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,
                 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.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, 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
 
alpha :  Regularization strength, will override max_rules parameter
 
cv : Whether to use cross-validation scores to select the regularization strength
the final regularization value out of all that satisfy max_rules. If False, the least regularization possible is used.
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(), GradientBoostingClassifier(), or RandomForestRegressor()

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,
                 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.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

Subclasses

Methods

def set_fit_request(self: FPLasso, *, feature_names: Union[bool, ForwardRef(None), str] = '$UNCHANGED$', undiscretized_features: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> FPLasso

Request metadata passed to the fit method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to fit if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to fit.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

feature_names : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for feature_names parameter in fit.
undiscretized_features : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for undiscretized_features parameter in fit.

Returns

self : object
The updated object.
Expand source code
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance

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, 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
 
alpha :  Regularization strength, will override max_rules parameter
 
cv : Whether to use cross-validation scores to select the regularization strength
the final regularization value out of all that satisfy max_rules. If False, the least regularization possible is used.
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(), GradientBoostingClassifier(), or RandomForestRegressor()

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.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester
  • sklearn.base.TransformerMixin
  • sklearn.utils._set_output._SetOutputMixin
  • RuleSet
  • sklearn.base.ClassifierMixin

Methods

def set_score_request(self: FPLassoClassifier, *, sample_weight: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> FPLassoClassifier

Request metadata passed to the score method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to score.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

sample_weight : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for sample_weight parameter in score.

Returns

self : object
The updated object.
Expand source code
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance

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, 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
 
alpha :  Regularization strength, will override max_rules parameter
 
cv : Whether to use cross-validation scores to select the regularization strength
the final regularization value out of all that satisfy max_rules. If False, the least regularization possible is used.
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(), GradientBoostingClassifier(), or RandomForestRegressor()

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.utils._estimator_html_repr._HTMLDocumentationLinkMixin
  • sklearn.utils._metadata_requests._MetadataRequester
  • sklearn.base.TransformerMixin
  • sklearn.utils._set_output._SetOutputMixin
  • RuleSet
  • sklearn.base.RegressorMixin

Methods

def set_score_request(self: FPLassoRegressor, *, sample_weight: Union[bool, ForwardRef(None), str] = '$UNCHANGED$') ‑> FPLassoRegressor

Request metadata passed to the score method.

Note that this method is only relevant if enable_metadata_routing=True (see :func:sklearn.set_config). Please see :ref:User Guide <metadata_routing> on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to score if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to score.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version: 1.3

Note

This method is only relevant if this estimator is used as a sub-estimator of a meta-estimator, e.g. used inside a :class:~sklearn.pipeline.Pipeline. Otherwise it has no effect.

Parameters

sample_weight : str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED
Metadata routing for sample_weight parameter in score.

Returns

self : object
The updated object.
Expand source code
def func(**kw):
    """Updates the request for provided parameters

    This docstring is overwritten below.
    See REQUESTER_DOC for expected functionality
    """
    if not _routing_enabled():
        raise RuntimeError(
            "This method is only available when metadata routing is enabled."
            " You can enable it using"
            " sklearn.set_config(enable_metadata_routing=True)."
        )

    if self.validate_keys and (set(kw) - set(self.keys)):
        raise TypeError(
            f"Unexpected args: {set(kw) - set(self.keys)}. Accepted arguments"
            f" are: {set(self.keys)}"
        )

    requests = instance._get_metadata_request()
    method_metadata_request = getattr(requests, self.name)

    for prop, alias in kw.items():
        if alias is not UNCHANGED:
            method_metadata_request.add_request(param=prop, alias=alias)
    instance._metadata_request = requests

    return instance

Inherited members