From 2194d5c721fba8aafc71a15548b78836d631a2eb Mon Sep 17 00:00:00 2001 From: Rogan Carr Date: Wed, 13 Mar 2019 15:00:43 -0700 Subject: [PATCH 1/2] Adding a note on how to turn off char-grams and word-grams in FeaturizeText. --- src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs | 2 ++ 1 file changed, 2 insertions(+) diff --git a/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs b/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs index c8d87fa3a0..158cfb6ed1 100644 --- a/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs +++ b/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs @@ -128,6 +128,7 @@ public sealed class Options : TransformInputBase /// /// Ngram feature extractor to use for words (WordBag/WordHashBag). + /// Set to null to turn off n-gram generation for words. /// public WordBagEstimator.Options WordFeatureExtractor { @@ -160,6 +161,7 @@ public WordBagEstimator.Options WordFeatureExtractor /// /// Ngram feature extractor to use for characters (WordBag/WordHashBag). + /// Set to null to turn off n-gram generation for characters. /// public WordBagEstimator.Options CharFeatureExtractor { From 0a3f0b74214dc5ebd28b0ffdb56ffae16447914e Mon Sep 17 00:00:00 2001 From: Rogan Carr Date: Wed, 13 Mar 2019 15:35:45 -0700 Subject: [PATCH 2/2] added langword identifiers --- src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs b/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs index 158cfb6ed1..2a801a7344 100644 --- a/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs +++ b/src/Microsoft.ML.Transforms/Text/TextFeaturizingEstimator.cs @@ -128,7 +128,7 @@ public sealed class Options : TransformInputBase /// /// Ngram feature extractor to use for words (WordBag/WordHashBag). - /// Set to null to turn off n-gram generation for words. + /// Set to to turn off n-gram generation for words. /// public WordBagEstimator.Options WordFeatureExtractor { @@ -161,7 +161,7 @@ public WordBagEstimator.Options WordFeatureExtractor /// /// Ngram feature extractor to use for characters (WordBag/WordHashBag). - /// Set to null to turn off n-gram generation for characters. + /// Set to to turn off n-gram generation for characters. /// public WordBagEstimator.Options CharFeatureExtractor {