fun=model_covid_predictions,
y0=x_0_cases,
t_span=[
t_predictions[0], t_predictions[-1]
],
t_eval=t_predictions,
args=tuple(optimal_params),
).y
return x_sol_best
x_sol_final = solve_best_params_and_predict(
best_params)
data_creator = DELPHIDataCreator(
x_sol_final=x_sol_final,
date_day_since100=date_day_since100,
best_params=best_params,
continent=continent,
country=country,
province=province,
)
# Creating the parameters dataset for this (Continent, Country, Province)
mape_data = (
mape(fitcasesnd,
x_sol_final[15, :len(fitcasesnd)]) +
mape(fitcasesd,
x_sol_final[14, :len(fitcasesd)])) / 2
try:
mape_data_2 = (
mape(
fitcasesnd[-15:],
x_sol_final[15,
len(fitcasesnd) -
x_0_cases = get_initial_conditions(
params_fitted=optimal_params,
global_params_fixed=GLOBAL_PARAMS_FIXED
)
x_sol_best = solve_ivp(
fun=model_covid,
y0=x_0_cases,
t_span=[t_predictions[0], t_predictions[-1]],
t_eval=t_predictions,
args=tuple(optimal_params),
).y
return x_sol_best
x_sol_final = solve_best_params_and_predict(best_params)
data_creator = DELPHIDataCreator(
x_sol_final=x_sol_final, date_day_since100=date_day_since100, best_params=best_params,
continent=continent, country=country, province=province, testing_data_included=False
)
# Creating the parameters dataset for this (Continent, Country, Province)
# mape_data = (
# mape(fitcasesnd, x_sol_final[15, :len(fitcasesnd)]) +
# mape(fitcasesd, x_sol_final[14, :len(fitcasesd)])
# ) / 2
if len(fitcasesnd)> 15:
mape_data_2 = (
mape(fitcasesnd[-15:], x_sol_final[15, len(fitcasesnd)-15:len(fitcasesnd)]) +
mape(fitcasesd[-15:], x_sol_final[14, len(fitcasesnd)-15:len(fitcasesd)])
) / 2
print(mape_data_2)
df_parameters_cont_country_prov = data_creator.create_dataset_parameters(mape_data_2)
list_df_global_parameters.append(df_parameters_cont_country_prov)
# Creating the datasets for predictions of this (Continent, Country, Province)
params_fitted=optimal_params,
global_params_fixed=GLOBAL_PARAMS_FIXED)
x_sol_best = solve_ivp(
fun=model_covid_predictions,
y0=x_0_cases,
t_span=[t_predictions[0], t_predictions[-1]],
t_eval=t_predictions,
args=tuple(optimal_params),
).y
return x_sol_best
x_sol_final = solve_best_params_and_predict(best_params)
data_creator = DELPHIDataCreator(
x_sol_final=x_sol_final,
date_day_since100=date_day_since100,
best_params=best_params,
continent=continent,
country=country,
province=province,
)
# Creating the parameters dataset for this (Continent, Country, Province)
mape_data = (
mape(fitcasesnd, x_sol_final[15, :len(fitcasesnd)]) +
mape(fitcasesd, x_sol_final[14, :len(fitcasesd)])) / 2
mape_data_2 = (mape(
fitcasesnd[-15:], x_sol_final[
15, len(fitcasesnd) - 15:len(fitcasesnd)]) + mape(
fitcasesd[-15:], x_sol_final[
14,
len(fitcasesnd) - 15:len(fitcasesd)])) / 2
print("Policy: ", future_policy, "\t Enacting Time: ",
future_time, "\t Total MAPE=", mape_data,
params_fitted=optimal_params,
global_params_fixed=GLOBAL_PARAMS_FIXED)
x_sol_best = solve_ivp(
fun=model_covid,
y0=x_0_cases,
t_span=[t_cases_all[0], t_cases_all[-1]],
t_eval=t_cases_all,
args=tuple(optimal_params),
).y
return x_sol_best
x_sol_final = solve_best_params_and_predict(best_params)
data_creator = DELPHIDataCreator(
x_sol_final=x_sol_final,
date_day_since100=date_day_since100,
best_params=best_params,
continent=continent,
country=country,
province=province,
)
df_backtest_performance_tuple = data_creator.create_df_backtest_performance_tuple(
fitcasesnd=fitcasesnd,
fitcasesd=fitcasesd,
testcasesnd=testcasesnd,
testcasesd=testcasesd,
n_days_fitting=n_days_fitting,
n_days_test=n_days_test,
)
# Appending the dataset for backtest performance of this (Continent, Country, Province)
list_df_backtest_performance.append(df_backtest_performance_tuple)
print(
f"Finished backtesting for Continent={continent}, Country={country}, Province={province}"