def implementation_checks(window: int = 7):
df = get_dataframe()
ts = get_time_series(df)
I = ts.Hospitalized.values
for kernel in kernels.keys():
plt.figure()
plt.bar(x = ts.index, height = I, label = "raw")
smoother = convolution(kernel, window)
plt.plot(ts.index, smoother(I)[:-window+1], label = "smooth")
plt.title(f"kernel: {kernel} (window: {window})", loc = "left")
plt.show()
.xlabel("date").ylabel("cases")\
.show()
# now, do district-level estimation
smoothing = 10
state_cases["geo_reported"] = state_cases.geo_reported.str.strip()
district_time_series = state_cases.groupby(
["geo_reported", "date_reported"])["date_reported"].count().sort_index()
migration = np.zeros((len(district_names), len(district_names)))
estimates = []
max_len = 1 + max(map(len, district_names))
with tqdm(etl.normalize(district_names)) as districts:
for district in districts:
districts.set_description(f"{district :<{max_len}}")
try:
(dates, Rt_pred, Rt_CI_upper, Rt_CI_lower,
*_) = analytical_MPVS(district_time_series.loc[district],
CI=CI,
smoothing=convolution(window=smoothing),
totals=False)
estimates.append(
(district, Rt_pred[-1], Rt_CI_lower[-1], Rt_CI_upper[-1],
linear_projection(dates, Rt_pred, smoothing)))
except (IndexError, ValueError):
estimates.append((district, np.nan, np.nan, np.nan, np.nan))
estimates = pd.DataFrame(estimates)
estimates.columns = ["district", "Rt", "Rt_CI_lower", "Rt_CI_upper", "Rt_proj"]
estimates.set_index("district", inplace=True)
estimates.to_csv(data / "Rt_estimates_private.csv")
print(estimates)
return (release, adaptive)
if __name__ == "__main__":
root = cwd()
data = root / "data"
figs = root / "figs"
# model details
gamma = 0.2
prevalence = 1
total_time = 90 * days
release_date = pd.to_datetime("July 28, 2020")
lockdown_period = (release_date - pd.to_datetime("today")).days
smoothing = convolution()
states = [
"Maharashtra", "Karnataka", "Andhra Pradesh", "Tamil Nadu",
"Madhya Pradesh", "Punjab", "Gujarat", "Kerala"
]
# use gravity matrix for states after 2001 census
new_state_data_paths = {
"Telangana": (data / "telangana.json", data / "telangana_pop.csv")
}
# define data versions for api files
paths = {
"v3": ["raw_data1.csv", "raw_data2.csv"],
"v4": [
plt.plot(sir_model.dT)
plt.show()
plt.plot(R0_timeseries, "-", color="black", label="$R_0$")
plt.plot(sir_model.Rt, "-", color="dodgerblue", label="$R_t$")
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"],
# # pass
df = load_all_data(v3_paths=[data / filepath for filepath in paths['v3']],
v4_paths=[data / filepath for filepath in paths['v4']])
data_recency = str(df["date_announced"].max()).split()[0]
run_date = str(pd.Timestamp.now()).split()[0]
ts = get_time_series(df) #, ["detected_state", "detected_district"])
one_day = pd.Timedelta(days=1)
# fig 1
infections = ts[
ts.date >= "May 01, 2020"].Hospitalized #.sum(level = 2).sort_index()
smoothed = convolution("uniform")
scatter = plt.scatter(infections.index[:-7],
infections.values[:-7],
color="#CC4C75",
marker="s",
s=5,
alpha=0.5)
lineplot, = plt.plot(infections.index[:-7],
smoothed(infections.values[:-7]),
color="#CC4C75",
linewidth=2)
plt.PlotDevice()\
.l_title("daily confirmed cases in India")\
.r_title("source:\nCOVID19India")\
.axis_labels(x = "date", y = "cases", enforce_spacing = True)\
.adjust(left = 0.10, bottom = 0.15, right = 0.98, top = 0.90)
CI = 0.95
# private data
state_cases = pd.read_csv(data/"Bihar_cases_data_Jul23.csv", parse_dates=["date_reported"], dayfirst=True)
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,
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(state_ts, CI = CI, smoothing = convolution(window = smoothing))
plot_RR_est(dates, RR_pred, RR_CI_upper, RR_CI_lower, CI, ymin=0, ymax=4)\
.title("Bihar: Reproductive Number Estimate Comparisons")\
.xlabel("Date")\
.ylabel("Rt", rotation=0, labelpad=20)
plt.ylim(0, 4)
# public data
paths = {
"v3": [data_path(_) for _ in (1, 2)],
"v4": [data_path(_) for _ in range(3, 13)]
}
for target in paths['v3'] + paths['v4']:
download_data(data, target)
.axis_labels(x = "date", y = "tests (millions)")\
.adjust(bottom = 0.16)
plt.gca().xaxis.set_major_formatter(formatter)
plt.show()
## b
plt.plot(india_data.tpr["July 01, 2020":], color="royalblue")
plt.PlotDevice()\
.l_title("test positivity rate over time")\
.axis_labels(x = "date", y = "TPR (%)")\
.adjust(bottom = 0.16)
plt.gca().xaxis.set_major_formatter(formatter)
plt.show()
# fig 5
smoothing = convolution("uniform", window=7)
plt.plot(india_data.index,
smoothing(india_data["cfr_maxcor"]),
color="maroon",
label="10-day lag CFR (upper bound)")
plt.plot(
india_data.index,
(smoothing(india_data["cfr_maxcor"]) + smoothing(india_data["adj_cfr"])) /
2,
color="indigo",
linestyle="dashed",
label="averaged")
plt.plot(india_data.index,
smoothing(india_data["adj_cfr"]),
color="navy",
label="adjusted CFR (lower bound)")