Update the entrypoints and manifest.json

src/python/nimbusml/cluster/kmeansplusplus.py

@@ -75,8 +75,8 @@ class KMeansPlusPlus(core, BasePredictor, ClusterMixin):
 
     :param init_algorithm: Cluster initialization algorithm.
 
-    :param opt_tol: Tolerance parameter for trainer convergence. Lower =
-        slower, more accurate.
+    :param opt_tol: Tolerance parameter for trainer convergence. Low = slower,
+        more accurate.
 
     :param max_iterations: Maximum number of iterations.
 

src/python/nimbusml/feature_extraction/text/lightlda.py

@@ -45,13 +45,13 @@ class LightLda(core, BaseTransform, TransformerMixin):
 
     :param columns: see `Columns </nimbusml/concepts/columns>`_.
 
-    :param num_topic: The number of topics in the LDA.
-
-    :param num_max_doc_token: The threshold of maximum count of tokens per doc.
+    :param num_topic: The number of topics.
 
     :param train_threads: The number of training threads. Default value depends
         on number of logical processors.
 
+    :param num_max_doc_token: The threshold of maximum count of tokens per doc.
+
     :param alpha_sum: Dirichlet prior on document-topic vectors.
 
     :param beta: Dirichlet prior on vocab-topic vectors.
@@ -95,8 +95,8 @@ class LightLda(core, BaseTransform, TransformerMixin):
     def __init__(
             self,
             num_topic=100,
+            train_threads=0,
             num_max_doc_token=512,
-            train_threads=None,
             alpha_sum=100.0,
             beta=0.01,
             mhstep=4,
@@ -115,8 +115,8 @@ def __init__(
         core.__init__(
             self,
             num_topic=num_topic,
-            num_max_doc_token=num_max_doc_token,
             train_threads=train_threads,
+            num_max_doc_token=num_max_doc_token,
             alpha_sum=alpha_sum,
             beta=beta,
             mhstep=mhstep,

src/python/nimbusml/feature_extraction/text/ngramfeaturizer.py

@@ -100,22 +100,7 @@ class NGramFeaturizer(core, BaseTransform, TransformerMixin):
         * ``"Spanish"``
         * ``"Japanese"``.
 
-    :param stop_words_remover: Specifies the stopwords remover to use. There
-        are
-        three options supported:
-
-        * `None`: No stopwords remover is used.
-        * :py:class:`PredefinedStopWordsRemover
-          <nimbusml.feature_extraction.text.stopwords.PredefinedStopWordsRemover>` :
-          A precompiled language-specific lists
-          of stop words is used that includes the most common words from
-          Microsoft Office.
-        * :py:class:`CustomStopWordsRemover
-          <nimbusml.feature_extraction.text.stopwords.CustomStopWordsRemover>` : A
-          user-defined list of stopwords. It accepts
-          the following option: ``stopword``.
-
-        The default value is `None`.
+    :param use_predefined_stop_word_remover: Use stop remover or not.
 
     :param text_case: Text casing using the rules of the invariant culture.
         Takes the
@@ -218,7 +203,7 @@ class NGramFeaturizer(core, BaseTransform, TransformerMixin):
     def __init__(
             self,
             language='English',
-            stop_words_remover=None,
+            use_predefined_stop_word_remover=False,
             text_case='Lower',
             keep_diacritics=False,
             keep_punctuations=True,
@@ -241,7 +226,7 @@ def __init__(
         core.__init__(
             self,
             language=language,
-            stop_words_remover=stop_words_remover,
+            use_predefined_stop_word_remover=use_predefined_stop_word_remover,
             text_case=text_case,
             keep_diacritics=keep_diacritics,
             keep_punctuations=keep_punctuations,

src/python/nimbusml/internal/core/cluster/kmeansplusplus.py

@@ -70,8 +70,8 @@ class KMeansPlusPlus(BasePipelineItem, DefaultSignatureWithRoles):
 
     :param init_algorithm: Cluster initialization algorithm.
 
-    :param opt_tol: Tolerance parameter for trainer convergence. Lower =
-        slower, more accurate.
+    :param opt_tol: Tolerance parameter for trainer convergence. Low = slower,
+        more accurate.
 
     :param max_iterations: Maximum number of iterations.
 

src/python/nimbusml/internal/core/feature_extraction/text/lightlda.py

@@ -41,13 +41,13 @@ class LightLda(BasePipelineItem, DefaultSignature):
         Gibbs samplers.
 
 
-    :param num_topic: The number of topics in the LDA.
-
-    :param num_max_doc_token: The threshold of maximum count of tokens per doc.
+    :param num_topic: The number of topics.
 
     :param train_threads: The number of training threads. Default value depends
         on number of logical processors.
 
+    :param num_max_doc_token: The threshold of maximum count of tokens per doc.
+
     :param alpha_sum: Dirichlet prior on document-topic vectors.
 
     :param beta: Dirichlet prior on vocab-topic vectors.
@@ -91,8 +91,8 @@ class LightLda(BasePipelineItem, DefaultSignature):
     def __init__(
             self,
             num_topic=100,
+            train_threads=0,
             num_max_doc_token=512,
-            train_threads=None,
             alpha_sum=100.0,
             beta=0.01,
             mhstep=4,
@@ -107,8 +107,8 @@ def __init__(
             self, type='transform', **params)
 
         self.num_topic = num_topic
-        self.num_max_doc_token = num_max_doc_token
         self.train_threads = train_threads
+        self.num_max_doc_token = num_max_doc_token
         self.alpha_sum = alpha_sum
         self.beta = beta
         self.mhstep = mhstep
@@ -166,8 +166,8 @@ def _get_node(self, **all_args):
                     input_columns,
                     output_columns)] if input_columns else None,
             num_topic=self.num_topic,
-            num_max_doc_token=self.num_max_doc_token,
             num_threads=self.train_threads,
+            num_max_doc_token=self.num_max_doc_token,
             alpha_sum=self.alpha_sum,
             beta=self.beta,
             mhstep=self.mhstep,

src/python/nimbusml/internal/core/feature_extraction/text/ngramfeaturizer.py

@@ -79,22 +79,7 @@ class NGramFeaturizer(BasePipelineItem, SingleOutputSignature):
         * ``"Spanish"``
         * ``"Japanese"``.
 
-    :param stop_words_remover: Specifies the stopwords remover to use. There
-        are
-        three options supported:
-
-        * `None`: No stopwords remover is used.
-        * :py:class:`PredefinedStopWordsRemover
-          <nimbusml.feature_extraction.text.stopwords.PredefinedStopWordsRemover>` :
-          A precompiled language-specific lists
-          of stop words is used that includes the most common words from
-          Microsoft Office.
-        * :py:class:`CustomStopWordsRemover
-          <nimbusml.feature_extraction.text.stopwords.CustomStopWordsRemover>` : A
-          user-defined list of stopwords. It accepts
-          the following option: ``stopword``.
-
-        The default value is `None`.
+    :param use_predefined_stop_word_remover: Use stop remover or not.
 
     :param text_case: Text casing using the rules of the invariant culture.
         Takes the
@@ -197,7 +182,7 @@ class NGramFeaturizer(BasePipelineItem, SingleOutputSignature):
     def __init__(
             self,
             language='English',
-            stop_words_remover=None,
+            use_predefined_stop_word_remover=False,
             text_case='Lower',
             keep_diacritics=False,
             keep_punctuations=True,
@@ -216,7 +201,7 @@ def __init__(
             self, type='transform', **params)
 
         self.language = language
-        self.stop_words_remover = stop_words_remover
+        self.use_predefined_stop_word_remover = use_predefined_stop_word_remover
         self.text_case = text_case
         self.keep_diacritics = keep_diacritics
         self.keep_punctuations = keep_punctuations
@@ -278,7 +263,7 @@ def _get_node(self, **all_args):
         algo_args = dict(
             column=column,
             language=self.language,
-            stop_words_remover=self.stop_words_remover,
+            use_predefined_stop_word_remover=self.use_predefined_stop_word_remover,
             text_case=self.text_case,
             keep_diacritics=self.keep_diacritics,
             keep_punctuations=self.keep_punctuations,

src/python/nimbusml/internal/core/linear_model/logisticregressionbinaryclassifier.py

@@ -118,7 +118,7 @@ class LogisticRegressionBinaryClassifier(
 
     :param l1_weight: L1 regularization weight.
 
-    :param opt_tol: Tolerance parameter for optimization convergence. Lower =
+    :param opt_tol: Tolerance parameter for optimization convergence. Low =
         slower, more accurate.
 
     :param memory_size: Memory size for L-BFGS. Lower=faster, less accurate.

src/python/nimbusml/internal/core/linear_model/logisticregressionclassifier.py

@@ -119,7 +119,7 @@ class LogisticRegressionClassifier(
 
     :param l1_weight: L1 regularization weight.
 
-    :param opt_tol: Tolerance parameter for optimization convergence. Lower =
+    :param opt_tol: Tolerance parameter for optimization convergence. Low =
         slower, more accurate.
 
     :param memory_size: Memory size for L-BFGS. Lower=faster, less accurate.

src/python/nimbusml/internal/core/linear_model/poissonregressionregressor.py

@@ -68,7 +68,7 @@ class PoissonRegressionRegressor(
 
     :param l1_weight: L1 regularization weight.
 
-    :param opt_tol: Tolerance parameter for optimization convergence. Lower =
+    :param opt_tol: Tolerance parameter for optimization convergence. Low =
         slower, more accurate.
 
     :param memory_size: Memory size for L-BFGS. Lower=faster, less accurate.