Module imodels.tree.cart_ccp

Expand source code
from sklearn.tree import DecisionTreeClassifier, export_text, DecisionTreeRegressor
from sklearn.base import BaseEstimator
from sklearn import datasets
from sklearn.datasets import make_friedman1,make_friedman2,make_friedman3
from imodels.util.tree import compute_tree_complexity
from copy import deepcopy



class DecisionTreeClassifierCCP(DecisionTreeClassifier):
    def __init__(self, estimator_: BaseEstimator, desired_complexity: int = 1):
        self.desired_complexity = desired_complexity
        #print('est', estimator_)
        self.estimator_ = estimator_
    
    def fit(self,X,y,sample_weight=None,*args, **kwargs):
        path = self.estimator_.cost_complexity_pruning_path(X,y)
        ccp_alphas, impurities = path.ccp_alphas, path.impurities
        complexities = {}
        for alpha in ccp_alphas: 
            est_params = self.estimator_.get_params()
            est_params['ccp_alpha'] = alpha
            copied_estimator =  deepcopy(self.estimator_).set_params(**est_params)
            copied_estimator.fit(X, y)
            complexities[alpha] = self._get_complexity(copied_estimator)
        closest_alpha, closest_leaves = min(complexities.items(), key=lambda x: abs(self.desired_complexity - x[1]))
        params_for_fitting = self.estimator_.get_params()
        params_for_fitting['ccp_alpha'] = closest_alpha
        self.estimator_.set_params(**params_for_fitting)
        self.estimator_.fit(X,y,*args, **kwargs)
    
    def _get_complexity(self,BaseEstimator):
        return compute_tree_complexity(BaseEstimator.tree_)
    
    def predict_proba(self, *args, **kwargs):
        if hasattr(self.estimator_, 'predict_proba'):
            return self.estimator_.predict_proba(*args, **kwargs)
        else:
            return NotImplemented

    
    def predict(self,X,*args, **kwargs):
        return self.estimator_.predict(X,*args, **kwargs)
    
    def score(self, *args, **kwargs):
        if hasattr(self.estimator_, 'score'):
            return self.estimator_.score(*args, **kwargs)
        else:
            return NotImplemented
        
        
class DecisionTreeRegressorCCP(BaseEstimator):
    
    def __init__(self, estimator_: BaseEstimator, desired_complexity: int = 1):
        self.desired_complexity = desired_complexity
        #print('est', estimator_)
        self.estimator_ = estimator_
    
    def fit(self,X,y,sample_weight=None,*args, **kwargs):
        path = self.estimator_.cost_complexity_pruning_path(X,y)
        ccp_alphas, impurities = path.ccp_alphas, path.impurities
        complexities = {}
        for alpha in ccp_alphas: 
            est_params = self.estimator_.get_params()
            est_params['ccp_alpha'] = alpha
            copied_estimator =  deepcopy(self.estimator_).set_params(**est_params)
            copied_estimator.fit(X, y)
            complexities[alpha] = self._get_complexity(copied_estimator)
        closest_alpha, closest_leaves = min(complexities.items(), key=lambda x: abs(self.desired_complexity - x[1]))
        params_for_fitting = self.estimator_.get_params()
        params_for_fitting['ccp_alpha'] = closest_alpha
        self.estimator_.set_params(**params_for_fitting)
        self.estimator_.fit(X,y,*args, **kwargs)
    
    def _get_complexity(self,BaseEstimator):
        return compute_tree_complexity(BaseEstimator.tree_)
    
    def predict(self,X,*args, **kwargs):
        return self.estimator_.predict(X,*args, **kwargs)
    
    def score(self, *args, **kwargs):
        if hasattr(self.estimator_, 'score'):
            return self.estimator_.score(*args, **kwargs)
        else:
            return NotImplemented

if __name__ == '__main__':
    m = DecisionTreeClassifierCCP(estimator_=DecisionTreeClassifier(min_samples_leaf = 5),desired_complexity = 10)
    #X,y = make_friedman1()
    X, y = datasets.load_breast_cancer(return_X_y=True)
    m.fit(X,y)
    m.predict(X)
    m.score(X,y)

Classes

class DecisionTreeClassifierCCP (estimator_: sklearn.base.BaseEstimator, desired_complexity: int = 1)

A decision tree classifier.

Read more in the :ref:User Guide <tree>.

Parameters

criterion : {"gini", "entropy"}, default="gini"
The function to measure the quality of a split. Supported criteria are "gini" for the Gini impurity and "entropy" for the information gain.
splitter : {"best", "random"}, default="best"
The strategy used to choose the split at each node. Supported strategies are "best" to choose the best split and "random" to choose the best random split.
max_depth : int, default=None
The maximum depth of the tree. If None, then nodes are expanded until all leaves are pure or until all leaves contain less than min_samples_split samples.
min_samples_split : int or float, default=2

The minimum number of samples required to split an internal node:

  • If int, then consider min_samples_split as the minimum number.
  • If float, then min_samples_split is a fraction and ceil(min_samples_split * n_samples) are the minimum number of samples for each split.

Changed in version: 0.18

Added float values for fractions.

min_samples_leaf : int or float, default=1

The minimum number of samples required to be at a leaf node. A split point at any depth will only be considered if it leaves at least min_samples_leaf training samples in each of the left and right branches. This may have the effect of smoothing the model, especially in regression.

  • If int, then consider min_samples_leaf as the minimum number.
  • If float, then min_samples_leaf is a fraction and ceil(min_samples_leaf * n_samples) are the minimum number of samples for each node.

Changed in version: 0.18

Added float values for fractions.

min_weight_fraction_leaf : float, default=0.0
The minimum weighted fraction of the sum total of weights (of all the input samples) required to be at a leaf node. Samples have equal weight when sample_weight is not provided.
max_features : int, float or {"auto", "sqrt", "log2"}, default=None

The number of features to consider when looking for the best split:

- If int, then consider <code>max\_features</code> features at each split.
- If float, then <code>max\_features</code> is a fraction and
  `int(max_features * n_features)` features are considered at each
  split.
- If "auto", then `max_features=sqrt(n_features)`.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.

Note: the search for a split does not stop until at least one valid partition of the node samples is found, even if it requires to effectively inspect more than max_features features.

random_state : int, RandomState instance or None, default=None
Controls the randomness of the estimator. The features are always randomly permuted at each split, even if splitter is set to "best". When max_features < n_features, the algorithm will select max_features at random at each split before finding the best split among them. But the best found split may vary across different runs, even if max_features=n_features. That is the case, if the improvement of the criterion is identical for several splits and one split has to be selected at random. To obtain a deterministic behaviour during fitting, random_state has to be fixed to an integer. See :term:Glossary <random_state> for details.
max_leaf_nodes : int, default=None
Grow a tree with max_leaf_nodes in best-first fashion. Best nodes are defined as relative reduction in impurity. If None then unlimited number of leaf nodes.
min_impurity_decrease : float, default=0.0

A node will be split if this split induces a decrease of the impurity greater than or equal to this value.

The weighted impurity decrease equation is the following::

N_t / N * (impurity - N_t_R / N_t * right_impurity
                    - N_t_L / N_t * left_impurity)

where N is the total number of samples, N_t is the number of samples at the current node, N_t_L is the number of samples in the left child, and N_t_R is the number of samples in the right child.

N, N_t, N_t_R and N_t_L all refer to the weighted sum, if sample_weight is passed.

Added in version: 0.19

class_weight : dict, list of dict or "balanced", default=None

Weights associated with classes in the form {class_label: weight}. If None, all classes are supposed to have weight one. For multi-output problems, a list of dicts can be provided in the same order as the columns of y.

Note that for multioutput (including multilabel) weights should be defined for each class of every column in its own dict. For example, for four-class multilabel classification weights should be [{0: 1, 1: 1}, {0: 1, 1: 5}, {0: 1, 1: 1}, {0: 1, 1: 1}] instead of [{1:1}, {2:5}, {3:1}, {4:1}].

The "balanced" mode uses the values of y to automatically adjust weights inversely proportional to class frequencies in the input data as n_samples / (n_classes * np.bincount(y))

For multi-output, the weights of each column of y will be multiplied.

Note that these weights will be multiplied with sample_weight (passed through the fit method) if sample_weight is specified.

ccp_alpha : non-negative float, default=0.0

Complexity parameter used for Minimal Cost-Complexity Pruning. The subtree with the largest cost complexity that is smaller than ccp_alpha will be chosen. By default, no pruning is performed. See :ref:minimal_cost_complexity_pruning for details.

Added in version: 0.22

Attributes

classes_ : ndarray of shape (n_classes,) or list of ndarray
The classes labels (single output problem), or a list of arrays of class labels (multi-output problem).
feature_importances_ : ndarray of shape (n_features,)

The impurity-based feature importances. The higher, the more important the feature. The importance of a feature is computed as the (normalized) total reduction of the criterion brought by that feature. It is also known as the Gini importance [4]_.

Warning: impurity-based feature importances can be misleading for high cardinality features (many unique values). See :func:sklearn.inspection.permutation_importance as an alternative.

max_features_ : int
The inferred value of max_features.
n_classes_ : int or list of int
The number of classes (for single output problems), or a list containing the number of classes for each output (for multi-output problems).
n_features_ : int

The number of features when fit is performed.

Deprecated since version: 1.0

n_features_ is deprecated in 1.0 and will be removed in 1.2. Use n_features_in_ instead.

n_features_in_ : int

Number of features seen during :term:fit.

Added in version: 0.24

feature_names_in_ : ndarray of shape (n_features_in_,)

Names of features seen during :term:fit. Defined only when X has feature names that are all strings.

Added in version: 1.0

n_outputs_ : int
The number of outputs when fit is performed.
tree_ : Tree instance
The underlying Tree object. Please refer to help(sklearn.tree._tree.Tree) for attributes of Tree object and :ref:sphx_glr_auto_examples_tree_plot_unveil_tree_structure.py for basic usage of these attributes.

See Also

DecisionTreeRegressor
A decision tree regressor.

Notes

The default values for the parameters controlling the size of the trees (e.g. max_depth, min_samples_leaf, etc.) lead to fully grown and unpruned trees which can potentially be very large on some data sets. To reduce memory consumption, the complexity and size of the trees should be controlled by setting those parameter values.

The :meth:predict method operates using the :func:numpy.argmax function on the outputs of :meth:predict_proba. This means that in case the highest predicted probabilities are tied, the classifier will predict the tied class with the lowest index in :term:classes_.

References

.. [1] https://en.wikipedia.org/wiki/Decision_tree_learning

.. [2] L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification and Regression Trees", Wadsworth, Belmont, CA, 1984.

.. [3] T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical Learning", Springer, 2009.

.. [4] L. Breiman, and A. Cutler, "Random Forests", https://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm

Examples

>>> from sklearn.datasets import load_iris
>>> from sklearn.model_selection import cross_val_score
>>> from sklearn.tree import DecisionTreeClassifier
>>> clf = DecisionTreeClassifier(random_state=0)
>>> iris = load_iris()
>>> cross_val_score(clf, iris.data, iris.target, cv=10)
...                             # doctest: +SKIP
...
array([ 1.     ,  0.93...,  0.86...,  0.93...,  0.93...,
        0.93...,  0.93...,  1.     ,  0.93...,  1.      ])
Expand source code
class DecisionTreeClassifierCCP(DecisionTreeClassifier):
    def __init__(self, estimator_: BaseEstimator, desired_complexity: int = 1):
        self.desired_complexity = desired_complexity
        #print('est', estimator_)
        self.estimator_ = estimator_
    
    def fit(self,X,y,sample_weight=None,*args, **kwargs):
        path = self.estimator_.cost_complexity_pruning_path(X,y)
        ccp_alphas, impurities = path.ccp_alphas, path.impurities
        complexities = {}
        for alpha in ccp_alphas: 
            est_params = self.estimator_.get_params()
            est_params['ccp_alpha'] = alpha
            copied_estimator =  deepcopy(self.estimator_).set_params(**est_params)
            copied_estimator.fit(X, y)
            complexities[alpha] = self._get_complexity(copied_estimator)
        closest_alpha, closest_leaves = min(complexities.items(), key=lambda x: abs(self.desired_complexity - x[1]))
        params_for_fitting = self.estimator_.get_params()
        params_for_fitting['ccp_alpha'] = closest_alpha
        self.estimator_.set_params(**params_for_fitting)
        self.estimator_.fit(X,y,*args, **kwargs)
    
    def _get_complexity(self,BaseEstimator):
        return compute_tree_complexity(BaseEstimator.tree_)
    
    def predict_proba(self, *args, **kwargs):
        if hasattr(self.estimator_, 'predict_proba'):
            return self.estimator_.predict_proba(*args, **kwargs)
        else:
            return NotImplemented

    
    def predict(self,X,*args, **kwargs):
        return self.estimator_.predict(X,*args, **kwargs)
    
    def score(self, *args, **kwargs):
        if hasattr(self.estimator_, 'score'):
            return self.estimator_.score(*args, **kwargs)
        else:
            return NotImplemented

Ancestors

  • sklearn.tree._classes.DecisionTreeClassifier
  • sklearn.base.ClassifierMixin
  • sklearn.tree._classes.BaseDecisionTree
  • sklearn.base.MultiOutputMixin
  • sklearn.base.BaseEstimator

Methods

def fit(self, X, y, sample_weight=None, *args, **kwargs)

Build a decision tree classifier from the training set (X, y).

Parameters

X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, it will be converted to dtype=np.float32 and if a sparse matrix is provided to a sparse csc_matrix.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (class labels) as integers or strings.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights. If None, then samples are equally weighted. Splits that would create child nodes with net zero or negative weight are ignored while searching for a split in each node. Splits are also ignored if they would result in any single class carrying a negative weight in either child node.
check_input : bool, default=True
Allow to bypass several input checking. Don't use this parameter unless you know what you do.
X_idx_sorted : deprecated, default="deprecated"

This parameter is deprecated and has no effect. It will be removed in 1.1 (renaming of 0.26).

Deprecated since version: 0.24

Returns

self : DecisionTreeClassifier
Fitted estimator.
Expand source code
def fit(self,X,y,sample_weight=None,*args, **kwargs):
    path = self.estimator_.cost_complexity_pruning_path(X,y)
    ccp_alphas, impurities = path.ccp_alphas, path.impurities
    complexities = {}
    for alpha in ccp_alphas: 
        est_params = self.estimator_.get_params()
        est_params['ccp_alpha'] = alpha
        copied_estimator =  deepcopy(self.estimator_).set_params(**est_params)
        copied_estimator.fit(X, y)
        complexities[alpha] = self._get_complexity(copied_estimator)
    closest_alpha, closest_leaves = min(complexities.items(), key=lambda x: abs(self.desired_complexity - x[1]))
    params_for_fitting = self.estimator_.get_params()
    params_for_fitting['ccp_alpha'] = closest_alpha
    self.estimator_.set_params(**params_for_fitting)
    self.estimator_.fit(X,y,*args, **kwargs)
def predict(self, X, *args, **kwargs)

Predict class or regression value for X.

For a classification model, the predicted class for each sample in X is returned. For a regression model, the predicted value based on X is returned.

Parameters

X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, it will be converted to dtype=np.float32 and if a sparse matrix is provided to a sparse csr_matrix.
check_input : bool, default=True
Allow to bypass several input checking. Don't use this parameter unless you know what you do.

Returns

y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The predicted classes, or the predict values.
Expand source code
def predict(self,X,*args, **kwargs):
    return self.estimator_.predict(X,*args, **kwargs)
def predict_proba(self, *args, **kwargs)

Predict class probabilities of the input samples X.

The predicted class probability is the fraction of samples of the same class in a leaf.

Parameters

X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, it will be converted to dtype=np.float32 and if a sparse matrix is provided to a sparse csr_matrix.
check_input : bool, default=True
Allow to bypass several input checking. Don't use this parameter unless you know what you do.

Returns

proba : ndarray of shape (n_samples, n_classes) or list of n_outputs such arrays if n_outputs > 1
The class probabilities of the input samples. The order of the classes corresponds to that in the attribute :term:classes_.
Expand source code
def predict_proba(self, *args, **kwargs):
    if hasattr(self.estimator_, 'predict_proba'):
        return self.estimator_.predict_proba(*args, **kwargs)
    else:
        return NotImplemented
def score(self, *args, **kwargs)

Return the mean accuracy on the given test data and labels.

In multi-label classification, this is the subset accuracy which is a harsh metric since you require for each sample that each label set be correctly predicted.

Parameters

X : array-like of shape (n_samples, n_features)
Test samples.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
True labels for X.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.

Returns

score : float
Mean accuracy of self.predict(X) wrt. y.
Expand source code
def score(self, *args, **kwargs):
    if hasattr(self.estimator_, 'score'):
        return self.estimator_.score(*args, **kwargs)
    else:
        return NotImplemented
class DecisionTreeRegressorCCP (estimator_: sklearn.base.BaseEstimator, desired_complexity: int = 1)

Base class for all estimators in scikit-learn.

Notes

All estimators should specify all the parameters that can be set at the class level in their __init__ as explicit keyword arguments (no *args or **kwargs).

Expand source code
class DecisionTreeRegressorCCP(BaseEstimator):
    
    def __init__(self, estimator_: BaseEstimator, desired_complexity: int = 1):
        self.desired_complexity = desired_complexity
        #print('est', estimator_)
        self.estimator_ = estimator_
    
    def fit(self,X,y,sample_weight=None,*args, **kwargs):
        path = self.estimator_.cost_complexity_pruning_path(X,y)
        ccp_alphas, impurities = path.ccp_alphas, path.impurities
        complexities = {}
        for alpha in ccp_alphas: 
            est_params = self.estimator_.get_params()
            est_params['ccp_alpha'] = alpha
            copied_estimator =  deepcopy(self.estimator_).set_params(**est_params)
            copied_estimator.fit(X, y)
            complexities[alpha] = self._get_complexity(copied_estimator)
        closest_alpha, closest_leaves = min(complexities.items(), key=lambda x: abs(self.desired_complexity - x[1]))
        params_for_fitting = self.estimator_.get_params()
        params_for_fitting['ccp_alpha'] = closest_alpha
        self.estimator_.set_params(**params_for_fitting)
        self.estimator_.fit(X,y,*args, **kwargs)
    
    def _get_complexity(self,BaseEstimator):
        return compute_tree_complexity(BaseEstimator.tree_)
    
    def predict(self,X,*args, **kwargs):
        return self.estimator_.predict(X,*args, **kwargs)
    
    def score(self, *args, **kwargs):
        if hasattr(self.estimator_, 'score'):
            return self.estimator_.score(*args, **kwargs)
        else:
            return NotImplemented

Ancestors

  • sklearn.base.BaseEstimator

Methods

def fit(self, X, y, sample_weight=None, *args, **kwargs)
Expand source code
def fit(self,X,y,sample_weight=None,*args, **kwargs):
    path = self.estimator_.cost_complexity_pruning_path(X,y)
    ccp_alphas, impurities = path.ccp_alphas, path.impurities
    complexities = {}
    for alpha in ccp_alphas: 
        est_params = self.estimator_.get_params()
        est_params['ccp_alpha'] = alpha
        copied_estimator =  deepcopy(self.estimator_).set_params(**est_params)
        copied_estimator.fit(X, y)
        complexities[alpha] = self._get_complexity(copied_estimator)
    closest_alpha, closest_leaves = min(complexities.items(), key=lambda x: abs(self.desired_complexity - x[1]))
    params_for_fitting = self.estimator_.get_params()
    params_for_fitting['ccp_alpha'] = closest_alpha
    self.estimator_.set_params(**params_for_fitting)
    self.estimator_.fit(X,y,*args, **kwargs)
def predict(self, X, *args, **kwargs)
Expand source code
def predict(self,X,*args, **kwargs):
    return self.estimator_.predict(X,*args, **kwargs)
def score(self, *args, **kwargs)
Expand source code
def score(self, *args, **kwargs):
    if hasattr(self.estimator_, 'score'):
        return self.estimator_.score(*args, **kwargs)
    else:
        return NotImplemented