Merge pull request #181 from gganapavarapu/master

format references and parameters

Author: vijay-arya

aix360/algorithms/gce/gce.py

@@ -31,6 +31,7 @@ def __init__(
         **kwargs,
     ):
         """GroupedCEExplainer initialization.
+
         Args:
             model (Callable): model prediction (predict/predict_proba) function that
                 results a real value like probability or regressed value.

aix360/algorithms/nncontrastive/nncontrastive.py

@@ -60,7 +60,7 @@ def __init__(
         classifier_bias_initializer: str = "zeros",
     ):
         """
-        Constructor method, initializes the explainer
+        NearestNeighborContrastiveExplainer initialization.
 
         Args:
             model (Callable): Classification Model which will be used for contrastive

aix360/algorithms/tsice/tsice.py

@@ -23,9 +23,9 @@ class TSICEExplainer(TSLocalBBExplainer):
     derived features.
 
     References:
-        .. [##] Goldstein et al. 'Peeking Inside the Black Box: Visualizing Statistical
+        .. [#0] `Goldstein et al. 'Peeking Inside the Black Box: Visualizing Statistical
             Learning with Plots of Individual Conditional Expectation'
-            https://arxiv.org/abs/1309.6392
+            <https://arxiv.org/abs/1309.6392>`_
     """
 
     def __init__(

aix360/algorithms/tslime/tslime.py

@@ -30,8 +30,9 @@ class TSLimeExplainer(TSLocalBBExplainer):
     The explanation weights produced by the TSLime explanation indicates model local sensitivity.
 
     References:
-        .. [##] Ribeiro et al. '"Why Should I Trust You?": Explaining the Predictions of Any Classifier'
-            https://arxiv.org/abs/1602.04938
+        .. [#0] `Ribeiro et al. '"Why Should I Trust You?": Explaining the Predictions of Any Classifier'
+            <https://arxiv.org/abs/1602.04938>`_
+
     """
 
     def __init__(

aix360/algorithms/tssaliency/gradient.py

@@ -11,8 +11,8 @@ def mc_gradient_compute(
     Monte Carlo Gradient computation.
 
     References:
-        [Section 3] Sijia Liu et al. "Zeroth-Order Stochastic Variance Reduction for
-        Nonconvex Optimization". https://arxiv.org/pdf/1906.00117.pdf
+        .. [#0] `Sijia Liu et al. "Zeroth-Order Stochastic Variance Reduction for
+        Nonconvex Optimization". <https://arxiv.org/pdf/1906.00117.pdf>`_
     """
 
     ### 1- Sample Directions in the uniform ball

aix360/algorithms/tssaliency/tssaliency.py

@@ -19,8 +19,8 @@ class TSSaliencyExplainer(TSLocalBBExplainer):
     temporal resolution.
 
     References:
-        .. [Section 3] Mukund Sundararajan et al. "Axiomatic Attribution for Deep Networks"
-            https://arxiv.org/pdf/1703.01365.pdf
+        .. [#0] `Mukund Sundararajan et al. "Axiomatic Attribution for Deep Networks"
+            <https://arxiv.org/pdf/1703.01365.pdf>`_
     """
 
     def __init__(

aix360/algorithms/tsutils/tsperturbers/block_bootstrap_perturber.py

@@ -17,9 +17,9 @@ class BlockBootstrapPerturber(TSPerturber):
     and added to the signal (mean) between randomly selected blocks.
 
     References:
-        .. [#BB1] `Bühlmann, Peter. "Bootstraps for time series."
+        .. [#0] `Bühlmann, Peter. "Bootstraps for time series."
             Statistical science (2002): 52-72.
-            https://projecteuclid.org/journals/statistical-science/volume-17/issue-1/Bootstraps-for-Time-Series/10.1214/ss/1023798998.full`_
+            <https://projecteuclid.org/journals/statistical-science/volume-17/issue-1/Bootstraps-for-Time-Series/10.1214/ss/1023798998.full>`_
     """
 
     def __init__(