Towards #3204 - documentation for FeatureContributionCalculatingEstimator #3384

yaeldekel · 2019-04-17T20:22:25Z

Adhering to the template in #3204 (comment) for the ColumnCopying estimator extensions, estimator, transformer.

artidoro · 2019-04-17T20:28:26Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    ///         StochasticGradientDescent (SGD), SymbolicStochasticGradientDescent, GeneralizedAdditiveModels (GAM),
+    ///         FastForest, FastTree, LightGbm
+    ///     Ranking:
+    ///         FastTree, LightGbm


Unfortunately this does not seem to look good in the xml doc:
https://docs.microsoft.com/en-us/dotnet/api/microsoft.ml.transforms.featurecontributioncalculatingtransformer?view=ml-dotnet

Could you find a way to itemize these points? Or another approach that will make it easier to read? #Resolved

natke · 2019-04-17T20:29:05Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    /// | Input column data type | Vector of floats |
+    /// | Output column data type | Vector of floats |
+    ///
+    /// <para>


This won't be processed or will cause an error, as you are inside a markdown block here. #Resolved

natke · 2019-04-17T20:29:36Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    /// it can be useful to inspect which features influenced them most significantly. This transformer computes a model-specific
+    /// list of per-feature contributions to the score for each example. These contributions can be positive (they make the score higher) or negative
+    /// (they make the score lower).
+    /// </para>


Remove #Resolved

natke · 2019-04-17T20:29:42Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    /// list of per-feature contributions to the score for each example. These contributions can be positive (they make the score higher) or negative
+    /// (they make the score lower).
+    /// </para>
+    /// <para>


Same #Resolved

natke · 2019-04-17T20:33:44Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    /// |  |  |
+    /// | -- | -- |
+    /// | Does this estimator need to look at the data to train its parameters? | No |
+    /// | Input column data type | Vector of floats |


@sfilipi @shmoradims were we going to use Single instead of float? #Resolved

yes

Use System.Single instead of 'float'. 'float' is a C# keywork, not a .NET type, and F# uses different terminology.

in xml
xref:System.Single in markdown

Same as above for 'double'

In reply to: 276422052 [](ancestors = 276422052)

yep, that's my recollection too.

In reply to: 276470283 [](ancestors = 276470283,276422052)

natke · 2019-04-17T20:35:30Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    /// (they make the score lower).
+    /// </para>
+    /// <para>
+    /// Feature Contribution Calculation is currently supported for the following models:


You could make this a bulleted list in markdown
Regression

OrdinaryLeastSquares

etc

Would also be good to get the algorithm names to be exactly the same as the name of the trainer classes #Resolved

natke · 2019-04-17T20:36:55Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    /// and the score obtained by taking the opposite decision at the node corresponding to feature F1. This algorithm extends naturally to models with
+    /// many decision trees.
+    /// </para>
+    /// See the See Also section for links to examples of the usage.


Not sure this line is necessary #Resolved

natke · 2019-04-17T20:37:43Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

+    /// the feature value.
+    /// </para>
+    /// <para>
+    /// For tree-based models, the calculation of feature contribution essentially consists in determining which splits in the tree have the most impact


This gives a good description of tree based models. Worth mentioning how it works for the other models?

The description for linear models and GAM is above. Do you think it should be more detailed?

In reply to: 276423670 [](ancestors = 276423670)

shmoradims

sfilipi · 2019-04-18T05:46:29Z

src/Microsoft.ML.Data/Transforms/FeatureContributionCalculationTransformer.cs

-    /// Estimator producing a FeatureContributionCalculatingTransformer which scores the model on an input dataset and
-    /// computes model-specific contribution scores for each feature.
+    /// Computes model-specific per-feature contributions to the score of each input vector.
+    /// See the list of currently supported models below.


See the list of currently supported models below. [](start = 8, length = 49)

I would remove this, because this line displays on the IntelliSense, and there won't be an option to see the remarks section there. #Resolved

sfilipi

codecov · 2019-04-18T17:41:02Z

Codecov Report

Merging #3384 into master will decrease coverage by 0.01%.
The diff coverage is n/a.

@@            Coverage Diff             @@
##           master    #3384      +/-   ##
==========================================
- Coverage   72.71%   72.69%   -0.02%     
==========================================
  Files         807      807              
  Lines      145172   145172              
  Branches    16225    16225              
==========================================
- Hits       105559   105538      -21     
- Misses      35195    35219      +24     
+ Partials     4418     4415       -3

Flag	Coverage Δ
#Debug	`72.69% <ø> (-0.02%)`	⬇️
#production	`68.23% <ø> (-0.02%)`	⬇️
#test	`88.97% <ø> (ø)`	⬆️

Impacted Files	Coverage Δ
...forms/FeatureContributionCalculationTransformer.cs	`73.55% <ø> (ø)`	⬆️
...rosoft.ML.Data/Transforms/ExplainabilityCatalog.cs	`100% <ø> (ø)`	⬆️
src/Microsoft.ML.Core/Data/ProgressReporter.cs	`70.95% <0%> (-6.99%)`	⬇️
src/Microsoft.ML.Maml/MAML.cs	`24.75% <0%> (-1.46%)`	⬇️
src/Microsoft.ML.FastTree/TreeTrainersCatalog.cs	`94.18% <0%> (ø)`	⬆️
...soft.ML.Data/DataLoadSave/Text/TextLoaderCursor.cs	`84.9% <0%> (+0.2%)`	⬆️

artidoro · 2019-04-20T00:07:02Z

@natke if this pr looks good to you could you unblock it?

Documentation for FeatureContributionEstimator

0b5d057

yaeldekel requested review from natke, artidoro and shmoradims April 17, 2019 20:22

artidoro reviewed Apr 17, 2019

View reviewed changes

natke suggested changes Apr 17, 2019

View reviewed changes

Address code review comments

33362a1

shmoradims approved these changes Apr 17, 2019

View reviewed changes

sfilipi reviewed Apr 18, 2019

View reviewed changes

Address code review comments

a231881

sfilipi approved these changes Apr 18, 2019

View reviewed changes

yaeldekel added the documentation Related to documentation of ML.NET label Apr 18, 2019

natke approved these changes Apr 20, 2019

View reviewed changes

yaeldekel merged commit b9a0b07 into dotnet:master Apr 20, 2019

yaeldekel deleted the featurecontribution branch April 20, 2019 00:20

sfilipi mentioned this pull request Apr 20, 2019

API reference - XML documentation template for transforms #3204

Closed

ghost locked as resolved and limited conversation to collaborators Mar 22, 2022

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Towards #3204 - documentation for FeatureContributionCalculatingEstimator #3384

Towards #3204 - documentation for FeatureContributionCalculatingEstimator #3384

yaeldekel commented Apr 17, 2019

artidoro Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

shmoradims Apr 17, 2019 •

edited

Loading

sfilipi Apr 18, 2019

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019

yaeldekel Apr 17, 2019

shmoradims left a comment

sfilipi Apr 18, 2019 •

edited by yaeldekel

Loading

sfilipi left a comment

codecov bot commented Apr 18, 2019 •

edited

Loading

artidoro commented Apr 20, 2019

Towards #3204 - documentation for FeatureContributionCalculatingEstimator #3384

Towards #3204 - documentation for FeatureContributionCalculatingEstimator #3384

Conversation

yaeldekel commented Apr 17, 2019

artidoro Apr 17, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

natke Apr 17, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

natke Apr 17, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

natke Apr 17, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

natke Apr 17, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

shmoradims Apr 17, 2019 • edited Loading

Choose a reason for hiding this comment

sfilipi Apr 18, 2019

Choose a reason for hiding this comment

natke Apr 17, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

natke Apr 17, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

natke Apr 17, 2019

Choose a reason for hiding this comment

yaeldekel Apr 17, 2019

Choose a reason for hiding this comment

shmoradims left a comment

Choose a reason for hiding this comment

sfilipi Apr 18, 2019 • edited by yaeldekel Loading

Choose a reason for hiding this comment

sfilipi left a comment

Choose a reason for hiding this comment

codecov bot commented Apr 18, 2019 • edited Loading

Codecov Report

artidoro commented Apr 20, 2019

artidoro Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

shmoradims Apr 17, 2019 •

edited

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

natke Apr 17, 2019 •

edited by yaeldekel

Loading

sfilipi Apr 18, 2019 •

edited by yaeldekel

Loading

codecov bot commented Apr 18, 2019 •

edited

Loading