def test_scipy_optimizer(seed):
np.random.seed(seed)
num_obs = 20
df = pd.DataFrame({
"obs": np.random.randn(num_obs),
"cov0": np.random.randn(num_obs),
"cov1": np.random.randn(num_obs)
})
data = Data(col_obs="obs", col_covs=["cov0", "cov1"], df=df)
spline_specs = SplineSpecs(knots=np.linspace(0.0, 1.0, 5),
degree=3,
knots_type="rel_domain")
var_cov0 = Variable(name="cov0")
var_cov1 = SplineVariable(name="cov1", spline_specs=spline_specs)
model = GaussianModel(
data, param_specs={"mu": {
"variables": [var_cov0, var_cov1]
}})
coefs = scipy_optimize(model)
tr_coef = np.linalg.solve(
(model.mat[0].T * model.data.weights).dot(model.mat[0]),
(model.mat[0].T * model.data.weights).dot(model.data.obs))
assert np.allclose(coefs, tr_coef)
def get_mortality_pattern_model(df: DataFrame,
col_time: str = "time_start",
units_per_year: int = 12,
knots: np.ndarray = np.arange(2010, 2021),
smooth_order: int = 1) -> ExcessMortalityModel:
seas_spline_specs = SplineSpecs(knots=np.linspace(0.0, 1.0, 5),
degree=3,
knots_type="rel_domain")
time_knots = get_time_knots(df.time.min(), df.time.max(), knots)
time_spline_specs = SplineSpecs(knots=time_knots,
degree=1,
knots_type="abs")
seas_var = SplineVariable(col_time, spline_specs=seas_spline_specs)
time_var = SplineVariable("time", spline_specs=time_spline_specs)
variables = [
SeasonalityModelVariables([seas_var], col_time, smooth_order),
TimeModelVariables([time_var])
]
return ExcessMortalityModel(df, variables)
def get_mortality_pattern_model(df: DataFrame,
col_time: str = "time_start",
units_per_year: int = 12,
knots_per_year: float = 0.5,
tail_size: int = 18,
smooth_order: int = 1) -> ExcessMortalityModel:
"""
Define one mortality pattern model
"""
seas_spline_specs = SplineSpecs(knots=np.linspace(0.0, 1.0, 5),
degree=3,
knots_type="rel_domain")
time_knots = get_time_knots(df.time.min(), df.time.max(), units_per_year,
knots_per_year, tail_size)
time_spline_specs = SplineSpecs(knots=time_knots,
degree=1,
knots_type="abs")
seas_var = SplineVariable(col_time, spline_specs=seas_spline_specs)
time_var = SplineVariable("time", spline_specs=time_spline_specs)
variables = [
SeasonalityModelVariables([seas_var], col_time, smooth_order),
TimeModelVariables([time_var])
]
return ExcessMortalityModel(df, variables)
def spline_specs():
return SplineSpecs(knots=np.linspace(0.0, 1.0, 5),
degree=3,
knots_type="rel_domain")
# time unit
time_unit = "week"
# start time
time_start = YearTime(2019, 1, time_unit=time_unit)
# end time for fit and prediction
time_end = {
"fit": YearTime(2020, 9, time_unit=time_unit),
"pred": YearTime(2020, 52, time_unit=time_unit)
}
# model setting
# spline specification for seasonality and time trend
seas_spline_specs = SplineSpecs(knots=np.linspace(1, 52, 3),
degree=2,
r_linear=True,
knots_type="abs")
time_spline_specs = SplineSpecs(knots=np.array([0.0, 1.0]),
degree=1,
knots_type="rel_domain")
def main():
# process input data
df = pd.read_csv(data_path)
df_2020 = df[[
"location_name", "year_x", "week", "pop_2020", "death_rate_2020"
]].copy()
df_2019 = df[[
"location_name", "year_y", "week", "pop_2019", "death_rate_2019"
]].copy()
def spline_variable():
return SplineVariable(name=COL_COVS[0],
spline_specs=SplineSpecs(knots=np.linspace(
0.0, 1.0, 5),
degree=3))
from regmod.optimizer import scipy_optimize
from emmodel.model import ExcessMortalityModel
from emmodel.variable import ModelVariables
from emmodel.cascade import CascadeSpecs, Cascade
# data file path
data_path = Path("./examples/data_debug/2020-04-22/stage2_input.csv")
# result folder
results_path = Path("./examples/results_debug")
# define all variables
intercept_variable = Variable("intercept")
idr_spline_specs = SplineSpecs(knots=np.linspace(0.0, 1.0, 5),
degree=2,
knots_type="rel_domain",
include_first_basis=False)
idr_variable = SplineVariable("idr_lagged",
spline_specs=idr_spline_specs,
priors=[
SplineUniformPrior(order=1,
lb=-np.inf,
ub=0.0),
SplineGaussianPrior(order=1,
mean=0.0,
sd=1e-4,
domain_lb=0.4,
domain_ub=1.0)
])
time_spline_specs = SplineSpecs(knots=np.linspace(0.0, 1.0, 10),