def _get_glm_coeffs(glm):
"""
Get the GLM coefficients by choosing the lambda with diminishing returns on explained deviance
"""
r = H2OGeneralizedLinearEstimator.getGLMRegularizationPath(glm)
deviance = r.get('explained_deviance_train')
inflection_pt = [i*3 for i, x in enumerate(np.diff(np.sign(np.diff(deviance, 2)))) if x != 0 and i > 0][0]
intercept = {k: v for k,v in r.get('coefficients')[inflection_pt].items() if k == "Intercept"}
coeffs = {k: v for k,v in r.get('coefficients')[inflection_pt].items() if abs(v) > 0 and k != "Intercept"}
return intercept, coeffs
def _get_glm_lambda(glm):
"""
Get the best GLM lambda by choosing one diminishing returns on explained deviance
"""
r = H2OGeneralizedLinearEstimator.getGLMRegularizationPath(glm)
deviance = r.get('explained_deviance_train')
rule_count = [len([k for k,v in x.items() if abs(v) > 0 and k != "Intercept"]) for x in r.get('coefficients')]
lambda_index = [i*3 for i, x in enumerate(np.diff(np.sign(np.diff(deviance, 2)))) if x != 0 and i > 0][0]
return r.get('lambdas')[lambda_index]
def _get_glm_lambda(glm):
"""
Get the best GLM lambda by choosing one diminishing returns on explained deviance
"""
r = H2OGeneralizedLinearEstimator.getGLMRegularizationPath(glm)
deviance = r.get('explained_deviance_train')
if len(deviance) < 5:
lambda_index = len(deviance) - 1
else:
lambda_index = [
i * 3 for i, x in enumerate(np.diff(np.sign(np.diff(deviance, 2))))
if x != 0 and i > 0
][0]
return r.get('lambdas')[lambda_index]
def _get_glm_lambda(glm, num_rules):
"""
Get the best GLM lambda by choosing one diminishing returns on explained deviance
:param num_rules: The number of rules to use in rulefit model.
"""
r = H2OGeneralizedLinearEstimator.getGLMRegularizationPath(glm)
deviance = r.get('explained_deviance_train')
rule_count = [
len([k for k, v in x.items() if abs(v) > 0 and k != "Intercept"])
for x in r.get('coefficients')
]
if num_rules is None:
lambda_index = [
i * 3 for i, x in enumerate(np.diff(np.sign(np.diff(deviance, 2))))
if x != 0 and i > 0
][0]
else:
lambda_index = [
x for x, val in enumerate(rule_count) if val > num_rules
][0]
return r.get('lambdas')[lambda_index]
