Source code for evalml.pipelines.binary_classification_pipeline

import pandas as pd

from evalml.objectives import get_objective
from evalml.pipelines.classification_pipeline import ClassificationPipeline
from evalml.problem_types import ProblemTypes


[docs]class BinaryClassificationPipeline(ClassificationPipeline): """Pipeline subclass for all binary classification pipelines.""" threshold = None problem_type = ProblemTypes.BINARY
[docs] def predict(self, X, objective=None): """Make predictions using selected features. Arguments: X (pd.DataFrame or np.array) : data of shape [n_samples, n_features] objective (Object or string): the objective to use to make predictions Returns: pd.Series : estimated labels """ if not isinstance(X, pd.DataFrame): X = pd.DataFrame(X) X_t = self._transform(X) if objective is not None: objective = get_objective(objective) if objective.problem_type != self.problem_type: raise ValueError("You can only use a binary classification objective to make predictions for a binary classification pipeline.") if self.threshold is None: return self.estimator.predict(X_t) ypred_proba = self.predict_proba(X) if isinstance(ypred_proba, pd.DataFrame): ypred_proba = ypred_proba.iloc[:, 1] else: ypred_proba = ypred_proba[:, 1] if objective is None: return ypred_proba > self.threshold return objective.decision_function(ypred_proba, threshold=self.threshold, X=X)
@staticmethod def _score(X, y, predictions, objective): """Given data, model predictions or predicted probabilities computed on the data, and an objective, evaluate and return the objective score. Will return `np.nan` if the objective errors. """ if predictions.ndim > 1: if isinstance(predictions, pd.DataFrame): predictions = predictions.iloc[:, 1] else: predictions = predictions[:, 1] return ClassificationPipeline._score(X, y, predictions, objective)