Fix sample_weights bug and update docs

doc/index.rst

@@ -27,7 +27,7 @@ Foreshadow: Simple Machine Learning Scaffolding
 
    import numpy as np
    import pandas as pd
-   from sklearn.datasets import boston_housing
+   from sklearn.datasets import load_boston
    from sklearn.model_selection import train_test_split
    import foreshadow as fs
 

doc/users.rst

@@ -22,7 +22,7 @@ Also import sklearn, pandas, and numpy for the demo
 
     import pandas as pd
 
-    from sklearn.datasets import boston_housing
+    from sklearn.datasets import load_boston
     from sklearn.model_selection import train_test_split
 
 Now load in the boston housing dataset from sklearn into pandas dataframes. This

foreshadow/estimators/auto.py

@@ -2,7 +2,6 @@
 AutoEstimator and its selection
 """
 
-import inspect
 import operator
 import warnings
 
@@ -215,12 +214,11 @@ def predict_proba(self, X):  # pragma: no cover
         X = check_df(X)
         return self.estimator.predict_proba(X)
 
-    def score(self, X, y):
+    def score(self, X, y, sample_weight=None):
         """Uses the trained estimator to compute the evaluation score defined
         by the estimator
 
-        Note: sample weight is not implemented as tpot does not accept it in 
-        its score field
+        Note: sample weights are not supported
 
         Args:
             X (pandas.DataFrame or numpy.ndarray or list): The input feature(s)

foreshadow/estimators/meta.py

@@ -2,6 +2,8 @@
 Wrapped Estimator
 """
 
+import inspect
+
 from sklearn.base import BaseEstimator, TransformerMixin
 
 from ..utils import check_df
@@ -62,22 +64,23 @@ def predict_proba(self, X):
         X = check_df(X)
         return self.estimator.predict_proba(X)
 
-    def score(self, X, y, sample_weight=None):
+    def score(self, X, y):
         """Uses the trained estimator to compute the evaluation score defined
         by the estimator
 
+        Note: sample weights are not supported
+
         Args:
             X (:obj:`pandas.DataFrame` or :obj:`numpy.ndarray` or list):
                 The input feature(s)
             y (:obj:`pandas.DataFrame` or :obj:`numpy.ndarray` or list):
                 The response feature(s)
-            sample_weight (:obj:`numpy.ndarray`, optional):
-                The weights to be used when scoring each sample
         
         Returns:
             float: A computed prediction fitness score
         """
         X = check_df(X)
         y = check_df(y)
         y = self.preprocessor.transform(y)
-        return self.estimator.score(X, y, sample_weight)
+
+        return self.estimator.score(X, y)

foreshadow/tests/test_estimators/test_auto.py

@@ -55,6 +55,8 @@ def test_invalid_kwargs_not_dict():
 def test_override_kwarg_dict():
     from foreshadow.estimators import AutoEstimator
 
+    # if this is erroring make sure that auto_sklearn is installed
+
     ae = AutoEstimator(
         problem_type="regression",
         auto="autosklearn",

foreshadow/tests/test_estimators/test_meta.py

@@ -8,7 +8,7 @@ def test_metaestimator_predict():
     from sklearn.linear_model import LinearRegression
     from sklearn.model_selection import train_test_split
 
-    from foreshadow.estimators.meta import MetaEstimator
+    from foreshadow.estimators import MetaEstimator
 
     np.random.seed(0)
 
@@ -34,7 +34,7 @@ def test_metaestimator_predict_proba():
     from sklearn.linear_model import LogisticRegression
     from sklearn.model_selection import train_test_split
 
-    from foreshadow.estimators.meta import MetaEstimator
+    from foreshadow.estimators import MetaEstimator
 
     np.random.seed(0)
 
@@ -58,7 +58,7 @@ def test_metaestimator_score():
     from sklearn.linear_model import LogisticRegression
     from sklearn.model_selection import train_test_split
 
-    from foreshadow.estimators.meta import MetaEstimator
+    from foreshadow.estimators import MetaEstimator
 
     np.random.seed(0)
 
@@ -75,10 +75,3 @@ def test_metaestimator_score():
     assert np.allclose(
         me.score(X_test, y_test), est.score(X_test, scaler.transform(y_test))
     )
-
-    # test score parameter
-    sample_weight = np.random.randint(1, 10, y_test.size)
-    assert np.allclose(
-        me.score(X_test, y_test, sample_weight=sample_weight),
-        est.score(X_test, scaler.transform(y_test), sample_weight=sample_weight),
-    )