#!/usr/bin/env python
# -*- encoding: utf-8 -*-
#
# This file is auto-generated by h2o-3/h2o-bindings/bin/gen_python.py
# Copyright 2016 H2O.ai; Apache License Version 2.0 (see LICENSE for details)
#
from __future__ import absolute_import, division, print_function, unicode_literals
from h2o.estimators.estimator_base import H2OEstimator
from h2o.exceptions import H2OValueError
from h2o.frame import H2OFrame
from h2o.utils.typechecks import assert_is_type, Enum, numeric
[docs]class H2ORuleFitEstimator(H2OEstimator):
"""
RuleFit
Builds a RuleFit on a parsed dataset, for regression or
classification.
"""
algo = "rulefit"
param_names = {"model_id", "training_frame", "seed", "response_column", "ignored_columns", "algorithm",
"min_rule_length", "max_rule_length", "max_num_rules", "model_type", "weights_column",
"distribution", "rule_generation_ntrees"}
def __init__(self, **kwargs):
super(H2ORuleFitEstimator, self).__init__()
self._parms = {}
for pname, pvalue in kwargs.items():
if pname == 'model_id':
self._id = pvalue
self._parms["model_id"] = pvalue
elif pname in self.param_names:
# Using setattr(...) will invoke type-checking of the arguments
setattr(self, pname, pvalue)
else:
raise H2OValueError("Unknown parameter %s = %r" % (pname, pvalue))
@property
def training_frame(self):
"""
Id of the training data frame.
Type: ``H2OFrame``.
"""
return self._parms.get("training_frame")
@training_frame.setter
def training_frame(self, training_frame):
self._parms["training_frame"] = H2OFrame._validate(training_frame, 'training_frame')
@property
def seed(self):
"""
Seed for pseudo random number generator (if applicable).
Type: ``int`` (default: ``-1``).
"""
return self._parms.get("seed")
@seed.setter
def seed(self, seed):
assert_is_type(seed, None, int)
self._parms["seed"] = seed
@property
def response_column(self):
"""
Response variable column.
Type: ``str``.
"""
return self._parms.get("response_column")
@response_column.setter
def response_column(self, response_column):
assert_is_type(response_column, None, str)
self._parms["response_column"] = response_column
@property
def ignored_columns(self):
"""
Names of columns to ignore for training.
Type: ``List[str]``.
"""
return self._parms.get("ignored_columns")
@ignored_columns.setter
def ignored_columns(self, ignored_columns):
assert_is_type(ignored_columns, None, [str])
self._parms["ignored_columns"] = ignored_columns
@property
def algorithm(self):
"""
The algorithm to use to generate rules.
One of: ``"auto"``, ``"drf"``, ``"gbm"`` (default: ``"auto"``).
"""
return self._parms.get("algorithm")
@algorithm.setter
def algorithm(self, algorithm):
assert_is_type(algorithm, None, Enum("auto", "drf", "gbm"))
self._parms["algorithm"] = algorithm
@property
def min_rule_length(self):
"""
Minimum length of rules. Defaults to 3.
Type: ``int`` (default: ``3``).
"""
return self._parms.get("min_rule_length")
@min_rule_length.setter
def min_rule_length(self, min_rule_length):
assert_is_type(min_rule_length, None, int)
self._parms["min_rule_length"] = min_rule_length
@property
def max_rule_length(self):
"""
Maximum length of rules. Defaults to 3.
Type: ``int`` (default: ``3``).
"""
return self._parms.get("max_rule_length")
@max_rule_length.setter
def max_rule_length(self, max_rule_length):
assert_is_type(max_rule_length, None, int)
self._parms["max_rule_length"] = max_rule_length
@property
def max_num_rules(self):
"""
The maximum number of rules to return. defaults to -1 which means the number of rules is selected by
diminishing returns in model deviance.
Type: ``int`` (default: ``-1``).
"""
return self._parms.get("max_num_rules")
@max_num_rules.setter
def max_num_rules(self, max_num_rules):
assert_is_type(max_num_rules, None, int)
self._parms["max_num_rules"] = max_num_rules
@property
def model_type(self):
"""
Specifies type of base learners in the ensemble.
One of: ``"rules_and_linear"``, ``"rules"``, ``"linear"`` (default: ``"rules_and_linear"``).
"""
return self._parms.get("model_type")
@model_type.setter
def model_type(self, model_type):
assert_is_type(model_type, None, Enum("rules_and_linear", "rules", "linear"))
self._parms["model_type"] = model_type
@property
def weights_column(self):
"""
Column with observation weights. Giving some observation a weight of zero is equivalent to excluding it from the
dataset; giving an observation a relative weight of 2 is equivalent to repeating that row twice. Negative
weights are not allowed. Note: Weights are per-row observation weights and do not increase the size of the data
frame. This is typically the number of times a row is repeated, but non-integer values are supported as well.
During training, rows with higher weights matter more, due to the larger loss function pre-factor.
Type: ``str``.
"""
return self._parms.get("weights_column")
@weights_column.setter
def weights_column(self, weights_column):
assert_is_type(weights_column, None, str)
self._parms["weights_column"] = weights_column
@property
def distribution(self):
"""
Distribution function
One of: ``"auto"``, ``"bernoulli"``, ``"multinomial"``, ``"gaussian"``, ``"poisson"``, ``"gamma"``,
``"tweedie"``, ``"laplace"``, ``"quantile"``, ``"huber"`` (default: ``"auto"``).
"""
return self._parms.get("distribution")
@distribution.setter
def distribution(self, distribution):
assert_is_type(distribution, None, Enum("auto", "bernoulli", "multinomial", "gaussian", "poisson", "gamma", "tweedie", "laplace", "quantile", "huber"))
self._parms["distribution"] = distribution
@property
def rule_generation_ntrees(self):
"""
specifies the number of trees to build in the tree model. Defaults to 50.
Type: ``int`` (default: ``50``).
"""
return self._parms.get("rule_generation_ntrees")
@rule_generation_ntrees.setter
def rule_generation_ntrees(self, rule_generation_ntrees):
assert_is_type(rule_generation_ntrees, None, int)
self._parms["rule_generation_ntrees"] = rule_generation_ntrees
[docs] def rule_importance(self):
"""
Retrieve rule importances for a Rulefit model
:return: H2OTwoDimTable
"""
if self._model_json["algo"] != "rulefit":
raise H2OValueError("This function is available for Rulefit models only")
return self._model_json["output"]['rule_importance']