diff options
Diffstat (limited to 'mllib')
5 files changed, 37 insertions, 29 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala index 7b203e2f40..88dbfe3fcc 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/GaussianMixture.scala @@ -45,10 +45,10 @@ import org.apache.spark.util.Utils * This is due to high-dimensional data (a) making it difficult to cluster at all (based * on statistical/theoretical arguments) and (b) numerical issues with Gaussian distributions. * - * @param k The number of independent Gaussians in the mixture model - * @param convergenceTol The maximum change in log-likelihood at which convergence - * is considered to have occurred. - * @param maxIterations The maximum number of iterations to perform + * @param k Number of independent Gaussians in the mixture model. + * @param convergenceTol Maximum change in log-likelihood at which convergence + * is considered to have occurred. + * @param maxIterations Maximum number of iterations allowed. */ @Since("1.3.0") class GaussianMixture private ( @@ -108,7 +108,7 @@ class GaussianMixture private ( def getK: Int = k /** - * Set the maximum number of iterations to run. Default: 100 + * Set the maximum number of iterations allowed. Default: 100 */ @Since("1.3.0") def setMaxIterations(maxIterations: Int): this.type = { @@ -117,7 +117,7 @@ class GaussianMixture private ( } /** - * Return the maximum number of iterations to run + * Return the maximum number of iterations allowed */ @Since("1.3.0") def getMaxIterations: Int = maxIterations diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala index ca11ede4cc..901164a391 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/KMeans.scala @@ -70,13 +70,13 @@ class KMeans private ( } /** - * Maximum number of iterations to run. + * Maximum number of iterations allowed. */ @Since("1.4.0") def getMaxIterations: Int = maxIterations /** - * Set maximum number of iterations to run. Default: 20. + * Set maximum number of iterations allowed. Default: 20. */ @Since("0.8.0") def setMaxIterations(maxIterations: Int): this.type = { @@ -482,12 +482,15 @@ object KMeans { /** * Trains a k-means model using the given set of parameters. * - * @param data training points stored as `RDD[Vector]` - * @param k number of clusters - * @param maxIterations max number of iterations - * @param runs number of parallel runs, defaults to 1. The best model is returned. - * @param initializationMode initialization model, either "random" or "k-means||" (default). - * @param seed random seed value for cluster initialization + * @param data Training points as an `RDD` of `Vector` types. + * @param k Number of clusters to create. + * @param maxIterations Maximum number of iterations allowed. + * @param runs Number of runs to execute in parallel. The best model according to the cost + * function will be returned. (default: 1) + * @param initializationMode The initialization algorithm. This can either be "random" or + * "k-means||". (default: "k-means||") + * @param seed Random seed for cluster initialization. Default is to generate seed based + * on system time. */ @Since("1.3.0") def train( @@ -508,11 +511,13 @@ object KMeans { /** * Trains a k-means model using the given set of parameters. * - * @param data training points stored as `RDD[Vector]` - * @param k number of clusters - * @param maxIterations max number of iterations - * @param runs number of parallel runs, defaults to 1. The best model is returned. - * @param initializationMode initialization model, either "random" or "k-means||" (default). + * @param data Training points as an `RDD` of `Vector` types. + * @param k Number of clusters to create. + * @param maxIterations Maximum number of iterations allowed. + * @param runs Number of runs to execute in parallel. The best model according to the cost + * function will be returned. (default: 1) + * @param initializationMode The initialization algorithm. This can either be "random" or + * "k-means||". (default: "k-means||") */ @Since("0.8.0") def train( diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala index eb802a365e..81566b4779 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/LDA.scala @@ -61,14 +61,13 @@ class LDA private ( ldaOptimizer = new EMLDAOptimizer) /** - * Number of topics to infer. I.e., the number of soft cluster centers. - * + * Number of topics to infer, i.e., the number of soft cluster centers. */ @Since("1.3.0") def getK: Int = k /** - * Number of topics to infer. I.e., the number of soft cluster centers. + * Set the number of topics to infer, i.e., the number of soft cluster centers. * (default = 10) */ @Since("1.3.0") @@ -222,13 +221,13 @@ class LDA private ( def setBeta(beta: Double): this.type = setTopicConcentration(beta) /** - * Maximum number of iterations for learning. + * Maximum number of iterations allowed. */ @Since("1.3.0") def getMaxIterations: Int = maxIterations /** - * Maximum number of iterations for learning. + * Set the maximum number of iterations allowed. * (default = 20) */ @Since("1.3.0") @@ -238,13 +237,13 @@ class LDA private ( } /** - * Random seed + * Random seed for cluster initialization. */ @Since("1.3.0") def getSeed: Long = seed /** - * Random seed + * Set the random seed for cluster initialization. */ @Since("1.3.0") def setSeed(seed: Long): this.type = { diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala index 2ab0920b06..1ab7cb393b 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/PowerIterationClustering.scala @@ -111,7 +111,9 @@ object PowerIterationClusteringModel extends Loader[PowerIterationClusteringMode * * @param k Number of clusters. * @param maxIterations Maximum number of iterations of the PIC algorithm. - * @param initMode Initialization mode. + * @param initMode Set the initialization mode. This can be either "random" to use a random vector + * as vertex properties, or "degree" to use normalized sum similarities. + * Default: random. * * @see [[http://en.wikipedia.org/wiki/Spectral_clustering Spectral clustering (Wikipedia)]] */ diff --git a/mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala b/mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala index 79d217e183..d99b89dc49 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/clustering/StreamingKMeans.scala @@ -183,7 +183,7 @@ class StreamingKMeans @Since("1.2.0") ( } /** - * Set the decay factor directly (for forgetful algorithms). + * Set the forgetfulness of the previous centroids. */ @Since("1.2.0") def setDecayFactor(a: Double): this.type = { @@ -192,7 +192,9 @@ class StreamingKMeans @Since("1.2.0") ( } /** - * Set the half life and time unit ("batches" or "points") for forgetful algorithms. + * Set the half life and time unit ("batches" or "points"). If points, then the decay factor + * is raised to the power of number of new points and if batches, then decay factor will be + * used as is. */ @Since("1.2.0") def setHalfLife(halfLife: Double, timeUnit: String): this.type = { |