Skip to content

Add release notes for ML.NET 0.1 #37

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 7, 2018
Merged

Add release notes for ML.NET 0.1 #37

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6c93efe
Add release notes for ML.NET 0.1
May 6, 2018
d4688ad
Merge remote-tracking branch 'upstream/master'
May 6, 2018
3530b52
Release note tweaks
danmoseley May 7, 2018
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
39 changes: 39 additions & 0 deletions Documentation/release-notes/0.1/release-0.1.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
# ML.NET 0.1 Release Notes

ML.NET 0.1 is the first preview release of ML.NET. Thank you for trying it out and we look forward to your feedback!
Copy link
Member

Choose a reason for hiding this comment

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

Maybe add statements about what we want people to try? E.g. try to use one of our samples to solve a problem you have, and then tell us how it went?


### Installation

You can install ML.NET NuGet from the CLI using:
```
dotnet add package Microsoft.ML
Copy link
Contributor

@glebuk glebuk May 7, 2018 •
edited
Loading

Choose a reason for hiding this comment

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

e Microsoft.ML [](start = 17, length = 14)

mention prerequisites and supported platforms #Resolved

```

From package manager:
```
Install-Package Microsoft.ML
```

### Release Notes
Copy link
Contributor

@glebuk glebuk May 7, 2018 •
edited
Loading

Choose a reason for hiding this comment

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

Release Notes [](start = 3, length = 14)

Please add pointers to samples, documentation and known issues. #Pending


This initial release contains core ML.NET components for enabling machine learning pipelines:

* ML Data Structures (e.g. `IDataView`, `LearningPipeline`)
* TextLoader (loading data from a text file into a `LearningPipeline`)
Copy link
Contributor

@glebuk glebuk May 7, 2018 •
edited
Loading

Choose a reason for hiding this comment

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

text [](start = 34, length = 4)

from a delimited text file #Resolved

Copy link
Member

Choose a reason for hiding this comment

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

TextLoader

* Transforms (to get data in the correct format for training):
* Processing/featurizing text: `TextFeaturizer`
* Schema modifcation: `ColumnConcatenator`, `ColumnSelector`, and `ColumnDropper`
* Working with categorical features: `CategoricalOneHotVectorizer` and `CategoricalHashOneHotVectorizer`
* Dealing with missing data: `MissingValueHandler`
* Filters: `RowTakeFilter`, `RowSkipFilter`, `RowRangeFilter`
* Feature selection: `FeatureSelectorByCount` and `FeatureSelectorByMutualInformation`
* Learners (to train machine learning models) for a variety of tasks:
* Binary classification: `FastTreeBinaryClassifier`, `StochasticDualCoordinateAscentBinaryClassifier`, `AveragedPerceptronBinaryClassifier`, `BinaryLogisticRegressor`, `FastForestBinaryClassifier`, `LinearSvmBinaryClassifier`, and `GeneralizedAdditiveModelBinaryClassifier`
* Multiclass classification: `StochasticDualCoordinateAscentClassifier`, `LogisticRegressor`, and`NaiveBayesClassifier`
* Regression: `FastTreeRegressor`, `FastTreeTweedieRegressor`, `StochasticDualCoordinateAscentRegressor`, `OrdinaryLeastSquaresRegressor`, `OnlineGradientDescentRegressor`, `PoissonRegressor`, and `GeneralizedAdditiveModelRegressor`
* Evaluators (to check the model works well):
Copy link
Contributor

@glebuk glebuk May 7, 2018 •
edited
Loading

Choose a reason for hiding this comment

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

to check the model works well [](start = 14, length = 29)

To check how well does the model perform #Resolved

* For Binary classification: `BinaryClassificationEvaluator`
* For Multiclass classification: `ClassificationEvaluator`
* For Regression: `RegressionEvaluator`

Additional components have been included in the repository but cannot be used in `LearningPipeline` yet (this will be updated in future releases).