])\
.title("\nDKI Jakarta: Daily Cases")\
.xlabel("\ndate")\
.ylabel("cases\n")\
.annotate("\nBayesian training process on empirical data, with anomalies identified")\
.show()
logger.info("district-level projections")
district_cases = dkij.groupby(["district", "date_positiveresult"])["id"].count().sort_index()
districts = dkij.district.unique()
migration = np.zeros((len(districts), len(districts)))
estimates = []
max_len = 1 + max(map(len, districts))
with tqdm(districts) as progress:
for district in districts:
progress.set_description(f"{district :<{max_len}}")
(dates, RR_pred, RR_CI_upper, RR_CI_lower, *_) = analytical_MPVS(district_cases.loc[district], CI = CI, smoothing = smoothing, totals=False)
estimates.append((district, RR_pred[-1], RR_CI_lower[-1], RR_CI_upper[-1], linear_projection(dates, RR_pred, window)))
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/"Jakarta_Rt_projections.csv")
print(estimates)
logger.info("generating choropleths")
gdf = gdf.merge(estimates, left_on = "NAME_2", right_on = "district")
plt.choropleth(gdf, lambda row: row["NAME_2"]+"\n")\
.adjust(left = 0.06)\
.title("\nDKI Jakarta: $R_t$ by District")\
.show()
def generate_report(state_code: str):
print(f"Received request for {state_code}.")
state = state_code_lookup[state_code]
normalized_state = state.replace(" and ", " And ").replace(" & ", " And ")
blobs = {
f"pipeline/est/{state_code}_state_Rt.csv":
f"/tmp/state_Rt_{state_code}.csv",
f"pipeline/est/{state_code}_district_Rt.csv":
f"/tmp/district_Rt_{state_code}.csv",
f"pipeline/commons/maps/{state_code}.json":
f"/tmp/state_{state_code}.geojson"
} if normalized_state not in dissolved_states else {
f"pipeline/est/{state_code}_state_Rt.csv":
f"/tmp/state_Rt_{state_code}.csv",
}
for (blob_name, filename) in blobs.items():
bucket.blob(blob_name).download_to_filename(filename)
print(f"Downloaded estimates for {state_code}.")
state_Rt = pd.read_csv(f"/tmp/state_Rt_{state_code}.csv",
parse_dates=["dates"],
index_col=0)
plt.close("all")
dates = [pd.Timestamp(date).to_pydatetime() for date in state_Rt.dates]
plt.Rt(dates, state_Rt.Rt_pred, state_Rt.Rt_CI_lower, state_Rt.Rt_CI_upper, CI)\
.axis_labels("date", "$R_t$")\
.title(f"{state}: $R_t$ over time", ha = "center", x = 0.5)\
.adjust(left = 0.11, bottom = 0.16)
plt.gcf().set_size_inches(3840 / 300, 1986 / 300)
plt.savefig(f"/tmp/{state_code}_Rt_timeseries.png")
plt.close()
print(f"Generated timeseries plot for {state_code}.")
# check output is at least 50 KB
timeseries_size_kb = os.stat(
f"/tmp/{state_code}_Rt_timeseries.png").st_size / 1000
print(f"Timeseries artifact size: {timeseries_size_kb} kb")
assert timeseries_size_kb > 50
bucket.blob(
f"pipeline/rpt/{state_code}_Rt_timeseries.png").upload_from_filename(
f"/tmp/{state_code}_Rt_timeseries.png", content_type="image/png")
if normalized_state not in (island_states + dissolved_states):
district_Rt = pd.read_csv(f"/tmp/district_Rt_{state_code}.csv",
parse_dates=["dates"],
index_col=0)
latest_Rt = district_Rt[district_Rt.dates == district_Rt.dates.max(
)].set_index("district")["Rt_pred"].to_dict()
top10 = [(k, "> 3.0" if v > 3 else f"{v:.2f}") for (k, v) in sorted(
latest_Rt.items(), key=lambda t: t[1], reverse=True)[:10]]
gdf = gpd.read_file(f"/tmp/state_{state_code}.geojson")
gdf["Rt"] = gdf.district.map(latest_Rt)
fig, ax = plt.subplots()
fig.set_size_inches(3840 / 300, 1986 / 300)
plt.choropleth(gdf, title = None, mappable = plt.get_cmap(0.75, 2.5), fig = fig, ax = ax)\
.adjust(left = 0)
plt.sca(fig.get_axes()[0])
plt.PlotDevice(fig).title(f"{state}: $R_t$ by district",
ha="center",
x=0.5)
plt.axis('off')
plt.savefig(f"/tmp/{state_code}_Rt_choropleth.png", dpi=300)
plt.close()
print(f"Generated choropleth for {state_code}.")
# check output is at least 100 KB
choropleth_size_kb = os.stat(
f"/tmp/{state_code}_Rt_choropleth.png").st_size / 1000
print(f"Choropleth artifact size: {choropleth_size_kb} kb")
assert choropleth_size_kb > 100
bucket.blob(f"pipeline/rpt/{state_code}_Rt_choropleth.png"
).upload_from_filename(
f"/tmp/{state_code}_Rt_choropleth.png",
content_type="image/png")
else:
print(f"Skipped choropleth for {state_code}.")
if normalized_state not in dissolved_states:
fig, ax = plt.subplots(1, 1)
ax.axis('tight')
ax.axis('off')
table = ax.table(cellText=top10,
colLabels=["district", "$R_t$"],
loc='center',
cellLoc="center")
table.scale(1, 2)
for (row, col), cell in table.get_celld().items():
if (row == 0):
cell.set_text_props(fontfamily=plt.theme.label["family"],
fontsize=plt.theme.label["size"],
fontweight="semibold")
else:
cell.set_text_props(fontfamily=plt.theme.label["family"],
fontsize=plt.theme.label["size"],
fontweight="light")
plt.PlotDevice().title(f"{state}: top districts by $R_t$",
ha="center",
x=0.5)
plt.savefig(f"/tmp/{state_code}_Rt_top10.png", dpi=600)
plt.close()
print(f"Generated top 10 district listing for {state_code}.")
# check output is at least 50 KB
top10_size_kb = os.stat(
f"/tmp/{state_code}_Rt_top10.png").st_size / 1000
print(f"Top 10 listing artifact size: {top10_size_kb} kb")
assert top10_size_kb > 50
bucket.blob(
f"pipeline/rpt/{state_code}_Rt_top10.png").upload_from_filename(
f"/tmp/{state_code}_Rt_top10.png", content_type="image/png")
else:
print(f"Skipped top 10 district listing for {state_code}.")
# sleep for 15 seconds to ensure the images finish saving
time.sleep(15)
print(f"Uploaded artifacts for {state_code}.")
return "OK!"
)].set_index("district")["Rt_pred"].to_dict()
plt.Rt(list(state_Rt.dates), state_Rt.Rt_pred, state_Rt.Rt_CI_lower, state_Rt.Rt_CI_upper, CI)\
.axis_labels("date", "$R_t$")\
.title("Maharashtra: $R_t$ over time", ha = "center", x = 0.5)\
.adjust(left = 0.11, bottom = 0.16)
plt.gcf().set_size_inches(3840 / 300, 1986 / 300)
plt.savefig("./MH_Rt_timeseries.png")
plt.clf()
gdf = gpd.read_file("data/maharashtra.json", dpi=600)
gdf["Rt"] = gdf.district.map(latest_Rt)
fig, ax = plt.subplots()
fig.set_size_inches(3840 / 300, 1986 / 300)
plt.choropleth(gdf, title = None, mappable = plt.get_cmap(0.75, 2.5), fig = fig, ax = ax)\
.adjust(left = 0)
plt.sca(fig.get_axes()[0])
plt.PlotDevice(fig).title(f"{state}: $R_t$ by district", ha="center", x=0.5)
plt.axis('off')
plt.savefig(f"./{state_code}_Rt_choropleth.png", dpi=300)
plt.clf()
top10 = [
(k, "> 3.0" if v > 3 else f"{v:.2f}", v)
for (k,
v) in sorted(latest_Rt.items(), key=lambda t: t[1], reverse=True)[:10]
]
fig, ax = plt.subplots(1, 1)
ax.axis('tight')
ax.axis('off')
smoothing=smoothing,
totals=False)
estimates.append(
(regency, Rt_pred[-1], Rt_CI_lower[-1], Rt_CI_upper[-1],
linear_projection(dates, Rt_pred, 7)))
estimates = pd.DataFrame(estimates)
estimates.columns = ["regency", "Rt", "Rt_CI_lower", "Rt_CI_upper", "Rt_proj"]
estimates.set_index("regency", inplace=True)
estimates.to_csv("data/SULSEL_Rt_projections.csv")
print(estimates)
gdf = gpd.read_file("data/gadm36_IDN_shp/gadm36_IDN_2.shp")\
.query("NAME_1 == 'Sulawesi Selatan'")\
.merge(estimates, left_on = "NAME_2", right_on = "regency")
choro = plt.choropleth(gdf, mappable=plt.get_cmap(0.4, 1.4, "viridis"))
for ax in choro.figure.axes[:-1]:
plt.sca(ax)
plt.xlim(left=119, right=122)
plt.ylim(bottom=-7.56, top=-1.86)
plt.show()
logger.info("adaptive control")
(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(new_cases, CI = CI, smoothing = smoothing, totals = False)
Rt = pd.DataFrame(data={"Rt": Rt_pred[1:]}, index=dates)
Rt_current = Rt_pred[-1]
Rt_m = np.mean(Rt[(Rt.index >= "April 21, 2020")
& (Rt.index <= "May 22, 2020")])[0]
logger.info("generating choropleths")
sm = mpl.cm.ScalarMappable(norm=mpl.colors.Normalize(vmin=0.9, vmax=1.4),
cmap="viridis")
gdf = gdf.merge(estimates, left_on="NAME_3", right_on="subdistrict")
def labeller():
count = 0
def label(row):
nonlocal count
if row["Rt"] >= 1.3 or row["Rt_proj"] >= 1.3:
letter = chr(67 - count)
count += 1
print(letter, row["NAME_3"].title(), row["Rt"], row["Rt_proj"])
return f"({letter})\n"
return ""
return label
plt.choropleth(gdf, label_fn = lambda _: "", mappable = sm)\
.adjust(left = 0.06)\
.show()
# # crop to right
# plt.choropleth(gdf, label_fn = None, Rt_col= "Rt_proj", Rt_proj_col= "Rt", titles = ["Projected $R_t$ (1 Week)", "Current $R_t$"], mappable = sm)\
# .adjust(left = 0.06)\
# .show()