Created
July 30, 2021 01:59
-
-
Save Erotemic/d88c30fd5163b3169d083f3b7ea9e25c to your computer and use it in GitHub Desktop.
Napkin Math Hospitalizations By Age
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# https://gis.cdc.gov/grasp/covidnet/COVID19_5.html | |
# 2020-21 | |
import ubelt as ub | |
US_POP_APPROX = 330e6 | |
SAMPLE_SIZE = US_POP_APPROX * 0.1 | |
print(SAMPLE_SIZE) | |
# NOTE: These are lab-verified COVID numbers. The sample size is 190509. This | |
# represents about 10% of the US population. This chart says total observed | |
# true positives 190_509 IN THE SAMPLE SET are observed. Google says total | |
# deaths is 612_000, lets see how accounting for sample size holds up. | |
groups = { | |
'0-4' : 1237, | |
'5-17' : 2062, | |
'18-49' : 51317, | |
'50-64' : 53054, | |
'65+' : 82839, | |
} | |
total = sum([v for k, v in groups.items()]) | |
print('total = {!r}'.format(total)) | |
print('groups = {}'.format(ub.repr2(groups, nl=1))) | |
for key in groups: | |
frac = groups[key] / total | |
print(f'{key} frac = {frac * 100:07.04f}% = {groups[key]} / {total}') | |
# Extrapolate the data, based on sample size | |
frac_of_population = 0.1 | |
est_groups = ub.map_vals(lambda x: x / frac_of_population, groups) | |
est_total = sum([v for k, v in est_groups.items()]) | |
print('est_groups = {}'.format(ub.repr2(est_groups, nl=2, align=':'))) | |
print('est_total = {}'.format(ub.repr2(est_total, nl=2))) | |
# Over 1_905_090 hospitlizations leading to 612_000 deaths. So that is | |
# consistent. I suppose its always imporant to read the notes about the data | |
# collect when reading notes about raw data. | |
# Expected kid hospilizations 12370.0, |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment