diff options
| author | Niranjan Padmanabhan <niranjan.padmanabhan@gmail.com> | 2017-01-04 15:07:29 +0000 |
|---|---|---|
| committer | Sean Owen <sowen@cloudera.com> | 2017-01-04 15:07:29 +0000 |
| commit | a1e40b1f5d651305bbd0ba05779263a44f607498 (patch) | |
| tree | f70fcf889a0c6f366bc44f5d012ec7f3e91ffbcc /mllib/src | |
| parent | 7a82505817d479007adff6424473063d2003fcc1 (diff) | |
| download | spark-a1e40b1f5d651305bbd0ba05779263a44f607498.tar.gz spark-a1e40b1f5d651305bbd0ba05779263a44f607498.tar.bz2 spark-a1e40b1f5d651305bbd0ba05779263a44f607498.zip | |
[MINOR][DOCS] Remove consecutive duplicated words/typo in Spark Repo
## What changes were proposed in this pull request?
There are many locations in the Spark repo where the same word occurs consecutively. Sometimes they are appropriately placed, but many times they are not. This PR removes the inappropriately duplicated words.
## How was this patch tested?
N/A since only docs or comments were updated.
Author: Niranjan Padmanabhan <niranjan.padmanabhan@gmail.com>
Closes #16455 from neurons/np.structure_streaming_doc.
Diffstat (limited to 'mllib/src')
4 files changed, 4 insertions, 4 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala b/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala index 583e5e0928..728a883b1a 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/clustering/LDA.scala @@ -512,7 +512,7 @@ abstract class LDAModel private[ml] ( } /** - * Calculate an upper bound bound on perplexity. (Lower is better.) + * Calculate an upper bound on perplexity. (Lower is better.) * See Equation (16) in the Online LDA paper (Hoffman et al., 2010). * * WARNING: If this model is an instance of [[DistributedLDAModel]] (produced when [[optimizer]] diff --git a/mllib/src/main/scala/org/apache/spark/mllib/api/python/Word2VecModelWrapper.scala b/mllib/src/main/scala/org/apache/spark/mllib/api/python/Word2VecModelWrapper.scala index 5cbfbff3e4..4d6520d0b2 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/api/python/Word2VecModelWrapper.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/api/python/Word2VecModelWrapper.scala @@ -54,7 +54,7 @@ private[python] class Word2VecModelWrapper(model: Word2VecModel) { } /** - * Finds words similar to the the vector representation of a word without + * Finds words similar to the vector representation of a word without * filtering results. * @param vector a vector * @param num number of synonyms to find diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala index 25ffd8561f..933a5f1d52 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDAModel.scala @@ -245,7 +245,7 @@ class LocalLDAModel private[spark] ( } /** - * Calculate an upper bound bound on perplexity. (Lower is better.) + * Calculate an upper bound on perplexity. (Lower is better.) * See Equation (16) in original Online LDA paper. * * @param documents test corpus to use for calculating perplexity diff --git a/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala b/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala index 46deb545af..f44c8fe351 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/regression/StreamingLinearAlgorithm.scala @@ -29,7 +29,7 @@ import org.apache.spark.streaming.dstream.DStream /** * :: DeveloperApi :: * StreamingLinearAlgorithm implements methods for continuously - * training a generalized linear model model on streaming data, + * training a generalized linear model on streaming data, * and using it for prediction on (possibly different) streaming data. * * This class takes as type parameters a GeneralizedLinearModel, |