From 59086acce8182a02785f00aad5f654649424a886 Mon Sep 17 00:00:00 2001 From: Najeeb Kazmi Date: Tue, 19 Nov 2019 18:10:49 -0800 Subject: [PATCH 1/2] Fix whitespaces and typos --- src/python/docs/docstrings/Dart.txt | 4 ++-- .../docstrings/FastLinearBinaryClassifier.txt | 2 +- .../docs/docstrings/FastLinearClassifier.txt | 3 ++- .../docs/docstrings/FastLinearRegressor.txt | 2 +- src/python/docs/docstrings/FromKey.txt | 3 +-- src/python/docs/docstrings/Goss.txt | 4 ++-- src/python/docs/docstrings/Handler.txt | 15 +++++++-------- src/python/docs/docstrings/Loader.txt | 2 +- src/python/docs/docstrings/NGram.txt | 2 +- src/python/docs/docstrings/NgramHash.txt | 2 +- src/python/docs/docstrings/Resizer.txt | 6 +++--- src/python/docs/docstrings/ToKey.txt | 3 +-- src/python/nimbusml/ensemble/booster/dart.py | 4 ++-- src/python/nimbusml/ensemble/booster/goss.py | 4 ++-- .../nimbusml/feature_extraction/image/loader.py | 2 +- .../nimbusml/feature_extraction/image/resizer.py | 6 +++--- .../feature_extraction/text/extractor/ngram.py | 2 +- .../text/extractor/ngramhash.py | 2 +- .../internal/core/ensemble/booster/dart.py | 4 ++-- .../internal/core/ensemble/booster/goss.py | 4 ++-- .../core/feature_extraction/image/loader.py | 2 +- .../core/feature_extraction/image/resizer.py | 4 ++-- .../feature_extraction/text/extractor/ngram.py | 2 +- .../text/extractor/ngramhash.py | 2 +- .../linear_model/fastlinearbinaryclassifier.py | 2 +- .../core/linear_model/fastlinearclassifier.py | 3 ++- .../core/linear_model/fastlinearregressor.py | 2 +- .../internal/core/preprocessing/fromkey.py | 3 +-- .../core/preprocessing/missing_values/handler.py | 15 +++++++-------- .../nimbusml/internal/core/preprocessing/tokey.py | 3 +-- .../linear_model/fastlinearbinaryclassifier.py | 2 +- .../nimbusml/linear_model/fastlinearclassifier.py | 3 ++- .../nimbusml/linear_model/fastlinearregressor.py | 2 +- src/python/nimbusml/model_selection/cv.py | 2 +- src/python/nimbusml/pipeline.py | 4 ++-- src/python/nimbusml/preprocessing/fromkey.py | 3 +-- .../preprocessing/missing_values/handler.py | 15 +++++++-------- src/python/nimbusml/preprocessing/tokey.py | 3 +-- 38 files changed, 71 insertions(+), 77 deletions(-) diff --git a/src/python/docs/docstrings/Dart.txt b/src/python/docs/docstrings/Dart.txt index faa504e0..5f83f192 100644 --- a/src/python/docs/docstrings/Dart.txt +++ b/src/python/docs/docstrings/Dart.txt @@ -7,9 +7,9 @@ `_ is an ensemble method of boosted regression trees. The Dropouts meet Multiple Additive Regression - Trees (DART) employs dropouts in MART and overcomes the issues of over- + Trees (DART) employs dropouts in MART and overcomes the issues of over- specialization of MART, - achiving better performance in many tasks. + achiving better performance in many tasks. **Reference** diff --git a/src/python/docs/docstrings/FastLinearBinaryClassifier.txt b/src/python/docs/docstrings/FastLinearBinaryClassifier.txt index c956db97..a16893e8 100644 --- a/src/python/docs/docstrings/FastLinearBinaryClassifier.txt +++ b/src/python/docs/docstrings/FastLinearBinaryClassifier.txt @@ -1,7 +1,7 @@ """ A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer - for linear binary classification and regression. + for linear binary classification. .. remarks:: ``FastLinearBinaryClassifier`` is a trainer based on the Stochastic diff --git a/src/python/docs/docstrings/FastLinearClassifier.txt b/src/python/docs/docstrings/FastLinearClassifier.txt index 32a3d35d..e7b839cf 100644 --- a/src/python/docs/docstrings/FastLinearClassifier.txt +++ b/src/python/docs/docstrings/FastLinearClassifier.txt @@ -1,6 +1,7 @@ """ - Train an SDCA multi class model + A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer for + multi class classification. .. remarks:: ``FastLinearClassifier`` is a trainer based on the Stochastic Dual diff --git a/src/python/docs/docstrings/FastLinearRegressor.txt b/src/python/docs/docstrings/FastLinearRegressor.txt index 080008fa..9e7c5d88 100644 --- a/src/python/docs/docstrings/FastLinearRegressor.txt +++ b/src/python/docs/docstrings/FastLinearRegressor.txt @@ -1,7 +1,7 @@ """ A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer - for linear binary classification and regression. + for linear regression. .. remarks:: ``FastLinearRegressor`` is a trainer based on the Stochastic Dual diff --git a/src/python/docs/docstrings/FromKey.txt b/src/python/docs/docstrings/FromKey.txt index a61b7064..fd162550 100644 --- a/src/python/docs/docstrings/FromKey.txt +++ b/src/python/docs/docstrings/FromKey.txt @@ -1,7 +1,6 @@ """ - Text transforms that can be performed on data before training - a model. + Converts the key types back to their original values. .. remarks:: The ``FromKey`` transform converts a column of keys, generated using diff --git a/src/python/docs/docstrings/Goss.txt b/src/python/docs/docstrings/Goss.txt index 7ae86ec2..29694860 100644 --- a/src/python/docs/docstrings/Goss.txt +++ b/src/python/docs/docstrings/Goss.txt @@ -5,9 +5,9 @@ .. remarks:: Gradient-based One-Side Sampling (GOSS) employs an adaptive sampling named gradient-based - sampling. For datasets with large sample size, GOSS has considerable + sampling. For datasets with large sample size, GOSS has considerable advantage in terms of - statistical and computational efficiency. + statistical and computational efficiency. diff --git a/src/python/docs/docstrings/Handler.txt b/src/python/docs/docstrings/Handler.txt index 01d767e8..4a639e1e 100644 --- a/src/python/docs/docstrings/Handler.txt +++ b/src/python/docs/docstrings/Handler.txt @@ -33,14 +33,13 @@ For more details see `Columns `_. :param replace_with: The method to use to replace NaN values. The - following choices are available. - - * Def: Replace with default value of that type, usually ``0``. If no - replace - method is specified, this is the default strategy. - * Mean: Replace NaN values with the mean of the values in that column. - * Min: Replace with minimum value in the column. - * Max: Replace with maximum value in the column. + following choices are available. + + * Def: Replace with default value of that type, usually ``0``. If no + replace method is specified, this is the default strategy. + * Mean: Replace NaN values with the mean of the values in that column. + * Min: Replace with minimum value in the column. + * Max: Replace with maximum value in the column. .. seealso:: :py:class:`Filter `, diff --git a/src/python/docs/docstrings/Loader.txt b/src/python/docs/docstrings/Loader.txt index ca290c1e..e94fb9e1 100644 --- a/src/python/docs/docstrings/Loader.txt +++ b/src/python/docs/docstrings/Loader.txt @@ -1,6 +1,6 @@ """ - Loaders image data. + Loads image data. .. remarks:: ``Loader`` loads images from paths. diff --git a/src/python/docs/docstrings/NGram.txt b/src/python/docs/docstrings/NGram.txt index e05c292a..e4d681db 100644 --- a/src/python/docs/docstrings/NGram.txt +++ b/src/python/docs/docstrings/NGram.txt @@ -1,6 +1,6 @@ """ - Extracts NGrams from text and convert them to vector using + Extracts NGrams from text and converts them to vector using dictionary. .. remarks:: diff --git a/src/python/docs/docstrings/NgramHash.txt b/src/python/docs/docstrings/NgramHash.txt index b7e34e8a..a1969901 100644 --- a/src/python/docs/docstrings/NgramHash.txt +++ b/src/python/docs/docstrings/NgramHash.txt @@ -1,6 +1,6 @@ """ - Extracts NGrams from text and convert them to vector using hashing + Extracts NGrams from text and converts them to vector using hashing trick. .. remarks:: diff --git a/src/python/docs/docstrings/Resizer.txt b/src/python/docs/docstrings/Resizer.txt index eb45128e..2bf9857f 100644 --- a/src/python/docs/docstrings/Resizer.txt +++ b/src/python/docs/docstrings/Resizer.txt @@ -1,15 +1,15 @@ """ - Resizers an image to a specified dimension using a specified + Resizes an image to a specified dimension using a specified resizing method. .. remarks:: - ``Resizer`` resizers an image to the specified height and width + ``Resizer`` resizes an image to the specified height and width using a specified resizing method. The input variables to this transforms must be images, typically the result of the ``Loader`` transform. - :param columns: a dictionary of key-value pairs, where key is the output + :param columns: A dictionary of key-value pairs, where key is the output column name and value is the input column name. * Multiple key-value pairs are allowed. diff --git a/src/python/docs/docstrings/ToKey.txt b/src/python/docs/docstrings/ToKey.txt index 2740561b..89a32047 100644 --- a/src/python/docs/docstrings/ToKey.txt +++ b/src/python/docs/docstrings/ToKey.txt @@ -1,7 +1,6 @@ """ - Text transforms that can be performed on data before training - a model. + Converts input values (words, numbers, etc.) to index in a dictionary. .. remarks:: The ``ToKey`` transform converts a column of text to key values diff --git a/src/python/nimbusml/ensemble/booster/dart.py b/src/python/nimbusml/ensemble/booster/dart.py index 33dc8295..ed6a5509 100644 --- a/src/python/nimbusml/ensemble/booster/dart.py +++ b/src/python/nimbusml/ensemble/booster/dart.py @@ -24,9 +24,9 @@ class Dart(core): `_ is an ensemble method of boosted regression trees. The Dropouts meet Multiple Additive Regression - Trees (DART) employs dropouts in MART and overcomes the issues of over- + Trees (DART) employs dropouts in MART and overcomes the issues of over- specialization of MART, - achiving better performance in many tasks. + achiving better performance in many tasks. **Reference** diff --git a/src/python/nimbusml/ensemble/booster/goss.py b/src/python/nimbusml/ensemble/booster/goss.py index 8e57181b..9b17e4ad 100644 --- a/src/python/nimbusml/ensemble/booster/goss.py +++ b/src/python/nimbusml/ensemble/booster/goss.py @@ -22,9 +22,9 @@ class Goss(core): .. remarks:: Gradient-based One-Side Sampling (GOSS) employs an adaptive sampling named gradient-based - sampling. For datasets with large sample size, GOSS has considerable + sampling. For datasets with large sample size, GOSS has considerable advantage in terms of - statistical and computational efficiency. + statistical and computational efficiency. diff --git a/src/python/nimbusml/feature_extraction/image/loader.py b/src/python/nimbusml/feature_extraction/image/loader.py index bd93a080..0ee0e305 100644 --- a/src/python/nimbusml/feature_extraction/image/loader.py +++ b/src/python/nimbusml/feature_extraction/image/loader.py @@ -20,7 +20,7 @@ class Loader(core, BaseTransform, TransformerMixin): """ - Loaders image data. + Loads image data. .. remarks:: ``Loader`` loads images from paths. diff --git a/src/python/nimbusml/feature_extraction/image/resizer.py b/src/python/nimbusml/feature_extraction/image/resizer.py index 77d9434f..2a8baf4a 100644 --- a/src/python/nimbusml/feature_extraction/image/resizer.py +++ b/src/python/nimbusml/feature_extraction/image/resizer.py @@ -20,16 +20,16 @@ class Resizer(core, BaseTransform, TransformerMixin): """ - Resizers an image to a specified dimension using a specified + Resizes an image to a specified dimension using a specified resizing method. .. remarks:: - ``Resizer`` resizers an image to the specified height and width + ``Resizer`` resizes an image to the specified height and width using a specified resizing method. The input variables to this transforms must be images, typically the result of the ``Loader`` transform. - :param columns: a dictionary of key-value pairs, where key is the output + :param columns: A dictionary of key-value pairs, where key is the output column name and value is the input column name. * Multiple key-value pairs are allowed. diff --git a/src/python/nimbusml/feature_extraction/text/extractor/ngram.py b/src/python/nimbusml/feature_extraction/text/extractor/ngram.py index 9ec1858f..6da8cfd2 100644 --- a/src/python/nimbusml/feature_extraction/text/extractor/ngram.py +++ b/src/python/nimbusml/feature_extraction/text/extractor/ngram.py @@ -18,7 +18,7 @@ class Ngram(core): """ - Extracts NGrams from text and convert them to vector using + Extracts NGrams from text and converts them to vector using dictionary. .. remarks:: diff --git a/src/python/nimbusml/feature_extraction/text/extractor/ngramhash.py b/src/python/nimbusml/feature_extraction/text/extractor/ngramhash.py index 2f373a31..fca66615 100644 --- a/src/python/nimbusml/feature_extraction/text/extractor/ngramhash.py +++ b/src/python/nimbusml/feature_extraction/text/extractor/ngramhash.py @@ -18,7 +18,7 @@ class NgramHash(core): """ - Extracts NGrams from text and convert them to vector using hashing + Extracts NGrams from text and converts them to vector using hashing trick. .. remarks:: diff --git a/src/python/nimbusml/internal/core/ensemble/booster/dart.py b/src/python/nimbusml/internal/core/ensemble/booster/dart.py index dd4418d3..a2aa0394 100644 --- a/src/python/nimbusml/internal/core/ensemble/booster/dart.py +++ b/src/python/nimbusml/internal/core/ensemble/booster/dart.py @@ -25,9 +25,9 @@ class Dart(Component): `_ is an ensemble method of boosted regression trees. The Dropouts meet Multiple Additive Regression - Trees (DART) employs dropouts in MART and overcomes the issues of over- + Trees (DART) employs dropouts in MART and overcomes the issues of over- specialization of MART, - achiving better performance in many tasks. + achiving better performance in many tasks. **Reference** diff --git a/src/python/nimbusml/internal/core/ensemble/booster/goss.py b/src/python/nimbusml/internal/core/ensemble/booster/goss.py index 694cb8bf..aa552afc 100644 --- a/src/python/nimbusml/internal/core/ensemble/booster/goss.py +++ b/src/python/nimbusml/internal/core/ensemble/booster/goss.py @@ -23,9 +23,9 @@ class Goss(Component): .. remarks:: Gradient-based One-Side Sampling (GOSS) employs an adaptive sampling named gradient-based - sampling. For datasets with large sample size, GOSS has considerable + sampling. For datasets with large sample size, GOSS has considerable advantage in terms of - statistical and computational efficiency. + statistical and computational efficiency. diff --git a/src/python/nimbusml/internal/core/feature_extraction/image/loader.py b/src/python/nimbusml/internal/core/feature_extraction/image/loader.py index ad8c70c1..888afab4 100644 --- a/src/python/nimbusml/internal/core/feature_extraction/image/loader.py +++ b/src/python/nimbusml/internal/core/feature_extraction/image/loader.py @@ -18,7 +18,7 @@ class Loader(BasePipelineItem, DefaultSignature): """ - Loaders image data. + Loads image data. .. remarks:: ``Loader`` loads images from paths. diff --git a/src/python/nimbusml/internal/core/feature_extraction/image/resizer.py b/src/python/nimbusml/internal/core/feature_extraction/image/resizer.py index 34ba1f39..819fb51c 100644 --- a/src/python/nimbusml/internal/core/feature_extraction/image/resizer.py +++ b/src/python/nimbusml/internal/core/feature_extraction/image/resizer.py @@ -18,11 +18,11 @@ class Resizer(BasePipelineItem, DefaultSignature): """ - Resizers an image to a specified dimension using a specified + Resizes an image to a specified dimension using a specified resizing method. .. remarks:: - ``Resizer`` resizers an image to the specified height and width + ``Resizer`` resizes an image to the specified height and width using a specified resizing method. The input variables to this transforms must be images, typically the result of the ``Loader`` transform. diff --git a/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngram.py b/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngram.py index 07fde941..a7292f9c 100644 --- a/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngram.py +++ b/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngram.py @@ -18,7 +18,7 @@ class Ngram(Component): """ - Extracts NGrams from text and convert them to vector using + Extracts NGrams from text and converts them to vector using dictionary. .. remarks:: diff --git a/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngramhash.py b/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngramhash.py index cd08b4be..04cb7713 100644 --- a/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngramhash.py +++ b/src/python/nimbusml/internal/core/feature_extraction/text/extractor/ngramhash.py @@ -18,7 +18,7 @@ class NgramHash(Component): """ - Extracts NGrams from text and convert them to vector using hashing + Extracts NGrams from text and converts them to vector using hashing trick. .. remarks:: diff --git a/src/python/nimbusml/internal/core/linear_model/fastlinearbinaryclassifier.py b/src/python/nimbusml/internal/core/linear_model/fastlinearbinaryclassifier.py index 3d43894a..f8346814 100644 --- a/src/python/nimbusml/internal/core/linear_model/fastlinearbinaryclassifier.py +++ b/src/python/nimbusml/internal/core/linear_model/fastlinearbinaryclassifier.py @@ -23,7 +23,7 @@ class FastLinearBinaryClassifier( """ A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer - for linear binary classification and regression. + for linear binary classification. .. remarks:: ``FastLinearBinaryClassifier`` is a trainer based on the Stochastic diff --git a/src/python/nimbusml/internal/core/linear_model/fastlinearclassifier.py b/src/python/nimbusml/internal/core/linear_model/fastlinearclassifier.py index b377eb11..4afcba87 100644 --- a/src/python/nimbusml/internal/core/linear_model/fastlinearclassifier.py +++ b/src/python/nimbusml/internal/core/linear_model/fastlinearclassifier.py @@ -22,7 +22,8 @@ class FastLinearClassifier( DefaultSignatureWithRoles): """ - Train an SDCA multi class model + A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer for + multi class classification. .. remarks:: ``FastLinearClassifier`` is a trainer based on the Stochastic Dual diff --git a/src/python/nimbusml/internal/core/linear_model/fastlinearregressor.py b/src/python/nimbusml/internal/core/linear_model/fastlinearregressor.py index f8a4b5ac..597e3dfb 100644 --- a/src/python/nimbusml/internal/core/linear_model/fastlinearregressor.py +++ b/src/python/nimbusml/internal/core/linear_model/fastlinearregressor.py @@ -23,7 +23,7 @@ class FastLinearRegressor( """ A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer - for linear binary classification and regression. + for linear regression. .. remarks:: ``FastLinearRegressor`` is a trainer based on the Stochastic Dual diff --git a/src/python/nimbusml/internal/core/preprocessing/fromkey.py b/src/python/nimbusml/internal/core/preprocessing/fromkey.py index bd5cfe10..ef7f8efb 100644 --- a/src/python/nimbusml/internal/core/preprocessing/fromkey.py +++ b/src/python/nimbusml/internal/core/preprocessing/fromkey.py @@ -19,8 +19,7 @@ class FromKey(BasePipelineItem, DefaultSignature): """ - Text transforms that can be performed on data before training - a model. + Converts the key types back to their original values. .. remarks:: The ``FromKey`` transform converts a column of keys, generated using diff --git a/src/python/nimbusml/internal/core/preprocessing/missing_values/handler.py b/src/python/nimbusml/internal/core/preprocessing/missing_values/handler.py index 55f0ed01..3fd199aa 100644 --- a/src/python/nimbusml/internal/core/preprocessing/missing_values/handler.py +++ b/src/python/nimbusml/internal/core/preprocessing/missing_values/handler.py @@ -33,14 +33,13 @@ class Handler(BasePipelineItem, DefaultSignature): were imputed. This works for columns that have numeric type. :param replace_with: The method to use to replace NaN values. The - following choices are available. - - * Def: Replace with default value of that type, usually ``0``. If no - replace - method is specified, this is the default strategy. - * Mean: Replace NaN values with the mean of the values in that column. - * Min: Replace with minimum value in the column. - * Max: Replace with maximum value in the column. + following choices are available. + + * Def: Replace with default value of that type, usually ``0``. If no + replace method is specified, this is the default strategy. + * Mean: Replace NaN values with the mean of the values in that column. + * Min: Replace with minimum value in the column. + * Max: Replace with maximum value in the column. :param impute_by_slot: Whether to impute values by slot. diff --git a/src/python/nimbusml/internal/core/preprocessing/tokey.py b/src/python/nimbusml/internal/core/preprocessing/tokey.py index 55cd7200..b1295adf 100644 --- a/src/python/nimbusml/internal/core/preprocessing/tokey.py +++ b/src/python/nimbusml/internal/core/preprocessing/tokey.py @@ -19,8 +19,7 @@ class ToKey(BasePipelineItem, DefaultSignature): """ - Text transforms that can be performed on data before training - a model. + Converts input values (words, numbers, etc.) to index in a dictionary. .. remarks:: The ``ToKey`` transform converts a column of text to key values diff --git a/src/python/nimbusml/linear_model/fastlinearbinaryclassifier.py b/src/python/nimbusml/linear_model/fastlinearbinaryclassifier.py index 6b99d165..3f0fd7c7 100644 --- a/src/python/nimbusml/linear_model/fastlinearbinaryclassifier.py +++ b/src/python/nimbusml/linear_model/fastlinearbinaryclassifier.py @@ -23,7 +23,7 @@ class FastLinearBinaryClassifier( """ A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer - for linear binary classification and regression. + for linear binary classification. .. remarks:: ``FastLinearBinaryClassifier`` is a trainer based on the Stochastic diff --git a/src/python/nimbusml/linear_model/fastlinearclassifier.py b/src/python/nimbusml/linear_model/fastlinearclassifier.py index 58e26ed3..50162961 100644 --- a/src/python/nimbusml/linear_model/fastlinearclassifier.py +++ b/src/python/nimbusml/linear_model/fastlinearclassifier.py @@ -21,7 +21,8 @@ class FastLinearClassifier(core, BasePredictor, ClassifierMixin): """ - Train an SDCA multi class model + A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer for + multi class classification. .. remarks:: ``FastLinearClassifier`` is a trainer based on the Stochastic Dual diff --git a/src/python/nimbusml/linear_model/fastlinearregressor.py b/src/python/nimbusml/linear_model/fastlinearregressor.py index 7baba2f6..73745f22 100644 --- a/src/python/nimbusml/linear_model/fastlinearregressor.py +++ b/src/python/nimbusml/linear_model/fastlinearregressor.py @@ -22,7 +22,7 @@ class FastLinearRegressor(core, BasePredictor, RegressorMixin): """ A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer - for linear binary classification and regression. + for linear regression. .. remarks:: ``FastLinearRegressor`` is a trainer based on the Stochastic Dual diff --git a/src/python/nimbusml/model_selection/cv.py b/src/python/nimbusml/model_selection/cv.py index 79a5def4..44c4275a 100644 --- a/src/python/nimbusml/model_selection/cv.py +++ b/src/python/nimbusml/model_selection/cv.py @@ -96,7 +96,7 @@ class CV: the average of each metric on all models. :param pipeline: Pipeline object or a list of pipeline steps that's - used for cross validation + used for cross validation ''' fold_column_name = 'Fold' diff --git a/src/python/nimbusml/pipeline.py b/src/python/nimbusml/pipeline.py index 71ee437d..8a2d88af 100644 --- a/src/python/nimbusml/pipeline.py +++ b/src/python/nimbusml/pipeline.py @@ -119,10 +119,10 @@ class Pipeline: for more details on how to select these. :param steps: the list of operator or (name, operator) tuples that - are chained in the appropriate order. + are chained in the appropriate order. :param model: the path to the model file (".zip") if want to load a - model directly from file (such as a trained model from ML.NET). + model directly from file (such as a trained model from ML.NET). :param random_state: the integer used as the random seed. diff --git a/src/python/nimbusml/preprocessing/fromkey.py b/src/python/nimbusml/preprocessing/fromkey.py index f83d90a7..126d6b5f 100644 --- a/src/python/nimbusml/preprocessing/fromkey.py +++ b/src/python/nimbusml/preprocessing/fromkey.py @@ -20,8 +20,7 @@ class FromKey(core, BaseTransform, TransformerMixin): """ - Text transforms that can be performed on data before training - a model. + Converts the key types back to their original values. .. remarks:: The ``FromKey`` transform converts a column of keys, generated using diff --git a/src/python/nimbusml/preprocessing/missing_values/handler.py b/src/python/nimbusml/preprocessing/missing_values/handler.py index 1a1fac0a..01da758b 100644 --- a/src/python/nimbusml/preprocessing/missing_values/handler.py +++ b/src/python/nimbusml/preprocessing/missing_values/handler.py @@ -54,14 +54,13 @@ class Handler(core, BaseTransform, TransformerMixin): For more details see `Columns `_. :param replace_with: The method to use to replace NaN values. The - following choices are available. - - * Def: Replace with default value of that type, usually ``0``. If no - replace - method is specified, this is the default strategy. - * Mean: Replace NaN values with the mean of the values in that column. - * Min: Replace with minimum value in the column. - * Max: Replace with maximum value in the column. + following choices are available. + + * Def: Replace with default value of that type, usually ``0``. If no + replace method is specified, this is the default strategy. + * Mean: Replace NaN values with the mean of the values in that column. + * Min: Replace with minimum value in the column. + * Max: Replace with maximum value in the column. :param impute_by_slot: Whether to impute values by slot. diff --git a/src/python/nimbusml/preprocessing/tokey.py b/src/python/nimbusml/preprocessing/tokey.py index 97c00ad3..c94c2eac 100644 --- a/src/python/nimbusml/preprocessing/tokey.py +++ b/src/python/nimbusml/preprocessing/tokey.py @@ -20,8 +20,7 @@ class ToKey(core, BaseTransform, TransformerMixin): """ - Text transforms that can be performed on data before training - a model. + Converts input values (words, numbers, etc.) to index in a dictionary. .. remarks:: The ``ToKey`` transform converts a column of text to key values From 1963a2ba9eb24c7c47f0113dfd9c58274f70190c Mon Sep 17 00:00:00 2001 From: Najeeb Kazmi Date: Tue, 19 Nov 2019 18:25:59 -0800 Subject: [PATCH 2/2] tabs and whitespaces --- src/python/docs/docstrings/Dart.txt | 4 ++-- src/python/docs/docstrings/FastLinearClassifier.txt | 2 +- src/python/docs/docstrings/Goss.txt | 4 ++-- src/python/nimbusml/ensemble/booster/dart.py | 2 +- src/python/nimbusml/internal/core/ensemble/booster/dart.py | 2 +- 5 files changed, 7 insertions(+), 7 deletions(-) diff --git a/src/python/docs/docstrings/Dart.txt b/src/python/docs/docstrings/Dart.txt index 5f83f192..d037b6f7 100644 --- a/src/python/docs/docstrings/Dart.txt +++ b/src/python/docs/docstrings/Dart.txt @@ -7,9 +7,9 @@ `_ is an ensemble method of boosted regression trees. The Dropouts meet Multiple Additive Regression - Trees (DART) employs dropouts in MART and overcomes the issues of over- + Trees (DART) employs dropouts in MART and overcomes the issues of over- specialization of MART, - achiving better performance in many tasks. + achieving better performance in many tasks. **Reference** diff --git a/src/python/docs/docstrings/FastLinearClassifier.txt b/src/python/docs/docstrings/FastLinearClassifier.txt index e7b839cf..d9984dd5 100644 --- a/src/python/docs/docstrings/FastLinearClassifier.txt +++ b/src/python/docs/docstrings/FastLinearClassifier.txt @@ -1,7 +1,7 @@ """ A Stochastic Dual Coordinate Ascent (SDCA) optimization trainer for - multi class classification. + multi class classification. .. remarks:: ``FastLinearClassifier`` is a trainer based on the Stochastic Dual diff --git a/src/python/docs/docstrings/Goss.txt b/src/python/docs/docstrings/Goss.txt index 29694860..97265859 100644 --- a/src/python/docs/docstrings/Goss.txt +++ b/src/python/docs/docstrings/Goss.txt @@ -5,9 +5,9 @@ .. remarks:: Gradient-based One-Side Sampling (GOSS) employs an adaptive sampling named gradient-based - sampling. For datasets with large sample size, GOSS has considerable + sampling. For datasets with large sample size, GOSS has considerable advantage in terms of - statistical and computational efficiency. + statistical and computational efficiency. diff --git a/src/python/nimbusml/ensemble/booster/dart.py b/src/python/nimbusml/ensemble/booster/dart.py index ed6a5509..ab6857e2 100644 --- a/src/python/nimbusml/ensemble/booster/dart.py +++ b/src/python/nimbusml/ensemble/booster/dart.py @@ -26,7 +26,7 @@ class Dart(core): Multiple Additive Regression Trees (DART) employs dropouts in MART and overcomes the issues of over- specialization of MART, - achiving better performance in many tasks. + achieving better performance in many tasks. **Reference** diff --git a/src/python/nimbusml/internal/core/ensemble/booster/dart.py b/src/python/nimbusml/internal/core/ensemble/booster/dart.py index a2aa0394..49297929 100644 --- a/src/python/nimbusml/internal/core/ensemble/booster/dart.py +++ b/src/python/nimbusml/internal/core/ensemble/booster/dart.py @@ -27,7 +27,7 @@ class Dart(Component): Multiple Additive Regression Trees (DART) employs dropouts in MART and overcomes the issues of over- specialization of MART, - achiving better performance in many tasks. + achieving better performance in many tasks. **Reference**