Source code for lale.lib.autogen.decision_tree_classifier


from sklearn.tree.tree import DecisionTreeClassifier as SKLModel
import lale.helpers
import lale.operators
from numpy import nan, inf

[docs]class DecisionTreeClassifierImpl(): def __init__(self, criterion='gini', splitter='best', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features=None, random_state=None, max_leaf_nodes=None, min_impurity_decrease=0.0, min_impurity_split=None, class_weight='balanced', presort=False): self._hyperparams = { 'criterion': criterion, 'splitter': splitter, 'max_depth': max_depth, 'min_samples_split': min_samples_split, 'min_samples_leaf': min_samples_leaf, 'min_weight_fraction_leaf': min_weight_fraction_leaf, 'max_features': max_features, 'random_state': random_state, 'max_leaf_nodes': max_leaf_nodes, 'min_impurity_decrease': min_impurity_decrease, 'min_impurity_split': min_impurity_split, 'class_weight': class_weight, 'presort': presort}
[docs] def fit(self, X, y=None): self._sklearn_model = SKLModel(**self._hyperparams) if (y is not None): self._sklearn_model.fit(X, y) else: self._sklearn_model.fit(X) return self
[docs] def predict(self, X): return self._sklearn_model.predict(X)
[docs] def predict_proba(self, X): return self._sklearn_model.predict_proba(X)
_hyperparams_schema = { '$schema': 'http://json-schema.org/draft-04/schema#', 'description': 'inherited docstring for DecisionTreeClassifier A decision tree classifier.', 'allOf': [{ 'type': 'object', 'required': ['criterion', 'splitter', 'max_depth', 'min_samples_split', 'min_samples_leaf', 'min_weight_fraction_leaf', 'max_features', 'random_state', 'max_leaf_nodes', 'min_impurity_decrease', 'min_impurity_split', 'class_weight', 'presort'], 'relevantToOptimizer': ['criterion', 'splitter', 'max_depth', 'min_samples_split', 'min_samples_leaf', 'max_features'], 'additionalProperties': False, 'properties': { 'criterion': { 'enum': ['entropy', 'gini'], 'default': 'gini', 'description': 'The function to measure the quality of a split. Supported criteria are'}, 'splitter': { 'enum': ['random', 'best'], 'default': 'best', 'description': 'The strategy used to choose the split at each node. Supported'}, 'max_depth': { 'anyOf': [{ 'type': 'integer', 'minimumForOptimizer': 3, 'maximumForOptimizer': 5, 'distribution': 'uniform'}, { 'enum': [None]}], 'default': None, 'description': 'The maximum depth of the tree. If None, then nodes are expanded until'}, 'min_samples_split': { 'anyOf': [{ 'type': 'integer', 'minimumForOptimizer': 2, 'maximumForOptimizer': 5, 'distribution': 'uniform'}, { 'type': 'number', 'forOptimizer': False}], 'default': 2, 'description': 'The minimum number of samples required to split an internal node:'}, 'min_samples_leaf': { 'anyOf': [{ 'type': 'integer', 'minimumForOptimizer': 1, 'maximumForOptimizer': 5, 'distribution': 'uniform'}, { 'type': 'number', 'forOptimizer': False}], 'default': 1, 'description': 'The minimum number of samples required to be at a leaf node.'}, 'min_weight_fraction_leaf': { 'type': 'number', 'default': 0.0, 'description': 'The minimum weighted fraction of the sum total of weights (of all'}, 'max_features': { 'anyOf': [{ 'type': 'integer', 'forOptimizer': False}, { 'type': 'number', 'minimumForOptimizer': 0.01, 'maximumForOptimizer': 1.0, 'distribution': 'uniform'}, { 'type': 'string', 'forOptimizer': False}, { 'enum': [None]}], 'default': None, 'description': 'The number of features to consider when looking for the best split:'}, 'random_state': { 'anyOf': [{ 'type': 'integer'}, { 'type': 'object'}, { 'enum': [None]}], 'default': None, 'description': 'If int, random_state is the seed used by the random number generator;'}, 'max_leaf_nodes': { 'anyOf': [{ 'type': 'integer'}, { 'enum': [None]}], 'default': None, 'description': 'Grow a tree with ``max_leaf_nodes`` in best-first fashion.'}, 'min_impurity_decrease': { 'type': 'number', 'default': 0.0, 'description': 'A node will be split if this split induces a decrease of the impurity'}, 'min_impurity_split': { 'anyOf': [{ 'type': 'number'}, { 'enum': [None]}], 'default': None, 'description': 'Threshold for early stopping in tree growth. A node will split'}, 'class_weight': { 'XXX TODO XXX': 'dict, list of dicts, "balanced" or None, default=None', 'description': 'Weights associated with classes in the form ``{class_label: weight}``.', 'enum': ['balanced'], 'default': 'balanced'}, 'presort': { 'type': 'boolean', 'default': False, 'description': 'Whether to presort the data to speed up the finding of best splits in'}, }}, { 'XXX TODO XXX': 'Parameter: min_samples_leaf > only be considered if it leaves at least min_samples_leaf training samples in each of the left and right branches'}], } _input_fit_schema = { '$schema': 'http://json-schema.org/draft-04/schema#', 'description': 'Build a decision tree classifier from the training set (X, y).', 'type': 'object', 'properties': { 'X': { 'anyOf': [{ 'type': 'array', 'items': { 'XXX TODO XXX': 'item type'}, 'XXX TODO XXX': 'array-like or sparse matrix, shape = [n_samples, n_features]'}, { 'type': 'array', 'items': { 'type': 'array', 'items': { 'type': 'number'}, }}], 'description': 'The training input samples. Internally, it will be converted to'}, 'y': { 'anyOf': [{ 'type': 'array', 'items': { 'type': 'number'}, }, { 'type': 'array', 'items': { 'type': 'array', 'items': { 'type': 'number'}, }}], 'description': 'The target values (class labels) as integers or strings.'}, 'sample_weight': { 'anyOf': [{ 'type': 'array', 'items': { 'type': 'number'}, }, { 'enum': [None]}], 'description': 'Sample weights. If None, then samples are equally weighted. Splits'}, 'check_input': { 'type': 'boolean', 'default': True, 'description': 'Allow to bypass several input checking.'}, 'X_idx_sorted': { 'anyOf': [{ 'type': 'array', 'items': { 'type': 'array', 'items': { 'type': 'number'}, }}, { 'enum': [None]}], 'default': None, 'description': 'The indexes of the sorted training input samples. If many tree'}, }, } _input_predict_schema = { '$schema': 'http://json-schema.org/draft-04/schema#', 'description': 'Predict class or regression value for X.', 'type': 'object', 'properties': { 'X': { 'anyOf': [{ 'type': 'array', 'items': { 'XXX TODO XXX': 'item type'}, 'XXX TODO XXX': 'array-like or sparse matrix of shape = [n_samples, n_features]'}, { 'type': 'array', 'items': { 'type': 'array', 'items': { 'type': 'number'}, }}], 'description': 'The input samples. Internally, it will be converted to'}, 'check_input': { 'type': 'boolean', 'default': True, 'description': 'Allow to bypass several input checking.'}, }, } _output_predict_schema = { '$schema': 'http://json-schema.org/draft-04/schema#', 'description': 'The predicted classes, or the predict values.', 'anyOf': [{ 'type': 'array', 'items': { 'type': 'number'}, }, { 'type': 'array', 'items': { 'type': 'array', 'items': { 'type': 'number'}, }}], } _input_predict_proba_schema = { '$schema': 'http://json-schema.org/draft-04/schema#', 'description': 'Predict class probabilities of the input samples X.', 'type': 'object', 'properties': { 'X': { 'anyOf': [{ 'type': 'array', 'items': { 'XXX TODO XXX': 'item type'}, 'XXX TODO XXX': 'array-like or sparse matrix of shape = [n_samples, n_features]'}, { 'type': 'array', 'items': { 'type': 'array', 'items': { 'type': 'number'}, }}], 'description': 'The input samples. Internally, it will be converted to'}, 'check_input': { 'type': 'boolean', 'description': 'Run check_array on X.'}, }, } _output_predict_proba_schema = { '$schema': 'http://json-schema.org/draft-04/schema#', 'description': 'such arrays if n_outputs > 1.', 'XXX TODO XXX': 'array of shape = [n_samples, n_classes], or a list of n_outputs', } _combined_schemas = { '$schema': 'http://json-schema.org/draft-04/schema#', 'description': 'Combined schema for expected data and hyperparameters.', 'type': 'object', 'tags': { 'pre': [], 'op': ['estimator'], 'post': []}, 'properties': { 'hyperparams': _hyperparams_schema, 'input_fit': _input_fit_schema, 'input_predict': _input_predict_schema, 'output_predict': _output_predict_schema, 'input_predict_proba': _input_predict_proba_schema, 'output_predict_proba': _output_predict_proba_schema}, } if (__name__ == '__main__'): lale.helpers.validate_is_schema(_combined_schemas) DecisionTreeClassifier = lale.operators.make_operator(DecisionTreeClassifierImpl, _combined_schemas)