diff --git a/core/src/main/java/org/apache/spark/TaskContext.java b/core/src/main/java/org/apache/spark/TaskContext.java index 2d998d4c7a5d94b78f01873a09ac66803784033f..0d6973203eba17dd168bc92d4e7a6acbd7226939 100644 --- a/core/src/main/java/org/apache/spark/TaskContext.java +++ b/core/src/main/java/org/apache/spark/TaskContext.java @@ -71,7 +71,6 @@ public abstract class TaskContext implements Serializable { /** * Add a (Java friendly) listener to be executed on task completion. * This will be called in all situation - success, failure, or cancellation. - * <p/> * An example use is for HadoopRDD to register a callback to close the input stream. */ public abstract TaskContext addTaskCompletionListener(TaskCompletionListener listener); @@ -79,7 +78,6 @@ public abstract class TaskContext implements Serializable { /** * Add a listener in the form of a Scala closure to be executed on task completion. * This will be called in all situations - success, failure, or cancellation. - * <p/> * An example use is for HadoopRDD to register a callback to close the input stream. */ public abstract TaskContext addTaskCompletionListener(final Function1<TaskContext, Unit> f); diff --git a/core/src/main/java/org/apache/spark/api/java/function/PairFunction.java b/core/src/main/java/org/apache/spark/api/java/function/PairFunction.java index abd9bcc07ac61a67404de69bbb765d298f7f221d..99bf240a172254ef8e812e060cdc6f507279ef8a 100644 --- a/core/src/main/java/org/apache/spark/api/java/function/PairFunction.java +++ b/core/src/main/java/org/apache/spark/api/java/function/PairFunction.java @@ -22,7 +22,8 @@ import java.io.Serializable; import scala.Tuple2; /** - * A function that returns key-value pairs (Tuple2<K, V>), and can be used to construct PairRDDs. + * A function that returns key-value pairs (Tuple2<K, V>), and can be used to + * construct PairRDDs. */ public interface PairFunction<T, K, V> extends Serializable { public Tuple2<K, V> call(T t) throws Exception; diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala index a6123bd108c116dd2ae02bf9d2c50ffb5258d005..8e8f7f6c4fda2cb470b2e247605c4bbe5281bd22 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaDoubleRDD.scala @@ -114,7 +114,7 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[JDouble, Ja * Return an RDD with the elements from `this` that are not in `other`. * * Uses `this` partitioner/partition size, because even if `other` is huge, the resulting - * RDD will be <= us. + * RDD will be <= us. */ def subtract(other: JavaDoubleRDD): JavaDoubleRDD = fromRDD(srdd.subtract(other)) @@ -233,11 +233,11 @@ class JavaDoubleRDD(val srdd: RDD[scala.Double]) extends JavaRDDLike[JDouble, Ja * to the left except for the last which is closed * e.g. for the array * [1,10,20,50] the buckets are [1,10) [10,20) [20,50] - * e.g 1<=x<10 , 10<=x<20, 20<=x<50 + * e.g 1<=x<10 , 10<=x<20, 20<=x<50 * And on the input of 1 and 50 we would have a histogram of 1,0,0 * * Note: if your histogram is evenly spaced (e.g. [0, 10, 20, 30]) this can be switched - * from an O(log n) inseration to O(1) per element. (where n = # buckets) if you set evenBuckets + * from an O(log n) insertion to O(1) per element. (where n = # buckets) if you set evenBuckets * to true. * buckets must be sorted and not contain any duplicates. * buckets array must be at least two elements diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala index c38b96528d0377b4e89cddd9ce70ee67af4eaa51..e37f3acaf6e30c8b737545fba82d9d5be1833f50 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaPairRDD.scala @@ -392,7 +392,7 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) * Return an RDD with the elements from `this` that are not in `other`. * * Uses `this` partitioner/partition size, because even if `other` is huge, the resulting - * RDD will be <= us. + * RDD will be <= us. */ def subtract(other: JavaPairRDD[K, V]): JavaPairRDD[K, V] = fromRDD(rdd.subtract(other)) @@ -413,7 +413,7 @@ class JavaPairRDD[K, V](val rdd: RDD[(K, V)]) * Return an RDD with the pairs from `this` whose keys are not in `other`. * * Uses `this` partitioner/partition size, because even if `other` is huge, the resulting - * RDD will be <= us. + * RDD will be <= us. */ def subtractByKey[W](other: JavaPairRDD[K, W]): JavaPairRDD[K, V] = { implicit val ctag: ClassTag[W] = fakeClassTag diff --git a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala index 45168ba62d3c1a751505ef2db1ee27ffc611077a..0565adf4d4ead16f102326d1ae3c1129e3373b5b 100644 --- a/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala +++ b/core/src/main/scala/org/apache/spark/api/java/JavaSparkContext.scala @@ -215,7 +215,10 @@ class JavaSparkContext(val sc: SparkContext) * hdfs://a-hdfs-path/part-nnnnn * }}} * - * Do `JavaPairRDD<String, String> rdd = sparkContext.wholeTextFiles("hdfs://a-hdfs-path")`, + * Do + * {{{ + * JavaPairRDD<String, String> rdd = sparkContext.wholeTextFiles("hdfs://a-hdfs-path") + * }}} * * <p> then `rdd` contains * {{{ diff --git a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala index 4734251127bb407629d5ed00f56f9b80637cffd7..dfad25d57c947253cd94246156d104523afc7d6a 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/feature/Normalizer.scala @@ -26,7 +26,7 @@ import org.apache.spark.mllib.linalg.{Vector, Vectors} * :: Experimental :: * Normalizes samples individually to unit L^p^ norm * - * For any 1 <= p < Double.PositiveInfinity, normalizes samples using + * For any 1 <= p < Double.PositiveInfinity, normalizes samples using * sum(abs(vector).^p^)^(1/p)^ as norm. * * For p = Double.PositiveInfinity, max(abs(vector)) will be used as norm for normalization. diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala index ec2d481dccc220b6ca8d4e8b6def096352e359c6..10a515af888023ded03fb4db97118b28378b320d 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/linalg/distributed/RowMatrix.scala @@ -152,7 +152,7 @@ class RowMatrix( * storing the right singular vectors, is computed via matrix multiplication as * U = A * (V * S^-1^), if requested by user. The actual method to use is determined * automatically based on the cost: - * - If n is small (n < 100) or k is large compared with n (k > n / 2), we compute the Gramian + * - If n is small (n < 100) or k is large compared with n (k > n / 2), we compute the Gramian * matrix first and then compute its top eigenvalues and eigenvectors locally on the driver. * This requires a single pass with O(n^2^) storage on each executor and on the driver, and * O(n^2^ k) time on the driver. @@ -169,7 +169,8 @@ class RowMatrix( * @note The conditions that decide which method to use internally and the default parameters are * subject to change. * - * @param k number of leading singular values to keep (0 < k <= n). It might return less than k if + * @param k number of leading singular values to keep (0 < k <= n). + * It might return less than k if * there are numerically zero singular values or there are not enough Ritz values * converged before the maximum number of Arnoldi update iterations is reached (in case * that matrix A is ill-conditioned). @@ -192,7 +193,7 @@ class RowMatrix( /** * The actual SVD implementation, visible for testing. * - * @param k number of leading singular values to keep (0 < k <= n) + * @param k number of leading singular values to keep (0 < k <= n) * @param computeU whether to compute U * @param rCond the reciprocal condition number * @param maxIter max number of iterations (if ARPACK is used) diff --git a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala index ca35100aa99c650dbc024f1419c908071f60d89b..dce0adffa6249668d55249d62cba04f86506e960 100644 --- a/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala +++ b/mllib/src/main/scala/org/apache/spark/mllib/util/MLUtils.scala @@ -196,8 +196,8 @@ object MLUtils { /** * Load labeled data from a file. The data format used here is - * <L>, <f1> <f2> ... - * where <f1>, <f2> are feature values in Double and <L> is the corresponding label as Double. + * L, f1 f2 ... + * where f1, f2 are feature values in Double and L is the corresponding label as Double. * * @param sc SparkContext * @param dir Directory to the input data files. @@ -219,8 +219,8 @@ object MLUtils { /** * Save labeled data to a file. The data format used here is - * <L>, <f1> <f2> ... - * where <f1>, <f2> are feature values in Double and <L> is the corresponding label as Double. + * L, f1 f2 ... + * where f1, f2 are feature values in Double and L is the corresponding label as Double. * * @param data An RDD of LabeledPoints containing data to be saved. * @param dir Directory to save the data. diff --git a/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSchemaRDD.scala b/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSchemaRDD.scala index e7faba0c7f6204e7091b597eb25c655ab8d2ac7d..1e0ccb368a2767b1475464604784d2a91c25b5d8 100644 --- a/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSchemaRDD.scala +++ b/sql/core/src/main/scala/org/apache/spark/sql/api/java/JavaSchemaRDD.scala @@ -193,7 +193,7 @@ class JavaSchemaRDD( * Return an RDD with the elements from `this` that are not in `other`. * * Uses `this` partitioner/partition size, because even if `other` is huge, the resulting - * RDD will be <= us. + * RDD will be <= us. */ def subtract(other: JavaSchemaRDD): JavaSchemaRDD = this.baseSchemaRDD.subtract(other.baseSchemaRDD).toJavaSchemaRDD