Repository: mahout Updated Branches: refs/heads/master d7a87936e -> 9df093c98
MAHOUT-1836:reorder javadoc paramter comments closes apache/mahout#227 Project: http://git-wip-us.apache.org/repos/asf/mahout/repo Commit: http://git-wip-us.apache.org/repos/asf/mahout/commit/9df093c9 Tree: http://git-wip-us.apache.org/repos/asf/mahout/tree/9df093c9 Diff: http://git-wip-us.apache.org/repos/asf/mahout/diff/9df093c9 Branch: refs/heads/master Commit: 9df093c98c985dce06841e31b40de4f7b9233069 Parents: d7a8793 Author: Marku <[email protected]> Authored: Wed Apr 27 19:02:46 2016 -0400 Committer: Andrew Palumbo <[email protected]> Committed: Wed Apr 27 19:02:46 2016 -0400 ---------------------------------------------------------------------- .../mahout/vectorizer/DictionaryVectorizer.java | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/mahout/blob/9df093c9/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 8a1f8f8..27e2452 100644 --- a/mr/src/main/java/org/apache/mahout/vectorizer/DictionaryVectorizer.java +++ b/mr/src/main/java/org/apache/mahout/vectorizer/DictionaryVectorizer.java @@ -122,10 +122,6 @@ 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 @@ -133,12 +129,22 @@ 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,
