{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Data from:\n",
"\n",
"* [Office of National Statistics](https://www.ons.gov.uk/peoplepopulationandcommunity/birthsdeathsandmarriages/deaths/datasets/weeklyprovisionalfiguresondeathsregisteredinenglandandwales) (Endland and Wales) Weeks start on a Saturday.\n",
"* [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.\n",
"* [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.\n"
]
},
{
"cell_type": "code",
"execution_count": 76,
"metadata": {},
"outputs": [],
"source": [
"import itertools\n",
"import collections\n",
"import json\n",
"import pandas as pd\n",
"import numpy as np\n",
"from scipy.stats import gmean\n",
"\n",
"import matplotlib as mpl\n",
"import matplotlib.pyplot as plt\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": 77,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" covid-deaths-data-scotland-week-21.xlsx\n",
" covid-deaths-data-scotland-week-31.xlsx\n",
" covid-deaths-data-week-23.xlsx\n",
" covid-deaths-data-week-24-scotland.xlsx\n",
" covid-deaths-data-week-25-scotland.xlsx\n",
" covid-deaths-data-week-27-scotland.xlsx\n",
" covid-deaths-data-week-28-scotland.xlsx\n",
" covid-deaths-data-week-32.xlsx\n",
" publishedweek1620201.xlsx\n",
" publishedweek172020.csv\n",
" publishedweek172020.ods\n",
" publishedweek172020.xlsx\n",
" publishedweek182020.csv\n",
" publishedweek182020.ods\n",
" publishedweek182020.xlsx\n",
" publishedweek192020.csv\n",
" publishedweek192020.ods\n",
" publishedweek192020.xlsx\n",
" publishedweek2015.csv\n",
" publishedweek2015.ods\n",
" publishedweek2015.xls\n",
" publishedweek202020.csv\n",
" publishedweek202020.ods\n",
" publishedweek202020.xlsx\n",
" publishedweek212020.csv\n",
" publishedweek212020.ods\n",
" publishedweek212020.xlsx\n",
" publishedweek222020.csv\n",
" publishedweek222020.xlsx\n",
" publishedweek232020.csv\n",
" publishedweek232020.xlsx\n",
" publishedweek242020.csv\n",
" publishedweek242020.xlsx\n",
" publishedweek252020.csv\n",
" publishedweek252020.xlsx\n",
" publishedweek262020.csv\n",
" publishedweek262020.xlsx\n",
" publishedweek272020.csv\n",
" publishedweek272020.xlsx\n",
" publishedweek282020.xlsx\n",
" publishedweek292020.xlsx\n",
" publishedweek302020.xlsx\n",
" publishedweek312020.xlsx\n",
" publishedweek522016.csv\n",
" publishedweek522016.ods\n",
" publishedweek522016.xls\n",
" publishedweek522017.csv\n",
" publishedweek522017.ods\n",
" publishedweek522017.xls\n",
" publishedweek522018.csv\n",
" publishedweek522018.ods\n",
" publishedweek522018withupdatedrespiratoryrow.xls\n",
" publishedweek522019.csv\n",
" publishedweek522019.ods\n",
" publishedweek522019.xls\n",
" scotland-deaths-2020.csv\n",
" weekly-april-20-tab2_Sheet.csv\n",
" weekly-april-20-tab2.xlsx\n",
" weekly-deaths-april-20-scotland.csv\n",
" weekly-deaths-april-20-scotland.xlsx\n",
" weekly-deaths-april-20-scotland.zip\n",
"'Weekly_Deaths - Historical_NI.xls'\n",
" Weekly_Deaths_NI_2015.csv\n",
" Weekly_Deaths_NI_2016.csv\n",
" Weekly_Deaths_NI_2017.csv\n",
" Weekly_Deaths_NI_2018.csv\n",
" Weekly_Deaths_NI_2019.csv\n",
" Weekly_Deaths_NI_2020.csv\n",
" Weekly_Deaths_NI_2020.xls\n",
" weekly-march-20-scotland.zip\n"
]
}
],
"source": [
"!ls uk-deaths-data"
]
},
{
"cell_type": "code",
"execution_count": 78,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2015 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2015.csv', \n",
" parse_dates=[1, 2], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1]\n",
" )\n",
"dh15i = raw_data_2015.iloc[:, [2]]\n",
"dh15i.columns = ['total_2015']\n",
"# dh15i.head()"
]
},
{
"cell_type": "code",
"execution_count": 79,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2016 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2016.csv', \n",
" parse_dates=[1, 2], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1]\n",
" )\n",
"dh16i = raw_data_2016.iloc[:, [2]]\n",
"dh16i.columns = ['total_2016']\n",
"# dh16i.head()"
]
},
{
"cell_type": "code",
"execution_count": 80,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2017 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2017.csv', \n",
" parse_dates=[1, 2], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1]\n",
" )\n",
"dh17i = raw_data_2017.iloc[:, [2]]\n",
"dh17i.columns = ['total_2017']\n",
"# dh17i.head()"
]
},
{
"cell_type": "code",
"execution_count": 81,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2018 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2018.csv', \n",
" parse_dates=[1, 2], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1]\n",
" )\n",
"dh18i = raw_data_2018.iloc[:, [2]]\n",
"dh18i.columns = ['total_2018']\n",
"# dh18i.head()"
]
},
{
"cell_type": "code",
"execution_count": 82,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2019 = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2019.csv', \n",
" parse_dates=[1, 2], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1]\n",
" )\n",
"dh19i = raw_data_2019.iloc[:, [2]]\n",
"dh19i.columns = ['total_2019']\n",
"# dh19i.head()"
]
},
{
"cell_type": "code",
"execution_count": 83,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"
\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 353 | \n",
"
\n",
" \n",
" 2 | \n",
" 395 | \n",
"
\n",
" \n",
" 3 | \n",
" 411 | \n",
"
\n",
" \n",
" 4 | \n",
" 347 | \n",
"
\n",
" \n",
" 5 | \n",
" 323 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020\n",
"1 353\n",
"2 395\n",
"3 411\n",
"4 347\n",
"5 323"
]
},
"execution_count": 83,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"raw_data_2020_i = pd.read_csv('uk-deaths-data/Weekly_Deaths_NI_2020.csv', \n",
" parse_dates=[1], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1]\n",
" )\n",
"deaths_headlines_i = raw_data_2020_i.iloc[:, [1]]\n",
"deaths_headlines_i.columns = ['total_2020']\n",
"deaths_headlines_i.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 84,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"raw_data_s = pd.read_csv('uk-deaths-data/weekly-deaths-april-20-scotland.csv', \n",
" index_col=0,\n",
" header=0,\n",
" skiprows=2\n",
" )\n",
"# raw_data_s"
]
},
{
"cell_type": "code",
"execution_count": 85,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
" total_2019 | \n",
" total_2018 | \n",
" total_2017 | \n",
" total_2016 | \n",
" total_2015 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 1161.0 | \n",
" 1104.0 | \n",
" 1531.0 | \n",
" 1205.0 | \n",
" 1394.0 | \n",
" 1146 | \n",
"
\n",
" \n",
" 2 | \n",
" 1567.0 | \n",
" 1507.0 | \n",
" 1899.0 | \n",
" 1379.0 | \n",
" 1305.0 | \n",
" 1708 | \n",
"
\n",
" \n",
" 3 | \n",
" 1322.0 | \n",
" 1353.0 | \n",
" 1629.0 | \n",
" 1224.0 | \n",
" 1215.0 | \n",
" 1489 | \n",
"
\n",
" \n",
" 4 | \n",
" 1226.0 | \n",
" 1208.0 | \n",
" 1610.0 | \n",
" 1197.0 | \n",
" 1187.0 | \n",
" 1381 | \n",
"
\n",
" \n",
" 5 | \n",
" 1188.0 | \n",
" 1206.0 | \n",
" 1369.0 | \n",
" 1332.0 | \n",
" 1205.0 | \n",
" 1286 | \n",
"
\n",
" \n",
" 6 | \n",
" 1216.0 | \n",
" 1243.0 | \n",
" 1265.0 | \n",
" 1200.0 | \n",
" 1217.0 | \n",
" 1344 | \n",
"
\n",
" \n",
" 7 | \n",
" 1162.0 | \n",
" 1181.0 | \n",
" 1315.0 | \n",
" 1231.0 | \n",
" 1209.0 | \n",
" 1360 | \n",
"
\n",
" \n",
" 8 | \n",
" 1162.0 | \n",
" 1245.0 | \n",
" 1245.0 | \n",
" 1185.0 | \n",
" 1239.0 | \n",
" 1320 | \n",
"
\n",
" \n",
" 9 | \n",
" 1171.0 | \n",
" 1125.0 | \n",
" 1022.0 | \n",
" 1219.0 | \n",
" 1150.0 | \n",
" 1308 | \n",
"
\n",
" \n",
" 10 | \n",
" 1208.0 | \n",
" 1156.0 | \n",
" 1475.0 | \n",
" 1146.0 | \n",
" 1174.0 | \n",
" 1192 | \n",
"
\n",
" \n",
" 11 | \n",
" 1156.0 | \n",
" 1108.0 | \n",
" 1220.0 | \n",
" 1141.0 | \n",
" 1175.0 | \n",
" 1201 | \n",
"
\n",
" \n",
" 12 | \n",
" 1196.0 | \n",
" 1101.0 | \n",
" 1158.0 | \n",
" 1152.0 | \n",
" 1042.0 | \n",
" 1149 | \n",
"
\n",
" \n",
" 13 | \n",
" 1079.0 | \n",
" 1086.0 | \n",
" 1050.0 | \n",
" 1112.0 | \n",
" 1172.0 | \n",
" 1171 | \n",
"
\n",
" \n",
" 14 | \n",
" 1744.0 | \n",
" 1032.0 | \n",
" 1192.0 | \n",
" 1060.0 | \n",
" 1166.0 | \n",
" 1042 | \n",
"
\n",
" \n",
" 15 | \n",
" 1978.0 | \n",
" 1069.0 | \n",
" 1192.0 | \n",
" 998.0 | \n",
" 1048.0 | \n",
" 1192 | \n",
"
\n",
" \n",
" 16 | \n",
" 1916.0 | \n",
" 902.0 | \n",
" 1136.0 | \n",
" 1111.0 | \n",
" 1092.0 | \n",
" 1095 | \n",
"
\n",
" \n",
" 17 | \n",
" 1836.0 | \n",
" 1121.0 | \n",
" 1008.0 | \n",
" 1121.0 | \n",
" 1076.0 | \n",
" 1108 | \n",
"
\n",
" \n",
" 18 | \n",
" 1679.0 | \n",
" 1131.0 | \n",
" 1093.0 | \n",
" 1050.0 | \n",
" 1006.0 | \n",
" 1117 | \n",
"
\n",
" \n",
" 19 | \n",
" 1435.0 | \n",
" 1018.0 | \n",
" 967.0 | \n",
" 1119.0 | \n",
" 1047.0 | \n",
" 1020 | \n",
"
\n",
" \n",
" 20 | \n",
" 1421.0 | \n",
" 1115.0 | \n",
" 977.0 | \n",
" 1115.0 | \n",
" 1010.0 | \n",
" 1103 | \n",
"
\n",
" \n",
" 21 | \n",
" 1226.0 | \n",
" 1061.0 | \n",
" 1070.0 | \n",
" 1063.0 | \n",
" 994.0 | \n",
" 1039 | \n",
"
\n",
" \n",
" 22 | \n",
" 1125.0 | \n",
" 1029.0 | \n",
" 998.0 | \n",
" 1015.0 | \n",
" 999.0 | \n",
" 1043 | \n",
"
\n",
" \n",
" 23 | \n",
" 1093.0 | \n",
" 1042.0 | \n",
" 1033.0 | \n",
" 1076.0 | \n",
" 1023.0 | \n",
" 1106 | \n",
"
\n",
" \n",
" 24 | \n",
" 1034.0 | \n",
" 1028.0 | \n",
" 915.0 | \n",
" 1031.0 | \n",
" 988.0 | \n",
" 1038 | \n",
"
\n",
" \n",
" 25 | \n",
" 1065.0 | \n",
" 1053.0 | \n",
" 993.0 | \n",
" 1032.0 | \n",
" 994.0 | \n",
" 1025 | \n",
"
\n",
" \n",
" 26 | \n",
" 1008.0 | \n",
" 1051.0 | \n",
" 1046.0 | \n",
" 994.0 | \n",
" 1007.0 | \n",
" 1032 | \n",
"
\n",
" \n",
" 27 | \n",
" 983.0 | \n",
" 981.0 | \n",
" 1041.0 | \n",
" 1040.0 | \n",
" 988.0 | \n",
" 1040 | \n",
"
\n",
" \n",
" 28 | \n",
" 976.0 | \n",
" 1077.0 | \n",
" 1002.0 | \n",
" 1014.0 | \n",
" 1022.0 | \n",
" 1011 | \n",
"
\n",
" \n",
" 29 | \n",
" 1033.0 | \n",
" 964.0 | \n",
" 928.0 | \n",
" 1025.0 | \n",
" 1041.0 | \n",
" 1023 | \n",
"
\n",
" \n",
" 30 | \n",
" 961.0 | \n",
" 1041.0 | \n",
" 933.0 | \n",
" 978.0 | \n",
" 979.0 | \n",
" 956 | \n",
"
\n",
" \n",
" 31 | \n",
" 1043.0 | \n",
" 1020.0 | \n",
" 969.0 | \n",
" 1011.0 | \n",
" 987.0 | \n",
" 985 | \n",
"
\n",
" \n",
" 32 | \n",
" 1002.0 | \n",
" 1018.0 | \n",
" 953.0 | \n",
" 1002.0 | \n",
" 997.0 | \n",
" 1043 | \n",
"
\n",
" \n",
" 33 | \n",
" NaN | \n",
" 1028.0 | \n",
" 978.0 | \n",
" 1004.0 | \n",
" 982.0 | \n",
" 969 | \n",
"
\n",
" \n",
" 34 | \n",
" NaN | \n",
" 1011.0 | \n",
" 941.0 | \n",
" 1045.0 | \n",
" 1017.0 | \n",
" 982 | \n",
"
\n",
" \n",
" 35 | \n",
" NaN | \n",
" 1013.0 | \n",
" 930.0 | \n",
" 980.0 | \n",
" 1039.0 | \n",
" 954 | \n",
"
\n",
" \n",
" 36 | \n",
" NaN | \n",
" 980.0 | \n",
" 970.0 | \n",
" 1006.0 | \n",
" 1007.0 | \n",
" 977 | \n",
"
\n",
" \n",
" 37 | \n",
" NaN | \n",
" 1074.0 | \n",
" 1020.0 | \n",
" 972.0 | \n",
" 983.0 | \n",
" 991 | \n",
"
\n",
" \n",
" 38 | \n",
" NaN | \n",
" 1071.0 | \n",
" 946.0 | \n",
" 1049.0 | \n",
" 966.0 | \n",
" 1001 | \n",
"
\n",
" \n",
" 39 | \n",
" NaN | \n",
" 1142.0 | \n",
" 1015.0 | \n",
" 1056.0 | \n",
" 1009.0 | \n",
" 1010 | \n",
"
\n",
" \n",
" 40 | \n",
" NaN | \n",
" 1051.0 | \n",
" 1042.0 | \n",
" 1016.0 | \n",
" 1072.0 | \n",
" 1008 | \n",
"
\n",
" \n",
" 41 | \n",
" NaN | \n",
" 1143.0 | \n",
" 1081.0 | \n",
" 1133.0 | \n",
" 1009.0 | \n",
" 1028 | \n",
"
\n",
" \n",
" 42 | \n",
" NaN | \n",
" 1153.0 | \n",
" 1031.0 | \n",
" 1067.0 | \n",
" 1070.0 | \n",
" 989 | \n",
"
\n",
" \n",
" 43 | \n",
" NaN | \n",
" 1115.0 | \n",
" 1019.0 | \n",
" 1095.0 | \n",
" 1052.0 | \n",
" 981 | \n",
"
\n",
" \n",
" 44 | \n",
" NaN | \n",
" 1101.0 | \n",
" 1085.0 | \n",
" 1062.0 | \n",
" 1032.0 | \n",
" 1116 | \n",
"
\n",
" \n",
" 45 | \n",
" NaN | \n",
" 1184.0 | \n",
" 1144.0 | \n",
" 1126.0 | \n",
" 1043.0 | \n",
" 1028 | \n",
"
\n",
" \n",
" 46 | \n",
" NaN | \n",
" 1160.0 | \n",
" 1084.0 | \n",
" 1175.0 | \n",
" 1174.0 | \n",
" 1103 | \n",
"
\n",
" \n",
" 47 | \n",
" NaN | \n",
" 1229.0 | \n",
" 1058.0 | \n",
" 1178.0 | \n",
" 1132.0 | \n",
" 1054 | \n",
"
\n",
" \n",
" 48 | \n",
" NaN | \n",
" 1163.0 | \n",
" 1062.0 | \n",
" 1153.0 | \n",
" 1159.0 | \n",
" 1115 | \n",
"
\n",
" \n",
" 49 | \n",
" NaN | \n",
" 1108.0 | \n",
" 1076.0 | \n",
" 1237.0 | \n",
" 1188.0 | \n",
" 1089 | \n",
"
\n",
" \n",
" 50 | \n",
" NaN | \n",
" 1312.0 | \n",
" 1212.0 | \n",
" 1335.0 | \n",
" 1219.0 | \n",
" 1101 | \n",
"
\n",
" \n",
" 51 | \n",
" NaN | \n",
" 1277.0 | \n",
" 1216.0 | \n",
" 1437.0 | \n",
" 1284.0 | \n",
" 1146 | \n",
"
\n",
" \n",
" 52 | \n",
" NaN | \n",
" 1000.0 | \n",
" 1058.0 | \n",
" 1168.0 | \n",
" 1133.0 | \n",
" 944 | \n",
"
\n",
" \n",
" 53 | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" 1018 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020 total_2019 total_2018 total_2017 total_2016 total_2015\n",
"1 1161.0 1104.0 1531.0 1205.0 1394.0 1146\n",
"2 1567.0 1507.0 1899.0 1379.0 1305.0 1708\n",
"3 1322.0 1353.0 1629.0 1224.0 1215.0 1489\n",
"4 1226.0 1208.0 1610.0 1197.0 1187.0 1381\n",
"5 1188.0 1206.0 1369.0 1332.0 1205.0 1286\n",
"6 1216.0 1243.0 1265.0 1200.0 1217.0 1344\n",
"7 1162.0 1181.0 1315.0 1231.0 1209.0 1360\n",
"8 1162.0 1245.0 1245.0 1185.0 1239.0 1320\n",
"9 1171.0 1125.0 1022.0 1219.0 1150.0 1308\n",
"10 1208.0 1156.0 1475.0 1146.0 1174.0 1192\n",
"11 1156.0 1108.0 1220.0 1141.0 1175.0 1201\n",
"12 1196.0 1101.0 1158.0 1152.0 1042.0 1149\n",
"13 1079.0 1086.0 1050.0 1112.0 1172.0 1171\n",
"14 1744.0 1032.0 1192.0 1060.0 1166.0 1042\n",
"15 1978.0 1069.0 1192.0 998.0 1048.0 1192\n",
"16 1916.0 902.0 1136.0 1111.0 1092.0 1095\n",
"17 1836.0 1121.0 1008.0 1121.0 1076.0 1108\n",
"18 1679.0 1131.0 1093.0 1050.0 1006.0 1117\n",
"19 1435.0 1018.0 967.0 1119.0 1047.0 1020\n",
"20 1421.0 1115.0 977.0 1115.0 1010.0 1103\n",
"21 1226.0 1061.0 1070.0 1063.0 994.0 1039\n",
"22 1125.0 1029.0 998.0 1015.0 999.0 1043\n",
"23 1093.0 1042.0 1033.0 1076.0 1023.0 1106\n",
"24 1034.0 1028.0 915.0 1031.0 988.0 1038\n",
"25 1065.0 1053.0 993.0 1032.0 994.0 1025\n",
"26 1008.0 1051.0 1046.0 994.0 1007.0 1032\n",
"27 983.0 981.0 1041.0 1040.0 988.0 1040\n",
"28 976.0 1077.0 1002.0 1014.0 1022.0 1011\n",
"29 1033.0 964.0 928.0 1025.0 1041.0 1023\n",
"30 961.0 1041.0 933.0 978.0 979.0 956\n",
"31 1043.0 1020.0 969.0 1011.0 987.0 985\n",
"32 1002.0 1018.0 953.0 1002.0 997.0 1043\n",
"33 NaN 1028.0 978.0 1004.0 982.0 969\n",
"34 NaN 1011.0 941.0 1045.0 1017.0 982\n",
"35 NaN 1013.0 930.0 980.0 1039.0 954\n",
"36 NaN 980.0 970.0 1006.0 1007.0 977\n",
"37 NaN 1074.0 1020.0 972.0 983.0 991\n",
"38 NaN 1071.0 946.0 1049.0 966.0 1001\n",
"39 NaN 1142.0 1015.0 1056.0 1009.0 1010\n",
"40 NaN 1051.0 1042.0 1016.0 1072.0 1008\n",
"41 NaN 1143.0 1081.0 1133.0 1009.0 1028\n",
"42 NaN 1153.0 1031.0 1067.0 1070.0 989\n",
"43 NaN 1115.0 1019.0 1095.0 1052.0 981\n",
"44 NaN 1101.0 1085.0 1062.0 1032.0 1116\n",
"45 NaN 1184.0 1144.0 1126.0 1043.0 1028\n",
"46 NaN 1160.0 1084.0 1175.0 1174.0 1103\n",
"47 NaN 1229.0 1058.0 1178.0 1132.0 1054\n",
"48 NaN 1163.0 1062.0 1153.0 1159.0 1115\n",
"49 NaN 1108.0 1076.0 1237.0 1188.0 1089\n",
"50 NaN 1312.0 1212.0 1335.0 1219.0 1101\n",
"51 NaN 1277.0 1216.0 1437.0 1284.0 1146\n",
"52 NaN 1000.0 1058.0 1168.0 1133.0 944\n",
"53 NaN NaN NaN NaN NaN 1018"
]
},
"execution_count": 85,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"deaths_headlines_s = raw_data_s[reversed('2015 2016 2017 2018 2019 2020'.split())]\n",
"deaths_headlines_s.columns = ['total_' + c for c in deaths_headlines_s.columns]\n",
"deaths_headlines_s.reset_index(drop=True, inplace=True)\n",
"deaths_headlines_s.index = deaths_headlines_s.index + 1\n",
"deaths_headlines_s"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 86,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" NaN | \n",
" ... | \n",
" North East | \n",
" North West | \n",
" Yorkshire and The Humber | \n",
" East Midlands | \n",
" West Midlands | \n",
" East | \n",
" London | \n",
" South East | \n",
" South West | \n",
" Wales | \n",
"
\n",
" \n",
" \n",
" \n",
" Week number | \n",
" Week ended | \n",
" NaT | \n",
" NaT | \n",
" Total deaths, all ages | \n",
" Total deaths: average of corresponding | \n",
" week over the previous 5 years 1 (England and ... | \n",
" Total deaths: average of corresponding | \n",
" week over the previous 5 years 1 (England) | \n",
" Total deaths: average of corresponding | \n",
" week over the previous 5 years 1 (Wales) | \n",
" ... | \n",
" E12000001 | \n",
" E12000002 | \n",
" E12000003 | \n",
" E12000004 | \n",
" E12000005 | \n",
" E12000006 | \n",
" E12000007 | \n",
" E12000008 | \n",
" E12000009 | \n",
" W92000004 | \n",
"
\n",
" \n",
" 1 | \n",
" 2020-01-03 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 12254 | \n",
" NaN | \n",
" 12175 | \n",
" NaN | \n",
" 11412 | \n",
" NaN | \n",
" 756 | \n",
" ... | \n",
" 673 | \n",
" 1806 | \n",
" 1240 | \n",
" 1060 | \n",
" 1349 | \n",
" 1162 | \n",
" 1113 | \n",
" 1814 | \n",
" 1225 | \n",
" 787 | \n",
"
\n",
" \n",
" 2 | \n",
" 2020-01-10 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 14058 | \n",
" NaN | \n",
" 13822 | \n",
" NaN | \n",
" 12933 | \n",
" NaN | \n",
" 856 | \n",
" ... | \n",
" 707 | \n",
" 1932 | \n",
" 1339 | \n",
" 1195 | \n",
" 1450 | \n",
" 1573 | \n",
" 1272 | \n",
" 2132 | \n",
" 1487 | \n",
" 939 | \n",
"
\n",
" \n",
" 3 | \n",
" 2020-01-17 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 12990 | \n",
" NaN | \n",
" 13216 | \n",
" NaN | \n",
" 12370 | \n",
" NaN | \n",
" 812 | \n",
" ... | \n",
" 647 | \n",
" 1696 | \n",
" 1278 | \n",
" 1106 | \n",
" 1407 | \n",
" 1457 | \n",
" 1073 | \n",
" 2064 | \n",
" 1466 | \n",
" 767 | \n",
"
\n",
" \n",
" 4 | \n",
" 2020-01-24 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 11856 | \n",
" NaN | \n",
" 12760 | \n",
" NaN | \n",
" 11933 | \n",
" NaN | \n",
" 802 | \n",
" ... | \n",
" 612 | \n",
" 1529 | \n",
" 1187 | \n",
" 1024 | \n",
" 1231 | \n",
" 1410 | \n",
" 1028 | \n",
" 1833 | \n",
" 1253 | \n",
" 723 | \n",
"
\n",
" \n",
" 5 | \n",
" 2020-01-31 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 11612 | \n",
" NaN | \n",
" 12206 | \n",
" NaN | \n",
" 11419 | \n",
" NaN | \n",
" 760 | \n",
" ... | \n",
" 561 | \n",
" 1461 | \n",
" 1136 | \n",
" 1015 | \n",
" 1262 | \n",
" 1286 | \n",
" 1092 | \n",
" 1820 | \n",
" 1233 | \n",
" 727 | \n",
"
\n",
" \n",
" 6 | \n",
" 2020-02-07 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 10986 | \n",
" NaN | \n",
" 11925 | \n",
" NaN | \n",
" 11154 | \n",
" NaN | \n",
" 729 | \n",
" ... | \n",
" 564 | \n",
" 1529 | \n",
" 1072 | \n",
" 922 | \n",
" 1052 | \n",
" 1259 | \n",
" 987 | \n",
" 1729 | \n",
" 1157 | \n",
" 690 | \n",
"
\n",
" \n",
" 7 | \n",
" 2020-02-14 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 10944 | \n",
" NaN | \n",
" 11627 | \n",
" NaN | \n",
" 10876 | \n",
" NaN | \n",
" 722 | \n",
" ... | \n",
" 573 | \n",
" 1427 | \n",
" 1059 | \n",
" 976 | \n",
" 1159 | \n",
" 1172 | \n",
" 967 | \n",
" 1688 | \n",
" 1169 | \n",
" 728 | \n",
"
\n",
" \n",
" 8 | \n",
" 2020-02-21 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 10841 | \n",
" NaN | \n",
" 11548 | \n",
" NaN | \n",
" 10790 | \n",
" NaN | \n",
" 724 | \n",
" ... | \n",
" 539 | \n",
" 1477 | \n",
" 1087 | \n",
" 924 | \n",
" 1116 | \n",
" 1167 | \n",
" 1032 | \n",
" 1675 | \n",
" 1118 | \n",
" 679 | \n",
"
\n",
" \n",
" 9 | \n",
" 2020-02-28 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 10816 | \n",
" NaN | \n",
" 11183 | \n",
" NaN | \n",
" 10448 | \n",
" NaN | \n",
" 698 | \n",
" ... | \n",
" 572 | \n",
" 1476 | \n",
" 1078 | \n",
" 919 | \n",
" 1174 | \n",
" 1115 | \n",
" 1085 | \n",
" 1587 | \n",
" 1133 | \n",
" 651 | \n",
"
\n",
" \n",
" 10 | \n",
" 2020-03-06 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 10895 | \n",
" NaN | \n",
" 11498 | \n",
" NaN | \n",
" 10745 | \n",
" NaN | \n",
" 720 | \n",
" ... | \n",
" 568 | \n",
" 1490 | \n",
" 1112 | \n",
" 930 | \n",
" 1098 | \n",
" 1149 | \n",
" 982 | \n",
" 1726 | \n",
" 1170 | \n",
" 652 | \n",
"
\n",
" \n",
" 11 | \n",
" 2020-03-13 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 11019 | \n",
" NaN | \n",
" 11205 | \n",
" NaN | \n",
" 10447 | \n",
" NaN | \n",
" 727 | \n",
" ... | \n",
" 590 | \n",
" 1472 | \n",
" 1053 | \n",
" 915 | \n",
" 1187 | \n",
" 1211 | \n",
" 964 | \n",
" 1751 | \n",
" 1174 | \n",
" 675 | \n",
"
\n",
" \n",
" 12 | \n",
" 2020-03-20 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 10645 | \n",
" NaN | \n",
" 10573 | \n",
" NaN | \n",
" 9841 | \n",
" NaN | \n",
" 677 | \n",
" ... | \n",
" 522 | \n",
" 1443 | \n",
" 1012 | \n",
" 947 | \n",
" 1115 | \n",
" 1043 | \n",
" 1008 | \n",
" 1657 | \n",
" 1156 | \n",
" 719 | \n",
"
\n",
" \n",
" 13 | \n",
" 2020-03-27 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 11141 | \n",
" NaN | \n",
" 10130 | \n",
" NaN | \n",
" 9414 | \n",
" NaN | \n",
" 665 | \n",
" ... | \n",
" 542 | \n",
" 1538 | \n",
" 982 | \n",
" 922 | \n",
" 1035 | \n",
" 1182 | \n",
" 1297 | \n",
" 1822 | \n",
" 1092 | \n",
" 719 | \n",
"
\n",
" \n",
" 14 | \n",
" 2020-04-03 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 16387 | \n",
" NaN | \n",
" 10305 | \n",
" NaN | \n",
" 9601 | \n",
" NaN | \n",
" 667 | \n",
" ... | \n",
" 770 | \n",
" 2137 | \n",
" 1436 | \n",
" 1246 | \n",
" 1812 | \n",
" 1717 | \n",
" 2511 | \n",
" 2294 | \n",
" 1520 | \n",
" 920 | \n",
"
\n",
" \n",
" 15 | \n",
" 2020-04-10 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 18516 | \n",
" NaN | \n",
" 10520 | \n",
" NaN | \n",
" 9807 | \n",
" NaN | \n",
" 671 | \n",
" ... | \n",
" 849 | \n",
" 2597 | \n",
" 1503 | \n",
" 1452 | \n",
" 2182 | \n",
" 1984 | \n",
" 2832 | \n",
" 2604 | \n",
" 1560 | \n",
" 928 | \n",
"
\n",
" \n",
" 16 | \n",
" 2020-04-17 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 22351 | \n",
" NaN | \n",
" 10497 | \n",
" NaN | \n",
" 9787 | \n",
" NaN | \n",
" 661 | \n",
" ... | \n",
" 1155 | \n",
" 3195 | \n",
" 1960 | \n",
" 1632 | \n",
" 2536 | \n",
" 2466 | \n",
" 3275 | \n",
" 3084 | \n",
" 1854 | \n",
" 1169 | \n",
"
\n",
" \n",
" 17 | \n",
" 2020-04-24 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 21997 | \n",
" NaN | \n",
" 10458 | \n",
" NaN | \n",
" 9768 | \n",
" NaN | \n",
" 662 | \n",
" ... | \n",
" 1103 | \n",
" 3109 | \n",
" 2095 | \n",
" 1711 | \n",
" 2481 | \n",
" 2299 | \n",
" 2785 | \n",
" 3334 | \n",
" 1924 | \n",
" 1124 | \n",
"
\n",
" \n",
" 18 | \n",
" 2020-05-01 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 17953 | \n",
" NaN | \n",
" 9941 | \n",
" NaN | \n",
" 9289 | \n",
" NaN | \n",
" 624 | \n",
" ... | \n",
" 922 | \n",
" 2503 | \n",
" 1844 | \n",
" 1418 | \n",
" 1975 | \n",
" 1982 | \n",
" 1953 | \n",
" 2853 | \n",
" 1554 | \n",
" 929 | \n",
"
\n",
" \n",
" 19 | \n",
" 2020-05-08 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 12657 | \n",
" NaN | \n",
" 9576 | \n",
" NaN | \n",
" 8937 | \n",
" NaN | \n",
" 612 | \n",
" ... | \n",
" 769 | \n",
" 1790 | \n",
" 1328 | \n",
" 1094 | \n",
" 1326 | \n",
" 1321 | \n",
" 1213 | \n",
" 1887 | \n",
" 1218 | \n",
" 692 | \n",
"
\n",
" \n",
" 20 | \n",
" 2020-05-15 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 14573 | \n",
" NaN | \n",
" 10188 | \n",
" NaN | \n",
" 9526 | \n",
" NaN | \n",
" 635 | \n",
" ... | \n",
" 845 | \n",
" 1992 | \n",
" 1589 | \n",
" 1283 | \n",
" 1502 | \n",
" 1543 | \n",
" 1329 | \n",
" 2251 | \n",
" 1449 | \n",
" 772 | \n",
"
\n",
" \n",
" 21 | \n",
" 2020-05-22 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 12288 | \n",
" NaN | \n",
" 9940 | \n",
" NaN | \n",
" 9299 | \n",
" NaN | \n",
" 614 | \n",
" ... | \n",
" 718 | \n",
" 1636 | \n",
" 1236 | \n",
" 1041 | \n",
" 1319 | \n",
" 1397 | \n",
" 1125 | \n",
" 1937 | \n",
" 1177 | \n",
" 692 | \n",
"
\n",
" \n",
" 22 | \n",
" 2020-05-29 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 9824 | \n",
" NaN | \n",
" 8171 | \n",
" NaN | \n",
" 7607 | \n",
" NaN | \n",
" 546 | \n",
" ... | \n",
" 550 | \n",
" 1337 | \n",
" 1046 | \n",
" 863 | \n",
" 970 | \n",
" 1095 | \n",
" 841 | \n",
" 1515 | \n",
" 1011 | \n",
" 587 | \n",
"
\n",
" \n",
" 23 | \n",
" 2020-06-05 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 10709 | \n",
" NaN | \n",
" 9977 | \n",
" NaN | \n",
" 9346 | \n",
" NaN | \n",
" 610 | \n",
" ... | \n",
" 576 | \n",
" 1478 | \n",
" 1090 | \n",
" 931 | \n",
" 1172 | \n",
" 1131 | \n",
" 891 | \n",
" 1610 | \n",
" 1116 | \n",
" 700 | \n",
"
\n",
" \n",
" 24 | \n",
" 2020-06-12 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 9976 | \n",
" NaN | \n",
" 9417 | \n",
" NaN | \n",
" 8803 | \n",
" NaN | \n",
" 588 | \n",
" ... | \n",
" 478 | \n",
" 1374 | \n",
" 980 | \n",
" 967 | \n",
" 1096 | \n",
" 1048 | \n",
" 883 | \n",
" 1530 | \n",
" 1035 | \n",
" 574 | \n",
"
\n",
" \n",
" 25 | \n",
" 2020-06-19 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 9339 | \n",
" NaN | \n",
" 9404 | \n",
" NaN | \n",
" 8810 | \n",
" NaN | \n",
" 573 | \n",
" ... | \n",
" 498 | \n",
" 1234 | \n",
" 952 | \n",
" 835 | \n",
" 973 | \n",
" 927 | \n",
" 896 | \n",
" 1411 | \n",
" 990 | \n",
" 617 | \n",
"
\n",
" \n",
" 26 | \n",
" 2020-06-26 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 8979 | \n",
" NaN | \n",
" 9293 | \n",
" NaN | \n",
" 8695 | \n",
" NaN | \n",
" 571 | \n",
" ... | \n",
" 485 | \n",
" 1300 | \n",
" 922 | \n",
" 800 | \n",
" 946 | \n",
" 880 | \n",
" 791 | \n",
" 1311 | \n",
" 979 | \n",
" 552 | \n",
"
\n",
" \n",
" 27 | \n",
" 2020-07-03 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 9140 | \n",
" NaN | \n",
" 9183 | \n",
" NaN | \n",
" 8606 | \n",
" NaN | \n",
" 555 | \n",
" ... | \n",
" 515 | \n",
" 1225 | \n",
" 875 | \n",
" 827 | \n",
" 949 | \n",
" 922 | \n",
" 837 | \n",
" 1454 | \n",
" 938 | \n",
" 584 | \n",
"
\n",
" \n",
" 28 | \n",
" 2020-07-10 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 8690 | \n",
" NaN | \n",
" 9250 | \n",
" NaN | \n",
" 8648 | \n",
" NaN | \n",
" 578 | \n",
" ... | \n",
" 468 | \n",
" 1154 | \n",
" 848 | \n",
" 771 | \n",
" 902 | \n",
" 999 | \n",
" 803 | \n",
" 1228 | \n",
" 930 | \n",
" 572 | \n",
"
\n",
" \n",
" 29 | \n",
" 2020-07-17 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 8823 | \n",
" NaN | \n",
" 9093 | \n",
" NaN | \n",
" 8502 | \n",
" NaN | \n",
" 557 | \n",
" ... | \n",
" 445 | \n",
" 1159 | \n",
" 843 | \n",
" 816 | \n",
" 956 | \n",
" 945 | \n",
" 806 | \n",
" 1339 | \n",
" 953 | \n",
" 550 | \n",
"
\n",
" \n",
" 30 | \n",
" 2020-07-24 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 8891 | \n",
" NaN | \n",
" 9052 | \n",
" NaN | \n",
" 8452 | \n",
" NaN | \n",
" 566 | \n",
" ... | \n",
" 493 | \n",
" 1197 | \n",
" 817 | \n",
" 798 | \n",
" 964 | \n",
" 951 | \n",
" 816 | \n",
" 1340 | \n",
" 941 | \n",
" 565 | \n",
"
\n",
" \n",
" 31 | \n",
" 2020-07-31 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" 8946 | \n",
" NaN | \n",
" 9036 | \n",
" NaN | \n",
" 8436 | \n",
" NaN | \n",
" 572 | \n",
" ... | \n",
" 507 | \n",
" 1272 | \n",
" 837 | \n",
" 729 | \n",
" 902 | \n",
" 949 | \n",
" 773 | \n",
" 1447 | \n",
" 988 | \n",
" 531 | \n",
"
\n",
" \n",
" 32 | \n",
" 2020-08-07 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 33 | \n",
" 2020-08-14 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 34 | \n",
" 2020-08-21 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 35 | \n",
" 2020-08-28 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 36 | \n",
" 2020-09-04 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 37 | \n",
" 2020-09-11 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 38 | \n",
" 2020-09-18 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 39 | \n",
" 2020-09-25 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 40 | \n",
" 2020-10-02 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 41 | \n",
" 2020-10-09 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 42 | \n",
" 2020-10-16 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 43 | \n",
" 2020-10-23 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 44 | \n",
" 2020-10-30 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 45 | \n",
" 2020-11-06 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 46 | \n",
" 2020-11-13 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 47 | \n",
" 2020-11-20 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 48 | \n",
" 2020-11-27 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 49 | \n",
" 2020-12-04 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 50 | \n",
" 2020-12-11 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 51 | \n",
" 2020-12-18 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 52 | \n",
" 2020-12-25 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
" 53 | \n",
" 2021-01-01 00:00:00 | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" ... | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
" NaT | \n",
"
\n",
" \n",
"
\n",
"
54 rows × 91 columns
\n",
"
"
],
"text/plain": [
" NaN NaN NaN NaN \\\n",
"Week number Week ended NaT NaT Total deaths, all ages \n",
"1 2020-01-03 00:00:00 NaT NaT 12254 \n",
"2 2020-01-10 00:00:00 NaT NaT 14058 \n",
"3 2020-01-17 00:00:00 NaT NaT 12990 \n",
"4 2020-01-24 00:00:00 NaT NaT 11856 \n",
"5 2020-01-31 00:00:00 NaT NaT 11612 \n",
"6 2020-02-07 00:00:00 NaT NaT 10986 \n",
"7 2020-02-14 00:00:00 NaT NaT 10944 \n",
"8 2020-02-21 00:00:00 NaT NaT 10841 \n",
"9 2020-02-28 00:00:00 NaT NaT 10816 \n",
"10 2020-03-06 00:00:00 NaT NaT 10895 \n",
"11 2020-03-13 00:00:00 NaT NaT 11019 \n",
"12 2020-03-20 00:00:00 NaT NaT 10645 \n",
"13 2020-03-27 00:00:00 NaT NaT 11141 \n",
"14 2020-04-03 00:00:00 NaT NaT 16387 \n",
"15 2020-04-10 00:00:00 NaT NaT 18516 \n",
"16 2020-04-17 00:00:00 NaT NaT 22351 \n",
"17 2020-04-24 00:00:00 NaT NaT 21997 \n",
"18 2020-05-01 00:00:00 NaT NaT 17953 \n",
"19 2020-05-08 00:00:00 NaT NaT 12657 \n",
"20 2020-05-15 00:00:00 NaT NaT 14573 \n",
"21 2020-05-22 00:00:00 NaT NaT 12288 \n",
"22 2020-05-29 00:00:00 NaT NaT 9824 \n",
"23 2020-06-05 00:00:00 NaT NaT 10709 \n",
"24 2020-06-12 00:00:00 NaT NaT 9976 \n",
"25 2020-06-19 00:00:00 NaT NaT 9339 \n",
"26 2020-06-26 00:00:00 NaT NaT 8979 \n",
"27 2020-07-03 00:00:00 NaT NaT 9140 \n",
"28 2020-07-10 00:00:00 NaT NaT 8690 \n",
"29 2020-07-17 00:00:00 NaT NaT 8823 \n",
"30 2020-07-24 00:00:00 NaT NaT 8891 \n",
"31 2020-07-31 00:00:00 NaT NaT 8946 \n",
"32 2020-08-07 00:00:00 NaT NaT NaT \n",
"33 2020-08-14 00:00:00 NaT NaT NaT \n",
"34 2020-08-21 00:00:00 NaT NaT NaT \n",
"35 2020-08-28 00:00:00 NaT NaT NaT \n",
"36 2020-09-04 00:00:00 NaT NaT NaT \n",
"37 2020-09-11 00:00:00 NaT NaT NaT \n",
"38 2020-09-18 00:00:00 NaT NaT NaT \n",
"39 2020-09-25 00:00:00 NaT NaT NaT \n",
"40 2020-10-02 00:00:00 NaT NaT NaT \n",
"41 2020-10-09 00:00:00 NaT NaT NaT \n",
"42 2020-10-16 00:00:00 NaT NaT NaT \n",
"43 2020-10-23 00:00:00 NaT NaT NaT \n",
"44 2020-10-30 00:00:00 NaT NaT NaT \n",
"45 2020-11-06 00:00:00 NaT NaT NaT \n",
"46 2020-11-13 00:00:00 NaT NaT NaT \n",
"47 2020-11-20 00:00:00 NaT NaT NaT \n",
"48 2020-11-27 00:00:00 NaT NaT NaT \n",
"49 2020-12-04 00:00:00 NaT NaT NaT \n",
"50 2020-12-11 00:00:00 NaT NaT NaT \n",
"51 2020-12-18 00:00:00 NaT NaT NaT \n",
"52 2020-12-25 00:00:00 NaT NaT NaT \n",
"53 2021-01-01 00:00:00 NaT NaT NaT \n",
"\n",
" NaN \\\n",
"Week number Total deaths: average of corresponding \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"5 NaN \n",
"6 NaN \n",
"7 NaN \n",
"8 NaN \n",
"9 NaN \n",
"10 NaN \n",
"11 NaN \n",
"12 NaN \n",
"13 NaN \n",
"14 NaN \n",
"15 NaN \n",
"16 NaN \n",
"17 NaN \n",
"18 NaN \n",
"19 NaN \n",
"20 NaN \n",
"21 NaN \n",
"22 NaN \n",
"23 NaN \n",
"24 NaN \n",
"25 NaN \n",
"26 NaN \n",
"27 NaN \n",
"28 NaN \n",
"29 NaN \n",
"30 NaN \n",
"31 NaN \n",
"32 NaT \n",
"33 NaT \n",
"34 NaT \n",
"35 NaT \n",
"36 NaT \n",
"37 NaT \n",
"38 NaT \n",
"39 NaT \n",
"40 NaT \n",
"41 NaT \n",
"42 NaT \n",
"43 NaT \n",
"44 NaT \n",
"45 NaT \n",
"46 NaT \n",
"47 NaT \n",
"48 NaT \n",
"49 NaT \n",
"50 NaT \n",
"51 NaT \n",
"52 NaT \n",
"53 NaT \n",
"\n",
" NaN \\\n",
"Week number week over the previous 5 years 1 (England and ... \n",
"1 12175 \n",
"2 13822 \n",
"3 13216 \n",
"4 12760 \n",
"5 12206 \n",
"6 11925 \n",
"7 11627 \n",
"8 11548 \n",
"9 11183 \n",
"10 11498 \n",
"11 11205 \n",
"12 10573 \n",
"13 10130 \n",
"14 10305 \n",
"15 10520 \n",
"16 10497 \n",
"17 10458 \n",
"18 9941 \n",
"19 9576 \n",
"20 10188 \n",
"21 9940 \n",
"22 8171 \n",
"23 9977 \n",
"24 9417 \n",
"25 9404 \n",
"26 9293 \n",
"27 9183 \n",
"28 9250 \n",
"29 9093 \n",
"30 9052 \n",
"31 9036 \n",
"32 NaT \n",
"33 NaT \n",
"34 NaT \n",
"35 NaT \n",
"36 NaT \n",
"37 NaT \n",
"38 NaT \n",
"39 NaT \n",
"40 NaT \n",
"41 NaT \n",
"42 NaT \n",
"43 NaT \n",
"44 NaT \n",
"45 NaT \n",
"46 NaT \n",
"47 NaT \n",
"48 NaT \n",
"49 NaT \n",
"50 NaT \n",
"51 NaT \n",
"52 NaT \n",
"53 NaT \n",
"\n",
" NaN \\\n",
"Week number Total deaths: average of corresponding \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"5 NaN \n",
"6 NaN \n",
"7 NaN \n",
"8 NaN \n",
"9 NaN \n",
"10 NaN \n",
"11 NaN \n",
"12 NaN \n",
"13 NaN \n",
"14 NaN \n",
"15 NaN \n",
"16 NaN \n",
"17 NaN \n",
"18 NaN \n",
"19 NaN \n",
"20 NaN \n",
"21 NaN \n",
"22 NaN \n",
"23 NaN \n",
"24 NaN \n",
"25 NaN \n",
"26 NaN \n",
"27 NaN \n",
"28 NaN \n",
"29 NaN \n",
"30 NaN \n",
"31 NaN \n",
"32 NaT \n",
"33 NaT \n",
"34 NaT \n",
"35 NaT \n",
"36 NaT \n",
"37 NaT \n",
"38 NaT \n",
"39 NaT \n",
"40 NaT \n",
"41 NaT \n",
"42 NaT \n",
"43 NaT \n",
"44 NaT \n",
"45 NaT \n",
"46 NaT \n",
"47 NaT \n",
"48 NaT \n",
"49 NaT \n",
"50 NaT \n",
"51 NaT \n",
"52 NaT \n",
"53 NaT \n",
"\n",
" NaN \\\n",
"Week number week over the previous 5 years 1 (England) \n",
"1 11412 \n",
"2 12933 \n",
"3 12370 \n",
"4 11933 \n",
"5 11419 \n",
"6 11154 \n",
"7 10876 \n",
"8 10790 \n",
"9 10448 \n",
"10 10745 \n",
"11 10447 \n",
"12 9841 \n",
"13 9414 \n",
"14 9601 \n",
"15 9807 \n",
"16 9787 \n",
"17 9768 \n",
"18 9289 \n",
"19 8937 \n",
"20 9526 \n",
"21 9299 \n",
"22 7607 \n",
"23 9346 \n",
"24 8803 \n",
"25 8810 \n",
"26 8695 \n",
"27 8606 \n",
"28 8648 \n",
"29 8502 \n",
"30 8452 \n",
"31 8436 \n",
"32 NaT \n",
"33 NaT \n",
"34 NaT \n",
"35 NaT \n",
"36 NaT \n",
"37 NaT \n",
"38 NaT \n",
"39 NaT \n",
"40 NaT \n",
"41 NaT \n",
"42 NaT \n",
"43 NaT \n",
"44 NaT \n",
"45 NaT \n",
"46 NaT \n",
"47 NaT \n",
"48 NaT \n",
"49 NaT \n",
"50 NaT \n",
"51 NaT \n",
"52 NaT \n",
"53 NaT \n",
"\n",
" NaN \\\n",
"Week number Total deaths: average of corresponding \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"5 NaN \n",
"6 NaN \n",
"7 NaN \n",
"8 NaN \n",
"9 NaN \n",
"10 NaN \n",
"11 NaN \n",
"12 NaN \n",
"13 NaN \n",
"14 NaN \n",
"15 NaN \n",
"16 NaN \n",
"17 NaN \n",
"18 NaN \n",
"19 NaN \n",
"20 NaN \n",
"21 NaN \n",
"22 NaN \n",
"23 NaN \n",
"24 NaN \n",
"25 NaN \n",
"26 NaN \n",
"27 NaN \n",
"28 NaN \n",
"29 NaN \n",
"30 NaN \n",
"31 NaN \n",
"32 NaT \n",
"33 NaT \n",
"34 NaT \n",
"35 NaT \n",
"36 NaT \n",
"37 NaT \n",
"38 NaT \n",
"39 NaT \n",
"40 NaT \n",
"41 NaT \n",
"42 NaT \n",
"43 NaT \n",
"44 NaT \n",
"45 NaT \n",
"46 NaT \n",
"47 NaT \n",
"48 NaT \n",
"49 NaT \n",
"50 NaT \n",
"51 NaT \n",
"52 NaT \n",
"53 NaT \n",
"\n",
" NaN ... North East \\\n",
"Week number week over the previous 5 years 1 (Wales) ... E12000001 \n",
"1 756 ... 673 \n",
"2 856 ... 707 \n",
"3 812 ... 647 \n",
"4 802 ... 612 \n",
"5 760 ... 561 \n",
"6 729 ... 564 \n",
"7 722 ... 573 \n",
"8 724 ... 539 \n",
"9 698 ... 572 \n",
"10 720 ... 568 \n",
"11 727 ... 590 \n",
"12 677 ... 522 \n",
"13 665 ... 542 \n",
"14 667 ... 770 \n",
"15 671 ... 849 \n",
"16 661 ... 1155 \n",
"17 662 ... 1103 \n",
"18 624 ... 922 \n",
"19 612 ... 769 \n",
"20 635 ... 845 \n",
"21 614 ... 718 \n",
"22 546 ... 550 \n",
"23 610 ... 576 \n",
"24 588 ... 478 \n",
"25 573 ... 498 \n",
"26 571 ... 485 \n",
"27 555 ... 515 \n",
"28 578 ... 468 \n",
"29 557 ... 445 \n",
"30 566 ... 493 \n",
"31 572 ... 507 \n",
"32 NaT ... NaT \n",
"33 NaT ... NaT \n",
"34 NaT ... NaT \n",
"35 NaT ... NaT \n",
"36 NaT ... NaT \n",
"37 NaT ... NaT \n",
"38 NaT ... NaT \n",
"39 NaT ... NaT \n",
"40 NaT ... NaT \n",
"41 NaT ... NaT \n",
"42 NaT ... NaT \n",
"43 NaT ... NaT \n",
"44 NaT ... NaT \n",
"45 NaT ... NaT \n",
"46 NaT ... NaT \n",
"47 NaT ... NaT \n",
"48 NaT ... NaT \n",
"49 NaT ... NaT \n",
"50 NaT ... NaT \n",
"51 NaT ... NaT \n",
"52 NaT ... NaT \n",
"53 NaT ... NaT \n",
"\n",
" North West Yorkshire and The Humber East Midlands West Midlands \\\n",
"Week number E12000002 E12000003 E12000004 E12000005 \n",
"1 1806 1240 1060 1349 \n",
"2 1932 1339 1195 1450 \n",
"3 1696 1278 1106 1407 \n",
"4 1529 1187 1024 1231 \n",
"5 1461 1136 1015 1262 \n",
"6 1529 1072 922 1052 \n",
"7 1427 1059 976 1159 \n",
"8 1477 1087 924 1116 \n",
"9 1476 1078 919 1174 \n",
"10 1490 1112 930 1098 \n",
"11 1472 1053 915 1187 \n",
"12 1443 1012 947 1115 \n",
"13 1538 982 922 1035 \n",
"14 2137 1436 1246 1812 \n",
"15 2597 1503 1452 2182 \n",
"16 3195 1960 1632 2536 \n",
"17 3109 2095 1711 2481 \n",
"18 2503 1844 1418 1975 \n",
"19 1790 1328 1094 1326 \n",
"20 1992 1589 1283 1502 \n",
"21 1636 1236 1041 1319 \n",
"22 1337 1046 863 970 \n",
"23 1478 1090 931 1172 \n",
"24 1374 980 967 1096 \n",
"25 1234 952 835 973 \n",
"26 1300 922 800 946 \n",
"27 1225 875 827 949 \n",
"28 1154 848 771 902 \n",
"29 1159 843 816 956 \n",
"30 1197 817 798 964 \n",
"31 1272 837 729 902 \n",
"32 NaT NaT NaT NaT \n",
"33 NaT NaT NaT NaT \n",
"34 NaT NaT NaT NaT \n",
"35 NaT NaT NaT NaT \n",
"36 NaT NaT NaT NaT \n",
"37 NaT NaT NaT NaT \n",
"38 NaT NaT NaT NaT \n",
"39 NaT NaT NaT NaT \n",
"40 NaT NaT NaT NaT \n",
"41 NaT NaT NaT NaT \n",
"42 NaT NaT NaT NaT \n",
"43 NaT NaT NaT NaT \n",
"44 NaT NaT NaT NaT \n",
"45 NaT NaT NaT NaT \n",
"46 NaT NaT NaT NaT \n",
"47 NaT NaT NaT NaT \n",
"48 NaT NaT NaT NaT \n",
"49 NaT NaT NaT NaT \n",
"50 NaT NaT NaT NaT \n",
"51 NaT NaT NaT NaT \n",
"52 NaT NaT NaT NaT \n",
"53 NaT NaT NaT NaT \n",
"\n",
" East London South East South West Wales \n",
"Week number E12000006 E12000007 E12000008 E12000009 W92000004 \n",
"1 1162 1113 1814 1225 787 \n",
"2 1573 1272 2132 1487 939 \n",
"3 1457 1073 2064 1466 767 \n",
"4 1410 1028 1833 1253 723 \n",
"5 1286 1092 1820 1233 727 \n",
"6 1259 987 1729 1157 690 \n",
"7 1172 967 1688 1169 728 \n",
"8 1167 1032 1675 1118 679 \n",
"9 1115 1085 1587 1133 651 \n",
"10 1149 982 1726 1170 652 \n",
"11 1211 964 1751 1174 675 \n",
"12 1043 1008 1657 1156 719 \n",
"13 1182 1297 1822 1092 719 \n",
"14 1717 2511 2294 1520 920 \n",
"15 1984 2832 2604 1560 928 \n",
"16 2466 3275 3084 1854 1169 \n",
"17 2299 2785 3334 1924 1124 \n",
"18 1982 1953 2853 1554 929 \n",
"19 1321 1213 1887 1218 692 \n",
"20 1543 1329 2251 1449 772 \n",
"21 1397 1125 1937 1177 692 \n",
"22 1095 841 1515 1011 587 \n",
"23 1131 891 1610 1116 700 \n",
"24 1048 883 1530 1035 574 \n",
"25 927 896 1411 990 617 \n",
"26 880 791 1311 979 552 \n",
"27 922 837 1454 938 584 \n",
"28 999 803 1228 930 572 \n",
"29 945 806 1339 953 550 \n",
"30 951 816 1340 941 565 \n",
"31 949 773 1447 988 531 \n",
"32 NaT NaT NaT NaT NaT \n",
"33 NaT NaT NaT NaT NaT \n",
"34 NaT NaT NaT NaT NaT \n",
"35 NaT NaT NaT NaT NaT \n",
"36 NaT NaT NaT NaT NaT \n",
"37 NaT NaT NaT NaT NaT \n",
"38 NaT NaT NaT NaT NaT \n",
"39 NaT NaT NaT NaT NaT \n",
"40 NaT NaT NaT NaT NaT \n",
"41 NaT NaT NaT NaT NaT \n",
"42 NaT NaT NaT NaT NaT \n",
"43 NaT NaT NaT NaT NaT \n",
"44 NaT NaT NaT NaT NaT \n",
"45 NaT NaT NaT NaT NaT \n",
"46 NaT NaT NaT NaT NaT \n",
"47 NaT NaT NaT NaT NaT \n",
"48 NaT NaT NaT NaT NaT \n",
"49 NaT NaT NaT NaT NaT \n",
"50 NaT NaT NaT NaT NaT \n",
"51 NaT NaT NaT NaT NaT \n",
"52 NaT NaT NaT NaT NaT \n",
"53 NaT NaT NaT NaT NaT \n",
"\n",
"[54 rows x 91 columns]"
]
},
"execution_count": 86,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"eng_xls = pd.read_excel('uk-deaths-data/publishedweek312020.xlsx', \n",
" sheet_name=\"Weekly figures 2020\",\n",
" skiprows=[0, 1, 2, 3],\n",
" header=0,\n",
" index_col=[1]\n",
" ).iloc[:91].T\n",
"eng_xls"
]
},
{
"cell_type": "code",
"execution_count": 87,
"metadata": {},
"outputs": [],
"source": [
"# eng_xls_columns"
]
},
{
"cell_type": "code",
"execution_count": 88,
"metadata": {},
"outputs": [],
"source": [
"eng_xls_columns = list(eng_xls.columns)\n",
"\n",
"for i, c in enumerate(eng_xls_columns):\n",
"# print(i, c, type(c), isinstance(c, float))\n",
" if isinstance(c, float) and np.isnan(c):\n",
" if eng_xls.iloc[0].iloc[i] is not pd.NaT:\n",
" eng_xls_columns[i] = eng_xls.iloc[0].iloc[i]\n",
"\n",
"# np.isnan(eng_xls_columns[0])\n",
"# eng_xls_columns\n",
"\n",
"eng_xls.columns = eng_xls_columns\n",
"# eng_xls.columns"
]
},
{
"cell_type": "code",
"execution_count": 89,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Week number Total deaths, all ages\n",
"1 12254\n",
"2 14058\n",
"3 12990\n",
"4 11856\n",
"5 11612\n",
"6 10986\n",
"7 10944\n",
"8 10841\n",
"9 10816\n",
"10 10895\n",
"11 11019\n",
"12 10645\n",
"13 11141\n",
"14 16387\n",
"15 18516\n",
"16 22351\n",
"17 21997\n",
"18 17953\n",
"19 12657\n",
"20 14573\n",
"21 12288\n",
"22 9824\n",
"23 10709\n",
"24 9976\n",
"25 9339\n",
"26 8979\n",
"27 9140\n",
"28 8690\n",
"29 8823\n",
"30 8891\n",
"31 8946\n",
"32 NaT\n",
"33 NaT\n",
"34 NaT\n",
"35 NaT\n",
"36 NaT\n",
"37 NaT\n",
"38 NaT\n",
"39 NaT\n",
"40 NaT\n",
"41 NaT\n",
"42 NaT\n",
"43 NaT\n",
"44 NaT\n",
"45 NaT\n",
"46 NaT\n",
"47 NaT\n",
"48 NaT\n",
"49 NaT\n",
"50 NaT\n",
"51 NaT\n",
"52 NaT\n",
"53 NaT\n",
"Name: Total deaths, all ages, dtype: object"
]
},
"execution_count": 89,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"eng_xls['Total deaths, all ages']"
]
},
{
"cell_type": "code",
"execution_count": 90,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"1 787\n",
"2 939\n",
"3 767\n",
"4 723\n",
"5 727\n",
"6 690\n",
"7 728\n",
"8 679\n",
"9 651\n",
"10 652\n",
"11 675\n",
"12 719\n",
"13 719\n",
"14 920\n",
"15 928\n",
"16 1169\n",
"17 1124\n",
"18 929\n",
"19 692\n",
"20 772\n",
"21 692\n",
"22 587\n",
"23 700\n",
"24 574\n",
"25 617\n",
"26 552\n",
"27 584\n",
"28 572\n",
"29 550\n",
"30 565\n",
"31 531\n",
"32 NaT\n",
"33 NaT\n",
"34 NaT\n",
"35 NaT\n",
"36 NaT\n",
"37 NaT\n",
"38 NaT\n",
"39 NaT\n",
"40 NaT\n",
"41 NaT\n",
"42 NaT\n",
"43 NaT\n",
"44 NaT\n",
"45 NaT\n",
"46 NaT\n",
"47 NaT\n",
"48 NaT\n",
"49 NaT\n",
"50 NaT\n",
"51 NaT\n",
"52 NaT\n",
"53 NaT\n",
"Name: Wales, dtype: object"
]
},
"execution_count": 90,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"eng_xls['Wales'].iloc[1:]"
]
},
{
"cell_type": "code",
"execution_count": 91,
"metadata": {},
"outputs": [],
"source": [
"# raw_data_2020 = pd.read_csv('uk-deaths-data/publishedweek272020.csv', \n",
"# parse_dates=[1], dayfirst=True,\n",
"# index_col=0,\n",
"# header=[0, 1])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 92,
"metadata": {},
"outputs": [],
"source": [
"# raw_data_2020.head()"
]
},
{
"cell_type": "code",
"execution_count": 93,
"metadata": {},
"outputs": [],
"source": [
"# raw_data_2020['W92000004', 'Wales']"
]
},
{
"cell_type": "code",
"execution_count": 94,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2019 = pd.read_csv('uk-deaths-data/publishedweek522019.csv', \n",
" parse_dates=[1], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1])\n",
"# raw_data_2019.head()"
]
},
{
"cell_type": "code",
"execution_count": 95,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2018 = pd.read_csv('uk-deaths-data/publishedweek522018.csv', \n",
" parse_dates=[1], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1])\n",
"# raw_data_2018.head()"
]
},
{
"cell_type": "code",
"execution_count": 96,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2017 = pd.read_csv('uk-deaths-data/publishedweek522017.csv', \n",
" parse_dates=[1], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1])\n",
"# raw_data_2017.head()"
]
},
{
"cell_type": "code",
"execution_count": 97,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2016 = pd.read_csv('uk-deaths-data/publishedweek522016.csv', \n",
" parse_dates=[1], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1])\n",
"# raw_data_2016.head()"
]
},
{
"cell_type": "code",
"execution_count": 98,
"metadata": {},
"outputs": [],
"source": [
"raw_data_2015 = pd.read_csv('uk-deaths-data/publishedweek2015.csv', \n",
" parse_dates=[1], dayfirst=True,\n",
" index_col=0,\n",
" header=[0, 1])\n",
"# raw_data_2015.head()"
]
},
{
"cell_type": "code",
"execution_count": 99,
"metadata": {},
"outputs": [],
"source": [
"dhw = eng_xls['Wales'].iloc[1:]\n",
"dhe = eng_xls['Total deaths, all ages'].iloc[1:] - dhw\n",
"deaths_headlines_e = pd.DataFrame({'total_2020': dhe.dropna()})\n",
"deaths_headlines_w = pd.DataFrame({'total_2020': dhw.dropna()})"
]
},
{
"cell_type": "code",
"execution_count": 100,
"metadata": {},
"outputs": [],
"source": [
"# deaths_headlines_e = raw_data_2020.iloc[:, [1]].copy()\n",
"# deaths_headlines_e.columns = ['total_2020']\n",
"# deaths_headlines_w = raw_data_2020['W92000004'].copy()\n",
"# deaths_headlines_e.columns = ['total_2020']\n",
"# deaths_headlines_w.columns = ['total_2020']\n",
"# deaths_headlines_e.total_2020 -= deaths_headlines_w.total_2020\n",
"# deaths_headlines_e.head()\n",
"# deaths_headlines_e"
]
},
{
"cell_type": "code",
"execution_count": 101,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2019 | \n",
"
\n",
" \n",
" \n",
" \n",
" 48 | \n",
" 10269 | \n",
"
\n",
" \n",
" 49 | \n",
" 10079 | \n",
"
\n",
" \n",
" 50 | \n",
" 10489 | \n",
"
\n",
" \n",
" 51 | \n",
" 11159 | \n",
"
\n",
" \n",
" 52 | \n",
" 7037 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2019\n",
"48 10269\n",
"49 10079\n",
"50 10489\n",
"51 11159\n",
"52 7037"
]
},
"execution_count": 101,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dh19e = raw_data_2019.iloc[:, [1]]\n",
"dh19w = raw_data_2019['W92000004']\n",
"dh19e.columns = ['total_2019']\n",
"dh19w.columns = ['total_2019']\n",
"dh19e.total_2019 -= dh19w.total_2019\n",
"dh19e.tail()"
]
},
{
"cell_type": "code",
"execution_count": 102,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2019 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 718 | \n",
"
\n",
" \n",
" 2 | \n",
" 809 | \n",
"
\n",
" \n",
" 3 | \n",
" 683 | \n",
"
\n",
" \n",
" 4 | \n",
" 734 | \n",
"
\n",
" \n",
" 5 | \n",
" 745 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2019\n",
"1 718\n",
"2 809\n",
"3 683\n",
"4 734\n",
"5 745"
]
},
"execution_count": 102,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dh19w.head()"
]
},
{
"cell_type": "code",
"execution_count": 103,
"metadata": {},
"outputs": [],
"source": [
"dh18e = raw_data_2018.iloc[:, [1]]\n",
"dh18w = raw_data_2018['W92000004']\n",
"dh18e.columns = ['total_2018']\n",
"dh18w.columns = ['total_2018']\n",
"dh18e.total_2018 -= dh18w.total_2018\n",
"# dh18e.head()"
]
},
{
"cell_type": "code",
"execution_count": 104,
"metadata": {},
"outputs": [],
"source": [
"dh17e = raw_data_2017.iloc[:, [1]]\n",
"dh17w = raw_data_2017['W92000004']\n",
"dh17e.columns = ['total_2017']\n",
"dh17w.columns = ['total_2017']\n",
"dh17e.total_2017 -= dh17w.total_2017\n",
"# dh17e.head()"
]
},
{
"cell_type": "code",
"execution_count": 105,
"metadata": {},
"outputs": [],
"source": [
"dh16e = raw_data_2016.iloc[:, [1]]\n",
"dh16w = raw_data_2016['W92000004']\n",
"dh16e.columns = ['total_2016']\n",
"dh16w.columns = ['total_2016']\n",
"dh16e.total_2016 -= dh16w.total_2016\n",
"# dh16e.head()"
]
},
{
"cell_type": "code",
"execution_count": 106,
"metadata": {},
"outputs": [],
"source": [
"dh15e = raw_data_2015.iloc[:, [1]]\n",
"dh15w = raw_data_2015['W92000004']\n",
"dh15e.columns = ['total_2015']\n",
"dh15w.columns = ['total_2015']\n",
"dh15e.total_2015 -= dh15w.total_2015\n",
"# dh15e.head()"
]
},
{
"cell_type": "code",
"execution_count": 107,
"metadata": {},
"outputs": [],
"source": [
"# dh18 = raw_data_2018.iloc[:, [1, 2]]\n",
"# dh18.columns = ['total_2018', 'total_previous']\n",
"# # dh18.head()"
]
},
{
"cell_type": "code",
"execution_count": 108,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
" total_2019 | \n",
" total_2018 | \n",
" total_2017 | \n",
" total_2016 | \n",
" total_2015 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 11467 | \n",
" 10237 | \n",
" 11940 | \n",
" 11247 | \n",
" 12236 | \n",
" 11561 | \n",
"
\n",
" \n",
" 2 | \n",
" 13119 | \n",
" 11800 | \n",
" 14146 | \n",
" 12890 | \n",
" 10790 | \n",
" 15206 | \n",
"
\n",
" \n",
" 3 | \n",
" 12223 | \n",
" 11177 | \n",
" 13371 | \n",
" 12775 | \n",
" 10753 | \n",
" 13930 | \n",
"
\n",
" \n",
" 4 | \n",
" 11133 | \n",
" 11006 | \n",
" 13085 | \n",
" 11996 | \n",
" 10600 | \n",
" 13106 | \n",
"
\n",
" \n",
" 5 | \n",
" 10885 | \n",
" 10552 | \n",
" 12470 | \n",
" 11736 | \n",
" 10362 | \n",
" 12099 | \n",
"
\n",
" \n",
" 6 | \n",
" 10296 | \n",
" 10959 | \n",
" 11694 | \n",
" 11546 | \n",
" 10470 | \n",
" 11319 | \n",
"
\n",
" \n",
" 7 | \n",
" 10216 | \n",
" 11076 | \n",
" 11443 | \n",
" 10954 | \n",
" 9933 | \n",
" 11112 | \n",
"
\n",
" \n",
" 8 | \n",
" 10162 | \n",
" 10600 | \n",
" 11353 | \n",
" 11093 | \n",
" 10360 | \n",
" 10695 | \n",
"
\n",
" \n",
" 9 | \n",
" 10165 | \n",
" 10360 | \n",
" 10220 | \n",
" 10533 | \n",
" 10564 | \n",
" 10736 | \n",
"
\n",
" \n",
" 10 | \n",
" 10243 | \n",
" 10276 | \n",
" 12101 | \n",
" 10443 | \n",
" 10276 | \n",
" 10757 | \n",
"
\n",
" \n",
" 11 | \n",
" 10344 | \n",
" 9901 | \n",
" 11870 | \n",
" 10044 | \n",
" 10284 | \n",
" 10290 | \n",
"
\n",
" \n",
" 12 | \n",
" 9926 | \n",
" 9774 | \n",
" 11139 | \n",
" 9690 | \n",
" 8967 | \n",
" 9888 | \n",
"
\n",
" \n",
" 13 | \n",
" 10422 | \n",
" 9213 | \n",
" 9308 | \n",
" 9369 | \n",
" 9574 | \n",
" 9827 | \n",
"
\n",
" \n",
" 14 | \n",
" 15467 | \n",
" 9484 | \n",
" 10064 | \n",
" 9297 | \n",
" 10857 | \n",
" 8482 | \n",
"
\n",
" \n",
" 15 | \n",
" 17588 | \n",
" 9654 | \n",
" 11558 | \n",
" 7916 | \n",
" 10679 | \n",
" 9429 | \n",
"
\n",
" \n",
" 16 | \n",
" 21182 | \n",
" 8445 | \n",
" 10535 | \n",
" 8990 | \n",
" 10211 | \n",
" 10968 | \n",
"
\n",
" \n",
" 17 | \n",
" 20873 | \n",
" 9381 | \n",
" 9692 | \n",
" 10181 | \n",
" 9784 | \n",
" 9937 | \n",
"
\n",
" \n",
" 18 | \n",
" 17024 | \n",
" 10519 | \n",
" 9520 | \n",
" 8464 | \n",
" 8568 | \n",
" 9506 | \n",
"
\n",
" \n",
" 19 | \n",
" 11965 | \n",
" 8455 | \n",
" 8094 | \n",
" 10006 | \n",
" 9985 | \n",
" 8273 | \n",
"
\n",
" \n",
" 20 | \n",
" 13801 | \n",
" 9614 | \n",
" 9474 | \n",
" 9673 | \n",
" 9342 | \n",
" 9668 | \n",
"
\n",
" \n",
" 21 | \n",
" 11596 | \n",
" 9657 | \n",
" 9033 | \n",
" 9438 | \n",
" 9115 | \n",
" 9391 | \n",
"
\n",
" \n",
" 22 | \n",
" 9237 | \n",
" 7742 | \n",
" 7609 | \n",
" 7746 | \n",
" 7409 | \n",
" 7625 | \n",
"
\n",
" \n",
" 23 | \n",
" 10009 | \n",
" 9514 | \n",
" 9343 | \n",
" 9182 | \n",
" 9289 | \n",
" 9509 | \n",
"
\n",
" \n",
" 24 | \n",
" 9402 | \n",
" 8847 | \n",
" 8782 | \n",
" 8768 | \n",
" 8808 | \n",
" 8942 | \n",
"
\n",
" \n",
" 25 | \n",
" 8722 | \n",
" 8916 | \n",
" 8694 | \n",
" 9019 | \n",
" 8807 | \n",
" 8717 | \n",
"
\n",
" \n",
" 26 | \n",
" 8427 | \n",
" 8947 | \n",
" 8613 | \n",
" 8788 | \n",
" 8679 | \n",
" 8593 | \n",
"
\n",
" \n",
" 27 | \n",
" 8556 | \n",
" 8528 | \n",
" 8633 | \n",
" 8707 | \n",
" 8614 | \n",
" 8670 | \n",
"
\n",
" \n",
" 28 | \n",
" 8118 | \n",
" 8591 | \n",
" 8710 | \n",
" 8812 | \n",
" 8789 | \n",
" 8461 | \n",
"
\n",
" \n",
" 29 | \n",
" 8273 | \n",
" 8527 | \n",
" 8579 | \n",
" 8562 | \n",
" 8790 | \n",
" 8228 | \n",
"
\n",
" \n",
" 30 | \n",
" 8326 | \n",
" 8569 | \n",
" 8581 | \n",
" 8296 | \n",
" 8725 | \n",
" 8262 | \n",
"
\n",
" \n",
" 31 | \n",
" 8415 | \n",
" 8701 | \n",
" 8587 | \n",
" 8351 | \n",
" 8602 | \n",
" 8071 | \n",
"
\n",
" \n",
" 32 | \n",
" NaN | \n",
" 8580 | \n",
" 8782 | \n",
" 8466 | \n",
" 8531 | \n",
" 8298 | \n",
"
\n",
" \n",
" 33 | \n",
" NaN | \n",
" 8504 | \n",
" 8312 | \n",
" 8707 | \n",
" 8496 | \n",
" 8600 | \n",
"
\n",
" \n",
" 34 | \n",
" NaN | \n",
" 8441 | \n",
" 8413 | \n",
" 8812 | \n",
" 8700 | \n",
" 8564 | \n",
"
\n",
" \n",
" 35 | \n",
" NaN | \n",
" 7684 | \n",
" 7354 | \n",
" 7594 | \n",
" 7453 | \n",
" 8423 | \n",
"
\n",
" \n",
" 36 | \n",
" NaN | \n",
" 9113 | \n",
" 8851 | \n",
" 8955 | \n",
" 8847 | \n",
" 7389 | \n",
"
\n",
" \n",
" 37 | \n",
" NaN | \n",
" 8946 | \n",
" 8612 | \n",
" 8845 | \n",
" 8548 | \n",
" 8704 | \n",
"
\n",
" \n",
" 38 | \n",
" NaN | \n",
" 8868 | \n",
" 8707 | \n",
" 8949 | \n",
" 8382 | \n",
" 8542 | \n",
"
\n",
" \n",
" 39 | \n",
" NaN | \n",
" 8906 | \n",
" 8590 | \n",
" 9096 | \n",
" 8402 | \n",
" 8865 | \n",
"
\n",
" \n",
" 40 | \n",
" NaN | \n",
" 9202 | \n",
" 8908 | \n",
" 9147 | \n",
" 8729 | \n",
" 8858 | \n",
"
\n",
" \n",
" 41 | \n",
" NaN | \n",
" 9383 | \n",
" 9043 | \n",
" 9300 | \n",
" 9132 | \n",
" 9124 | \n",
"
\n",
" \n",
" 42 | \n",
" NaN | \n",
" 9534 | \n",
" 9224 | \n",
" 9381 | \n",
" 9144 | \n",
" 8899 | \n",
"
\n",
" \n",
" 43 | \n",
" NaN | \n",
" 9351 | \n",
" 8970 | \n",
" 9131 | \n",
" 9100 | \n",
" 9104 | \n",
"
\n",
" \n",
" 44 | \n",
" NaN | \n",
" 9522 | \n",
" 8925 | \n",
" 9389 | \n",
" 9508 | \n",
" 9025 | \n",
"
\n",
" \n",
" 45 | \n",
" NaN | \n",
" 10044 | \n",
" 9509 | \n",
" 9748 | \n",
" 9844 | \n",
" 9388 | \n",
"
\n",
" \n",
" 46 | \n",
" NaN | \n",
" 9976 | \n",
" 9537 | \n",
" 9609 | \n",
" 10013 | \n",
" 9325 | \n",
"
\n",
" \n",
" 47 | \n",
" NaN | \n",
" 10183 | \n",
" 9300 | \n",
" 9982 | \n",
" 9942 | \n",
" 9219 | \n",
"
\n",
" \n",
" 48 | \n",
" NaN | \n",
" 10269 | \n",
" 9360 | \n",
" 9902 | \n",
" 9796 | \n",
" 9233 | \n",
"
\n",
" \n",
" 49 | \n",
" NaN | \n",
" 10079 | \n",
" 9613 | \n",
" 10151 | \n",
" 10530 | \n",
" 9706 | \n",
"
\n",
" \n",
" 50 | \n",
" NaN | \n",
" 10489 | \n",
" 9842 | \n",
" 10509 | \n",
" 9870 | \n",
" 9581 | \n",
"
\n",
" \n",
" 51 | \n",
" NaN | \n",
" 11159 | \n",
" 10392 | \n",
" 11755 | \n",
" 10802 | \n",
" 10043 | \n",
"
\n",
" \n",
" 52 | \n",
" NaN | \n",
" 7037 | \n",
" 6670 | \n",
" 7946 | \n",
" 7445 | \n",
" 8095 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020 total_2019 total_2018 total_2017 total_2016 total_2015\n",
"1 11467 10237 11940 11247 12236 11561\n",
"2 13119 11800 14146 12890 10790 15206\n",
"3 12223 11177 13371 12775 10753 13930\n",
"4 11133 11006 13085 11996 10600 13106\n",
"5 10885 10552 12470 11736 10362 12099\n",
"6 10296 10959 11694 11546 10470 11319\n",
"7 10216 11076 11443 10954 9933 11112\n",
"8 10162 10600 11353 11093 10360 10695\n",
"9 10165 10360 10220 10533 10564 10736\n",
"10 10243 10276 12101 10443 10276 10757\n",
"11 10344 9901 11870 10044 10284 10290\n",
"12 9926 9774 11139 9690 8967 9888\n",
"13 10422 9213 9308 9369 9574 9827\n",
"14 15467 9484 10064 9297 10857 8482\n",
"15 17588 9654 11558 7916 10679 9429\n",
"16 21182 8445 10535 8990 10211 10968\n",
"17 20873 9381 9692 10181 9784 9937\n",
"18 17024 10519 9520 8464 8568 9506\n",
"19 11965 8455 8094 10006 9985 8273\n",
"20 13801 9614 9474 9673 9342 9668\n",
"21 11596 9657 9033 9438 9115 9391\n",
"22 9237 7742 7609 7746 7409 7625\n",
"23 10009 9514 9343 9182 9289 9509\n",
"24 9402 8847 8782 8768 8808 8942\n",
"25 8722 8916 8694 9019 8807 8717\n",
"26 8427 8947 8613 8788 8679 8593\n",
"27 8556 8528 8633 8707 8614 8670\n",
"28 8118 8591 8710 8812 8789 8461\n",
"29 8273 8527 8579 8562 8790 8228\n",
"30 8326 8569 8581 8296 8725 8262\n",
"31 8415 8701 8587 8351 8602 8071\n",
"32 NaN 8580 8782 8466 8531 8298\n",
"33 NaN 8504 8312 8707 8496 8600\n",
"34 NaN 8441 8413 8812 8700 8564\n",
"35 NaN 7684 7354 7594 7453 8423\n",
"36 NaN 9113 8851 8955 8847 7389\n",
"37 NaN 8946 8612 8845 8548 8704\n",
"38 NaN 8868 8707 8949 8382 8542\n",
"39 NaN 8906 8590 9096 8402 8865\n",
"40 NaN 9202 8908 9147 8729 8858\n",
"41 NaN 9383 9043 9300 9132 9124\n",
"42 NaN 9534 9224 9381 9144 8899\n",
"43 NaN 9351 8970 9131 9100 9104\n",
"44 NaN 9522 8925 9389 9508 9025\n",
"45 NaN 10044 9509 9748 9844 9388\n",
"46 NaN 9976 9537 9609 10013 9325\n",
"47 NaN 10183 9300 9982 9942 9219\n",
"48 NaN 10269 9360 9902 9796 9233\n",
"49 NaN 10079 9613 10151 10530 9706\n",
"50 NaN 10489 9842 10509 9870 9581\n",
"51 NaN 11159 10392 11755 10802 10043\n",
"52 NaN 7037 6670 7946 7445 8095"
]
},
"execution_count": 108,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"deaths_headlines_e = deaths_headlines_e.merge(dh19e['total_2019'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_e = deaths_headlines_e.merge(dh18e['total_2018'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_e = deaths_headlines_e.merge(dh17e['total_2017'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_e = deaths_headlines_e.merge(dh16e['total_2016'], how='outer', left_index=True, right_index=True)\n",
"# deaths_headlines = deaths_headlines.merge(dh15['total_2015'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_e = deaths_headlines_e.merge(dh15e['total_2015'], how='left', left_index=True, right_index=True)\n",
"deaths_headlines_e"
]
},
{
"cell_type": "code",
"execution_count": 109,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
" total_2019 | \n",
" total_2018 | \n",
" total_2017 | \n",
" total_2016 | \n",
" total_2015 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 1161.0 | \n",
" 1104.0 | \n",
" 1531.0 | \n",
" 1205.0 | \n",
" 1394.0 | \n",
" 1146 | \n",
"
\n",
" \n",
" 2 | \n",
" 1567.0 | \n",
" 1507.0 | \n",
" 1899.0 | \n",
" 1379.0 | \n",
" 1305.0 | \n",
" 1708 | \n",
"
\n",
" \n",
" 3 | \n",
" 1322.0 | \n",
" 1353.0 | \n",
" 1629.0 | \n",
" 1224.0 | \n",
" 1215.0 | \n",
" 1489 | \n",
"
\n",
" \n",
" 4 | \n",
" 1226.0 | \n",
" 1208.0 | \n",
" 1610.0 | \n",
" 1197.0 | \n",
" 1187.0 | \n",
" 1381 | \n",
"
\n",
" \n",
" 5 | \n",
" 1188.0 | \n",
" 1206.0 | \n",
" 1369.0 | \n",
" 1332.0 | \n",
" 1205.0 | \n",
" 1286 | \n",
"
\n",
" \n",
" 6 | \n",
" 1216.0 | \n",
" 1243.0 | \n",
" 1265.0 | \n",
" 1200.0 | \n",
" 1217.0 | \n",
" 1344 | \n",
"
\n",
" \n",
" 7 | \n",
" 1162.0 | \n",
" 1181.0 | \n",
" 1315.0 | \n",
" 1231.0 | \n",
" 1209.0 | \n",
" 1360 | \n",
"
\n",
" \n",
" 8 | \n",
" 1162.0 | \n",
" 1245.0 | \n",
" 1245.0 | \n",
" 1185.0 | \n",
" 1239.0 | \n",
" 1320 | \n",
"
\n",
" \n",
" 9 | \n",
" 1171.0 | \n",
" 1125.0 | \n",
" 1022.0 | \n",
" 1219.0 | \n",
" 1150.0 | \n",
" 1308 | \n",
"
\n",
" \n",
" 10 | \n",
" 1208.0 | \n",
" 1156.0 | \n",
" 1475.0 | \n",
" 1146.0 | \n",
" 1174.0 | \n",
" 1192 | \n",
"
\n",
" \n",
" 11 | \n",
" 1156.0 | \n",
" 1108.0 | \n",
" 1220.0 | \n",
" 1141.0 | \n",
" 1175.0 | \n",
" 1201 | \n",
"
\n",
" \n",
" 12 | \n",
" 1196.0 | \n",
" 1101.0 | \n",
" 1158.0 | \n",
" 1152.0 | \n",
" 1042.0 | \n",
" 1149 | \n",
"
\n",
" \n",
" 13 | \n",
" 1079.0 | \n",
" 1086.0 | \n",
" 1050.0 | \n",
" 1112.0 | \n",
" 1172.0 | \n",
" 1171 | \n",
"
\n",
" \n",
" 14 | \n",
" 1744.0 | \n",
" 1032.0 | \n",
" 1192.0 | \n",
" 1060.0 | \n",
" 1166.0 | \n",
" 1042 | \n",
"
\n",
" \n",
" 15 | \n",
" 1978.0 | \n",
" 1069.0 | \n",
" 1192.0 | \n",
" 998.0 | \n",
" 1048.0 | \n",
" 1192 | \n",
"
\n",
" \n",
" 16 | \n",
" 1916.0 | \n",
" 902.0 | \n",
" 1136.0 | \n",
" 1111.0 | \n",
" 1092.0 | \n",
" 1095 | \n",
"
\n",
" \n",
" 17 | \n",
" 1836.0 | \n",
" 1121.0 | \n",
" 1008.0 | \n",
" 1121.0 | \n",
" 1076.0 | \n",
" 1108 | \n",
"
\n",
" \n",
" 18 | \n",
" 1679.0 | \n",
" 1131.0 | \n",
" 1093.0 | \n",
" 1050.0 | \n",
" 1006.0 | \n",
" 1117 | \n",
"
\n",
" \n",
" 19 | \n",
" 1435.0 | \n",
" 1018.0 | \n",
" 967.0 | \n",
" 1119.0 | \n",
" 1047.0 | \n",
" 1020 | \n",
"
\n",
" \n",
" 20 | \n",
" 1421.0 | \n",
" 1115.0 | \n",
" 977.0 | \n",
" 1115.0 | \n",
" 1010.0 | \n",
" 1103 | \n",
"
\n",
" \n",
" 21 | \n",
" 1226.0 | \n",
" 1061.0 | \n",
" 1070.0 | \n",
" 1063.0 | \n",
" 994.0 | \n",
" 1039 | \n",
"
\n",
" \n",
" 22 | \n",
" 1125.0 | \n",
" 1029.0 | \n",
" 998.0 | \n",
" 1015.0 | \n",
" 999.0 | \n",
" 1043 | \n",
"
\n",
" \n",
" 23 | \n",
" 1093.0 | \n",
" 1042.0 | \n",
" 1033.0 | \n",
" 1076.0 | \n",
" 1023.0 | \n",
" 1106 | \n",
"
\n",
" \n",
" 24 | \n",
" 1034.0 | \n",
" 1028.0 | \n",
" 915.0 | \n",
" 1031.0 | \n",
" 988.0 | \n",
" 1038 | \n",
"
\n",
" \n",
" 25 | \n",
" 1065.0 | \n",
" 1053.0 | \n",
" 993.0 | \n",
" 1032.0 | \n",
" 994.0 | \n",
" 1025 | \n",
"
\n",
" \n",
" 26 | \n",
" 1008.0 | \n",
" 1051.0 | \n",
" 1046.0 | \n",
" 994.0 | \n",
" 1007.0 | \n",
" 1032 | \n",
"
\n",
" \n",
" 27 | \n",
" 983.0 | \n",
" 981.0 | \n",
" 1041.0 | \n",
" 1040.0 | \n",
" 988.0 | \n",
" 1040 | \n",
"
\n",
" \n",
" 28 | \n",
" 976.0 | \n",
" 1077.0 | \n",
" 1002.0 | \n",
" 1014.0 | \n",
" 1022.0 | \n",
" 1011 | \n",
"
\n",
" \n",
" 29 | \n",
" 1033.0 | \n",
" 964.0 | \n",
" 928.0 | \n",
" 1025.0 | \n",
" 1041.0 | \n",
" 1023 | \n",
"
\n",
" \n",
" 30 | \n",
" 961.0 | \n",
" 1041.0 | \n",
" 933.0 | \n",
" 978.0 | \n",
" 979.0 | \n",
" 956 | \n",
"
\n",
" \n",
" 31 | \n",
" 1043.0 | \n",
" 1020.0 | \n",
" 969.0 | \n",
" 1011.0 | \n",
" 987.0 | \n",
" 985 | \n",
"
\n",
" \n",
" 32 | \n",
" 1002.0 | \n",
" 1018.0 | \n",
" 953.0 | \n",
" 1002.0 | \n",
" 997.0 | \n",
" 1043 | \n",
"
\n",
" \n",
" 33 | \n",
" NaN | \n",
" 1028.0 | \n",
" 978.0 | \n",
" 1004.0 | \n",
" 982.0 | \n",
" 969 | \n",
"
\n",
" \n",
" 34 | \n",
" NaN | \n",
" 1011.0 | \n",
" 941.0 | \n",
" 1045.0 | \n",
" 1017.0 | \n",
" 982 | \n",
"
\n",
" \n",
" 35 | \n",
" NaN | \n",
" 1013.0 | \n",
" 930.0 | \n",
" 980.0 | \n",
" 1039.0 | \n",
" 954 | \n",
"
\n",
" \n",
" 36 | \n",
" NaN | \n",
" 980.0 | \n",
" 970.0 | \n",
" 1006.0 | \n",
" 1007.0 | \n",
" 977 | \n",
"
\n",
" \n",
" 37 | \n",
" NaN | \n",
" 1074.0 | \n",
" 1020.0 | \n",
" 972.0 | \n",
" 983.0 | \n",
" 991 | \n",
"
\n",
" \n",
" 38 | \n",
" NaN | \n",
" 1071.0 | \n",
" 946.0 | \n",
" 1049.0 | \n",
" 966.0 | \n",
" 1001 | \n",
"
\n",
" \n",
" 39 | \n",
" NaN | \n",
" 1142.0 | \n",
" 1015.0 | \n",
" 1056.0 | \n",
" 1009.0 | \n",
" 1010 | \n",
"
\n",
" \n",
" 40 | \n",
" NaN | \n",
" 1051.0 | \n",
" 1042.0 | \n",
" 1016.0 | \n",
" 1072.0 | \n",
" 1008 | \n",
"
\n",
" \n",
" 41 | \n",
" NaN | \n",
" 1143.0 | \n",
" 1081.0 | \n",
" 1133.0 | \n",
" 1009.0 | \n",
" 1028 | \n",
"
\n",
" \n",
" 42 | \n",
" NaN | \n",
" 1153.0 | \n",
" 1031.0 | \n",
" 1067.0 | \n",
" 1070.0 | \n",
" 989 | \n",
"
\n",
" \n",
" 43 | \n",
" NaN | \n",
" 1115.0 | \n",
" 1019.0 | \n",
" 1095.0 | \n",
" 1052.0 | \n",
" 981 | \n",
"
\n",
" \n",
" 44 | \n",
" NaN | \n",
" 1101.0 | \n",
" 1085.0 | \n",
" 1062.0 | \n",
" 1032.0 | \n",
" 1116 | \n",
"
\n",
" \n",
" 45 | \n",
" NaN | \n",
" 1184.0 | \n",
" 1144.0 | \n",
" 1126.0 | \n",
" 1043.0 | \n",
" 1028 | \n",
"
\n",
" \n",
" 46 | \n",
" NaN | \n",
" 1160.0 | \n",
" 1084.0 | \n",
" 1175.0 | \n",
" 1174.0 | \n",
" 1103 | \n",
"
\n",
" \n",
" 47 | \n",
" NaN | \n",
" 1229.0 | \n",
" 1058.0 | \n",
" 1178.0 | \n",
" 1132.0 | \n",
" 1054 | \n",
"
\n",
" \n",
" 48 | \n",
" NaN | \n",
" 1163.0 | \n",
" 1062.0 | \n",
" 1153.0 | \n",
" 1159.0 | \n",
" 1115 | \n",
"
\n",
" \n",
" 49 | \n",
" NaN | \n",
" 1108.0 | \n",
" 1076.0 | \n",
" 1237.0 | \n",
" 1188.0 | \n",
" 1089 | \n",
"
\n",
" \n",
" 50 | \n",
" NaN | \n",
" 1312.0 | \n",
" 1212.0 | \n",
" 1335.0 | \n",
" 1219.0 | \n",
" 1101 | \n",
"
\n",
" \n",
" 51 | \n",
" NaN | \n",
" 1277.0 | \n",
" 1216.0 | \n",
" 1437.0 | \n",
" 1284.0 | \n",
" 1146 | \n",
"
\n",
" \n",
" 52 | \n",
" NaN | \n",
" 1000.0 | \n",
" 1058.0 | \n",
" 1168.0 | \n",
" 1133.0 | \n",
" 944 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020 total_2019 total_2018 total_2017 total_2016 total_2015\n",
"1 1161.0 1104.0 1531.0 1205.0 1394.0 1146\n",
"2 1567.0 1507.0 1899.0 1379.0 1305.0 1708\n",
"3 1322.0 1353.0 1629.0 1224.0 1215.0 1489\n",
"4 1226.0 1208.0 1610.0 1197.0 1187.0 1381\n",
"5 1188.0 1206.0 1369.0 1332.0 1205.0 1286\n",
"6 1216.0 1243.0 1265.0 1200.0 1217.0 1344\n",
"7 1162.0 1181.0 1315.0 1231.0 1209.0 1360\n",
"8 1162.0 1245.0 1245.0 1185.0 1239.0 1320\n",
"9 1171.0 1125.0 1022.0 1219.0 1150.0 1308\n",
"10 1208.0 1156.0 1475.0 1146.0 1174.0 1192\n",
"11 1156.0 1108.0 1220.0 1141.0 1175.0 1201\n",
"12 1196.0 1101.0 1158.0 1152.0 1042.0 1149\n",
"13 1079.0 1086.0 1050.0 1112.0 1172.0 1171\n",
"14 1744.0 1032.0 1192.0 1060.0 1166.0 1042\n",
"15 1978.0 1069.0 1192.0 998.0 1048.0 1192\n",
"16 1916.0 902.0 1136.0 1111.0 1092.0 1095\n",
"17 1836.0 1121.0 1008.0 1121.0 1076.0 1108\n",
"18 1679.0 1131.0 1093.0 1050.0 1006.0 1117\n",
"19 1435.0 1018.0 967.0 1119.0 1047.0 1020\n",
"20 1421.0 1115.0 977.0 1115.0 1010.0 1103\n",
"21 1226.0 1061.0 1070.0 1063.0 994.0 1039\n",
"22 1125.0 1029.0 998.0 1015.0 999.0 1043\n",
"23 1093.0 1042.0 1033.0 1076.0 1023.0 1106\n",
"24 1034.0 1028.0 915.0 1031.0 988.0 1038\n",
"25 1065.0 1053.0 993.0 1032.0 994.0 1025\n",
"26 1008.0 1051.0 1046.0 994.0 1007.0 1032\n",
"27 983.0 981.0 1041.0 1040.0 988.0 1040\n",
"28 976.0 1077.0 1002.0 1014.0 1022.0 1011\n",
"29 1033.0 964.0 928.0 1025.0 1041.0 1023\n",
"30 961.0 1041.0 933.0 978.0 979.0 956\n",
"31 1043.0 1020.0 969.0 1011.0 987.0 985\n",
"32 1002.0 1018.0 953.0 1002.0 997.0 1043\n",
"33 NaN 1028.0 978.0 1004.0 982.0 969\n",
"34 NaN 1011.0 941.0 1045.0 1017.0 982\n",
"35 NaN 1013.0 930.0 980.0 1039.0 954\n",
"36 NaN 980.0 970.0 1006.0 1007.0 977\n",
"37 NaN 1074.0 1020.0 972.0 983.0 991\n",
"38 NaN 1071.0 946.0 1049.0 966.0 1001\n",
"39 NaN 1142.0 1015.0 1056.0 1009.0 1010\n",
"40 NaN 1051.0 1042.0 1016.0 1072.0 1008\n",
"41 NaN 1143.0 1081.0 1133.0 1009.0 1028\n",
"42 NaN 1153.0 1031.0 1067.0 1070.0 989\n",
"43 NaN 1115.0 1019.0 1095.0 1052.0 981\n",
"44 NaN 1101.0 1085.0 1062.0 1032.0 1116\n",
"45 NaN 1184.0 1144.0 1126.0 1043.0 1028\n",
"46 NaN 1160.0 1084.0 1175.0 1174.0 1103\n",
"47 NaN 1229.0 1058.0 1178.0 1132.0 1054\n",
"48 NaN 1163.0 1062.0 1153.0 1159.0 1115\n",
"49 NaN 1108.0 1076.0 1237.0 1188.0 1089\n",
"50 NaN 1312.0 1212.0 1335.0 1219.0 1101\n",
"51 NaN 1277.0 1216.0 1437.0 1284.0 1146\n",
"52 NaN 1000.0 1058.0 1168.0 1133.0 944"
]
},
"execution_count": 109,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"deaths_headlines_s = raw_data_s[reversed('2015 2016 2017 2018 2019 2020'.split())]\n",
"deaths_headlines_s.columns = ['total_' + c for c in deaths_headlines_s.columns]\n",
"deaths_headlines_s.reset_index(drop=True, inplace=True)\n",
"deaths_headlines_s.index = deaths_headlines_s.index + 1\n",
"deaths_headlines_s = deaths_headlines_s.loc[1:52]\n",
"deaths_headlines_s"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Correction for missing data"
]
},
{
"cell_type": "code",
"execution_count": 110,
"metadata": {},
"outputs": [],
"source": [
"# deaths_headlines_s.loc[20, 'total_2020'] = 1000\n",
"# deaths_headlines_s"
]
},
{
"cell_type": "code",
"execution_count": 111,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
" total_2019 | \n",
" total_2018 | \n",
" total_2017 | \n",
" total_2016 | \n",
" total_2015 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 787 | \n",
" 718 | \n",
" 783 | \n",
" 744 | \n",
" 809 | \n",
" 725 | \n",
"
\n",
" \n",
" 2 | \n",
" 939 | \n",
" 809 | \n",
" 904 | \n",
" 825 | \n",
" 711 | \n",
" 1031 | \n",
"
\n",
" \n",
" 3 | \n",
" 767 | \n",
" 683 | \n",
" 885 | \n",
" 835 | \n",
" 720 | \n",
" 936 | \n",
"
\n",
" \n",
" 4 | \n",
" 723 | \n",
" 734 | \n",
" 850 | \n",
" 881 | \n",
" 717 | \n",
" 828 | \n",
"
\n",
" \n",
" 5 | \n",
" 727 | \n",
" 745 | \n",
" 815 | \n",
" 749 | \n",
" 690 | \n",
" 801 | \n",
"
\n",
" \n",
" 6 | \n",
" 690 | \n",
" 701 | \n",
" 801 | \n",
" 723 | \n",
" 700 | \n",
" 720 | \n",
"
\n",
" \n",
" 7 | \n",
" 728 | \n",
" 748 | \n",
" 803 | \n",
" 690 | \n",
" 657 | \n",
" 710 | \n",
"
\n",
" \n",
" 8 | \n",
" 679 | \n",
" 695 | \n",
" 789 | \n",
" 701 | \n",
" 696 | \n",
" 739 | \n",
"
\n",
" \n",
" 9 | \n",
" 651 | \n",
" 684 | \n",
" 634 | \n",
" 715 | \n",
" 721 | \n",
" 736 | \n",
"
\n",
" \n",
" 10 | \n",
" 652 | \n",
" 622 | \n",
" 896 | \n",
" 634 | \n",
" 734 | \n",
" 712 | \n",
"
\n",
" \n",
" 11 | \n",
" 675 | \n",
" 666 | \n",
" 918 | \n",
" 653 | \n",
" 738 | \n",
" 661 | \n",
"
\n",
" \n",
" 12 | \n",
" 719 | \n",
" 628 | \n",
" 774 | \n",
" 635 | \n",
" 668 | \n",
" 680 | \n",
"
\n",
" \n",
" 13 | \n",
" 719 | \n",
" 654 | \n",
" 633 | \n",
" 658 | \n",
" 712 | \n",
" 666 | \n",
"
\n",
" \n",
" 14 | \n",
" 920 | \n",
" 642 | \n",
" 730 | \n",
" 642 | \n",
" 742 | \n",
" 580 | \n",
"
\n",
" \n",
" 15 | \n",
" 928 | \n",
" 637 | \n",
" 743 | \n",
" 577 | \n",
" 738 | \n",
" 660 | \n",
"
\n",
" \n",
" 16 | \n",
" 1169 | \n",
" 580 | \n",
" 688 | \n",
" 654 | \n",
" 714 | \n",
" 671 | \n",
"
\n",
" \n",
" 17 | \n",
" 1124 | \n",
" 678 | \n",
" 614 | \n",
" 727 | \n",
" 629 | \n",
" 662 | \n",
"
\n",
" \n",
" 18 | \n",
" 929 | \n",
" 688 | \n",
" 633 | \n",
" 600 | \n",
" 569 | \n",
" 628 | \n",
"
\n",
" \n",
" 19 | \n",
" 692 | \n",
" 600 | \n",
" 530 | \n",
" 687 | \n",
" 652 | \n",
" 589 | \n",
"
\n",
" \n",
" 20 | \n",
" 772 | \n",
" 658 | \n",
" 667 | \n",
" 615 | \n",
" 611 | \n",
" 622 | \n",
"
\n",
" \n",
" 21 | \n",
" 692 | \n",
" 627 | \n",
" 603 | \n",
" 602 | \n",
" 624 | \n",
" 614 | \n",
"
\n",
" \n",
" 22 | \n",
" 587 | \n",
" 518 | \n",
" 538 | \n",
" 586 | \n",
" 500 | \n",
" 588 | \n",
"
\n",
" \n",
" 23 | \n",
" 700 | \n",
" 626 | \n",
" 607 | \n",
" 584 | \n",
" 584 | \n",
" 648 | \n",
"
\n",
" \n",
" 24 | \n",
" 574 | \n",
" 598 | \n",
" 561 | \n",
" 599 | \n",
" 578 | \n",
" 606 | \n",
"
\n",
" \n",
" 25 | \n",
" 617 | \n",
" 542 | \n",
" 562 | \n",
" 608 | \n",
" 558 | \n",
" 595 | \n",
"
\n",
" \n",
" 26 | \n",
" 552 | \n",
" 564 | \n",
" 599 | \n",
" 546 | \n",
" 549 | \n",
" 597 | \n",
"
\n",
" \n",
" 27 | \n",
" 584 | \n",
" 534 | \n",
" 625 | \n",
" 556 | \n",
" 524 | \n",
" 535 | \n",
"
\n",
" \n",
" 28 | \n",
" 572 | \n",
" 588 | \n",
" 583 | \n",
" 564 | \n",
" 599 | \n",
" 554 | \n",
"
\n",
" \n",
" 29 | \n",
" 550 | \n",
" 553 | \n",
" 548 | \n",
" 551 | \n",
" 560 | \n",
" 574 | \n",
"
\n",
" \n",
" 30 | \n",
" 565 | \n",
" 543 | \n",
" 560 | \n",
" 586 | \n",
" 610 | \n",
" 529 | \n",
"
\n",
" \n",
" 31 | \n",
" 531 | \n",
" 570 | \n",
" 574 | \n",
" 590 | \n",
" 580 | \n",
" 546 | \n",
"
\n",
" \n",
" 32 | \n",
" NaN | \n",
" 542 | \n",
" 537 | \n",
" 572 | \n",
" 641 | \n",
" 564 | \n",
"
\n",
" \n",
" 33 | \n",
" NaN | \n",
" 589 | \n",
" 518 | \n",
" 592 | \n",
" 574 | \n",
" 548 | \n",
"
\n",
" \n",
" 34 | \n",
" NaN | \n",
" 553 | \n",
" 565 | \n",
" 570 | \n",
" 619 | \n",
" 557 | \n",
"
\n",
" \n",
" 35 | \n",
" NaN | \n",
" 558 | \n",
" 511 | \n",
" 555 | \n",
" 470 | \n",
" 603 | \n",
"
\n",
" \n",
" 36 | \n",
" NaN | \n",
" 582 | \n",
" 594 | \n",
" 542 | \n",
" 552 | \n",
" 489 | \n",
"
\n",
" \n",
" 37 | \n",
" NaN | \n",
" 567 | \n",
" 579 | \n",
" 609 | \n",
" 576 | \n",
" 554 | \n",
"
\n",
" \n",
" 38 | \n",
" NaN | \n",
" 572 | \n",
" 598 | \n",
" 585 | \n",
" 563 | \n",
" 555 | \n",
"
\n",
" \n",
" 39 | \n",
" NaN | \n",
" 611 | \n",
" 560 | \n",
" 593 | \n",
" 592 | \n",
" 664 | \n",
"
\n",
" \n",
" 40 | \n",
" NaN | \n",
" 597 | \n",
" 595 | \n",
" 631 | \n",
" 562 | \n",
" 552 | \n",
"
\n",
" \n",
" 41 | \n",
" NaN | \n",
" 590 | \n",
" 606 | \n",
" 640 | \n",
" 587 | \n",
" 652 | \n",
"
\n",
" \n",
" 42 | \n",
" NaN | \n",
" 622 | \n",
" 640 | \n",
" 650 | \n",
" 624 | \n",
" 612 | \n",
"
\n",
" \n",
" 43 | \n",
" NaN | \n",
" 670 | \n",
" 633 | \n",
" 608 | \n",
" 624 | \n",
" 607 | \n",
"
\n",
" \n",
" 44 | \n",
" NaN | \n",
" 642 | \n",
" 604 | \n",
" 595 | \n",
" 644 | \n",
" 593 | \n",
"
\n",
" \n",
" 45 | \n",
" NaN | \n",
" 653 | \n",
" 642 | \n",
" 598 | \n",
" 626 | \n",
" 606 | \n",
"
\n",
" \n",
" 46 | \n",
" NaN | \n",
" 674 | \n",
" 656 | \n",
" 666 | \n",
" 681 | \n",
" 613 | \n",
"
\n",
" \n",
" 47 | \n",
" NaN | \n",
" 699 | \n",
" 657 | \n",
" 639 | \n",
" 661 | \n",
" 611 | \n",
"
\n",
" \n",
" 48 | \n",
" NaN | \n",
" 689 | \n",
" 673 | \n",
" 636 | \n",
" 643 | \n",
" 589 | \n",
"
\n",
" \n",
" 49 | \n",
" NaN | \n",
" 737 | \n",
" 674 | \n",
" 630 | \n",
" 693 | \n",
" 659 | \n",
"
\n",
" \n",
" 50 | \n",
" NaN | \n",
" 699 | \n",
" 708 | \n",
" 708 | \n",
" 663 | \n",
" 688 | \n",
"
\n",
" \n",
" 51 | \n",
" NaN | \n",
" 767 | \n",
" 724 | \n",
" 762 | \n",
" 691 | \n",
" 646 | \n",
"
\n",
" \n",
" 52 | \n",
" NaN | \n",
" 496 | \n",
" 461 | \n",
" 541 | \n",
" 558 | \n",
" 535 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020 total_2019 total_2018 total_2017 total_2016 total_2015\n",
"1 787 718 783 744 809 725\n",
"2 939 809 904 825 711 1031\n",
"3 767 683 885 835 720 936\n",
"4 723 734 850 881 717 828\n",
"5 727 745 815 749 690 801\n",
"6 690 701 801 723 700 720\n",
"7 728 748 803 690 657 710\n",
"8 679 695 789 701 696 739\n",
"9 651 684 634 715 721 736\n",
"10 652 622 896 634 734 712\n",
"11 675 666 918 653 738 661\n",
"12 719 628 774 635 668 680\n",
"13 719 654 633 658 712 666\n",
"14 920 642 730 642 742 580\n",
"15 928 637 743 577 738 660\n",
"16 1169 580 688 654 714 671\n",
"17 1124 678 614 727 629 662\n",
"18 929 688 633 600 569 628\n",
"19 692 600 530 687 652 589\n",
"20 772 658 667 615 611 622\n",
"21 692 627 603 602 624 614\n",
"22 587 518 538 586 500 588\n",
"23 700 626 607 584 584 648\n",
"24 574 598 561 599 578 606\n",
"25 617 542 562 608 558 595\n",
"26 552 564 599 546 549 597\n",
"27 584 534 625 556 524 535\n",
"28 572 588 583 564 599 554\n",
"29 550 553 548 551 560 574\n",
"30 565 543 560 586 610 529\n",
"31 531 570 574 590 580 546\n",
"32 NaN 542 537 572 641 564\n",
"33 NaN 589 518 592 574 548\n",
"34 NaN 553 565 570 619 557\n",
"35 NaN 558 511 555 470 603\n",
"36 NaN 582 594 542 552 489\n",
"37 NaN 567 579 609 576 554\n",
"38 NaN 572 598 585 563 555\n",
"39 NaN 611 560 593 592 664\n",
"40 NaN 597 595 631 562 552\n",
"41 NaN 590 606 640 587 652\n",
"42 NaN 622 640 650 624 612\n",
"43 NaN 670 633 608 624 607\n",
"44 NaN 642 604 595 644 593\n",
"45 NaN 653 642 598 626 606\n",
"46 NaN 674 656 666 681 613\n",
"47 NaN 699 657 639 661 611\n",
"48 NaN 689 673 636 643 589\n",
"49 NaN 737 674 630 693 659\n",
"50 NaN 699 708 708 663 688\n",
"51 NaN 767 724 762 691 646\n",
"52 NaN 496 461 541 558 535"
]
},
"execution_count": 111,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"deaths_headlines_w = deaths_headlines_w.merge(dh19w['total_2019'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_w = deaths_headlines_w.merge(dh18w['total_2018'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_w = deaths_headlines_w.merge(dh17w['total_2017'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_w = deaths_headlines_w.merge(dh16w['total_2016'], how='outer', left_index=True, right_index=True)\n",
"# deaths_headlines = deaths_headlines.merge(dh15['total_2015'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_w = deaths_headlines_w.merge(dh15w['total_2015'], how='left', left_index=True, right_index=True)\n",
"deaths_headlines_w"
]
},
{
"cell_type": "code",
"execution_count": 112,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
" total_2019 | \n",
" total_2018 | \n",
" total_2017 | \n",
" total_2016 | \n",
" total_2015 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 353.0 | \n",
" 365 | \n",
" 447 | \n",
" 416 | \n",
" 424 | \n",
" 319 | \n",
"
\n",
" \n",
" 2 | \n",
" 395.0 | \n",
" 371 | \n",
" 481 | \n",
" 434 | \n",
" 348 | \n",
" 373 | \n",
"
\n",
" \n",
" 3 | \n",
" 411.0 | \n",
" 332 | \n",
" 470 | \n",
" 397 | \n",
" 372 | \n",
" 383 | \n",
"
\n",
" \n",
" 4 | \n",
" 347.0 | \n",
" 335 | \n",
" 426 | \n",
" 387 | \n",
" 355 | \n",
" 397 | \n",
"
\n",
" \n",
" 5 | \n",
" 323.0 | \n",
" 296 | \n",
" 433 | \n",
" 371 | \n",
" 314 | \n",
" 374 | \n",
"
\n",
" \n",
" 6 | \n",
" 332.0 | \n",
" 319 | \n",
" 351 | \n",
" 336 | \n",
" 310 | \n",
" 347 | \n",
"
\n",
" \n",
" 7 | \n",
" 306.0 | \n",
" 342 | \n",
" 364 | \n",
" 337 | \n",
" 217 | \n",
" 328 | \n",
"
\n",
" \n",
" 8 | \n",
" 297.0 | \n",
" 337 | \n",
" 366 | \n",
" 351 | \n",
" 423 | \n",
" 317 | \n",
"
\n",
" \n",
" 9 | \n",
" 347.0 | \n",
" 310 | \n",
" 314 | \n",
" 352 | \n",
" 298 | \n",
" 401 | \n",
"
\n",
" \n",
" 10 | \n",
" 312.0 | \n",
" 342 | \n",
" 387 | \n",
" 357 | \n",
" 309 | \n",
" 346 | \n",
"
\n",
" \n",
" 11 | \n",
" 324.0 | \n",
" 343 | \n",
" 359 | \n",
" 251 | \n",
" 292 | \n",
" 323 | \n",
"
\n",
" \n",
" 12 | \n",
" 271.0 | \n",
" 294 | \n",
" 326 | \n",
" 356 | \n",
" 306 | \n",
" 310 | \n",
"
\n",
" \n",
" 13 | \n",
" 287.0 | \n",
" 307 | \n",
" 319 | \n",
" 314 | \n",
" 280 | \n",
" 323 | \n",
"
\n",
" \n",
" 14 | \n",
" 434.0 | \n",
" 287 | \n",
" 286 | \n",
" 306 | \n",
" 295 | \n",
" 221 | \n",
"
\n",
" \n",
" 15 | \n",
" 435.0 | \n",
" 301 | \n",
" 350 | \n",
" 270 | \n",
" 292 | \n",
" 294 | \n",
"
\n",
" \n",
" 16 | \n",
" 424.0 | \n",
" 316 | \n",
" 280 | \n",
" 245 | \n",
" 293 | \n",
" 327 | \n",
"
\n",
" \n",
" 17 | \n",
" 470.0 | \n",
" 272 | \n",
" 282 | \n",
" 327 | \n",
" 306 | \n",
" 316 | \n",
"
\n",
" \n",
" 18 | \n",
" 427.0 | \n",
" 357 | \n",
" 292 | \n",
" 258 | \n",
" 258 | \n",
" 335 | \n",
"
\n",
" \n",
" 19 | \n",
" 336.0 | \n",
" 288 | \n",
" 230 | \n",
" 302 | \n",
" 318 | \n",
" 256 | \n",
"
\n",
" \n",
" 20 | \n",
" 396.0 | \n",
" 330 | \n",
" 268 | \n",
" 315 | \n",
" 259 | \n",
" 299 | \n",
"
\n",
" \n",
" 21 | \n",
" 325.0 | \n",
" 308 | \n",
" 268 | \n",
" 328 | \n",
" 280 | \n",
" 290 | \n",
"
\n",
" \n",
" 22 | \n",
" 316.0 | \n",
" 245 | \n",
" 252 | \n",
" 256 | \n",
" 284 | \n",
" 258 | \n",
"
\n",
" \n",
" 23 | \n",
" 304.0 | \n",
" 279 | \n",
" 276 | \n",
" 292 | \n",
" 275 | \n",
" 340 | \n",
"
\n",
" \n",
" 24 | \n",
" 292.0 | \n",
" 281 | \n",
" 277 | \n",
" 300 | \n",
" 299 | \n",
" 272 | \n",
"
\n",
" \n",
" 25 | \n",
" 290.0 | \n",
" 296 | \n",
" 265 | \n",
" 271 | \n",
" 252 | \n",
" 292 | \n",
"
\n",
" \n",
" 26 | \n",
" 295.0 | \n",
" 262 | \n",
" 271 | \n",
" 296 | \n",
" 291 | \n",
" 303 | \n",
"
\n",
" \n",
" 27 | \n",
" 289.0 | \n",
" 285 | \n",
" 266 | \n",
" 262 | \n",
" 286 | \n",
" 300 | \n",
"
\n",
" \n",
" 28 | \n",
" 275.0 | \n",
" 256 | \n",
" 172 | \n",
" 253 | \n",
" 237 | \n",
" 252 | \n",
"
\n",
" \n",
" 29 | \n",
" 240.0 | \n",
" 280 | \n",
" 298 | \n",
" 288 | \n",
" 281 | \n",
" 203 | \n",
"
\n",
" \n",
" 30 | \n",
" 307.0 | \n",
" 269 | \n",
" 282 | \n",
" 287 | \n",
" 298 | \n",
" 274 | \n",
"
\n",
" \n",
" 31 | \n",
" 273.0 | \n",
" 273 | \n",
" 278 | \n",
" 287 | \n",
" 264 | \n",
" 291 | \n",
"
\n",
" \n",
" 32 | \n",
" NaN | \n",
" 266 | \n",
" 270 | \n",
" 238 | \n",
" 270 | \n",
" 248 | \n",
"
\n",
" \n",
" 33 | \n",
" NaN | \n",
" 284 | \n",
" 283 | \n",
" 266 | \n",
" 260 | \n",
" 235 | \n",
"
\n",
" \n",
" 34 | \n",
" NaN | \n",
" 274 | \n",
" 280 | \n",
" 271 | \n",
" 301 | \n",
" 251 | \n",
"
\n",
" \n",
" 35 | \n",
" NaN | \n",
" 223 | \n",
" 251 | \n",
" 243 | \n",
" 264 | \n",
" 259 | \n",
"
\n",
" \n",
" 36 | \n",
" NaN | \n",
" 243 | \n",
" 265 | \n",
" 278 | \n",
" 275 | \n",
" 237 | \n",
"
\n",
" \n",
" 37 | \n",
" NaN | \n",
" 305 | \n",
" 285 | \n",
" 266 | \n",
" 294 | \n",
" 324 | \n",
"
\n",
" \n",
" 38 | \n",
" NaN | \n",
" 281 | \n",
" 247 | \n",
" 292 | \n",
" 272 | \n",
" 283 | \n",
"
\n",
" \n",
" 39 | \n",
" NaN | \n",
" 295 | \n",
" 298 | \n",
" 282 | \n",
" 275 | \n",
" 287 | \n",
"
\n",
" \n",
" 40 | \n",
" NaN | \n",
" 263 | \n",
" 324 | \n",
" 307 | \n",
" 308 | \n",
" 282 | \n",
"
\n",
" \n",
" 41 | \n",
" NaN | \n",
" 287 | \n",
" 318 | \n",
" 284 | \n",
" 288 | \n",
" 304 | \n",
"
\n",
" \n",
" 42 | \n",
" NaN | \n",
" 316 | \n",
" 282 | \n",
" 291 | \n",
" 296 | \n",
" 299 | \n",
"
\n",
" \n",
" 43 | \n",
" NaN | \n",
" 279 | \n",
" 263 | \n",
" 318 | \n",
" 272 | \n",
" 274 | \n",
"
\n",
" \n",
" 44 | \n",
" NaN | \n",
" 302 | \n",
" 252 | \n",
" 320 | \n",
" 279 | \n",
" 292 | \n",
"
\n",
" \n",
" 45 | \n",
" NaN | \n",
" 296 | \n",
" 293 | \n",
" 295 | \n",
" 290 | \n",
" 290 | \n",
"
\n",
" \n",
" 46 | \n",
" NaN | \n",
" 336 | \n",
" 275 | \n",
" 323 | \n",
" 341 | \n",
" 297 | \n",
"
\n",
" \n",
" 47 | \n",
" NaN | \n",
" 361 | \n",
" 274 | \n",
" 303 | \n",
" 329 | \n",
" 294 | \n",
"
\n",
" \n",
" 48 | \n",
" NaN | \n",
" 334 | \n",
" 297 | \n",
" 355 | \n",
" 303 | \n",
" 279 | \n",
"
\n",
" \n",
" 49 | \n",
" NaN | \n",
" 351 | \n",
" 324 | \n",
" 324 | \n",
" 322 | \n",
" 294 | \n",
"
\n",
" \n",
" 50 | \n",
" NaN | \n",
" 353 | \n",
" 316 | \n",
" 372 | \n",
" 324 | \n",
" 343 | \n",
"
\n",
" \n",
" 51 | \n",
" NaN | \n",
" 363 | \n",
" 317 | \n",
" 354 | \n",
" 360 | \n",
" 301 | \n",
"
\n",
" \n",
" 52 | \n",
" NaN | \n",
" 194 | \n",
" 195 | \n",
" 249 | \n",
" 199 | \n",
" 232 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020 total_2019 total_2018 total_2017 total_2016 total_2015\n",
"1 353.0 365 447 416 424 319\n",
"2 395.0 371 481 434 348 373\n",
"3 411.0 332 470 397 372 383\n",
"4 347.0 335 426 387 355 397\n",
"5 323.0 296 433 371 314 374\n",
"6 332.0 319 351 336 310 347\n",
"7 306.0 342 364 337 217 328\n",
"8 297.0 337 366 351 423 317\n",
"9 347.0 310 314 352 298 401\n",
"10 312.0 342 387 357 309 346\n",
"11 324.0 343 359 251 292 323\n",
"12 271.0 294 326 356 306 310\n",
"13 287.0 307 319 314 280 323\n",
"14 434.0 287 286 306 295 221\n",
"15 435.0 301 350 270 292 294\n",
"16 424.0 316 280 245 293 327\n",
"17 470.0 272 282 327 306 316\n",
"18 427.0 357 292 258 258 335\n",
"19 336.0 288 230 302 318 256\n",
"20 396.0 330 268 315 259 299\n",
"21 325.0 308 268 328 280 290\n",
"22 316.0 245 252 256 284 258\n",
"23 304.0 279 276 292 275 340\n",
"24 292.0 281 277 300 299 272\n",
"25 290.0 296 265 271 252 292\n",
"26 295.0 262 271 296 291 303\n",
"27 289.0 285 266 262 286 300\n",
"28 275.0 256 172 253 237 252\n",
"29 240.0 280 298 288 281 203\n",
"30 307.0 269 282 287 298 274\n",
"31 273.0 273 278 287 264 291\n",
"32 NaN 266 270 238 270 248\n",
"33 NaN 284 283 266 260 235\n",
"34 NaN 274 280 271 301 251\n",
"35 NaN 223 251 243 264 259\n",
"36 NaN 243 265 278 275 237\n",
"37 NaN 305 285 266 294 324\n",
"38 NaN 281 247 292 272 283\n",
"39 NaN 295 298 282 275 287\n",
"40 NaN 263 324 307 308 282\n",
"41 NaN 287 318 284 288 304\n",
"42 NaN 316 282 291 296 299\n",
"43 NaN 279 263 318 272 274\n",
"44 NaN 302 252 320 279 292\n",
"45 NaN 296 293 295 290 290\n",
"46 NaN 336 275 323 341 297\n",
"47 NaN 361 274 303 329 294\n",
"48 NaN 334 297 355 303 279\n",
"49 NaN 351 324 324 322 294\n",
"50 NaN 353 316 372 324 343\n",
"51 NaN 363 317 354 360 301\n",
"52 NaN 194 195 249 199 232"
]
},
"execution_count": 112,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"deaths_headlines_i = deaths_headlines_i.merge(dh19i['total_2019'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_i = deaths_headlines_i.merge(dh18i['total_2018'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_i = deaths_headlines_i.merge(dh17i['total_2017'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_i = deaths_headlines_i.merge(dh16i['total_2016'], how='outer', left_index=True, right_index=True)\n",
"deaths_headlines_i = deaths_headlines_i.merge(dh15i['total_2015'], how='left', left_index=True, right_index=True)\n",
"deaths_headlines_i"
]
},
{
"cell_type": "code",
"execution_count": 113,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
" total_2019 | \n",
" total_2018 | \n",
" total_2017 | \n",
" total_2016 | \n",
" total_2015 | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 13768 | \n",
" 12424.0 | \n",
" 14701.0 | \n",
" 13612.0 | \n",
" 14863.0 | \n",
" 13751 | \n",
"
\n",
" \n",
" 2 | \n",
" 16020 | \n",
" 14487.0 | \n",
" 17430.0 | \n",
" 15528.0 | \n",
" 13154.0 | \n",
" 18318 | \n",
"
\n",
" \n",
" 3 | \n",
" 14723 | \n",
" 13545.0 | \n",
" 16355.0 | \n",
" 15231.0 | \n",
" 13060.0 | \n",
" 16738 | \n",
"
\n",
" \n",
" 4 | \n",
" 13429 | \n",
" 13283.0 | \n",
" 15971.0 | \n",
" 14461.0 | \n",
" 12859.0 | \n",
" 15712 | \n",
"
\n",
" \n",
" 5 | \n",
" 13123 | \n",
" 12799.0 | \n",
" 15087.0 | \n",
" 14188.0 | \n",
" 12571.0 | \n",
" 14560 | \n",
"
\n",
" \n",
" 6 | \n",
" 12534 | \n",
" 13222.0 | \n",
" 14111.0 | \n",
" 13805.0 | \n",
" 12697.0 | \n",
" 13730 | \n",
"
\n",
" \n",
" 7 | \n",
" 12412 | \n",
" 13347.0 | \n",
" 13925.0 | \n",
" 13212.0 | \n",
" 12016.0 | \n",
" 13510 | \n",
"
\n",
" \n",
" 8 | \n",
" 12300 | \n",
" 12877.0 | \n",
" 13753.0 | \n",
" 13330.0 | \n",
" 12718.0 | \n",
" 13071 | \n",
"
\n",
" \n",
" 9 | \n",
" 12334 | \n",
" 12479.0 | \n",
" 12190.0 | \n",
" 12819.0 | \n",
" 12733.0 | \n",
" 13181 | \n",
"
\n",
" \n",
" 10 | \n",
" 12415 | \n",
" 12396.0 | \n",
" 14859.0 | \n",
" 12580.0 | \n",
" 12493.0 | \n",
" 13007 | \n",
"
\n",
" \n",
" 11 | \n",
" 12499 | \n",
" 12018.0 | \n",
" 14367.0 | \n",
" 12089.0 | \n",
" 12489.0 | \n",
" 12475 | \n",
"
\n",
" \n",
" 12 | \n",
" 12112 | \n",
" 11797.0 | \n",
" 13397.0 | \n",
" 11833.0 | \n",
" 10983.0 | \n",
" 12027 | \n",
"
\n",
" \n",
" 13 | \n",
" 12507 | \n",
" 11260.0 | \n",
" 11310.0 | \n",
" 11453.0 | \n",
" 11738.0 | \n",
" 11987 | \n",
"
\n",
" \n",
" 14 | \n",
" 18565 | \n",
" 11445.0 | \n",
" 12272.0 | \n",
" 11305.0 | \n",
" 13060.0 | \n",
" 10325 | \n",
"
\n",
" \n",
" 15 | \n",
" 20929 | \n",
" 11661.0 | \n",
" 13843.0 | \n",
" 9761.0 | \n",
" 12757.0 | \n",
" 11575 | \n",
"
\n",
" \n",
" 16 | \n",
" 24691 | \n",
" 10243.0 | \n",
" 12639.0 | \n",
" 11000.0 | \n",
" 12310.0 | \n",
" 13061 | \n",
"
\n",
" \n",
" 17 | \n",
" 24303 | \n",
" 11452.0 | \n",
" 11596.0 | \n",
" 12356.0 | \n",
" 11795.0 | \n",
" 12023 | \n",
"
\n",
" \n",
" 18 | \n",
" 20059 | \n",
" 12695.0 | \n",
" 11538.0 | \n",
" 10372.0 | \n",
" 10401.0 | \n",
" 11586 | \n",
"
\n",
" \n",
" 19 | \n",
" 14428 | \n",
" 10361.0 | \n",
" 9821.0 | \n",
" 12114.0 | \n",
" 12002.0 | \n",
" 10138 | \n",
"
\n",
" \n",
" 20 | \n",
" 16390 | \n",
" 11717.0 | \n",
" 11386.0 | \n",
" 11718.0 | \n",
" 11222.0 | \n",
" 11692 | \n",
"
\n",
" \n",
" 21 | \n",
" 13839 | \n",
" 11653.0 | \n",
" 10974.0 | \n",
" 11431.0 | \n",
" 11013.0 | \n",
" 11334 | \n",
"
\n",
" \n",
" 22 | \n",
" 11265 | \n",
" 9534.0 | \n",
" 9397.0 | \n",
" 9603.0 | \n",
" 9192.0 | \n",
" 9514 | \n",
"
\n",
" \n",
" 23 | \n",
" 12106 | \n",
" 11461.0 | \n",
" 11259.0 | \n",
" 11134.0 | \n",
" 11171.0 | \n",
" 11603 | \n",
"
\n",
" \n",
" 24 | \n",
" 11302 | \n",
" 10754.0 | \n",
" 10535.0 | \n",
" 10698.0 | \n",
" 10673.0 | \n",
" 10858 | \n",
"
\n",
" \n",
" 25 | \n",
" 10694 | \n",
" 10807.0 | \n",
" 10514.0 | \n",
" 10930.0 | \n",
" 10611.0 | \n",
" 10629 | \n",
"
\n",
" \n",
" 26 | \n",
" 10282 | \n",
" 10824.0 | \n",
" 10529.0 | \n",
" 10624.0 | \n",
" 10526.0 | \n",
" 10525 | \n",
"
\n",
" \n",
" 27 | \n",
" 10412 | \n",
" 10328.0 | \n",
" 10565.0 | \n",
" 10565.0 | \n",
" 10412.0 | \n",
" 10545 | \n",
"
\n",
" \n",
" 28 | \n",
" 9941 | \n",
" 10512.0 | \n",
" 10467.0 | \n",
" 10643.0 | \n",
" 10647.0 | \n",
" 10278 | \n",
"
\n",
" \n",
" 29 | \n",
" 10096 | \n",
" 10324.0 | \n",
" 10353.0 | \n",
" 10426.0 | \n",
" 10672.0 | \n",
" 10028 | \n",
"
\n",
" \n",
" 30 | \n",
" 10159 | \n",
" 10422.0 | \n",
" 10356.0 | \n",
" 10147.0 | \n",
" 10612.0 | \n",
" 10021 | \n",
"
\n",
" \n",
" 31 | \n",
" 10262 | \n",
" 10564.0 | \n",
" 10408.0 | \n",
" 10239.0 | \n",
" 10433.0 | \n",
" 9893 | \n",
"
\n",
" \n",
" 32 | \n",
" NaN | \n",
" 10406.0 | \n",
" 10542.0 | \n",
" 10278.0 | \n",
" 10439.0 | \n",
" 10153 | \n",
"
\n",
" \n",
" 33 | \n",
" NaN | \n",
" 10405.0 | \n",
" 10091.0 | \n",
" 10569.0 | \n",
" 10312.0 | \n",
" 10352 | \n",
"
\n",
" \n",
" 34 | \n",
" NaN | \n",
" 10279.0 | \n",
" 10199.0 | \n",
" 10698.0 | \n",
" 10637.0 | \n",
" 10354 | \n",
"
\n",
" \n",
" 35 | \n",
" NaN | \n",
" 9478.0 | \n",
" 9046.0 | \n",
" 9372.0 | \n",
" 9226.0 | \n",
" 10239 | \n",
"
\n",
" \n",
" 36 | \n",
" NaN | \n",
" 10918.0 | \n",
" 10680.0 | \n",
" 10781.0 | \n",
" 10681.0 | \n",
" 9092 | \n",
"
\n",
" \n",
" 37 | \n",
" NaN | \n",
" 10892.0 | \n",
" 10496.0 | \n",
" 10692.0 | \n",
" 10401.0 | \n",
" 10573 | \n",
"
\n",
" \n",
" 38 | \n",
" NaN | \n",
" 10792.0 | \n",
" 10498.0 | \n",
" 10875.0 | \n",
" 10183.0 | \n",
" 10381 | \n",
"
\n",
" \n",
" 39 | \n",
" NaN | \n",
" 10954.0 | \n",
" 10463.0 | \n",
" 11027.0 | \n",
" 10278.0 | \n",
" 10826 | \n",
"
\n",
" \n",
" 40 | \n",
" NaN | \n",
" 11113.0 | \n",
" 10869.0 | \n",
" 11101.0 | \n",
" 10671.0 | \n",
" 10700 | \n",
"
\n",
" \n",
" 41 | \n",
" NaN | \n",
" 11403.0 | \n",
" 11048.0 | \n",
" 11357.0 | \n",
" 11016.0 | \n",
" 11108 | \n",
"
\n",
" \n",
" 42 | \n",
" NaN | \n",
" 11625.0 | \n",
" 11177.0 | \n",
" 11389.0 | \n",
" 11134.0 | \n",
" 10799 | \n",
"
\n",
" \n",
" 43 | \n",
" NaN | \n",
" 11415.0 | \n",
" 10885.0 | \n",
" 11152.0 | \n",
" 11048.0 | \n",
" 10966 | \n",
"
\n",
" \n",
" 44 | \n",
" NaN | \n",
" 11567.0 | \n",
" 10866.0 | \n",
" 11366.0 | \n",
" 11463.0 | \n",
" 11026 | \n",
"
\n",
" \n",
" 45 | \n",
" NaN | \n",
" 12177.0 | \n",
" 11588.0 | \n",
" 11767.0 | \n",
" 11803.0 | \n",
" 11312 | \n",
"
\n",
" \n",
" 46 | \n",
" NaN | \n",
" 12146.0 | \n",
" 11552.0 | \n",
" 11773.0 | \n",
" 12209.0 | \n",
" 11338 | \n",
"
\n",
" \n",
" 47 | \n",
" NaN | \n",
" 12472.0 | \n",
" 11289.0 | \n",
" 12102.0 | \n",
" 12064.0 | \n",
" 11178 | \n",
"
\n",
" \n",
" 48 | \n",
" NaN | \n",
" 12455.0 | \n",
" 11392.0 | \n",
" 12046.0 | \n",
" 11901.0 | \n",
" 11216 | \n",
"
\n",
" \n",
" 49 | \n",
" NaN | \n",
" 12275.0 | \n",
" 11687.0 | \n",
" 12342.0 | \n",
" 12733.0 | \n",
" 11748 | \n",
"
\n",
" \n",
" 50 | \n",
" NaN | \n",
" 12853.0 | \n",
" 12078.0 | \n",
" 12924.0 | \n",
" 12076.0 | \n",
" 11713 | \n",
"
\n",
" \n",
" 51 | \n",
" NaN | \n",
" 13566.0 | \n",
" 12649.0 | \n",
" 14308.0 | \n",
" 13137.0 | \n",
" 12136 | \n",
"
\n",
" \n",
" 52 | \n",
" NaN | \n",
" 8727.0 | \n",
" 8384.0 | \n",
" 9904.0 | \n",
" 9335.0 | \n",
" 9806 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020 total_2019 total_2018 total_2017 total_2016 total_2015\n",
"1 13768 12424.0 14701.0 13612.0 14863.0 13751\n",
"2 16020 14487.0 17430.0 15528.0 13154.0 18318\n",
"3 14723 13545.0 16355.0 15231.0 13060.0 16738\n",
"4 13429 13283.0 15971.0 14461.0 12859.0 15712\n",
"5 13123 12799.0 15087.0 14188.0 12571.0 14560\n",
"6 12534 13222.0 14111.0 13805.0 12697.0 13730\n",
"7 12412 13347.0 13925.0 13212.0 12016.0 13510\n",
"8 12300 12877.0 13753.0 13330.0 12718.0 13071\n",
"9 12334 12479.0 12190.0 12819.0 12733.0 13181\n",
"10 12415 12396.0 14859.0 12580.0 12493.0 13007\n",
"11 12499 12018.0 14367.0 12089.0 12489.0 12475\n",
"12 12112 11797.0 13397.0 11833.0 10983.0 12027\n",
"13 12507 11260.0 11310.0 11453.0 11738.0 11987\n",
"14 18565 11445.0 12272.0 11305.0 13060.0 10325\n",
"15 20929 11661.0 13843.0 9761.0 12757.0 11575\n",
"16 24691 10243.0 12639.0 11000.0 12310.0 13061\n",
"17 24303 11452.0 11596.0 12356.0 11795.0 12023\n",
"18 20059 12695.0 11538.0 10372.0 10401.0 11586\n",
"19 14428 10361.0 9821.0 12114.0 12002.0 10138\n",
"20 16390 11717.0 11386.0 11718.0 11222.0 11692\n",
"21 13839 11653.0 10974.0 11431.0 11013.0 11334\n",
"22 11265 9534.0 9397.0 9603.0 9192.0 9514\n",
"23 12106 11461.0 11259.0 11134.0 11171.0 11603\n",
"24 11302 10754.0 10535.0 10698.0 10673.0 10858\n",
"25 10694 10807.0 10514.0 10930.0 10611.0 10629\n",
"26 10282 10824.0 10529.0 10624.0 10526.0 10525\n",
"27 10412 10328.0 10565.0 10565.0 10412.0 10545\n",
"28 9941 10512.0 10467.0 10643.0 10647.0 10278\n",
"29 10096 10324.0 10353.0 10426.0 10672.0 10028\n",
"30 10159 10422.0 10356.0 10147.0 10612.0 10021\n",
"31 10262 10564.0 10408.0 10239.0 10433.0 9893\n",
"32 NaN 10406.0 10542.0 10278.0 10439.0 10153\n",
"33 NaN 10405.0 10091.0 10569.0 10312.0 10352\n",
"34 NaN 10279.0 10199.0 10698.0 10637.0 10354\n",
"35 NaN 9478.0 9046.0 9372.0 9226.0 10239\n",
"36 NaN 10918.0 10680.0 10781.0 10681.0 9092\n",
"37 NaN 10892.0 10496.0 10692.0 10401.0 10573\n",
"38 NaN 10792.0 10498.0 10875.0 10183.0 10381\n",
"39 NaN 10954.0 10463.0 11027.0 10278.0 10826\n",
"40 NaN 11113.0 10869.0 11101.0 10671.0 10700\n",
"41 NaN 11403.0 11048.0 11357.0 11016.0 11108\n",
"42 NaN 11625.0 11177.0 11389.0 11134.0 10799\n",
"43 NaN 11415.0 10885.0 11152.0 11048.0 10966\n",
"44 NaN 11567.0 10866.0 11366.0 11463.0 11026\n",
"45 NaN 12177.0 11588.0 11767.0 11803.0 11312\n",
"46 NaN 12146.0 11552.0 11773.0 12209.0 11338\n",
"47 NaN 12472.0 11289.0 12102.0 12064.0 11178\n",
"48 NaN 12455.0 11392.0 12046.0 11901.0 11216\n",
"49 NaN 12275.0 11687.0 12342.0 12733.0 11748\n",
"50 NaN 12853.0 12078.0 12924.0 12076.0 11713\n",
"51 NaN 13566.0 12649.0 14308.0 13137.0 12136\n",
"52 NaN 8727.0 8384.0 9904.0 9335.0 9806"
]
},
"execution_count": 113,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"deaths_headlines = deaths_headlines_e + deaths_headlines_w + deaths_headlines_i + deaths_headlines_s\n",
"deaths_headlines"
]
},
{
"cell_type": "code",
"execution_count": 114,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"\n",
"\n",
"
\n",
" \n",
" \n",
" | \n",
" total_2020 | \n",
" total_2019 | \n",
" total_2018 | \n",
" total_2017 | \n",
" total_2016 | \n",
" total_2015 | \n",
" previous_mean | \n",
"
\n",
" \n",
" \n",
" \n",
" 1 | \n",
" 13768 | \n",
" 12424.0 | \n",
" 14701.0 | \n",
" 13612.0 | \n",
" 14863.0 | \n",
" 13751 | \n",
" 13870.2 | \n",
"
\n",
" \n",
" 2 | \n",
" 16020 | \n",
" 14487.0 | \n",
" 17430.0 | \n",
" 15528.0 | \n",
" 13154.0 | \n",
" 18318 | \n",
" 15783.4 | \n",
"
\n",
" \n",
" 3 | \n",
" 14723 | \n",
" 13545.0 | \n",
" 16355.0 | \n",
" 15231.0 | \n",
" 13060.0 | \n",
" 16738 | \n",
" 14985.8 | \n",
"
\n",
" \n",
" 4 | \n",
" 13429 | \n",
" 13283.0 | \n",
" 15971.0 | \n",
" 14461.0 | \n",
" 12859.0 | \n",
" 15712 | \n",
" 14457.2 | \n",
"
\n",
" \n",
" 5 | \n",
" 13123 | \n",
" 12799.0 | \n",
" 15087.0 | \n",
" 14188.0 | \n",
" 12571.0 | \n",
" 14560 | \n",
" 13841.0 | \n",
"
\n",
" \n",
" 6 | \n",
" 12534 | \n",
" 13222.0 | \n",
" 14111.0 | \n",
" 13805.0 | \n",
" 12697.0 | \n",
" 13730 | \n",
" 13513.0 | \n",
"
\n",
" \n",
" 7 | \n",
" 12412 | \n",
" 13347.0 | \n",
" 13925.0 | \n",
" 13212.0 | \n",
" 12016.0 | \n",
" 13510 | \n",
" 13202.0 | \n",
"
\n",
" \n",
" 8 | \n",
" 12300 | \n",
" 12877.0 | \n",
" 13753.0 | \n",
" 13330.0 | \n",
" 12718.0 | \n",
" 13071 | \n",
" 13149.8 | \n",
"
\n",
" \n",
" 9 | \n",
" 12334 | \n",
" 12479.0 | \n",
" 12190.0 | \n",
" 12819.0 | \n",
" 12733.0 | \n",
" 13181 | \n",
" 12680.4 | \n",
"
\n",
" \n",
" 10 | \n",
" 12415 | \n",
" 12396.0 | \n",
" 14859.0 | \n",
" 12580.0 | \n",
" 12493.0 | \n",
" 13007 | \n",
" 13067.0 | \n",
"
\n",
" \n",
" 11 | \n",
" 12499 | \n",
" 12018.0 | \n",
" 14367.0 | \n",
" 12089.0 | \n",
" 12489.0 | \n",
" 12475 | \n",
" 12687.6 | \n",
"
\n",
" \n",
" 12 | \n",
" 12112 | \n",
" 11797.0 | \n",
" 13397.0 | \n",
" 11833.0 | \n",
" 10983.0 | \n",
" 12027 | \n",
" 12007.4 | \n",
"
\n",
" \n",
" 13 | \n",
" 12507 | \n",
" 11260.0 | \n",
" 11310.0 | \n",
" 11453.0 | \n",
" 11738.0 | \n",
" 11987 | \n",
" 11549.6 | \n",
"
\n",
" \n",
" 14 | \n",
" 18565 | \n",
" 11445.0 | \n",
" 12272.0 | \n",
" 11305.0 | \n",
" 13060.0 | \n",
" 10325 | \n",
" 11681.4 | \n",
"
\n",
" \n",
" 15 | \n",
" 20929 | \n",
" 11661.0 | \n",
" 13843.0 | \n",
" 9761.0 | \n",
" 12757.0 | \n",
" 11575 | \n",
" 11919.4 | \n",
"
\n",
" \n",
" 16 | \n",
" 24691 | \n",
" 10243.0 | \n",
" 12639.0 | \n",
" 11000.0 | \n",
" 12310.0 | \n",
" 13061 | \n",
" 11850.6 | \n",
"
\n",
" \n",
" 17 | \n",
" 24303 | \n",
" 11452.0 | \n",
" 11596.0 | \n",
" 12356.0 | \n",
" 11795.0 | \n",
" 12023 | \n",
" 11844.4 | \n",
"
\n",
" \n",
" 18 | \n",
" 20059 | \n",
" 12695.0 | \n",
" 11538.0 | \n",
" 10372.0 | \n",
" 10401.0 | \n",
" 11586 | \n",
" 11318.4 | \n",
"
\n",
" \n",
" 19 | \n",
" 14428 | \n",
" 10361.0 | \n",
" 9821.0 | \n",
" 12114.0 | \n",
" 12002.0 | \n",
" 10138 | \n",
" 10887.2 | \n",
"
\n",
" \n",
" 20 | \n",
" 16390 | \n",
" 11717.0 | \n",
" 11386.0 | \n",
" 11718.0 | \n",
" 11222.0 | \n",
" 11692 | \n",
" 11547.0 | \n",
"
\n",
" \n",
" 21 | \n",
" 13839 | \n",
" 11653.0 | \n",
" 10974.0 | \n",
" 11431.0 | \n",
" 11013.0 | \n",
" 11334 | \n",
" 11281.0 | \n",
"
\n",
" \n",
" 22 | \n",
" 11265 | \n",
" 9534.0 | \n",
" 9397.0 | \n",
" 9603.0 | \n",
" 9192.0 | \n",
" 9514 | \n",
" 9448.0 | \n",
"
\n",
" \n",
" 23 | \n",
" 12106 | \n",
" 11461.0 | \n",
" 11259.0 | \n",
" 11134.0 | \n",
" 11171.0 | \n",
" 11603 | \n",
" 11325.6 | \n",
"
\n",
" \n",
" 24 | \n",
" 11302 | \n",
" 10754.0 | \n",
" 10535.0 | \n",
" 10698.0 | \n",
" 10673.0 | \n",
" 10858 | \n",
" 10703.6 | \n",
"
\n",
" \n",
" 25 | \n",
" 10694 | \n",
" 10807.0 | \n",
" 10514.0 | \n",
" 10930.0 | \n",
" 10611.0 | \n",
" 10629 | \n",
" 10698.2 | \n",
"
\n",
" \n",
" 26 | \n",
" 10282 | \n",
" 10824.0 | \n",
" 10529.0 | \n",
" 10624.0 | \n",
" 10526.0 | \n",
" 10525 | \n",
" 10605.6 | \n",
"
\n",
" \n",
" 27 | \n",
" 10412 | \n",
" 10328.0 | \n",
" 10565.0 | \n",
" 10565.0 | \n",
" 10412.0 | \n",
" 10545 | \n",
" 10483.0 | \n",
"
\n",
" \n",
" 28 | \n",
" 9941 | \n",
" 10512.0 | \n",
" 10467.0 | \n",
" 10643.0 | \n",
" 10647.0 | \n",
" 10278 | \n",
" 10509.4 | \n",
"
\n",
" \n",
" 29 | \n",
" 10096 | \n",
" 10324.0 | \n",
" 10353.0 | \n",
" 10426.0 | \n",
" 10672.0 | \n",
" 10028 | \n",
" 10360.6 | \n",
"
\n",
" \n",
" 30 | \n",
" 10159 | \n",
" 10422.0 | \n",
" 10356.0 | \n",
" 10147.0 | \n",
" 10612.0 | \n",
" 10021 | \n",
" 10311.6 | \n",
"
\n",
" \n",
" 31 | \n",
" 10262 | \n",
" 10564.0 | \n",
" 10408.0 | \n",
" 10239.0 | \n",
" 10433.0 | \n",
" 9893 | \n",
" 10307.4 | \n",
"
\n",
" \n",
" 32 | \n",
" NaN | \n",
" 10406.0 | \n",
" 10542.0 | \n",
" 10278.0 | \n",
" 10439.0 | \n",
" 10153 | \n",
" 10363.6 | \n",
"
\n",
" \n",
" 33 | \n",
" NaN | \n",
" 10405.0 | \n",
" 10091.0 | \n",
" 10569.0 | \n",
" 10312.0 | \n",
" 10352 | \n",
" 10345.8 | \n",
"
\n",
" \n",
" 34 | \n",
" NaN | \n",
" 10279.0 | \n",
" 10199.0 | \n",
" 10698.0 | \n",
" 10637.0 | \n",
" 10354 | \n",
" 10433.4 | \n",
"
\n",
" \n",
" 35 | \n",
" NaN | \n",
" 9478.0 | \n",
" 9046.0 | \n",
" 9372.0 | \n",
" 9226.0 | \n",
" 10239 | \n",
" 9472.2 | \n",
"
\n",
" \n",
" 36 | \n",
" NaN | \n",
" 10918.0 | \n",
" 10680.0 | \n",
" 10781.0 | \n",
" 10681.0 | \n",
" 9092 | \n",
" 10430.4 | \n",
"
\n",
" \n",
" 37 | \n",
" NaN | \n",
" 10892.0 | \n",
" 10496.0 | \n",
" 10692.0 | \n",
" 10401.0 | \n",
" 10573 | \n",
" 10610.8 | \n",
"
\n",
" \n",
" 38 | \n",
" NaN | \n",
" 10792.0 | \n",
" 10498.0 | \n",
" 10875.0 | \n",
" 10183.0 | \n",
" 10381 | \n",
" 10545.8 | \n",
"
\n",
" \n",
" 39 | \n",
" NaN | \n",
" 10954.0 | \n",
" 10463.0 | \n",
" 11027.0 | \n",
" 10278.0 | \n",
" 10826 | \n",
" 10709.6 | \n",
"
\n",
" \n",
" 40 | \n",
" NaN | \n",
" 11113.0 | \n",
" 10869.0 | \n",
" 11101.0 | \n",
" 10671.0 | \n",
" 10700 | \n",
" 10890.8 | \n",
"
\n",
" \n",
" 41 | \n",
" NaN | \n",
" 11403.0 | \n",
" 11048.0 | \n",
" 11357.0 | \n",
" 11016.0 | \n",
" 11108 | \n",
" 11186.4 | \n",
"
\n",
" \n",
" 42 | \n",
" NaN | \n",
" 11625.0 | \n",
" 11177.0 | \n",
" 11389.0 | \n",
" 11134.0 | \n",
" 10799 | \n",
" 11224.8 | \n",
"
\n",
" \n",
" 43 | \n",
" NaN | \n",
" 11415.0 | \n",
" 10885.0 | \n",
" 11152.0 | \n",
" 11048.0 | \n",
" 10966 | \n",
" 11093.2 | \n",
"
\n",
" \n",
" 44 | \n",
" NaN | \n",
" 11567.0 | \n",
" 10866.0 | \n",
" 11366.0 | \n",
" 11463.0 | \n",
" 11026 | \n",
" 11257.6 | \n",
"
\n",
" \n",
" 45 | \n",
" NaN | \n",
" 12177.0 | \n",
" 11588.0 | \n",
" 11767.0 | \n",
" 11803.0 | \n",
" 11312 | \n",
" 11729.4 | \n",
"
\n",
" \n",
" 46 | \n",
" NaN | \n",
" 12146.0 | \n",
" 11552.0 | \n",
" 11773.0 | \n",
" 12209.0 | \n",
" 11338 | \n",
" 11803.6 | \n",
"
\n",
" \n",
" 47 | \n",
" NaN | \n",
" 12472.0 | \n",
" 11289.0 | \n",
" 12102.0 | \n",
" 12064.0 | \n",
" 11178 | \n",
" 11821.0 | \n",
"
\n",
" \n",
" 48 | \n",
" NaN | \n",
" 12455.0 | \n",
" 11392.0 | \n",
" 12046.0 | \n",
" 11901.0 | \n",
" 11216 | \n",
" 11802.0 | \n",
"
\n",
" \n",
" 49 | \n",
" NaN | \n",
" 12275.0 | \n",
" 11687.0 | \n",
" 12342.0 | \n",
" 12733.0 | \n",
" 11748 | \n",
" 12157.0 | \n",
"
\n",
" \n",
" 50 | \n",
" NaN | \n",
" 12853.0 | \n",
" 12078.0 | \n",
" 12924.0 | \n",
" 12076.0 | \n",
" 11713 | \n",
" 12328.8 | \n",
"
\n",
" \n",
" 51 | \n",
" NaN | \n",
" 13566.0 | \n",
" 12649.0 | \n",
" 14308.0 | \n",
" 13137.0 | \n",
" 12136 | \n",
" 13159.2 | \n",
"
\n",
" \n",
" 52 | \n",
" NaN | \n",
" 8727.0 | \n",
" 8384.0 | \n",
" 9904.0 | \n",
" 9335.0 | \n",
" 9806 | \n",
" 9231.2 | \n",
"
\n",
" \n",
"
\n",
"
"
],
"text/plain": [
" total_2020 total_2019 total_2018 total_2017 total_2016 total_2015 \\\n",
"1 13768 12424.0 14701.0 13612.0 14863.0 13751 \n",
"2 16020 14487.0 17430.0 15528.0 13154.0 18318 \n",
"3 14723 13545.0 16355.0 15231.0 13060.0 16738 \n",
"4 13429 13283.0 15971.0 14461.0 12859.0 15712 \n",
"5 13123 12799.0 15087.0 14188.0 12571.0 14560 \n",
"6 12534 13222.0 14111.0 13805.0 12697.0 13730 \n",
"7 12412 13347.0 13925.0 13212.0 12016.0 13510 \n",
"8 12300 12877.0 13753.0 13330.0 12718.0 13071 \n",
"9 12334 12479.0 12190.0 12819.0 12733.0 13181 \n",
"10 12415 12396.0 14859.0 12580.0 12493.0 13007 \n",
"11 12499 12018.0 14367.0 12089.0 12489.0 12475 \n",
"12 12112 11797.0 13397.0 11833.0 10983.0 12027 \n",
"13 12507 11260.0 11310.0 11453.0 11738.0 11987 \n",
"14 18565 11445.0 12272.0 11305.0 13060.0 10325 \n",
"15 20929 11661.0 13843.0 9761.0 12757.0 11575 \n",
"16 24691 10243.0 12639.0 11000.0 12310.0 13061 \n",
"17 24303 11452.0 11596.0 12356.0 11795.0 12023 \n",
"18 20059 12695.0 11538.0 10372.0 10401.0 11586 \n",
"19 14428 10361.0 9821.0 12114.0 12002.0 10138 \n",
"20 16390 11717.0 11386.0 11718.0 11222.0 11692 \n",
"21 13839 11653.0 10974.0 11431.0 11013.0 11334 \n",
"22 11265 9534.0 9397.0 9603.0 9192.0 9514 \n",
"23 12106 11461.0 11259.0 11134.0 11171.0 11603 \n",
"24 11302 10754.0 10535.0 10698.0 10673.0 10858 \n",
"25 10694 10807.0 10514.0 10930.0 10611.0 10629 \n",
"26 10282 10824.0 10529.0 10624.0 10526.0 10525 \n",
"27 10412 10328.0 10565.0 10565.0 10412.0 10545 \n",
"28 9941 10512.0 10467.0 10643.0 10647.0 10278 \n",
"29 10096 10324.0 10353.0 10426.0 10672.0 10028 \n",
"30 10159 10422.0 10356.0 10147.0 10612.0 10021 \n",
"31 10262 10564.0 10408.0 10239.0 10433.0 9893 \n",
"32 NaN 10406.0 10542.0 10278.0 10439.0 10153 \n",
"33 NaN 10405.0 10091.0 10569.0 10312.0 10352 \n",
"34 NaN 10279.0 10199.0 10698.0 10637.0 10354 \n",
"35 NaN 9478.0 9046.0 9372.0 9226.0 10239 \n",
"36 NaN 10918.0 10680.0 10781.0 10681.0 9092 \n",
"37 NaN 10892.0 10496.0 10692.0 10401.0 10573 \n",
"38 NaN 10792.0 10498.0 10875.0 10183.0 10381 \n",
"39 NaN 10954.0 10463.0 11027.0 10278.0 10826 \n",
"40 NaN 11113.0 10869.0 11101.0 10671.0 10700 \n",
"41 NaN 11403.0 11048.0 11357.0 11016.0 11108 \n",
"42 NaN 11625.0 11177.0 11389.0 11134.0 10799 \n",
"43 NaN 11415.0 10885.0 11152.0 11048.0 10966 \n",
"44 NaN 11567.0 10866.0 11366.0 11463.0 11026 \n",
"45 NaN 12177.0 11588.0 11767.0 11803.0 11312 \n",
"46 NaN 12146.0 11552.0 11773.0 12209.0 11338 \n",
"47 NaN 12472.0 11289.0 12102.0 12064.0 11178 \n",
"48 NaN 12455.0 11392.0 12046.0 11901.0 11216 \n",
"49 NaN 12275.0 11687.0 12342.0 12733.0 11748 \n",
"50 NaN 12853.0 12078.0 12924.0 12076.0 11713 \n",
"51 NaN 13566.0 12649.0 14308.0 13137.0 12136 \n",
"52 NaN 8727.0 8384.0 9904.0 9335.0 9806 \n",
"\n",
" previous_mean \n",
"1 13870.2 \n",
"2 15783.4 \n",
"3 14985.8 \n",
"4 14457.2 \n",
"5 13841.0 \n",
"6 13513.0 \n",
"7 13202.0 \n",
"8 13149.8 \n",
"9 12680.4 \n",
"10 13067.0 \n",
"11 12687.6 \n",
"12 12007.4 \n",
"13 11549.6 \n",
"14 11681.4 \n",
"15 11919.4 \n",
"16 11850.6 \n",
"17 11844.4 \n",
"18 11318.4 \n",
"19 10887.2 \n",
"20 11547.0 \n",
"21 11281.0 \n",
"22 9448.0 \n",
"23 11325.6 \n",
"24 10703.6 \n",
"25 10698.2 \n",
"26 10605.6 \n",
"27 10483.0 \n",
"28 10509.4 \n",
"29 10360.6 \n",
"30 10311.6 \n",
"31 10307.4 \n",
"32 10363.6 \n",
"33 10345.8 \n",
"34 10433.4 \n",
"35 9472.2 \n",
"36 10430.4 \n",
"37 10610.8 \n",
"38 10545.8 \n",
"39 10709.6 \n",
"40 10890.8 \n",
"41 11186.4 \n",
"42 11224.8 \n",
"43 11093.2 \n",
"44 11257.6 \n",
"45 11729.4 \n",
"46 11803.6 \n",
"47 11821.0 \n",
"48 11802.0 \n",
"49 12157.0 \n",
"50 12328.8 \n",
"51 13159.2 \n",
"52 9231.2 "
]
},
"execution_count": 114,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"deaths_headlines_e['previous_mean'] = deaths_headlines_e['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)\n",
"deaths_headlines_w['previous_mean'] = deaths_headlines_w['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)\n",
"deaths_headlines_s['previous_mean'] = deaths_headlines_s['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)\n",
"deaths_headlines_i['previous_mean'] = deaths_headlines_i['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)\n",
"deaths_headlines['previous_mean'] = deaths_headlines['total_2019 total_2018 total_2017 total_2016 total_2015'.split()].apply(np.mean, axis=1)\n",
"deaths_headlines"
]
},
{
"cell_type": "code",
"execution_count": 115,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 115,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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\n",
"text/plain": [
"