plt.plot(0.2093 * df[state][:, "delta", "tested"],
label="national test-scaled")
plt.plot(scale_factor * df[state][:, "delta", "tested"],
label="state test-scaled")
plt.plot(df[state][:, "delta", "confirmed"], label="confirmed")
plt.legend()
plt.PlotDevice().title(f"\n{state} / case scaling comparison").xlabel(
"\ndate").ylabel("cases\n")
plt.show()
# I vs D estimators
gamma = 0.2
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()
gamma = 0.2
window = 10
CI = 0.95
state_cases = pd.read_csv(data/"Bihar_cases_data_Oct03.csv", parse_dates=["date_reported", "date_status_change"], dayfirst=True)
state_cases["geo_reported"] = state_cases.geo_reported.str.strip()
state_cases = state_cases[state_cases.date_reported <= "2020-09-30"]
state_ts = state_cases["date_reported"].value_counts().sort_index()
district_ts = state_cases.groupby(["geo_reported", "date_reported"])["date_reported"].count().sort_index()
districts, pops, migrations = etl.district_migration_matrix(data/"Migration Matrix - District.csv")
districts = sorted([etl.replacements.get(dn, dn) for dn in districts])
R_mandatory = dict()
for district in districts:#district_ts.index.get_level_values(0).unique():
try:
(_, Rt, *_) = analytical_MPVS(district_ts.loc[district], CI = CI, smoothing = notched_smoothing(window = 10), totals = False)
Rm = np.mean(Rt)
except ValueError as v:
Rm = 1.5
R_mandatory[district] = Rm
R_voluntary = {district: 1.2*R for (district, R) in R_mandatory.items()}
si, sf = 0, 10
simulation_results = [
run_policies(state_cases, pops, districts, migrations, gamma, R_mandatory, R_voluntary, lockdown_period = lockdown_period, total = total_time, seed = seed)
for seed in tqdm(range(si, sf))
]
plt.simulations(
run_date = str(pd.Timestamp.now()).split()[0]
ts = get_time_series(df, "detected_state")
states = ["Maharashtra", "Bihar", "Delhi", "Andhra Pradesh", "Telangana", "Tamil Nadu", "Madhya Pradesh"]
for state in states:
print(state)
print(" + running estimation...")
(
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 = notched_smoothing(window = smoothing), totals = False)
estimates = pd.DataFrame(data = {
"dates": dates,
"Rt_pred": Rt_pred,
"RR_CI_upper": RR_CI_upper,
"RR_CI_lower": RR_CI_lower,
"T_pred": T_pred,
"T_CI_upper": T_CI_upper,
"T_CI_lower": T_CI_lower,
"total_cases": total_cases[2:],
"new_cases_ts": new_cases_ts,
})
print(" + Rt today:", Rt_pred[-1])
# plt.Rt(dates, Rt_pred, RR_CI_lower, RR_CI_upper, CI)\
# .ylabel("Estimated $R_t$")\
import pandas as pd
import shapely
from adaptive.estimators import analytical_MPVS, linear_projection
from adaptive.etl.commons import download_data
from adaptive.models import SIR, NetworkedSIR
from adaptive.policy import simulate_adaptive_control, simulate_lockdown
from adaptive.smoothing import notched_smoothing
from adaptive.utils import days, setup, weeks, million
from tqdm import tqdm
logger = getLogger("SULSEL")
CI = 0.95
gamma = 0.2
window = 5
smoothing = notched_smoothing(window = window)
# load case data
schema = {
"Date Symptom Onset" : "symptom_onset",
"Date of Hospital Admissions": "admission",
"Date tested" : "tested",
"Date of positive test result": "confirmed",
"Date Recovered" : "recovered",
"Date Died" : "died",
"Kebupaten/Kota" : "regency",
"Kecamatan" : "district",
"age " : "age"
}
CI = 0.95
state_cases = pd.read_csv(data / "Bihar_cases_data_Oct03.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, 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],
from adaptive.etl.commons import download_data
from adaptive.etl.covid19india import state_code_lookup
from adaptive.models import SIR
from adaptive.smoothing import notched_smoothing
sns.set(style="whitegrid")
# root = Path(__file__).parent
# data = root/"data"
data = Path("./data").resolve()
CI = 0.95
window = 14
gamma = 0.2
infectious_period = 5
smooth = notched_smoothing(window)
num_sims = 50000
# load admin data on population
IN_age_structure = { # WPP2019_POP_F01_1_POPULATION_BY_AGE_BOTH_SEXES
0: 116_880,
5: 117_982 + 126_156 + 126_046,
18: 122_505 + 117_397,
30: 112_176 + 103_460,
40: 90_220 + 79_440,
50: 68_876 + 59_256 + 48_891,
65: 38_260 + 24_091,
75: 15_084 + 8_489 + 3_531 + 993 + 223 + 48,
}
# normalize
age_structure_norm = sum(IN_age_structure.values())
import pandas as pd
from adaptive.smoothing import notched_smoothing
from adaptive.estimators import analytical_MPVS
import adaptive.plots as plt
CI = 0.95
gamma = 0.2
window = 3
smoothing = notched_smoothing(window=window)
schema = {
"Date Symptom Onset": "symptom_onset",
"Date of Hospital Admissions": "admission",
"Date tested": "tested",
"Date of positive test result": "confirmed",
"Date Recovered": "recovered",
"Date Died": "died",
"Kebupaten/Kota": "regency",
"Kecamatan": "district",
"age ": "age"
}
regency_names = {
'Pangkep': 'Pangkajene Dan Kepulauan',
'Pare-Pare': 'Parepare',
'Selayar': 'Kepulauan Selayar',
'Sidrap': 'Sidenreng Rappang'
}
age_structure_norm = sum(IN_age_structure.values())
IN_age_ratios = np.array(
[v / age_structure_norm for (k, v) in IN_age_structure.items()])
split_by_age = lambda v: (v * IN_age_ratios).astype(int)
# get age-specific prevalence from KA sero
KA = pd.read_stata("data/ka_cases_deaths_time_newagecat.dta")
KA.agecat = KA.agecat.where(
KA.agecat != 85,
75) # we don't have econ data for 85+ so combine 75+ and 85+ categories
KA_agecases = KA.groupby(["agecat", "date"])["patientcode"]\
.count().sort_index().rename("cases")\
.unstack().fillna(0).stack()
KA_ts = KA_agecases.sum(level=1)
(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(KA_ts, notched_smoothing(5))
COVID_age_ratios = (KA_agecases.sum(level=0) / KA_agecases.sum()).values
split_by_prevalence = lambda v: (v * IN_age_ratios).astype(int)
for seed in range(10):
model = AgeStructured("KA", 6.11e7, 857, 915345, 1.826,
diag(u) @ C, IN_age_ratios, COVID_age_ratios, seed)
counter = 0
while model.dT[-1].sum() > 0:
model.forward_epi_step()
counter += 1
print(seed, counter, model.dT)
import adaptive.plots as plt
from adaptive.smoothing import notched_smoothing
import pandas as pd
import seaborn as sns
sns.set_style("whitegrid", {'axes.grid': False})
smoothed = notched_smoothing(window=7)
mobility = pd.read_csv("data/2020_IN_Region_Mobility_Report.csv",
parse_dates=["date"])
stringency = pd.read_csv("data/OxCGRT_latest.csv", parse_dates=["Date"])
def plot_mobility(
series,
label,
stringency=None,
until=None,
annotation="Google Mobility Data; baseline mobility measured from Jan 3 - Feb 6"
):
plt.plot(series.date,
smoothed(
series.retail_and_recreation_percent_change_from_baseline),
label="Retail/Recreation")
plt.plot(series.date,
smoothed(
series.grocery_and_pharmacy_percent_change_from_baseline),
label="Grocery/Pharmacy")
plt.plot(series.date,
smoothed(series.parks_percent_change_from_baseline),
.set_axis(dkij.columns.str.lower(), 1)\
.assign(
district = dkij.district.str.title(),
subdistrict = dkij.subdistrict.apply(lambda name: next((k for (k, v) in replacements.items() if name in v), name)),
)
district_cases = dkij.groupby(["district", "date_positiveresult"])["id"].count().sort_index()
districts = sorted(dkij.district.unique())
migration = np.zeros((len(districts), len(districts)))
R_mandatory = dict()
R_voluntary = dict()
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, *_) = analytical_MPVS(district_cases.loc[district], CI = CI, smoothing = notched_smoothing(window = window), totals=False)
Rt = pd.DataFrame(data = {"Rt": RR_pred[1:]}, index = dates)
R_mandatory[district] = np.mean(Rt[(Rt.index > "April 1, 2020") & (Rt.index < "June 1, 2020")])[0]
R_voluntary[district] = np.mean(Rt[(Rt.index < "April 1, 2020")])[0]
pops = [
2_430_410,
910_381,
2_164_070,
2_817_994,
1_729_444,
23_011
]
gdf = gpd.read_file("data/gadm36_IDN_shp/gadm36_IDN_2.shp")\
.query("NAME_1 == 'Jakarta Raya'")\
run_date = str(pd.Timestamp.now()).split()[0]
ts_full = get_time_series(df, "detected_state")
ts = ts_full.query("status_change_date <= 'October 14, 2020'")
states = ["Bihar", "Maharashtra", "Punjab", "Tamil Nadu"][-1:]
codes = ["BR", "MH", "PN", "TN"][-1:]
pops = [99.02e6, 114.2e6, 27.98e6, 67.86e6][-1:]
Rt_ranges = [(0.9, 2.4), (0.55, 2.06), (0.55, 2.22), (0.84, 1.06)][-1:]
windows = [7, 14, 7, 10][-1:]
for (state, code, pop, Rt_range, smoothing) in zip(states, codes, pops, Rt_ranges, windows):
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]}")\