raise notfittederror in stacking estimators

docs/sources/CHANGELOG.md

@@ -27,11 +27,13 @@ The fit method of the SequentialFeatureSelector now optionally accepts **fit_par
 
 
 - Replaces `plot_decision_regions` colors by a colorblind-friendly palette and adds contour lines for decision regions. ([#348](https://github.com/rasbt/mlxtend/issues/348))
+- All stacking estimators now raise `NonFittedErrors` if any method for inference is called prior to fitting the estimator. ([#353](https://github.com/rasbt/mlxtend/issues/353))
 
 
 ##### Bug Fixes
 
-- -
+
+
 
 
 ### Version 0.11.0 (2018-03-14)

mlxtend/classifier/stacking_classification.py

@@ -8,13 +8,13 @@
 #
 # License: BSD 3 clause
 
+from ..externals.estimator_checks import check_is_fitted
+from ..externals.name_estimators import _name_estimators
+from ..externals import six
 from sklearn.base import BaseEstimator
 from sklearn.base import ClassifierMixin
 from sklearn.base import TransformerMixin
 from sklearn.base import clone
-from sklearn.utils.validation import check_is_fitted
-from ..externals.name_estimators import _name_estimators
-from ..externals import six
 import numpy as np
 
 
@@ -188,6 +188,7 @@ def predict_meta_features(self, X):
             Returns the meta-features for test data.
 
         """
+        check_is_fitted(self, 'clfs_')
         if self.use_probas:
             probas = np.asarray([clf.predict_proba(X)
                                  for clf in self.clfs_])

mlxtend/classifier/stacking_cv_classification.py

@@ -10,11 +10,11 @@
 # License: BSD 3 clause
 
 from ..externals.name_estimators import _name_estimators
+from ..externals.estimator_checks import check_is_fitted
 from sklearn.base import BaseEstimator
 from sklearn.base import ClassifierMixin
 from sklearn.base import TransformerMixin
 from sklearn.base import clone
-from sklearn.utils.validation import check_is_fitted
 from sklearn.externals import six
 from sklearn.model_selection._split import check_cv
 import numpy as np
@@ -321,6 +321,7 @@ def predict(self, X):
             Predicted class labels.
 
         """
+        check_is_fitted(self, 'clfs_')
         all_model_predictions = self.predict_meta_features(X)
         if not self.use_features_in_secondary:
             return self.meta_clf_.predict(all_model_predictions)

mlxtend/classifier/tests/test_stacking_classifier.py

@@ -5,13 +5,13 @@
 # License: BSD 3 clause
 
 from mlxtend.classifier import StackingClassifier
+from mlxtend.externals.estimator_checks import NotFittedError
 from sklearn.linear_model import LogisticRegression
 from sklearn.naive_bayes import GaussianNB
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.model_selection import GridSearchCV
 from sklearn.model_selection import cross_val_score
-from sklearn.exceptions import NotFittedError
 import numpy as np
 from sklearn import datasets
 from mlxtend.utils import assert_raises
@@ -197,6 +197,13 @@ def test_not_fitted():
                   sclf.predict_proba,
                   iris.data)
 
+    assert_raises(NotFittedError,
+                  "This StackingClassifier instance is not fitted yet."
+                  " Call 'fit' with appropriate arguments"
+                  " before using this method.",
+                  sclf.predict_meta_features,
+                  iris.data)
+
 
 def test_verbose():
     np.random.seed(123)

mlxtend/classifier/tests/test_stacking_cv_classifier.py

@@ -5,19 +5,18 @@
 #
 # License: BSD 3 clause
 
-from mlxtend.classifier import StackingCVClassifier
-
 import pandas as pd
+import numpy as np
+from mlxtend.classifier import StackingCVClassifier
+from mlxtend.externals.estimator_checks import NotFittedError
+from mlxtend.utils import assert_raises
 from sklearn.linear_model import LogisticRegression
 from sklearn.naive_bayes import GaussianNB
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.neighbors import KNeighborsClassifier
-import numpy as np
 from sklearn import datasets
-from mlxtend.utils import assert_raises
 from sklearn.model_selection import GridSearchCV
 from sklearn.model_selection import KFold
-from sklearn.exceptions import NotFittedError
 from sklearn.model_selection import cross_val_score
 from sklearn.model_selection import train_test_split
 
@@ -203,6 +202,13 @@ def test_not_fitted():
                   sclf.predict_proba,
                   iris.data)
 
+    assert_raises(NotFittedError,
+                  "This StackingCVClassifier instance is not fitted yet."
+                  " Call 'fit' with appropriate arguments"
+                  " before using this method.",
+                  sclf.predict_meta_features,
+                  iris.data)
+
 
 def test_verbose():
     np.random.seed(123)

mlxtend/externals/estimator_checks.py

@@ -0,0 +1,73 @@
+
+# Source: https://github.com/scikit-learn/scikit-learn
+
+"""Utilities for input validation"""
+
+# Authors: Olivier Grisel
+#          Gael Varoquaux
+#          Andreas Mueller
+#          Lars Buitinck
+#          Alexandre Gramfort
+#          Nicolas Tresegnie
+# License: BSD 3 clause
+
+
+class NotFittedError(ValueError, AttributeError):
+    """Exception class to raise if estimator is used before fitting.
+    This class inherits from both ValueError and AttributeError to help with
+    exception handling and backward compatibility.
+    Examples
+    --------
+    >>> from sklearn.svm import LinearSVC
+    >>> from sklearn.exceptions import NotFittedError
+    >>> try:
+    ...     LinearSVC().predict([[1, 2], [2, 3], [3, 4]])
+    ... except NotFittedError as e:
+    ...     print(repr(e))
+    ...                        # doctest: +NORMALIZE_WHITESPACE +ELLIPSIS
+    NotFittedError('This LinearSVC instance is not fitted yet',)
+    .. versionchanged:: 0.18
+       Moved from sklearn.utils.validation.
+    """
+
+
+def check_is_fitted(estimator, attributes, msg=None, all_or_any=all):
+    """Perform is_fitted validation for estimator.
+    Checks if the estimator is fitted by verifying the presence of
+    "all_or_any" of the passed attributes and raises a NotFittedError with the
+    given message.
+    Parameters
+    ----------
+    estimator : estimator instance.
+        estimator instance for which the check is performed.
+    attributes : attribute name(s) given as string or a list/tuple of strings
+        Eg.:
+            ``["coef_", "estimator_", ...], "coef_"``
+    msg : string
+        The default error message is, "This %(name)s instance is not fitted
+        yet. Call 'fit' with appropriate arguments before using this method."
+        For custom messages if "%(name)s" is present in the message string,
+        it is substituted for the estimator name.
+        Eg. : "Estimator, %(name)s, must be fitted before sparsifying".
+    all_or_any : callable, {all, any}, default all
+        Specify whether all or any of the given attributes must exist.
+    Returns
+    -------
+    None
+    Raises
+    ------
+    NotFittedError
+        If the attributes are not found.
+    """
+    if msg is None:
+        msg = ("This %(name)s instance is not fitted yet. Call 'fit' with "
+               "appropriate arguments before using this method.")
+
+    if not hasattr(estimator, 'fit'):
+        raise TypeError("%s is not an estimator instance." % (estimator))
+
+    if not isinstance(attributes, (list, tuple)):
+        attributes = [attributes]
+
+    if not all_or_any([hasattr(estimator, attr) for attr in attributes]):
+        raise NotFittedError(msg % {'name': type(estimator).__name__})

mlxtend/regressor/stacking_cv_regression.py

@@ -13,14 +13,15 @@
 #
 # License: BSD 3 clause
 
+from ..externals.estimator_checks import check_is_fitted
+from ..externals import six
+from ..externals.name_estimators import _name_estimators
 from sklearn.base import BaseEstimator
 from sklearn.base import RegressorMixin
 from sklearn.base import TransformerMixin
 from sklearn.base import clone
-from sklearn.exceptions import NotFittedError
 from sklearn.model_selection._split import check_cv
-from ..externals import six
-from ..externals.name_estimators import _name_estimators
+
 import numpy as np
 
 
@@ -203,9 +204,7 @@ def predict(self, X):
         # the meta-model from that info.
         #
 
-        if not hasattr(self, 'regr_'):
-            raise NotFittedError("Estimator not fitted, "
-                                 "call `fit` before exploiting the model.")
+        check_is_fitted(self, 'regr_')
 
         meta_features = np.column_stack([
             regr.predict(X) for regr in self.regr_
@@ -233,9 +232,7 @@ def predict_meta_features(self, X):
             of regressors.
 
         """
-        if not hasattr(self, 'regr_'):
-            raise NotFittedError("Estimator not fitted, "
-                                 "call `fit` before exploiting the model.")
+        check_is_fitted(self, 'regr_')
         return np.column_stack([regr.predict(X) for regr in self.regr_])
 
     def get_params(self, deep=True):

mlxtend/regressor/stacking_regression.py

@@ -8,13 +8,13 @@
 #
 # License: BSD 3 clause
 
+from ..externals.estimator_checks import check_is_fitted
+from ..externals.name_estimators import _name_estimators
+from ..externals import six
 from sklearn.base import BaseEstimator
 from sklearn.base import RegressorMixin
 from sklearn.base import TransformerMixin
 from sklearn.base import clone
-from sklearn.exceptions import NotFittedError
-from ..externals.name_estimators import _name_estimators
-from ..externals import six
 import numpy as np
 
 
@@ -183,9 +183,7 @@ def predict_meta_features(self, X):
             of regressors.
 
         """
-        if not hasattr(self, 'regr_'):
-            raise NotFittedError("Estimator not fitted, "
-                                 "call `fit` before exploiting the model.")
+        check_is_fitted(self, 'regr_')
         return np.column_stack([r.predict(X) for r in self.regr_])
 
     def predict(self, X):
@@ -202,5 +200,6 @@ def predict(self, X):
         y_target : array-like, shape = [n_samples] or [n_samples, n_targets]
             Predicted target values.
         """
+        check_is_fitted(self, 'regr_')
         meta_features = self.predict_meta_features(X)
         return self.meta_regr_.predict(meta_features)

mlxtend/regressor/tests/test_stacking_cv_regression.py

@@ -8,13 +8,13 @@
 # License: BSD 3 clause
 
 import numpy as np
+from mlxtend.externals.estimator_checks import NotFittedError
 from mlxtend.regressor import StackingCVRegressor
+from mlxtend.utils import assert_raises
 from sklearn.linear_model import LinearRegression
 from sklearn.linear_model import Ridge
 from sklearn.svm import SVR
-from sklearn.exceptions import NotFittedError
 from sklearn.model_selection import GridSearchCV, train_test_split
-from mlxtend.utils import assert_raises
 
 
 # Some test data
@@ -180,27 +180,14 @@ def test_not_fitted_predict():
                                  store_train_meta_features=True)
     X_train, X_test, y_train, y_test = train_test_split(X2, y, test_size=0.3)
 
-    expect = ("Estimator not fitted, "
-              "call `fit` before exploiting the model.")
+    expect = ("This StackingCVRegressor instance is not fitted yet. Call "
+              "'fit' with appropriate arguments before using this method.")
 
     assert_raises(NotFittedError,
                   expect,
                   stregr.predict,
                   X_train)
 
-
-def test_not_fitted_predict_meta_features():
-    lr = LinearRegression()
-    svr_rbf = SVR(kernel='rbf')
-    ridge = Ridge(random_state=1)
-    stregr = StackingCVRegressor(regressors=[lr, ridge],
-                                 meta_regressor=svr_rbf,
-                                 store_train_meta_features=True)
-    X_train, X_test, y_train, y_test = train_test_split(X2, y, test_size=0.3)
-
-    expect = ("Estimator not fitted, "
-              "call `fit` before exploiting the model.")
-
     assert_raises(NotFittedError,
                   expect,
                   stregr.predict_meta_features,

mlxtend/regressor/tests/test_stacking_regression.py

@@ -4,17 +4,18 @@
 #
 # License: BSD 3 clause
 
+from mlxtend.externals.estimator_checks import NotFittedError
+from mlxtend.utils import assert_raises
 from mlxtend.regressor import StackingRegressor
 from sklearn.linear_model import LinearRegression
 from sklearn.linear_model import Ridge
 from sklearn.svm import SVR
+from sklearn.model_selection import GridSearchCV
+from sklearn.model_selection import train_test_split
 import numpy as np
 from numpy.testing import assert_almost_equal
 from nose.tools import raises
-from sklearn.model_selection import GridSearchCV
-from sklearn.model_selection import train_test_split
-from sklearn.exceptions import NotFittedError
-from mlxtend.utils import assert_raises
+
 
 
 # Generating a sample dataset
@@ -220,27 +221,14 @@ def test_not_fitted_predict():
                                store_train_meta_features=True)
     X_train, X_test, y_train, y_test = train_test_split(X2, y, test_size=0.3)
 
-    expect = ("Estimator not fitted, "
-              "call `fit` before exploiting the model.")
+    expect = ("This StackingRegressor instance is not fitted yet. Call "
+              "'fit' with appropriate arguments before using this method.")
 
     assert_raises(NotFittedError,
                   expect,
                   stregr.predict,
                   X_train)
 
-
-def test_not_fitted_predict_meta_features():
-    lr = LinearRegression()
-    svr_rbf = SVR(kernel='rbf')
-    ridge = Ridge(random_state=1)
-    stregr = StackingRegressor(regressors=[lr, ridge],
-                               meta_regressor=svr_rbf,
-                               store_train_meta_features=True)
-    X_train, X_test, y_train, y_test = train_test_split(X2, y, test_size=0.3)
-
-    expect = ("Estimator not fitted, "
-              "call `fit` before exploiting the model.")
-
     assert_raises(NotFittedError,
                   expect,
                   stregr.predict_meta_features,