Repository: mahout Updated Branches: refs/heads/master 383493d6c -> d7a87936e
Revert "reorder javadoc paramter comments" This reverts commit 383493d6c2d4f7b011030c3f00324f11042f381f. Project: http://git-wip-us.apache.org/repos/asf/mahout/repo Commit: http://git-wip-us.apache.org/repos/asf/mahout/commit/d7a87936 Tree: http://git-wip-us.apache.org/repos/asf/mahout/tree/d7a87936 Diff: http://git-wip-us.apache.org/repos/asf/mahout/diff/d7a87936 Branch: refs/heads/master Commit: d7a87936ef386476db88db323d19345b1064eae2 Parents: 383493d Author: Andrew Palumbo <[email protected]> Authored: Wed Apr 27 18:54:28 2016 -0400 Committer: Andrew Palumbo <[email protected]> Committed: Wed Apr 27 18:54:28 2016 -0400 ---------------------------------------------------------------------- .../mahout/vectorizer/DictionaryVectorizer.java | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/mahout/blob/d7a87936/mr/src/main/java/org/apache/mahout/vectorizer/DictionaryVectorizer.java ---------------------------------------------------------------------- diff --git a/mr/src/main/java/org/apache/mahout/vectorizer/DictionaryVectorizer.java b/mr/src/main/java/org/apache/mahout/vectorizer/DictionaryVectorizer.java index 27e2452..8a1f8f8 100644 --- a/mr/src/main/java/org/apache/mahout/vectorizer/DictionaryVectorizer.java +++ b/mr/src/main/java/org/apache/mahout/vectorizer/DictionaryVectorizer.java @@ -122,6 +122,10 @@ public final class DictionaryVectorizer extends AbstractJob implements Vectorize * The name of the folder in which the final output vectors will be stored * @param baseConf * job configuration + * @param normPower + * L_p norm to be computed + * @param logNormalize + * whether to use log normalization * @param minSupport * the minimum frequency of the feature in the entire corpus to be considered for inclusion in the * sparse vector @@ -129,22 +133,12 @@ public final class DictionaryVectorizer extends AbstractJob implements Vectorize * 1 = unigram, 2 = unigram and bigram, 3 = unigram, bigram and trigram * @param minLLRValue * minValue of log likelihood ratio to used to prune ngrams - * @param normPower - * L_p norm to be computed - * @param logNormalize - * whether to use log normalization - * @param numReducers - * * @param chunkSizeInMegabytes * the size in MB of the feature => id chunk to be kept in memory at each node during Map/Reduce * stage. Its recommended you calculated this based on the number of cores and the free memory * available to you per node. Say, you have 2 cores and around 1GB extra memory to spare we * recommend you use a split size of around 400-500MB so that two simultaneous reducers can create * partial vectors without thrashing the system due to increased swapping - * @param sequentialAccess - * - * @param namedVectors - * */ public static void createTermFrequencyVectors(Path input, Path output,
