diff --git a/docs/sources/user_guide/classifier/StackingCVClassifier.ipynb b/docs/sources/user_guide/classifier/StackingCVClassifier.ipynb
index 7556278b9..92e8fd7e2 100644
--- a/docs/sources/user_guide/classifier/StackingCVClassifier.ipynb
+++ b/docs/sources/user_guide/classifier/StackingCVClassifier.ipynb
@@ -517,7 +517,7 @@
      "text": [
       "## StackingCVClassifier\n",
       "\n",
-      "*StackingCVClassifier(classifiers, meta_classifier, use_probas=False, cv=2, use_features_in_secondary=False, stratify=True, shuffle=True, verbose=0, store_train_meta_features=False)*\n",
+      "*StackingCVClassifier(classifiers, meta_classifier, use_probas=False, cv=2, use_features_in_secondary=False, stratify=True, shuffle=True, verbose=0, store_train_meta_features=False, refit=True)*\n",
       "\n",
       "A 'Stacking Cross-Validation' classifier for scikit-learn estimators.\n",
       "\n",
@@ -601,6 +601,15 @@
       "    `self.train_meta_features_` array, which can be\n",
       "    accessed after calling `fit`.\n",
       "\n",
+      "- `refit` : bool (default: True)\n",
+      "\n",
+      "    Clones the classifiers for stacking classification if True (default)\n",
+      "    or else uses the original ones, which will be refitted on the dataset\n",
+      "    upon calling the `fit` method. Setting refit=False is\n",
+      "    recommended if you are working with estimators that are supporting\n",
+      "    the scikit-learn fit/predict API interface but are not compatible\n",
+      "    to scikit-learn's `clone` function.\n",
+      "\n",
       "**Attributes**\n",
       "\n",
       "- `clfs_` : list, shape=[n_classifiers]\n",
@@ -714,12 +723,9 @@
       "\n",
       "**Returns**\n",
       "\n",
-      "- `meta-features` : numpy array\n",
+      "- `meta-features` : numpy array, shape = [n_samples, n_classifiers]\n",
       "\n",
-      "    Returns the meta-features for test data. The shape of the\n",
-      "    returned numpy array is [n_samples, n_classifiers] if\n",
-      "    `self.use_probas=False` and\n",
-      "    [n_samples, n_classifiers*n_unique_classlabels] otherwise.\n",
+      "    Returns the meta-features for test data.\n",
       "\n",
       "<hr>\n",
       "\n",
@@ -823,7 +829,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.1"
+   "version": "3.6.3"
   }
  },
  "nbformat": 4,
diff --git a/docs/sources/user_guide/classifier/StackingClassifier.ipynb b/docs/sources/user_guide/classifier/StackingClassifier.ipynb
index 6b36185cd..fd88dedaa 100644
--- a/docs/sources/user_guide/classifier/StackingClassifier.ipynb
+++ b/docs/sources/user_guide/classifier/StackingClassifier.ipynb
@@ -493,7 +493,7 @@
      "text": [
       "## StackingClassifier\n",
       "\n",
-      "*StackingClassifier(classifiers, meta_classifier, use_probas=False, average_probas=False, verbose=0, use_features_in_secondary=False, store_train_meta_features=False)*\n",
+      "*StackingClassifier(classifiers, meta_classifier, use_probas=False, average_probas=False, verbose=0, use_features_in_secondary=False, store_train_meta_features=False, refit=True)*\n",
       "\n",
       "A Stacking classifier for scikit-learn estimators for classification.\n",
       "\n",
@@ -545,6 +545,15 @@
       "    `self.train_meta_features_` array, which can be\n",
       "    accessed after calling `fit`.\n",
       "\n",
+      "- `refit` : bool (default: True)\n",
+      "\n",
+      "    Clones the classifiers for stacking classification if True (default)\n",
+      "    or else uses the original ones, which will be refitted on the dataset\n",
+      "    upon calling the `fit` method. Setting refit=False is\n",
+      "    recommended if you are working with estimators that are supporting\n",
+      "    the scikit-learn fit/predict API interface but are not compatible\n",
+      "    to scikit-learn's `clone` function.\n",
+      "\n",
       "**Attributes**\n",
       "\n",
       "- `clfs_` : list, shape=[n_classifiers]\n",
@@ -651,15 +660,9 @@
       "\n",
       "**Returns**\n",
       "\n",
-      "- `meta-features` : numpy array\n",
+      "- `meta-features` : numpy array, shape = [n_samples, n_classifiers]\n",
       "\n",
-      "    Returns the meta-features for test data. The shape of the\n",
-      "    returned numpy array is\n",
-      "    - [n_samples, n_classifiers] if `self.use_probas=False`\n",
-      "    - [n_samples, n_classifiers*n_unique_classlabels] if\n",
-      "    `self.use_probas=True` and `self.average_probas=False`\n",
-      "    - [n_samples, n_unique_classlabels] if\n",
-      "    `self.use_probas=True` and `self.average_probas=True`\n",
+      "    Returns the meta-features for test data.\n",
       "\n",
       "<hr>\n",
       "\n",
@@ -763,7 +766,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.1"
+   "version": "3.6.3"
   }
  },
  "nbformat": 4,
diff --git a/docs/sources/user_guide/regressor/StackingCVRegressor.ipynb b/docs/sources/user_guide/regressor/StackingCVRegressor.ipynb
index cc3ba7a8b..137cb2453 100644
--- a/docs/sources/user_guide/regressor/StackingCVRegressor.ipynb
+++ b/docs/sources/user_guide/regressor/StackingCVRegressor.ipynb
@@ -310,7 +310,7 @@
      "text": [
       "## StackingCVRegressor\n",
       "\n",
-      "*StackingCVRegressor(regressors, meta_regressor, cv=5, shuffle=True, use_features_in_secondary=False, store_train_meta_features=False)*\n",
+      "*StackingCVRegressor(regressors, meta_regressor, cv=5, shuffle=True, use_features_in_secondary=False, store_train_meta_features=False, refit=True)*\n",
       "\n",
       "A 'Stacking Cross-Validation' regressor for scikit-learn estimators.\n",
       "\n",
@@ -372,9 +372,18 @@
       "    which can be\n",
       "    accessed after calling `fit`.\n",
       "\n",
+      "- `refit` : bool (default: True)\n",
+      "\n",
+      "    Clones the regressors for stacking regression if True (default)\n",
+      "    or else uses the original ones, which will be refitted on the dataset\n",
+      "    upon calling the `fit` method. Setting refit=False is\n",
+      "    recommended if you are working with estimators that are supporting\n",
+      "    the scikit-learn fit/predict API interface but are not compatible\n",
+      "    to scikit-learn's `clone` function.\n",
+      "\n",
       "**Attributes**\n",
       "\n",
-      "- `train_meta_features` : numpy array, shape = [n_samples, len(self.regressors)]\n",
+      "- `train_meta_features` : numpy array, shape = [n_samples, n_regressors]\n",
       "\n",
       "    meta-features for training data, where n_samples is the\n",
       "    number of samples\n",
@@ -585,7 +594,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.1"
+   "version": "3.6.3"
   }
  },
  "nbformat": 4,
diff --git a/docs/sources/user_guide/regressor/StackingRegressor.ipynb b/docs/sources/user_guide/regressor/StackingRegressor.ipynb
index bec46fcbb..0532f4756 100644
--- a/docs/sources/user_guide/regressor/StackingRegressor.ipynb
+++ b/docs/sources/user_guide/regressor/StackingRegressor.ipynb
@@ -634,7 +634,7 @@
      "text": [
       "## StackingRegressor\n",
       "\n",
-      "*StackingRegressor(regressors, meta_regressor, verbose=0, store_train_meta_features=False)*\n",
+      "*StackingRegressor(regressors, meta_regressor, verbose=0, store_train_meta_features=False, refit=True)*\n",
       "\n",
       "A Stacking regressor for scikit-learn estimators for regression.\n",
       "\n",
@@ -695,6 +695,15 @@
       "    number of samples\n",
       "    in training data and len(self.regressors) is the number of regressors.\n",
       "\n",
+      "- `refit` : bool (default: True)\n",
+      "\n",
+      "    Clones the regressors for stacking regression if True (default)\n",
+      "    or else uses the original ones, which will be refitted on the dataset\n",
+      "    upon calling the `fit` method. Setting refit=False is\n",
+      "    recommended if you are working with estimators that are supporting\n",
+      "    the scikit-learn fit/predict API interface but are not compatible\n",
+      "    to scikit-learn's `clone` function.\n",
+      "\n",
       "### Methods\n",
       "\n",
       "<hr>\n",
@@ -894,7 +903,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.6.1"
+   "version": "3.6.3"
   }
  },
  "nbformat": 4,