cases = cases.query("regency == 'Makassar'").dropna(subset = ["age"])
cases["age_bin"] = pd.cut(cases.age, [0, 20, 100], labels = ["school", "nonschool"])
cases = cases[cases.confirmed <= "Oct 25, 2020"]
age_ts = cases[["age_bin", "confirmed"]].groupby(["age_bin", "confirmed"]).size().sort_index()
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, T_pred, T_CI_upper, T_CI_lower, total_cases, new_cases_ts, anomalies, anomaly_dates)\
= analytical_MPVS(age_ts.loc["school"], CI = CI, smoothing = smoothing, totals = False)
school_Rt = np.mean(Rt_pred[-14:])
school_T_lb = T_CI_lower[-1]
school_T_ub = T_CI_upper[-1]
plt.Rt(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, CI)\
.title("\nMakassar: Reproductive Number Estimate: school-age population")\
.xlabel("\ndate")\
.ylabel("$R_t$\n", rotation=0, labelpad=30)\
.annotate(f"\n{window}-day smoothing window, gamma-prior Bayesian estimation method")\
.show()
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, T_pred, T_CI_upper, T_CI_lower, total_cases, new_cases_ts, anomalies, anomaly_dates)\
= analytical_MPVS(age_ts.loc["nonschool"], CI = CI, smoothing = smoothing, totals = False)
plt.Rt(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, CI)\
.title("\nMakassar: Reproductive Number Estimate: non-school-age population")\
.xlabel("\ndate")\
.ylabel("$R_t$\n", rotation=0, labelpad=30)\
.annotate(f"\n{window}-day smoothing window, gamma-prior Bayesian estimation method")\
.show()
nonschool_Rt = np.mean(Rt_pred[-14:])
nonschool_T_lb = T_CI_lower[-1]
window = 7 * days
CI = 0.95
smooth = notched_smoothing(window)
(dates_I, Rt_I, Rtu_I, Rtl_I, *_) = analytical_MPVS(df[state][:, "delta",
"confirmed"],
CI=CI,
smoothing=smooth,
totals=False)
(dates_D, Rt_D, Rtu_D, Rtl_D, *_) = analytical_MPVS(df[state][:, "delta",
"deceased"],
CI=CI,
smoothing=smooth,
totals=False)
plt.Rt(dates_I, Rt_I, Rtu_I, Rtl_I, CI)\
.title(f"{state} - $R_t(I)$ estimator")
plt.figure()
plt.Rt(dates_D, Rt_D, Rtu_D, Rtl_D, CI)\
.title(f"{state} - $R_t(D)$ estimator")
plt.show()
KA_dD = df["KA"][:, "delta", "deceased"]
KA_D = KA_dD.cumsum()
L = 14
dist = Exponential(scale=1 / L)
pmf = dist.pdf(np.linspace(dist.ppf(0.005), dist.ppf(1 - 0.005)))
pmf /= pmf.sum()
D_deconv, _ = deconvolve(KA_D, pmf)
D_deconv *= 1 / 0.02
province_cases = {province: load_province_timeseries(data, province) for province in provinces}
bgn = min(cases.index.min() for cases in province_cases.values())
end = max(cases.index.max() for cases in province_cases.values())
idx = pd.date_range(bgn, end)
province_cases = {province: cases.reindex(idx, method = "pad").fillna(0) for (province, cases) in province_cases.items()}
natl_cases = sum(province_cases.values())
logger.info("running national-level Rt estimate")
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, T_pred, T_CI_upper, T_CI_lower, total_cases, new_cases_ts, anomalies, anomaly_dates)\
= analytical_MPVS(natl_cases, CI = CI, smoothing = smoothing)
plt.Rt(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, CI, ymin=0, ymax=4)\
.title("\nIndonesia: Reproductive Number Estimate")\
.xlabel("\ndate")\
.ylabel("$R_t$", rotation=0, labelpad=30)\
.annotate(f"\n{window}-day smoothing window, gamma-prior Bayesian estimation method")\
.show()
logger.info("running case-forward prediction")
IDN = SIR("IDN", 267.7e6, dT0 = T_pred[-1], Rt0 = Rt_pred[-1], mobility = 0, random_seed = 0).run(14)
logger.info("province-level projections")
migration = np.zeros((len(provinces), len(provinces)))
estimates = []
max_len = 1 + max(map(len, provinces))
with tqdm(provinces) as progress:
for (province, cases) in province_cases.items():
progress.set_description(f"{province :<{max_len}}")
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, *_) = analytical_MPVS(cases, CI = CI, smoothing = smoothing)
plt.legend(framealpha=1, handlelength=1, loc="best")
plt.PlotDevice().xlabel("time").ylabel("reproductive rate").adjust(left=0.10,
bottom=0.15,
right=0.99,
top=0.99)
plt.ylim(0.5, 1.5)
plt.show()
# 1: parametric scheme:
dates, Rt, Rt_lb, Rt_ub, *_, anomalies, anomaly_dates = analytical_MPVS(
pd.DataFrame(sir_model.dT),
smoothing=convolution("uniform", 2),
CI=0.99,
totals=False)
pd = plt.Rt(dates, Rt, Rt_ub, Rt_lb, ymin = 0.5, ymax = 2.5, CI = 0.99, yaxis_colors = False, format_dates = False, critical_threshold = False)\
.xlabel("time")\
.ylabel("reproductive rate")\
.adjust(left = 0.11, bottom = 0.15, right = 0.98, top = 0.98)
plt.plot(sir_model.Rt, "-", color="white", linewidth=3, zorder=10)
sim_rt, = plt.plot(sir_model.Rt,
"-",
color="dodgerblue",
linewidth=2,
zorder=11)
anoms = plt.vlines(anomaly_dates, 0, 4, colors="red", linewidth=2, alpha=0.5)
plt.legend([pd.markers["Rt"], sim_rt, anoms],
["Estimated $R_t$ (99% CI)", "simulated $R_t$", "anomalies"],
**pd.legend_props)
plt.show()
# 2: naive MCMC
model, trace, summary = parametric_scheme_mcmc(sir_model.dT,
]
model = lambda: Model.single_unit(name=state,
RR0=Rt_pred[-1],
population=pop,
infectious_period=infectious_period,
I0=T_pred[-1],
lower_CI=T_CI_lower[-1],
upper_CI=T_CI_upper[-1],
random_seed=33)
forward_pred_period = 9
t_pred = [
dates[-1] + pd.Timedelta(days=i)
for i in range(forward_pred_period + 1)
]
current = model().run(forward_pred_period)
target = simulate_PID_controller(model(), 0, forward_pred_period)
plt.Rt(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, CI, ymin = 0, ymax = 5, yaxis_colors = False)\
.adjust(left = 0.10, right = 0.95, bottom = 0.15, top = 0.95)\
.xlabel("date")\
.ylabel("$R_t$")\
.show()
plt.daily_cases(dates, T_pred, T_CI_upper, T_CI_lower, new_cases_ts, anomaly_dates, anomalies, CI,
prediction_ts = [
(current[0].delta_T[1:], current[0].lower_CI[1:], current[0].upper_CI[1:], "orange", r"projection with current $R_t$"),
(target[0].delta_T[1:], target[0].lower_CI[1:], target[0].upper_CI[1:], "green", r"projection with $R_t \rightarrow 0.9$")
])\
.adjust(left = 0.10, right = 0.95, bottom = 0.15, top = 0.95)\
.xlabel("date")\
.ylabel("cases")\
.show()
state_ts = state_cases["date_reported"].value_counts().sort_index()
district_names, population_counts, _ = etl.district_migration_matrix(
data / "Migration Matrix - District.csv")
populations = dict(zip(district_names, population_counts))
# first, look at state level predictions
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, T_pred, T_CI_upper, T_CI_lower,
total_cases, new_cases_ts, anomalies, anomaly_dates) = analytical_MPVS(
state_ts,
CI=CI,
smoothing=notched_smoothing(window=smoothing),
totals=False)
plt.Rt(dates, Rt_pred[1:], Rt_CI_upper[1:], Rt_CI_lower[1:], CI, ymin=0, ymax=4)\
.title("\nBihar: Reproductive Number Estimate")\
.annotate(f"data from {str(dates[0]).split()[0]} to {str(dates[-1]).split()[0]}")\
.xlabel("date")\
.ylabel("$R_t$", rotation=0, labelpad=20)\
.show()
np.random.seed(33)
Bihar = SIR("Bihar",
99_000_000,
dT0=T_pred[-1],
Rt0=Rt_pred[-1],
lower_CI=T_CI_lower[-1],
upper_CI=T_CI_upper[-1],
mobility=0)
Bihar.run(14)
t_pred = [dates[-1] + pd.Timedelta(days=i) for i in range(len(Bihar.dT))]
cases = cases.dropna(subset=["age"])
cases["age_bin"] = pd.cut(cases.age,
bins=[0] + list(range(20, 80, 10)) + [100])
age_ts = cases[["age_bin",
"confirmed"]].groupby(["age_bin",
"confirmed"]).size().sort_index()
ss_max_rts = {}
fig, axs = plt.subplots(4, 2, True, True)
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, T_pred, T_CI_upper, T_CI_lower, total_cases, new_cases_ts, anomalies, anomaly_dates)\
= analytical_MPVS(age_ts.sum(level = 1), CI = CI, smoothing = notched_smoothing(window = 5), totals = False)
plt.sca(axs.flat[0])
plt.Rt(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower,
CI).annotate(f"all ages").adjust(left=0.04,
right=0.96,
top=0.95,
bottom=0.05,
hspace=0.3,
wspace=0.15)
r = pd.Series(Rt_pred, index=dates)
ss_max_rts["all"] = r[r.index.month_name() == "April"].max()
for (age_bin,
ax) in zip(age_ts.index.get_level_values(0).categories, axs.flat[1:]):
print(age_bin)
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower, T_pred, T_CI_upper, T_CI_lower, total_cases, new_cases_ts, anomalies, anomaly_dates)\
= analytical_MPVS(age_ts.loc[age_bin], CI = CI, smoothing = smoothing, totals = False)
plt.sca(ax)
plt.Rt(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower,
CI).annotate(f"age bin: {age_bin}")
ax.get_legend().remove()
gdf = gpd.read_file("data/gadm36_IDN_shp/gadm36_IDN_2.shp")\
.query("NAME_1 == 'Jakarta Raya'")\
.drop(columns=shp_drop_cols)
bbox = shapely.geometry.box(minx = 106.65, maxx = 107.00, miny = -6.40, maxy=-6.05)
gdf = gdf[gdf.intersects(bbox)]
jakarta_districts = dkij.district.str.title().unique()
jakarta_cases = dkij.groupby("date_positiveresult")["id"].count().rename("cases")
logger.info("running province-level Rt estimate")
(dates, RR_pred, RR_CI_upper, RR_CI_lower, T_pred, T_CI_upper, T_CI_lower, total_cases, new_cases_ts, anomalies, anomaly_dates)\
= analytical_MPVS(jakarta_cases, CI = CI, smoothing = smoothing, totals=False)
plt.Rt(dates, RR_pred[1:], RR_CI_upper[1:], RR_CI_lower[1:], CI)\
.title("\nDKI Jakarta: Reproductive Number Estimate")\
.xlabel("\ndate")\
.ylabel("$R_t$\n", rotation=0, labelpad=30)\
.annotate(f"\n{window}-day smoothing window, gamma-prior Bayesian estimation method")\
.show()
logger.info("running case-forward prediction")
prediction_period = 14*days
IDN = SIR(name = "IDN", population = 267.7e6, dT0 = T_pred[-1], Rt0 = RR_pred[-1], upper_CI = T_CI_upper[-1], lower_CI = T_CI_lower[-1], mobility = 0, random_seed = 0)\
.run(prediction_period)
plt.daily_cases(dates, T_pred[1:], T_CI_upper[1:], T_CI_lower[1:], new_cases_ts[1:], anomaly_dates, anomalies, CI,
prediction_ts = [
(IDN.dT[:-1], IDN.lower_CI[1:], IDN.upper_CI[1:], None, "predicted cases")
])\
.title("\nDKI Jakarta: Daily Cases")\
.xlabel("\ndate")\
print(state)
print(" + running estimation...")
state_ts_full = pd.Series(data = notched_smoothing(window = smoothing)(ts_full.loc[state].Hospitalized), index = ts_full.loc[state].Hospitalized.index)
(dates, Rt_pred, RR_CI_upper, RR_CI_lower, T_pred, T_CI_upper, T_CI_lower, total_cases, new_cases_ts, anomalies, anomaly_dates)\
= analytical_MPVS(ts.loc[state].Hospitalized, CI = CI, smoothing = lambda x:x, totals = False)
Rt = pd.DataFrame({"Rt": Rt_pred}, index = dates)
Rt_m = np.mean(Rt[(Rt.index >= "31 March, 2020") & (Rt.index <= "17 May, 2020")])[0]
Rt_v = np.mean(Rt[(Rt.index < "31 March, 2020")])[0]
print(" + Rt today:", Rt_pred[-1])
print(" + Rt_m :", Rt_m)
print(" + Rt_v :", Rt_v)
historical = pd.DataFrame({"smoothed": new_cases_ts}, index = dates)
plt.Rt(dates, Rt_pred, RR_CI_lower, RR_CI_upper, CI)\
.ylabel("$R_t$")\
.xlabel("date")\
.title(f"\n{state}: Reproductive Number Estimate")\
.annotate(f"public data from {str(dates[0]).split()[0]} to {str(dates[-1]).split()[0]}")\
.show()
I0 = (ts.loc[state].Hospitalized - ts.loc[state].Recovered - ts.loc[state].Deceased).sum()
state_model = SIR(name = state, population = pop, dT0 = T_pred[-1], Rt0 = Rt_pred[-1], mobility = 0, I0 = I0, upper_CI = T_CI_upper[-1], lower_CI = T_CI_lower[-1], random_seed = 0).run(10)
empirical = state_ts_full[(state_ts_full.index >= "Oct 14, 2020") & (state_ts_full.index < "Oct 25, 2020")]
plt.daily_cases(dates, T_pred, T_CI_upper, T_CI_lower, new_cases_ts, anomaly_dates, anomalies, CI,
prediction_ts=[
(state_model.dT, state_model.lower_CI, state_model.upper_CI, plt.PRED_PURPLE, "predicted cases"),
] + [(empirical, empirical, empirical, "black", "empirical post-prediction cases")] if state != "Maharashtra" else [])\
.ylabel("cases")\
.xlabel("date")\
.title(f"\n{state}: Daily Cases")\