Expand source code 
from typing import List

import pandas as pd
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,
                 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,
                 cv=True,
                 random_state=None):
        # passed by keyword: RuleFit takes cv between alpha and random_state,
        # so positional arguments silently put random_state into cv
        super().__init__(n_estimators=n_estimators,
                         tree_size=tree_size,
                         sample_fract=sample_fract,
                         max_rules=max_rules,
                         memory_par=memory_par,
                         tree_generator=tree_generator,
                         lin_trim_quantile=lin_trim_quantile,
                         lin_standardise=lin_standardise,
                         exp_rand_tree_size=exp_rand_tree_size,
                         include_linear=include_linear,
                         alpha=alpha,
                         cv=cv,
                         random_state=random_state)
        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]:
        X = pd.DataFrame(X, columns=self.feature_placeholders)
        itemsets = extract_fpgrowth(X, minsupport=self.minsupport,
                                    maxcardinality=self.maxcardinality,
                                    verbose=self.verbose)
        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, 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, cv=True, random_state=None)

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

Parameters

n_estimators : int, default=100
Number of trees grown to generate candidate rules.
tree_size : int, default=4
Number of terminal nodes in generated trees. If exp_rand_tree_size=True, this is the mean number of terminal nodes.
sample_fract : float or "default", default="default"
Fraction of randomly chosen training observations used to produce each tree (Friedman and Popescu 2004, Sec. 2).
max_rules : int, default=30
Total number of terms included in the final model (both linear terms and rules). The approximate number of candidate rules generated is also based on this; the actual number is usually lower because of duplicates.
memory_par : float, default=0.01
Scale multiplier (shrinkage factor) applied to each new tree when sequentially induced (Friedman and Popescu 2004, Sec. 2).
tree_generator : estimator, optional
Used as provided to generate the rules, overriding most of the parameters above. Must be GradientBoostingRegressor(), GradientBoostingClassifier() or RandomForestRegressor(). A copy is fitted on the training data, so the object passed in is left untouched (and any previous fit of it is not reused). n_estimators, max_leaf_nodes and random_state are set on that copy while the trees are grown, so tuning them on the generator has no effect.
lin_trim_quantile : float, default=0.025
If lin_standardise is True, this quantile is used to trim linear terms before standardisation.
lin_standardise : bool, default=True
If True, linear terms are standardised as in Friedman and Popescu (Sec. 3.2), by multiplying the winsorised variable by 0.4 / stdev.
exp_rand_tree_size : bool, default=True
If True, each boosted tree has a different maximum number of terminal nodes, drawn from an exponential distribution about tree_size (Sec. 3.3).
include_linear : bool, default=True
Include linear terms as well as rules.
alpha : float, optional
Regularization strength; overrides max_rules.
cv : bool, default=True
Whether to use cross-validation scores to select the regularization strength, out of all values that satisfy max_rules. If False, the least regularization possible is used.
random_state : int, optional
Seed for the random objects, for repeatability.
verbose : int, default=0
Verbosity.

Attributes

rule_ensemble : RuleEnsemble
The rule ensemble.
feature_names : list of str, optional
The names of the features (columns).
Expand source code 
class FPLasso(RuleFit):

    def __init__(self,
                 minsupport=0.1,
                 maxcardinality=2,
                 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,
                 cv=True,
                 random_state=None):
        # passed by keyword: RuleFit takes cv between alpha and random_state,
        # so positional arguments silently put random_state into cv
        super().__init__(n_estimators=n_estimators,
                         tree_size=tree_size,
                         sample_fract=sample_fract,
                         max_rules=max_rules,
                         memory_par=memory_par,
                         tree_generator=tree_generator,
                         lin_trim_quantile=lin_trim_quantile,
                         lin_standardise=lin_standardise,
                         exp_rand_tree_size=exp_rand_tree_size,
                         include_linear=include_linear,
                         alpha=alpha,
                         cv=cv,
                         random_state=random_state)
        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]:
        X = pd.DataFrame(X, columns=self.feature_placeholders)
        itemsets = extract_fpgrowth(X, minsupport=self.minsupport,
                                    maxcardinality=self.maxcardinality,
                                    verbose=self.verbose)
        return itemsets_to_rules(itemsets)

Ancestors

  • RuleFit
  • sklearn.base.BaseEstimator
  • sklearn.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester
  • sklearn.base.TransformerMixin
  • sklearn.utils._set_output._SetOutputMixin
  • RuleSet
  • RulesMixin
  • TextMixin

Subclasses

Inherited members

class FPLassoClassifier (minsupport=0.1, maxcardinality=2, 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, cv=True, random_state=None)

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

Parameters

n_estimators : int, default=100
Number of trees grown to generate candidate rules.
tree_size : int, default=4
Number of terminal nodes in generated trees. If exp_rand_tree_size=True, this is the mean number of terminal nodes.
sample_fract : float or "default", default="default"
Fraction of randomly chosen training observations used to produce each tree (Friedman and Popescu 2004, Sec. 2).
max_rules : int, default=30
Total number of terms included in the final model (both linear terms and rules). The approximate number of candidate rules generated is also based on this; the actual number is usually lower because of duplicates.
memory_par : float, default=0.01
Scale multiplier (shrinkage factor) applied to each new tree when sequentially induced (Friedman and Popescu 2004, Sec. 2).
tree_generator : estimator, optional
Used as provided to generate the rules, overriding most of the parameters above. Must be GradientBoostingRegressor(), GradientBoostingClassifier() or RandomForestRegressor(). A copy is fitted on the training data, so the object passed in is left untouched (and any previous fit of it is not reused). n_estimators, max_leaf_nodes and random_state are set on that copy while the trees are grown, so tuning them on the generator has no effect.
lin_trim_quantile : float, default=0.025
If lin_standardise is True, this quantile is used to trim linear terms before standardisation.
lin_standardise : bool, default=True
If True, linear terms are standardised as in Friedman and Popescu (Sec. 3.2), by multiplying the winsorised variable by 0.4 / stdev.
exp_rand_tree_size : bool, default=True
If True, each boosted tree has a different maximum number of terminal nodes, drawn from an exponential distribution about tree_size (Sec. 3.3).
include_linear : bool, default=True
Include linear terms as well as rules.
alpha : float, optional
Regularization strength; overrides max_rules.
cv : bool, default=True
Whether to use cross-validation scores to select the regularization strength, out of all values that satisfy max_rules. If False, the least regularization possible is used.
random_state : int, optional
Seed for the random objects, for repeatability.
verbose : int, default=0
Verbosity.

Attributes

rule_ensemble : RuleEnsemble
The rule ensemble.
feature_names : list of str, optional
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.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester
  • sklearn.base.TransformerMixin
  • sklearn.utils._set_output._SetOutputMixin
  • RuleSet
  • RulesMixin
  • TextMixin
  • sklearn.base.ClassifierMixin

Inherited members

class FPLassoRegressor (minsupport=0.1, maxcardinality=2, 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, cv=True, random_state=None)

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

Parameters

n_estimators : int, default=100
Number of trees grown to generate candidate rules.
tree_size : int, default=4
Number of terminal nodes in generated trees. If exp_rand_tree_size=True, this is the mean number of terminal nodes.
sample_fract : float or "default", default="default"
Fraction of randomly chosen training observations used to produce each tree (Friedman and Popescu 2004, Sec. 2).
max_rules : int, default=30
Total number of terms included in the final model (both linear terms and rules). The approximate number of candidate rules generated is also based on this; the actual number is usually lower because of duplicates.
memory_par : float, default=0.01
Scale multiplier (shrinkage factor) applied to each new tree when sequentially induced (Friedman and Popescu 2004, Sec. 2).
tree_generator : estimator, optional
Used as provided to generate the rules, overriding most of the parameters above. Must be GradientBoostingRegressor(), GradientBoostingClassifier() or RandomForestRegressor(). A copy is fitted on the training data, so the object passed in is left untouched (and any previous fit of it is not reused). n_estimators, max_leaf_nodes and random_state are set on that copy while the trees are grown, so tuning them on the generator has no effect.
lin_trim_quantile : float, default=0.025
If lin_standardise is True, this quantile is used to trim linear terms before standardisation.
lin_standardise : bool, default=True
If True, linear terms are standardised as in Friedman and Popescu (Sec. 3.2), by multiplying the winsorised variable by 0.4 / stdev.
exp_rand_tree_size : bool, default=True
If True, each boosted tree has a different maximum number of terminal nodes, drawn from an exponential distribution about tree_size (Sec. 3.3).
include_linear : bool, default=True
Include linear terms as well as rules.
alpha : float, optional
Regularization strength; overrides max_rules.
cv : bool, default=True
Whether to use cross-validation scores to select the regularization strength, out of all values that satisfy max_rules. If False, the least regularization possible is used.
random_state : int, optional
Seed for the random objects, for repeatability.
verbose : int, default=0
Verbosity.

Attributes

rule_ensemble : RuleEnsemble
The rule ensemble.
feature_names : list of str, optional
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.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester
  • sklearn.base.TransformerMixin
  • sklearn.utils._set_output._SetOutputMixin
  • RuleSet
  • RulesMixin
  • TextMixin
  • sklearn.base.RegressorMixin

Inherited members