Skip to content
This repository was archived by the owner on Nov 16, 2023. It is now read-only.

Change Linear SVM lambda_ parameter to regularization #255

Closed
gregorybchris wants to merge 3 commits into from
Closed

Change Linear SVM lambda_ parameter to regularization #255

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
691d22b
Change Linear SVM lambda_ parameter to regularization
Sep 4, 2019
ff120b3
Use manifest to update _lambda param
Sep 6, 2019
c9307e2
Merge branch 'master' into chgrego/svm-lambda
ganik Sep 6, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions src/python/nimbusml/internal/core/linear_model/linearsvmbinaryclassifier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,7 @@ class LinearSvmBinaryClassifier(

:param caching: Whether trainer should cache input training data.

:param lambda_: Regularizer constant.
:param regularization: Regularizer constant.

@ganik ganik Sep 6, 2019 •
edited
Loading

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

These 3 files are auto generated from manifest.json. You could use manifest_diff.json to specify renaming of the parameter then re-run entrypoint_compiler tools with generate options set to True. There are many examples in manifest_diff.json how to do renaming. #Resolved


:param perform_projection: Perform projection to unit-ball? Typically used
with batch size > 1.
Expand Down Expand Up @@ -105,7 +105,7 @@ def __init__(
self,
normalize='Auto',
caching='Auto',
lambda_=0.001,
regularization=0.001,
perform_projection=False,
number_of_iterations=1,
initial_weights_diameter=0.0,
Expand All @@ -119,7 +119,7 @@ def __init__(

self.normalize = normalize
self.caching = caching
self.lambda_ = lambda_
self.regularization = regularization
self.perform_projection = perform_projection
self.number_of_iterations = number_of_iterations
self.initial_weights_diameter = initial_weights_diameter
Expand All @@ -146,7 +146,7 @@ def _get_node(self, **all_args):
all_args),
normalize_features=self.normalize,
caching=self.caching,
lambda_=self.lambda_,
regularization=self.regularization,
perform_projection=self.perform_projection,
number_of_iterations=self.number_of_iterations,
initial_weights_diameter=self.initial_weights_diameter,
Expand Down
8 changes: 4 additions & 4 deletions src/python/nimbusml/internal/entrypoints/trainers_linearsvmbinaryclassifier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ def trainers_linearsvmbinaryclassifier(
example_weight_column_name=None,
normalize_features='Auto',
caching='Auto',
lambda_=0.001,
regularization=0.001,
perform_projection=False,
number_of_iterations=1,
initial_weights_diameter=0.0,
Expand All @@ -41,7 +41,7 @@ def trainers_linearsvmbinaryclassifier(
column (inputs).
:param caching: Whether trainer should cache input training data
(inputs).
:param lambda_: Regularizer constant (inputs).
:param regularization: Regularizer constant (inputs).
:param perform_projection: Perform projection to unit-ball?
Typically used with batch size > 1. (inputs).
:param number_of_iterations: Number of iterations (inputs).
Expand Down Expand Up @@ -105,9 +105,9 @@ def trainers_linearsvmbinaryclassifier(
'Auto',
'Memory',
'None'])
if lambda_ is not None:
if regularization is not None:
inputs['Lambda'] = try_set(
obj=lambda_,
obj=regularization,
none_acceptable=True,
is_of_type=numbers.Real)
if perform_projection is not None:
Expand Down
6 changes: 3 additions & 3 deletions src/python/nimbusml/linear_model/linearsvmbinaryclassifier.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ class LinearSvmBinaryClassifier(

:param caching: Whether trainer should cache input training data.

:param lambda_: Regularizer constant.
:param regularization: Regularizer constant.

:param perform_projection: Perform projection to unit-ball? Typically used
with batch size > 1.
Expand Down Expand Up @@ -114,7 +114,7 @@ def __init__(
self,
normalize='Auto',
caching='Auto',
lambda_=0.001,
regularization=0.001,
perform_projection=False,
number_of_iterations=1,
initial_weights_diameter=0.0,
Expand Down Expand Up @@ -147,7 +147,7 @@ def __init__(
self,
normalize=normalize,
caching=caching,
lambda_=lambda_,
regularization=regularization,
perform_projection=perform_projection,
number_of_iterations=number_of_iterations,
initial_weights_diameter=initial_weights_diameter,
Expand Down