import numpy as np
import pandas as pd
from evalml.model_family import ModelFamily
from evalml.pipelines.components.estimators import Estimator
from evalml.problem_types import ProblemTypes
from evalml.utils import infer_feature_types
[docs]class BaselineRegressor(Estimator):
"""Regressor that predicts using the specified strategy.
This is useful as a simple baseline regressor to compare with other regressors.
"""
name = "Baseline Regressor"
hyperparameter_ranges = {}
model_family = ModelFamily.BASELINE
supported_problem_types = [ProblemTypes.REGRESSION, ProblemTypes.TIME_SERIES_REGRESSION]
[docs] def __init__(self, strategy="mean", random_seed=0, **kwargs):
"""Baseline regressor that uses a simple strategy to make predictions.
Arguments:
strategy (str): Method used to predict. Valid options are "mean", "median". Defaults to "mean".
random_seed (int): Seed for the random number generator. Defaults to 0.
"""
if strategy not in ["mean", "median"]:
raise ValueError("'strategy' parameter must equal either 'mean' or 'median'")
parameters = {"strategy": strategy}
parameters.update(kwargs)
self._prediction_value = None
self._num_features = None
super().__init__(parameters=parameters,
component_obj=None,
random_seed=random_seed)
[docs] def fit(self, X, y=None):
if y is None:
raise ValueError("Cannot fit Baseline regressor if y is None")
X = infer_feature_types(X)
y = infer_feature_types(y)
if self.parameters["strategy"] == "mean":
self._prediction_value = y.mean()
elif self.parameters["strategy"] == "median":
self._prediction_value = y.median()
self._num_features = X.shape[1]
return self
[docs] def predict(self, X):
X = infer_feature_types(X)
predictions = pd.Series([self._prediction_value] * len(X))
return infer_feature_types(predictions)
@property
def feature_importance(self):
"""Returns importance associated with each feature. Since baseline regressors do not use input features to calculate predictions, returns an array of zeroes.
Returns:
np.ndarray (float): An array of zeroes
"""
return np.zeros(self._num_features)