def fit(self, df, group=None):
"""
Fits a loose, tight, beta, and p combinations model. If you pass in
update group it will override the initial parameters with new
initial parameters based on the df you pass.
Args:
df:
group: (str) passing in the group will update the initialization
dictionary (not replacing the old one) for this particular fit.
Returns:
"""
if group is not None:
init_dict = self.update_init_model(df=df, group=group)
else:
init_dict = deepcopy(self.init_dict)
for param in ['beta', 'p']:
for fit_type in ['loose', 'tight']:
model_arg_dict = deepcopy(
getattr(self, f'{param}_model_kwargs'))
fit_arg_dict = deepcopy(
getattr(self, f'{fit_type}_{param}_fit_dict'))
model = CurveModel(df=df, **model_arg_dict)
fe_init, re_init = compute_starting_params(
init_dict[param][fit_type])
fit_arg_dict.update(fe_init=fe_init, re_init=re_init)
model.fit_params(**fit_arg_dict)
setattr(self, f'{fit_type}_{param}_model', model)
class BasicModel(ModelPipeline):
def __init__(self, fit_dict, **basic_model_kwargs):
"""
Generic class for a function to produce predictions from a model
with the following attributes.
Args:
predict_group: (str) which group to make predictions for
fit_dict: keyword arguments to CurveModel.fit_params()
**basic_model_kwargs: keyword arguments to CurveModel.__init__()
"""
super().__init__()
self.fit_dict = fit_dict
self.basic_model_kwargs = basic_model_kwargs
self.mod = None
def refresh(self):
self.mod = None
def fit(self, df):
self.mod = CurveModel(df=df, **self.basic_model_kwargs)
self.mod.fit_params(**self.fit_dict)
def predict(self, times, predict_space, predict_group='all'):
predictions = self.mod.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
return predictions
class BasicModel(ModelPipeline):
def __init__(self, fit_dict, basic_model_dict, **pipeline_kwargs):
"""
Generic class for a function to produce predictions from a model
with the following attributes.
Args:
**pipeline_kwargs: keyword arguments for the base class of ModelPipeline
predict_group: (str) which group to make predictions for
fit_dict: keyword arguments to CurveModel.fit_params()
basic_model_dict: additional keyword arguments to the CurveModel class
col_obs_se: (str) of observation standard error
col_covs: List[str] list of names of covariates to put on the parameters
param_names (list{str}):
Names of the parameters in the specific functional form.
link_fun (list{function}):
List of link functions for each parameter.
var_link_fun (list{function}):
List of link functions for the variables including fixed effects
and random effects.
"""
super().__init__(**pipeline_kwargs)
self.fit_dict = fit_dict
self.basic_model_dict = basic_model_dict
self.basic_model_dict.update({'col_obs_se': self.col_obs_se})
generator_kwargs = pipeline_kwargs
for arg in self.pop_cols:
generator_kwargs.pop(arg)
self.basic_model_dict.update(**generator_kwargs)
self.mod = None
self.setup_pipeline()
def refresh(self):
self.mod = None
def fit(self, df, group=None):
self.mod = CurveModel(df=df, **self.basic_model_dict)
self.mod.fit_params(**self.fit_dict)
def predict(self, times, predict_space, predict_group):
predictions = self.mod.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
return predictions
class TightLooseBetaPModel(ModelPipeline):
def __init__(self,
loose_beta_fit_dict,
tight_beta_fit_dict,
loose_p_fit_dict,
tight_p_fit_dict,
beta_model_extras=None,
p_model_extras=None,
blend_start_t=2,
blend_end_t=30,
**basic_model_kwargs):
"""
Produces two tight-loose models as a convex combination between the two of them,
and then averages
Args:
loose_beta_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() for the loose beta model
tight_beta_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() fro the tight beta model
loose_p_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() for the loose p model
tight_p_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() fro the tight p model
beta_model_extras: (optional) dictionary of keyword arguments to
override the basic_model_kwargs for the beta model
p_model_extras: (optional) dictionary of keyword arguments to
override the basic_model_kwargs for the p model
blend_start_t: (int) the time to start blending tight and loose
blend_end_t: (int) the time to stop blending tight and loose
predict_group: (str) which group to make predictions for
**basic_model_kwargs: keyword arguments to the basic model
"""
super().__init__()
self.beta_model_kwargs = basic_model_kwargs
self.p_model_kwargs = basic_model_kwargs
if beta_model_extras is not None:
self.beta_model_kwargs = self.beta_model_kwargs.update(
beta_model_extras)
if p_model_extras is not None:
self.p_model_kwargs = self.p_model_kwargs.update(p_model_extras)
self.loose_beta_fit_dict = loose_beta_fit_dict
self.tight_beta_fit_dict = tight_beta_fit_dict
self.loose_p_fit_dict = loose_p_fit_dict
self.tight_p_fit_dict = tight_p_fit_dict
self.blend_start_t = blend_start_t
self.blend_end_t = blend_end_t
self.loose_beta_model = None
self.tight_beta_model = None
self.loose_p_model = None
self.tight_p_model = None
def refresh(self):
self.loose_beta_model = None
self.tight_beta_model = None
self.loose_p_model = None
self.tight_p_model = None
def fit(self, df):
self.loose_beta_model = CurveModel(df=df, **self.beta_model_kwargs)
self.tight_beta_model = CurveModel(df=df, **self.beta_model_kwargs)
self.loose_p_model = CurveModel(df=df, **self.p_model_kwargs)
self.tight_p_model = CurveModel(df=df, **self.p_model_kwargs)
self.loose_beta_model.fit_params(**self.loose_beta_fit_dict)
self.tight_beta_model.fit_params(**self.tight_beta_fit_dict)
self.loose_p_model.fit_params(**self.loose_p_fit_dict)
self.tight_p_model.fit_params(**self.tight_p_fit_dict)
def predict(self, times, predict_space, predict_group='all'):
loose_beta_predictions = self.loose_beta_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
tight_beta_predictions = self.tight_beta_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
loose_p_predictions = self.loose_p_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
tight_p_predictions = self.tight_p_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
beta_predictions = convex_combination(t=times,
pred1=tight_beta_predictions,
pred2=loose_beta_predictions,
pred_fun=predict_space,
start_day=self.blend_start_t,
end_day=self.blend_end_t)
p_predictions = convex_combination(t=times,
pred1=tight_p_predictions,
pred2=loose_p_predictions,
pred_fun=predict_space,
start_day=self.blend_start_t,
end_day=self.blend_end_t)
averaged_predictions = model_average(pred1=beta_predictions,
pred2=p_predictions,
w1=0.5,
w2=0.5,
pred_fun=predict_space)
return averaged_predictions
class TightLooseBetaPModel(ModelPipeline):
def __init__(self,
loose_beta_fit_dict,
tight_beta_fit_dict,
loose_p_fit_dict,
tight_p_fit_dict,
basic_model_dict,
beta_model_extras=None,
p_model_extras=None,
blend_start_t=2,
blend_end_t=30,
**pipeline_kwargs):
"""
Produces two tight-loose models as a convex combination between the two of them,
and then averages
Args:
**pipeline_kwargs: keyword arguments for the base class of ModelPipeline
loose_beta_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() for the loose beta model
tight_beta_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() fro the tight beta model
loose_p_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() for the loose p model
tight_p_fit_dict: dictionary of keyword arguments to CurveModel.fit_params() fro the tight p model
basic_model_dict: additional keyword arguments to the CurveModel class
col_obs_se: (str) of observation standard error
col_covs: List[str] list of names of covariates to put on the parameters
param_names (list{str}):
Names of the parameters in the specific functional form.
link_fun (list{function}):
List of link functions for each parameter.
var_link_fun (list{function}):
List of link functions for the variables including fixed effects
and random effects.
beta_model_extras: (optional) dictionary of keyword arguments to
override the basic_model_kwargs for the beta model
p_model_extras: (optional) dictionary of keyword arguments to
override the basic_model_kwargs for the p model
blend_start_t: (int) the time to start blending tight and loose
blend_end_t: (int) the time to stop blending tight and loose
"""
super().__init__(**pipeline_kwargs)
generator_kwargs = pipeline_kwargs
for arg in self.pop_cols:
generator_kwargs.pop(arg)
self.basic_model_dict = basic_model_dict
self.basic_model_dict.update(**generator_kwargs)
self.basic_model_dict.update({'col_obs_se': self.col_obs_se})
self.beta_model_kwargs = self.basic_model_dict
self.p_model_kwargs = self.basic_model_dict
if beta_model_extras is not None:
self.beta_model_kwargs = self.beta_model_kwargs.update(
beta_model_extras)
if p_model_extras is not None:
self.p_model_kwargs = self.p_model_kwargs.update(p_model_extras)
self.loose_beta_fit_dict = loose_beta_fit_dict
self.tight_beta_fit_dict = tight_beta_fit_dict
self.loose_p_fit_dict = loose_p_fit_dict
self.tight_p_fit_dict = tight_p_fit_dict
self.blend_start_t = blend_start_t
self.blend_end_t = blend_end_t
self.loose_beta_model = None
self.tight_beta_model = None
self.loose_p_model = None
self.tight_p_model = None
self.setup_pipeline()
def refresh(self):
self.loose_beta_model = None
self.tight_beta_model = None
self.loose_p_model = None
self.tight_p_model = None
def fit(self, df):
self.loose_beta_model = CurveModel(df=df, **self.beta_model_kwargs)
self.tight_beta_model = CurveModel(df=df, **self.beta_model_kwargs)
self.loose_p_model = CurveModel(df=df, **self.p_model_kwargs)
self.tight_p_model = CurveModel(df=df, **self.p_model_kwargs)
self.loose_beta_model.fit_params(**self.loose_beta_fit_dict)
self.tight_beta_model.fit_params(**self.tight_beta_fit_dict)
self.loose_p_model.fit_params(**self.loose_p_fit_dict)
self.tight_p_model.fit_params(**self.tight_p_fit_dict)
def predict(self, times, predict_space, predict_group):
loose_beta_predictions = self.loose_beta_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
tight_beta_predictions = self.tight_beta_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
loose_p_predictions = self.loose_p_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
tight_p_predictions = self.tight_p_model.predict(
t=times,
group_name=predict_group,
prediction_functional_form=predict_space)
beta_predictions = convex_combination(t=times,
pred1=tight_beta_predictions,
pred2=loose_beta_predictions,
pred_fun=predict_space,
start_day=self.blend_start_t,
end_day=self.blend_end_t)
p_predictions = convex_combination(t=times,
pred1=tight_p_predictions,
pred2=loose_p_predictions,
pred_fun=predict_space,
start_day=self.blend_start_t,
end_day=self.blend_end_t)
averaged_predictions = model_average(pred1=beta_predictions,
pred2=p_predictions,
w1=0.5,
w2=0.5,
pred_fun=predict_space)
return averaged_predictions
class BasicModelWithInit(BasicModel):
def __init__(self, smart_init_options=None, **kwargs):
if smart_init_options is None:
smart_init_options = {}
self.smart_init_options = smart_init_options
super().__init__(**kwargs)
if self.fit_dict['options']:
self.smart_init_options = {
**self.fit_dict['options'],
**self.smart_init_options
}
self.init_dict = None
self.mod = None
def run_init_model(self):
self.init_dict = self.get_init_dict(df=self.all_data,
groups=self.groups)
def update_init_model(self, df, group):
"""
Update the initial model with a re-fit model
from the specified group. Returns a new copy of the init dict
Args:
df: (pd.DataFrame) data used to update the init model
group: (str) the group to update
Returns:
"""
new_init_dict = deepcopy(self.init_dict)
new_init_dict.update(self.get_init_dict(df=df, groups=[group]))
return new_init_dict
def get_init_dict(self, df, groups):
"""
Run the init model for each location.
Args:
df: (pd.DataFrame) data frame to fit the model that will
be subset by group
groups: (str) groups to get in the dict
Returns:
(dict) dictionary of fixed effects keyed by group
"""
model = CurveModel(df=df, **self.basic_model_dict)
init_fit_dict = deepcopy(self.fit_dict)
init_fit_dict.update(options=self.smart_init_options)
init_dict = get_initial_params(groups=groups,
model=model,
fit_arg_dict=init_fit_dict)
return init_dict
def fit(self, df, group=None):
"""
Fits a loose, tight, beta, and p combinations model. If you pass in
update group it will override the initial parameters with new
initial parameters based on the df you pass.
Args:
df:
group: (str) passing in the group will update the initialization
dictionary (not replacing the old one) for this particular fit.
Returns:
"""
if group is not None:
init_dict = self.update_init_model(df=df, group=group)
else:
init_dict = deepcopy(self.init_dict)
fit_dict = deepcopy(self.fit_dict)
fe_init, re_init = compute_starting_params(init_dict)
fit_dict.update(fe_init=fe_init, re_init=re_init)
self.mod = CurveModel(df=df, **self.basic_model_dict)
self.mod.fit_params(**fit_dict)
def refresh(self):
self.mod = None