Stree¶

class stree.Stree(C: float = 1.0, kernel: str = 'linear', max_iter: int = 100000.0, random_state: Optional[int] = None, max_depth: Optional[int] = None, tol: float = 0.0001, degree: int = 3, gamma='scale', split_criteria: str = 'impurity', criterion: str = 'entropy', min_samples_split: int = 0, max_features=None, splitter: str = 'random', multiclass_strategy: str = 'ovo', normalize: bool = False)[source]¶

Bases: sklearn.base.BaseEstimator, sklearn.base.ClassifierMixin

Estimator that is based on binary trees of svm nodes can deal with sample_weights in predict, used in boosting sklearn methods inheriting from BaseEstimator implements get_params and set_params methods inheriting from ClassifierMixin implement the attribute _estimator_type with “classifier” as value

_build_clf()[source]¶: Build the right classifier for the node

_initialize_max_features() → int[source]¶

_more_tags() → dict[source]¶

Required by sklearn to supply features of the classifier make mandatory the labels array

Returns: the tag required
Return type: dict

static _reorder_results(y: numpy.array, indices: numpy.array) → numpy.array[source]¶

Reorder an array based on the array of indices passed

ynp.array: data untidy
indicesnp.array: indices used to set order

np.array: array y ordered

_train(X: numpy.ndarray, y: numpy.ndarray, sample_weight: numpy.ndarray, depth: int, title: str) → Optional[stree.Splitter.Snode][source]¶

Recursive function to split the original dataset into predictor nodes (leaves)

Xnp.ndarray: samples dataset
ynp.ndarray: samples labels
sample_weightnp.ndarray: weight of samples. Rescale C per sample.
depthint: actual depth in the tree
titlestr: description of the node

Optional[Snode]: binary tree

fit(X: numpy.ndarray, y: numpy.ndarray, sample_weight: Optional[numpy.array] = None) → stree.Strees.Stree[source]¶

Build the tree based on the dataset of samples and its labels

Stree: itself to be able to chain actions: fit().predict() …

ValueError: if C < 0
ValueError: if max_depth < 1
ValueError: if all samples have 0 or negative weights

nodes_leaves() → tuple[source]¶

Compute the number of nodes and leaves in the built tree

[tuple]: tuple with the number of nodes and the number of leaves

predict(X: numpy.array) → numpy.array[source]¶

Predict labels for each sample in dataset passed

Xnp.array: dataset of samples

np.array: array of labels

ValueError: if dataset with inconsistent number of features
NotFittedError: if model is not fitted