Skip to content

Instantly share code, notes, and snippets.

@xenatisch

xenatisch/population_test.ipynb

Last active January 16, 2021 18:17
Show Gist options
  • Save xenatisch/3b8d5cacdf9c97bcc62929aff3650d98 to your computer and use it in GitHub Desktop.
Save xenatisch/3b8d5cacdf9c97bcc62929aff3650d98 to your computer and use it in GitHub Desktop.
Download ZIP
Reproduction of population from incidence rates
Display the source blob
Display the rendered blob
Raw
population_test.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"from uk_covid19 import Cov19API"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>areaCode</th>\n",
" <th>areaName</th>\n",
" <th>date</th>\n",
" <th>cumCasesBySpecimenDate</th>\n",
" <th>cumCasesBySpecimenDateRate</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>E12000004</td>\n",
" <td>East Midlands</td>\n",
" <td>2021-01-15</td>\n",
" <td>235286</td>\n",
" <td>4865.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>E12000006</td>\n",
" <td>East of England</td>\n",
" <td>2021-01-15</td>\n",
" <td>292530</td>\n",
" <td>4690.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>E12000007</td>\n",
" <td>London</td>\n",
" <td>2021-01-15</td>\n",
" <td>567931</td>\n",
" <td>6337.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>E12000001</td>\n",
" <td>North East</td>\n",
" <td>2021-01-15</td>\n",
" <td>148883</td>\n",
" <td>5576.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>E12000002</td>\n",
" <td>North West</td>\n",
" <td>2021-01-15</td>\n",
" <td>466629</td>\n",
" <td>6356.3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" areaCode areaName date cumCasesBySpecimenDate \\\n",
"0 E12000004 East Midlands 2021-01-15 235286 \n",
"1 E12000006 East of England 2021-01-15 292530 \n",
"2 E12000007 London 2021-01-15 567931 \n",
"3 E12000001 North East 2021-01-15 148883 \n",
"4 E12000002 North West 2021-01-15 466629 \n",
"\n",
" cumCasesBySpecimenDateRate \n",
"0 4865.4 \n",
"1 4690.9 \n",
"2 6337.1 \n",
"3 5576.3 \n",
"4 6356.3 "
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"metric_names = [\n",
" \"areaCode\",\n",
" \"areaName\",\n",
" \"date\",\n",
" \"cumCasesBySpecimenDate\",\n",
" \"cumCasesBySpecimenDateRate\"\n",
"]\n",
"\n",
"api = Cov19API(\n",
" filters=[\"areaType=region\"],\n",
" structure=dict(zip(metric_names, metric_names)),\n",
" latest_by=\"cumCasesBySpecimenDate\"\n",
")\n",
"\n",
"df = api.get_dataframe()\n",
"\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>areaCode</th>\n",
" <th>areaName</th>\n",
" <th>date</th>\n",
" <th>cumCasesBySpecimenDate</th>\n",
" <th>cumCasesBySpecimenDateRate</th>\n",
" <th>population_repr</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>E12000004</td>\n",
" <td>East Midlands</td>\n",
" <td>2021-01-15</td>\n",
" <td>235286</td>\n",
" <td>4865.4</td>\n",
" <td>4835902</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>E12000006</td>\n",
" <td>East of England</td>\n",
" <td>2021-01-15</td>\n",
" <td>292530</td>\n",
" <td>4690.9</td>\n",
" <td>6236117</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>E12000007</td>\n",
" <td>London</td>\n",
" <td>2021-01-15</td>\n",
" <td>567931</td>\n",
" <td>6337.1</td>\n",
" <td>8962002</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>E12000001</td>\n",
" <td>North East</td>\n",
" <td>2021-01-15</td>\n",
" <td>148883</td>\n",
" <td>5576.3</td>\n",
" <td>2669925</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>E12000002</td>\n",
" <td>North West</td>\n",
" <td>2021-01-15</td>\n",
" <td>466629</td>\n",
" <td>6356.3</td>\n",
" <td>7341205</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>E12000008</td>\n",
" <td>South East</td>\n",
" <td>2021-01-15</td>\n",
" <td>415842</td>\n",
" <td>4529.8</td>\n",
" <td>9180140</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>E12000009</td>\n",
" <td>South West</td>\n",
" <td>2021-01-15</td>\n",
" <td>162556</td>\n",
" <td>2890.0</td>\n",
" <td>5624775</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>E12000005</td>\n",
" <td>West Midlands</td>\n",
" <td>2021-01-15</td>\n",
" <td>309690</td>\n",
" <td>5218.9</td>\n",
" <td>5934009</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>E12000003</td>\n",
" <td>Yorkshire and The Humber</td>\n",
" <td>2021-01-15</td>\n",
" <td>294186</td>\n",
" <td>5346.0</td>\n",
" <td>5502918</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" areaCode areaName date cumCasesBySpecimenDate \\\n",
"0 E12000004 East Midlands 2021-01-15 235286 \n",
"1 E12000006 East of England 2021-01-15 292530 \n",
"2 E12000007 London 2021-01-15 567931 \n",
"3 E12000001 North East 2021-01-15 148883 \n",
"4 E12000002 North West 2021-01-15 466629 \n",
"5 E12000008 South East 2021-01-15 415842 \n",
"6 E12000009 South West 2021-01-15 162556 \n",
"7 E12000005 West Midlands 2021-01-15 309690 \n",
"8 E12000003 Yorkshire and The Humber 2021-01-15 294186 \n",
"\n",
" cumCasesBySpecimenDateRate population_repr \n",
"0 4865.4 4835902 \n",
"1 4690.9 6236117 \n",
"2 6337.1 8962002 \n",
"3 5576.3 2669925 \n",
"4 6356.3 7341205 \n",
"5 4529.8 9180140 \n",
"6 2890.0 5624775 \n",
"7 5218.9 5934009 \n",
"8 5346.0 5502918 "
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = df.assign(\n",
" population_repr=(\n",
" df.cumCasesBySpecimenDate / df.cumCasesBySpecimenDateRate * 100000\n",
" ).round().astype(int)\n",
")\n",
"\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'56,286,993'"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"format(df.population_repr.sum(), \",d\")"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"England - regions: 55,977,178\n",
"England - Nation: 55,977,178\n"
]
}
],
"source": [
"from requests import request\n",
"from itertools import chain\n",
"\n",
"\n",
"region_url = (\n",
" 'https://coronavirus.data.gov.uk/api/v1/'\n",
" 'lookup?filters=areaType=region'\n",
" '&structure=[\"areaCode\"]'\n",
")\n",
"\n",
"resp = request(\"GET\", region_url)\n",
"region_codes = list(chain(*resp.json()[\"data\"]))\n",
"\n",
"\n",
"pop_url = \"https://coronavirus.data.gov.uk/public/assets/population/population.json\"\n",
"\n",
"resp = request(\"GET\", pop_url)\n",
"\n",
"data = resp.json()\n",
"england_regions = {\n",
" key: value for key, value in data.items() \n",
" if key.startswith(\"E\") and key in region_codes\n",
"}\n",
"\n",
"print(f\"England - regions: {sum(england_regions.values()):,d}\")\n",
"print(f\"England - Nation: {data['E92000001']:,d}\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'E12000001': 2657909,\n",
" 'E12000002': 7292093,\n",
" 'E12000003': 5479615,\n",
" 'E12000004': 4804149,\n",
" 'E12000005': 5900757,\n",
" 'E12000006': 6201214,\n",
" 'E12000007': 8908081,\n",
" 'E12000008': 9133625,\n",
" 'E12000009': 5599735}"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"england_regions"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3.7.7 64-bit ('anaconda3': virtualenv)",
"language": "python",
"name": "python37764bitanaconda3virtualenv170a8a6454fc493eac0c047df6a6a6c0"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.7"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment