various new features: new vaccination overview on country specific side, slightly changed text on index head, moved data correction to parser, made population an int, added the used vaccines to the vaccination table, and some bugfixing here and there
This commit is contained in:
fordprefect
56
coronavis.py
56
coronavis.py
@@ -94,6 +94,7 @@ def get_data():
|
||||
metadata = {}
|
||||
with open(datafile, "r") as f:
|
||||
reader = csv.reader(f)
|
||||
|
||||
for row in reader:
|
||||
if len(row) == 6:
|
||||
date,location,new_cases,new_deaths,total_cases,total_deaths = row
|
||||
@@ -105,6 +106,8 @@ def get_data():
|
||||
iso_code,continent,location,date,total_cases,new_cases,new_cases_smoothed,total_deaths,new_deaths,new_deaths_smoothed,total_cases_per_million,new_cases_per_million,new_cases_smoothed_per_million,total_deaths_per_million,new_deaths_per_million,new_deaths_smoothed_per_million,reproduction_rate,icu_patients,icu_patients_per_million,hosp_patients,hosp_patients_per_million,weekly_icu_admissions,weekly_icu_admissions_per_million,weekly_hosp_admissions,weekly_hosp_admissions_per_million,new_tests,total_tests,total_tests_per_thousand,new_tests_per_thousand,new_tests_smoothed,new_tests_smoothed_per_thousand,positive_rate,tests_per_case,tests_units,total_vaccinations,total_vaccinations_per_hundred,stringency_index,population,population_density,median_age,aged_65_older,aged_70_older,gdp_per_capita,extreme_poverty,cardiovasc_death_rate,diabetes_prevalence,female_smokers,male_smokers,handwashing_facilities,hospital_beds_per_thousand,life_expectancy,human_development_index = row
|
||||
elif len(row) == 54:
|
||||
iso_code, continent, location, date, total_cases, new_cases, new_cases_smoothed, total_deaths, new_deaths, new_deaths_smoothed, total_cases_per_million, new_cases_per_million, new_cases_smoothed_per_million, total_deaths_per_million, new_deaths_per_million, new_deaths_smoothed_per_million, reproduction_rate, icu_patients, icu_patients_per_million, hosp_patients, hosp_patients_per_million, weekly_icu_admissions, weekly_icu_admissions_per_million, weekly_hosp_admissions, weekly_hosp_admissions_per_million, new_tests, total_tests, total_tests_per_thousand, new_tests_per_thousand, new_tests_smoothed, new_tests_smoothed_per_thousand, positive_rate, tests_per_case, tests_units, total_vaccinations, new_vaccinations, total_vaccinations_per_hundred, new_vaccinations_per_million, stringency_index, population, population_density, median_age, aged_65_older, aged_70_older, gdp_per_capita, extreme_poverty, cardiovasc_death_rate, diabetes_prevalence, female_smokers, male_smokers, handwashing_facilities, hospital_beds_per_thousand, life_expectancy, human_development_index = row
|
||||
elif len(row) == 55:
|
||||
iso_code, continent, location, date, total_cases, new_cases, new_cases_smoothed, total_deaths, new_deaths, new_deaths_smoothed, total_cases_per_million, new_cases_per_million, new_cases_smoothed_per_million, total_deaths_per_million, new_deaths_per_million, new_deaths_smoothed_per_million, reproduction_rate, icu_patients, icu_patients_per_million, hosp_patients, hosp_patients_per_million, weekly_icu_admissions, weekly_icu_admissions_per_million, weekly_hosp_admissions, weekly_hosp_admissions_per_million, new_tests, total_tests, total_tests_per_thousand, new_tests_per_thousand, new_tests_smoothed, new_tests_smoothed_per_thousand, positive_rate, tests_per_case, tests_units, total_vaccinations, new_vaccinations, new_vaccinations_smoothed, total_vaccinations_per_hundred, new_vaccinations_smoothed_per_million, stringency_index, population, population_density, median_age, aged_65_older, aged_70_older, gdp_per_capita, extreme_poverty, cardiovasc_death_rate, diabetes_prevalence, female_smokers, male_smokers, handwashing_facilities, hospital_beds_per_thousand, life_expectancy, human_development_index = row
|
||||
else:
|
||||
print(f"WARNING! Table format changed, length now {len(row)}, new header:\n{row})")
|
||||
exit(1)
|
||||
@@ -130,6 +133,7 @@ def get_data():
|
||||
total_tests = tofloat(total_tests)
|
||||
positive_rate = tofloat(positive_rate)
|
||||
tests_per_case = tofloat(tests_per_case)
|
||||
new_vaccinations = tofloat(new_vaccinations)
|
||||
tests_units = tests_units
|
||||
|
||||
if location not in data:
|
||||
@@ -141,7 +145,8 @@ def get_data():
|
||||
new_cases, new_deaths, total_cases, total_deaths, total_vaccinations,
|
||||
stringency_index, reproduction_rate, icu_patients, hosp_patients,
|
||||
weekly_icu_admissions, weekly_hosp_admissions, new_tests,
|
||||
total_tests, positive_rate, tests_per_case, tests_units,]
|
||||
total_tests, positive_rate, tests_per_case, tests_units,
|
||||
new_vaccinations,]
|
||||
)
|
||||
|
||||
|
||||
@@ -155,6 +160,21 @@ def get_data():
|
||||
else:
|
||||
if metadata[location][field] != row[n]:
|
||||
print(f"{location}: {field} seems not to be a constant ({metadata[location][field]} vs {row[n]})")
|
||||
|
||||
### End of csv reading loop
|
||||
|
||||
# get data about vaccines
|
||||
vaccinesurl = "https://github.com/owid/covid-19-data/raw/master/public/data/vaccinations/locations.csv"
|
||||
vacraw = requests.get(vaccinesurl).content.decode("UTF8").split('\n')[1:-1]
|
||||
vacreader = csv.reader(vacraw)
|
||||
vaccines_country_dict = {}
|
||||
|
||||
for row in vacreader:
|
||||
land = row[0]
|
||||
vaccines = row[2]
|
||||
vaccines_country_dict[land] = vaccines
|
||||
del(vaccinesurl, vacraw, vacreader)
|
||||
|
||||
# reorganize data
|
||||
data2 = {}
|
||||
for loc in data:
|
||||
@@ -170,8 +190,9 @@ def get_data():
|
||||
positive_rate = []
|
||||
tests_per_case = []
|
||||
tests_units = []
|
||||
new_vaccinations = []
|
||||
for entry in data[loc]:
|
||||
t_, new_cases_, new_deaths_, total_cases_, total_deaths_, total_vaccinations_, stringency_index_, reproduction_rate_, icu_patients_, hosp_patients_, weekly_icu_admissions_, weekly_hosp_admissions_, new_tests_, total_tests_, positive_rate_, tests_per_case_, tests_units_ = entry
|
||||
t_, new_cases_, new_deaths_, total_cases_, total_deaths_, total_vaccinations_, stringency_index_, reproduction_rate_, icu_patients_, hosp_patients_, weekly_icu_admissions_, weekly_hosp_admissions_, new_tests_, total_tests_, positive_rate_, tests_per_case_, tests_units_, new_vaccinations_ = entry
|
||||
|
||||
time.append(t_)
|
||||
new_cases.append(toint(new_cases_))
|
||||
@@ -189,7 +210,21 @@ def get_data():
|
||||
total_tests.append(toint(total_tests_))
|
||||
positive_rate.append(positive_rate_)
|
||||
tests_per_case.append(tests_per_case_)
|
||||
new_vaccinations.append(toint(new_vaccinations_))
|
||||
tests_units.append(tests_units_)
|
||||
|
||||
### data tweaking and fixing goes here
|
||||
|
||||
# fix vaccination data: not all countries report daily vaccinations
|
||||
for n in range(1, len(total_vaccinations)):
|
||||
if np.isnan(total_vaccinations[n]) and not np.isnan(total_vaccinations[n-1]):
|
||||
total_vaccinations[n] = total_vaccinations[n-1]
|
||||
|
||||
|
||||
###
|
||||
|
||||
|
||||
# collecting data
|
||||
data2[loc] = {'time': time,
|
||||
'new_cases': new_cases,
|
||||
'new_deaths': new_deaths,
|
||||
@@ -207,11 +242,28 @@ def get_data():
|
||||
'positive_rate': positive_rate,
|
||||
'tests_per_case': tests_per_case,
|
||||
'tests_units': tests_units,
|
||||
'new_vaccinations': new_vaccinations,
|
||||
}
|
||||
# add vaccine info to metadata
|
||||
if loc in vaccines_country_dict:
|
||||
metadata[loc]['vaccines'] = vaccines_country_dict[loc]
|
||||
# cast population to int
|
||||
if loc != "International":
|
||||
try: metadata[loc]['population'] = int(float(metadata[loc]['population']))
|
||||
except: metadata[loc][loc]['population'] = np.nan
|
||||
|
||||
return data2, metadata
|
||||
|
||||
data, metadata = get_data()
|
||||
|
||||
## dump data instead of plotting
|
||||
if False:
|
||||
print("dumping data, no plotting")
|
||||
import pickle
|
||||
with open("data.dump", "wb") as f:
|
||||
pickle.dump([data, metadata], f)
|
||||
exit()
|
||||
|
||||
for plot in plots:
|
||||
i = importlib.import_module(plot)
|
||||
i.plot(data, countries, pop, metadata=metadata)
|
||||
|
||||
Reference in New Issue
Block a user