Module imodels.rule_set.fplasso

Expand source code 
from typing import List

from sklearn.base import ClassifierMixin, RegressorMixin

from imodels.rule_set.rule_fit import RuleFit
from imodels.util.convert import itemsets_to_rules
from imodels.util.extract import extract_fpgrowth


class FPLasso(RuleFit):

    def __init__(self,
                 minsupport=0.1,
                 maxcardinality=2,
                 disc_strategy='mdlp',
                 disc_kwargs={},
                 verbose=False,
                 n_estimators=100,
                 tree_size=4,
                 sample_fract='default',
                 max_rules=2000,
                 memory_par=0.01,
                 tree_generator=None,
                 lin_trim_quantile=0.025,
                 lin_standardise=True,
                 exp_rand_tree_size=True,
                 include_linear=True,
                 alpha=None,
                 random_state=None):
        super().__init__(n_estimators,
                         tree_size,
                         sample_fract,
                         max_rules,
                         memory_par,
                         tree_generator,
                         lin_trim_quantile,
                         lin_standardise,
                         exp_rand_tree_size,
                         include_linear,
                         alpha,
                         random_state)
        self.disc_strategy = disc_strategy
        self.disc_kwargs = disc_kwargs
        self.minsupport = minsupport
        self.maxcardinality = maxcardinality
        self.verbose = verbose

    def fit(self, X, y=None, feature_names=None, undiscretized_features=[]):
        self.undiscretized_features = undiscretized_features
        super().fit(X, y, feature_names=feature_names)
        return self

    def _extract_rules(self, X, y) -> List[str]:
        itemsets = extract_fpgrowth(X, y,
                                    feature_names=self.feature_placeholders,
                                    minsupport=self.minsupport,
                                    maxcardinality=self.maxcardinality,
                                    undiscretized_features=self.undiscretized_features,
                                    disc_strategy=self.disc_strategy,
                                    disc_kwargs=self.disc_kwargs,
                                    verbose=self.verbose)[0]
        return itemsets_to_rules(itemsets)


class FPLassoRegressor(FPLasso, RegressorMixin):
    def _init_prediction_task(self):
        self.prediction_task = 'regression'


class FPLassoClassifier(FPLasso, ClassifierMixin):
    def _init_prediction_task(self):
        self.prediction_task = 'classification'

Classes

class FPLasso (minsupport=0.1, maxcardinality=2, disc_strategy='mdlp', disc_kwargs={}, verbose=False, n_estimators=100, tree_size=4, sample_fract='default', max_rules=2000, memory_par=0.01, tree_generator=None, lin_trim_quantile=0.025, lin_standardise=True, exp_rand_tree_size=True, include_linear=True, alpha=None, random_state=None)

Rulefit class. Rather than using this class directly, should use RuleFitRegressor or RuleFitClassifier

Parameters

tree_size :  Number of terminal nodes in generated trees. If exp_rand_tree_size=True,
this will be the mean number of terminal nodes.
sample_fract :  fraction of randomly chosen training observations used to produce each tree.
FP 2004 (Sec. 2)
max_rules :  total number of terms included in the final model (both linear and rules)
approximate total number of candidate rules generated for fitting also is based on this Note that actual number of candidate rules will usually be lower than this due to duplicates.
memory_par :  scale multiplier (shrinkage factor) applied to each new tree when
sequentially induced. FP 2004 (Sec. 2)
lin_standardise : If True, the linear terms will be standardised as per Friedman Sec 3.2
by multiplying the winsorised variable by 0.4/stdev.
lin_trim_quantile : If lin_standardise is True, this quantile will be used to trim linear
terms before standardisation.
exp_rand_tree_size : If True, each boosted tree will have a different maximum number of
terminal nodes based on an exponential distribution about tree_size. (Friedman Sec 3.3)
include_linear : Include linear terms as opposed to only rules
 
random_state: Integer to initialise random objects and provide repeatability.
tree_generator : Optional: this object will be used as provided to generate the rules.
This will override almost all the other properties above. Must be GradientBoostingRegressor or GradientBoostingClassifier, optional (default=None)

Attributes

rule_ensemble : RuleEnsemble
The rule ensemble
feature_names : list of strings, optional (default=None)
The names of the features (columns)
Expand source code 
class FPLasso(RuleFit):

    def __init__(self,
                 minsupport=0.1,
                 maxcardinality=2,
                 disc_strategy='mdlp',
                 disc_kwargs={},
                 verbose=False,
                 n_estimators=100,
                 tree_size=4,
                 sample_fract='default',
                 max_rules=2000,
                 memory_par=0.01,
                 tree_generator=None,
                 lin_trim_quantile=0.025,
                 lin_standardise=True,
                 exp_rand_tree_size=True,
                 include_linear=True,
                 alpha=None,
                 random_state=None):
        super().__init__(n_estimators,
                         tree_size,
                         sample_fract,
                         max_rules,
                         memory_par,
                         tree_generator,
                         lin_trim_quantile,
                         lin_standardise,
                         exp_rand_tree_size,
                         include_linear,
                         alpha,
                         random_state)
        self.disc_strategy = disc_strategy
        self.disc_kwargs = disc_kwargs
        self.minsupport = minsupport
        self.maxcardinality = maxcardinality
        self.verbose = verbose

    def fit(self, X, y=None, feature_names=None, undiscretized_features=[]):
        self.undiscretized_features = undiscretized_features
        super().fit(X, y, feature_names=feature_names)
        return self

    def _extract_rules(self, X, y) -> List[str]:
        itemsets = extract_fpgrowth(X, y,
                                    feature_names=self.feature_placeholders,
                                    minsupport=self.minsupport,
                                    maxcardinality=self.maxcardinality,
                                    undiscretized_features=self.undiscretized_features,
                                    disc_strategy=self.disc_strategy,
                                    disc_kwargs=self.disc_kwargs,
                                    verbose=self.verbose)[0]
        return itemsets_to_rules(itemsets)

Ancestors

  • RuleFit
  • sklearn.base.BaseEstimator
  • sklearn.base.TransformerMixin
  • RuleSet

Subclasses

Inherited members

class FPLassoClassifier (minsupport=0.1, maxcardinality=2, disc_strategy='mdlp', disc_kwargs={}, verbose=False, n_estimators=100, tree_size=4, sample_fract='default', max_rules=2000, memory_par=0.01, tree_generator=None, lin_trim_quantile=0.025, lin_standardise=True, exp_rand_tree_size=True, include_linear=True, alpha=None, random_state=None)

Rulefit class. Rather than using this class directly, should use RuleFitRegressor or RuleFitClassifier

Parameters

tree_size :  Number of terminal nodes in generated trees. If exp_rand_tree_size=True,
this will be the mean number of terminal nodes.
sample_fract :  fraction of randomly chosen training observations used to produce each tree.
FP 2004 (Sec. 2)
max_rules :  total number of terms included in the final model (both linear and rules)
approximate total number of candidate rules generated for fitting also is based on this Note that actual number of candidate rules will usually be lower than this due to duplicates.
memory_par :  scale multiplier (shrinkage factor) applied to each new tree when
sequentially induced. FP 2004 (Sec. 2)
lin_standardise : If True, the linear terms will be standardised as per Friedman Sec 3.2
by multiplying the winsorised variable by 0.4/stdev.
lin_trim_quantile : If lin_standardise is True, this quantile will be used to trim linear
terms before standardisation.
exp_rand_tree_size : If True, each boosted tree will have a different maximum number of
terminal nodes based on an exponential distribution about tree_size. (Friedman Sec 3.3)
include_linear : Include linear terms as opposed to only rules
 
random_state: Integer to initialise random objects and provide repeatability.
tree_generator : Optional: this object will be used as provided to generate the rules.
This will override almost all the other properties above. Must be GradientBoostingRegressor or GradientBoostingClassifier, optional (default=None)

Attributes

rule_ensemble : RuleEnsemble
The rule ensemble
feature_names : list of strings, optional (default=None)
The names of the features (columns)
Expand source code 
class FPLassoClassifier(FPLasso, ClassifierMixin):
    def _init_prediction_task(self):
        self.prediction_task = 'classification'

Ancestors

  • FPLasso
  • RuleFit
  • sklearn.base.BaseEstimator
  • sklearn.base.TransformerMixin
  • RuleSet
  • sklearn.base.ClassifierMixin

Inherited members

class FPLassoRegressor (minsupport=0.1, maxcardinality=2, disc_strategy='mdlp', disc_kwargs={}, verbose=False, n_estimators=100, tree_size=4, sample_fract='default', max_rules=2000, memory_par=0.01, tree_generator=None, lin_trim_quantile=0.025, lin_standardise=True, exp_rand_tree_size=True, include_linear=True, alpha=None, random_state=None)

Rulefit class. Rather than using this class directly, should use RuleFitRegressor or RuleFitClassifier

Parameters

tree_size :  Number of terminal nodes in generated trees. If exp_rand_tree_size=True,
this will be the mean number of terminal nodes.
sample_fract :  fraction of randomly chosen training observations used to produce each tree.
FP 2004 (Sec. 2)
max_rules :  total number of terms included in the final model (both linear and rules)
approximate total number of candidate rules generated for fitting also is based on this Note that actual number of candidate rules will usually be lower than this due to duplicates.
memory_par :  scale multiplier (shrinkage factor) applied to each new tree when
sequentially induced. FP 2004 (Sec. 2)
lin_standardise : If True, the linear terms will be standardised as per Friedman Sec 3.2
by multiplying the winsorised variable by 0.4/stdev.
lin_trim_quantile : If lin_standardise is True, this quantile will be used to trim linear
terms before standardisation.
exp_rand_tree_size : If True, each boosted tree will have a different maximum number of
terminal nodes based on an exponential distribution about tree_size. (Friedman Sec 3.3)
include_linear : Include linear terms as opposed to only rules
 
random_state: Integer to initialise random objects and provide repeatability.
tree_generator : Optional: this object will be used as provided to generate the rules.
This will override almost all the other properties above. Must be GradientBoostingRegressor or GradientBoostingClassifier, optional (default=None)

Attributes

rule_ensemble : RuleEnsemble
The rule ensemble
feature_names : list of strings, optional (default=None)
The names of the features (columns)
Expand source code 
class FPLassoRegressor(FPLasso, RegressorMixin):
    def _init_prediction_task(self):
        self.prediction_task = 'regression'

Ancestors

  • FPLasso
  • RuleFit
  • sklearn.base.BaseEstimator
  • sklearn.base.TransformerMixin
  • RuleSet
  • sklearn.base.RegressorMixin

Inherited members