv', header=True, index=False)
 529 ```
 530
 531 <!-- #region Collapsed="false" -->
 532 # Plots for UK nations
 533 <!-- #endregion -->
 534
 535 ```python Collapsed="false"
 536 # Radar plot code taken from example at https://stackoverflow.com/questions/42878485/getting-matplotlib-radar-plot-with-pandas#
 537
 538 fig = plt.figure(figsize=(10, 10))
 539 ax = fig.add_subplot(111, projection="polar")
 540
 541 theta = np.roll(
 542     np.flip(
 543         np.arange(len(deaths_headlines_e))/float(len(deaths_headlines_e))*2.*np.pi),
 544     14)
 545 l15, = ax.plot(theta, deaths_headlines_e['total_2015'], color="#e47d7d", label="2015") # 0
 546 l16, = ax.plot(theta, deaths_headlines_e['total_2016'], color="#afc169", label="2016") # 72 , d0e47d
 547 l17, = ax.plot(theta, deaths_headlines_e['total_2017'], color="#7de4a6", label="2017") # 144
 548 l18, = ax.plot(theta, deaths_headlines_e['total_2018'], color="#7da6e4", label="2018") # 216
 549 l19, = ax.plot(theta, deaths_headlines_e['total_2019'], color="#d07de4", label="2019") # 288
 550
 551 lmean, = ax.plot(theta, deaths_headlines_e['previous_mean'], color="black", linestyle='dashed', label="mean")
 552
 553 l20, = ax.plot(theta, deaths_headlines_e['total_2020'], color="red", label="2020")
 554
 555 # deaths_headlines.total_2019.plot(ax=ax)
 556
 557 def _closeline(line):
 558     x, y = line.get_data()
 559     x = np.concatenate((x, [x[0]]))
 560     y = np.concatenate((y, [y[0]]))
 561     line.set_data(x, y)
 562
 563 [_closeline(l) for l in [l19, l18, l17, l16, l15, lmean]]
 564
 565
 566 ax.set_xticks(theta)
 567 ax.set_xticklabels(deaths_headlines_e.index)
 568 plt.legend()
 569 plt.title("Deaths by week over years, England")
 570 plt.savefig('deaths-radar_england.png')
 571 plt.show()
 572 ```
 573
 574 ```python Collapsed="false"
 575 # Radar plot code taken from example at https://stackoverflow.com/questions/42878485/getting-matplotlib-radar-plot-with-pandas#
 576
 577 fig = plt.figure(figsize=(10, 10))
 578 ax = fig.add_subplot(111, projection="polar")
 579
 580 theta = np.roll(
 581     np.flip(
 582         np.arange(len(deaths_headlines_w))/float(len(deaths_headlines_w))*2.*np.pi),
 583     14)
 584 l15, = ax.plot(theta, deaths_headlines_w['total_2015'], color="#e47d7d", label="2015") # 0
 585 l16, = ax.plot(theta, deaths_headlines_w['total_2016'], color="#afc169", label="2016") # 72 , d0e47d
 586 l17, = ax.plot(theta, deaths_headlines_w['total_2017'], color="#7de4a6", label="2017") # 144
 587 l18, = ax.plot(theta, deaths_headlines_w['total_2018'], color="#7da6e4", label="2018") # 216
 588 l19, = ax.plot(theta, deaths_headlines_w['total_2019'], color="#d07de4", label="2019") # 288
 589
 590 lmean, = ax.plot(theta, deaths_headlines_w['previous_mean'], color="black", linestyle='dashed', label="mean")
 591
 592 l20, = ax.plot(theta, deaths_headlines_w['total_2020'], color="red", label="2020")
 593
 594
 595 def _closeline(line):
 596     x, y = line.get_data()
 597     x = np.concatenate((x, [x[0]]))
 598     y = np.concatenate((y, [y[0]]))
 599     line.set_data(x, y)
 600
 601 [_closeline(l) for l in [l19, l18, l17, l16, l15, lmean]]
 602
 603
 604 ax.set_xticks(theta)
 605 ax.set_xticklabels(deaths_headlines_w.index)
 606 plt.legend()
 607 plt.title("Deaths by week over years, Wales")
 608 plt.savefig('deaths-radar_wales.png')
 609 plt.show()
 610 ```
 611
 612 ```python Collapsed="false"
 613 # Radar plot code taken from example at https://stackoverflow.com/questions/42878485/getting-matplotlib-radar-plot-with-pandas#
 614
 615 fig = plt.figure(figsize=(10, 10))
 616 ax = fig.add_subplot(111, projection="polar")
 617
 618 theta = np.roll(
 619     np.flip(
 620         np.arange(len(deaths_headlines_s))/float(len(deaths_headlines_s))*2.*np.pi),
 621     14)
 622 l15, = ax.plot(theta, deaths_headlines_s['total_2015'], color="#e47d7d", label="2015") # 0
 623 l16, = ax.plot(theta, deaths_headlines_s['total_2016'], color="#afc169", label="2016") # 72 , d0e47d
 624 l17, = ax.plot(theta, deaths_headlines_s['total_2017'], color="#7de4a6", label="2017") # 144
 625 l18, = ax.plot(theta, deaths_headlines_s['total_2018'], color="#7da6e4", label="2018") # 216
 626 l19, = ax.plot(theta, deaths_headlines_s['total_2019'], color="#d07de4", label="2019") # 288
 627
 628 lmean, = ax.plot(theta, deaths_headlines_s['previous_mean'], color="black", linestyle='dashed', label="mean")
 629
 630 l20, = ax.plot(theta, deaths_headlines_s['total_2020'], color="red", label="2020")
 631
 632
 633 def _closeline(line):
 634     x, y = line.get_data()
 635     x = np.concatenate((x, [x[0]]))
 636     y = np.concatenate((y, [y[0]]))
 637     line.set_data(x, y)
 638
 639 [_closeline(l) for l in [l19, l18, l17, l16, l15, lmean]]
 640
 641
 642 ax.set_xticks(theta)
 643 ax.set_xticklabels(deaths_headlines_s.index)
 644 plt.legend()
 645 plt.title("Deaths by week over years, Scotland")
 646 plt.savefig('deaths-radar_scotland.png')
 647 plt.show()
 648 ```
 649
 650 ```python Collapsed="false"
 651 # Radar plot code taken from example at https://stackoverflow.com/questions/42878485/getting-matplotlib-radar-plot-with-pandas#
 652
 653 fig = plt.figure(figsize=(10, 10))
 654 ax = fig.add_subplot(111, projection="polar")
 655
 656 theta = np.roll(
 657     np.flip(
 658         np.arange(len(deaths_headlines_i))/float(len(deaths_headlines_i))*2.*np.pi),
 659     14)
 660 l15, = ax.plot(theta, deaths_headlines_i['total_2015'], color="#e47d7d", label="2015") # 0
 661 l16, = ax.plot(theta, deaths_headlines_i['total_2016'], color="#afc169", label="2016") # 72 , d0e47d
 662 l17, = ax.plot(theta, deaths_headlines_i['total_2017'], color="#7de4a6", label="2017") # 144
 663 l18, = ax.plot(theta, deaths_headlines_i['total_2018'], color="#7da6e4", label="2018") # 216
 664 l19, = ax.plot(theta, deaths_headlines_i['total_2019'], color="#d07de4", label="2019") # 288
 665
 666 lmean, = ax.plot(theta, deaths_headlines_i['previous_mean'], color="black", linestyle='dashed', label="mean")
 667
 668 l20, = ax.plot(theta, deaths_headlines_i['total_2020'], color="red", label="2020")
 669
 670
 671 def _closeline(line):
 672     x, y = line.get_data()
 673     x = np.concatenate((x, [x[0]]))
 674     y = np.concatenate((y, [y[0]]))
 675     line.set_data(x, y)
 676
 677 [_closeline(l) for l in [l19, l18, l17, l16, l15, lmean]]
 678
 679
 680 ax.set_xticks(theta)
 681 ax.set_xticklabels(deaths_headlines_i.index)
 682 plt.legend()
 683 plt.title("Deaths by week over years, Northern Ireland")
 684 plt.savefig('deaths-radar_northern_ireland.png')
 685 plt.show()
 686 ```
 687
 688 ```python Collapsed="false"
 689 # list(raw_data_2020.columns)
 690 ```
 691
 692 ```python Collapsed="false"
 693 # deaths_headlines_e = raw_data_2020.iloc[:, [1]].copy()
 694 # deaths_headlines_e.columns = ['total_2020']
 695 # deaths_headlines_w = raw_data_2020['W92000004'].copy()
 696 # deaths_headlines_e.columns = ['total_2020']
 697 # deaths_headlines_w.columns = ['total_2020']
 698 # deaths_headlines_e.total_2020 -= deaths_headlines_w.total_2020
 699 # deaths_headlines_e.head()
 700 # deaths_headlines_e
 701 ```
 702
 703 ```python Collapsed="false"
 704
 705 ```
 706
 707 ```python Collapsed="false"
 708
 709 ```