Merge pull request #183 from gganapavarapu/master

docstring fixes

Author: vijay-arya

aix360/algorithms/gce/gce.py

@@ -219,7 +219,11 @@ def explain_instance(
             instance (Union[pd.DataFrame, np.ndarray]): input instance to be explained.
 
         Returns:
-            explanation (Union[List[Dict], Dict]): Dictionary
+            dict: explanation object
+                Dictionary with feature_name, feature_value, ice_value, current_value
+                for ICE explanation. Dictionary with gce_values, x_grid, y_pred,
+                current_values for GCE explanation.
+
         """
 
         np.random.seed(self.random_seed)

aix360/algorithms/nncontrastive/nncontrastive.py

@@ -363,14 +363,19 @@ def get_params(self, *argv, **kwargs) -> dict:
         return self._config.copy()
 
     def explain_instance(self, x, **kwargs):
-        """Explain the model prediction for an instance (local explanation).
+        """Explain (local explanation) the model prediction for provided instance(s).
 
         Args:
             x (Union[pd.DataFrame, np.ndarray]): input instance to be explained.
 
         Additional Parameters:
-            neighbors (int): Overrides neighbors parameter provided in the init method
-                of NearestNeighborContrastiveExplainer.
+            neighbors (int): Number of neighbors
+                Overrides neighbors parameter provided in the initializer.
+
+        Returns:
+            Union(List[dict], dict): explanation object
+                Dictionary or list of dictionaries with keys: features,
+                categorical_features, query, neighbors, distances.
 
         """
         if not self.is_fitted:

aix360/algorithms/tsice/tsice.py

@@ -309,9 +309,9 @@ def explain_instance(
             explain_params: Arbitrary explainer parameters.
 
         Returns:
-            explanation (Union[List[Dict], Dict]): dictionary with data_x, feature_names,
-                feature_values, signed_impact, total_impact, current_forecast, current_feature_values,
-                perturbations and forecasts_on_perturbations.
+            dict: explanation object
+                Dictionary with data_x, feature_names, feature_values, signed_impact, total_impact,
+                current_forecast, current_feature_values, perturbations and forecasts_on_perturbations.
 
         """
 

aix360/algorithms/tslime/tslime.py

@@ -145,16 +145,17 @@ def explain_instance(self, ts: tsFrame, **explain_params):
         """Explain the prediction made by the time series model at a certain point in time
         (**local explanation**).
 
-        Args
+        Args:
             ts (tsFrame): Input time series signal in ``tsFrame`` format. This can
                 be generated using :py:mod:`aix360.algorithms.tsframe.tsFrame`.
                 A ``tsFrame`` is a pandas ``DataFrame`` indexed by ``Timestamp`` objects
                 (that is ``DatetimeIndex``). Each column corresponds to an input feature.
             explain_params: Arbitrary explainer parameters.
 
         Returns:
-            explanation (Union[List[Dict], Dict]): Dictionary with keys: input_data, history_weights,
-                model_prediction, surrogate_prediction, x_perturbations, y_perturbations.
+            dict: explanation object
+                Dictionary with keys: input_data, history_weights, model_prediction,
+                surrogate_prediction, x_perturbations, y_perturbations.
         """
         return super(TSLimeExplainer, self).explain_instance(
             ts=ts, ts_related=None, **explain_params

aix360/algorithms/tssaliency/tssaliency.py

@@ -98,16 +98,17 @@ def explain_instance(self, ts: tsFrame, **explain_params):
         """Explain the prediction made by the time series model at a certain point in time
         (**local explanation**).
 
-        Args
+        Args:
             ts (tsFrame): Input time series signal in ``tsFrame`` format. This can
                 be generated using :py:mod:`aix360.algorithms.tsframe.tsFrame`.
                 A ``tsFrame`` is a pandas ``DataFrame`` indexed by ``Timestamp`` objects
                 (that is ``DatetimeIndex``). Each column corresponds to an input feature.
             explain_params: Arbitrary explainer parameters.
 
         Returns:
-            explanation (Union[List[Dict], Dict]): Dictionary with keys: input_data, saliency,
-                feature_names, timestamps, base_value, instance_prediction, base_value_prediction.
+            dict: explanation object
+                Dictionary with input_data, saliency, feature_names, timestamps, base_value,
+                instance_prediction, base_value_prediction.
         """
         return super(TSSaliencyExplainer, self).explain_instance(
             ts=ts, ts_related=None, **explain_params