[MINOR] Fix Typos

docs/ml-guide.md

@@ -257,7 +257,7 @@ Currently, `spark.ml` supports model selection using the [`CrossValidator`](api/
 
 The `Evaluator` can be a [`RegressionEvaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.RegressionEvaluator)
 for regression problems, a [`BinaryClassificationEvaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.BinaryClassificationEvaluator)
-for binary data, or a [`MultiClassClassificationEvaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator)
+for binary data, or a [`MulticlassClassificationEvaluator`](api/scala/index.html#org.apache.spark.ml.evaluation.MulticlassClassificationEvaluator)
 for multiclass problems. The default metric used to choose the best `ParamMap` can be overridden by the `setMetricName`
 method in each of these evaluators.
 

mllib/src/main/scala/org/apache/spark/ml/ann/BreezeUtil.scala

@@ -26,38 +26,39 @@ import com.github.fommil.netlib.BLAS.{getInstance => NativeBLAS}
 private[ann] object BreezeUtil {
 
   // TODO: switch to MLlib BLAS interface
-  private def transposeString(a: BDM[Double]): String = if (a.isTranspose) "T" else "N"
+  private def transposeString(A: BDM[Double]): String = if (A.isTranspose) "T" else "N"
 
   /**
    * DGEMM: C := alpha * A * B + beta * C
    * @param alpha alpha
-   * @param a A
-   * @param b B
+   * @param A A
+   * @param B B
    * @param beta beta
-   * @param c C
+   * @param C C
    */
-  def dgemm(alpha: Double, a: BDM[Double], b: BDM[Double], beta: Double, c: BDM[Double]): Unit = {
+  def dgemm(alpha: Double, A: BDM[Double], B: BDM[Double], beta: Double, C: BDM[Double]): Unit = {
     // TODO: add code if matrices isTranspose!!!
-    require(a.cols == b.rows, "A & B Dimension mismatch!")
-    require(a.rows == c.rows, "A & C Dimension mismatch!")
-    require(b.cols == c.cols, "A & C Dimension mismatch!")
-    NativeBLAS.dgemm(transposeString(a), transposeString(b), c.rows, c.cols, a.cols,
-      alpha, a.data, a.offset, a.majorStride, b.data, b.offset, b.majorStride,
-      beta, c.data, c.offset, c.rows)
+    require(A.cols == B.rows, "A & B Dimension mismatch!")
+    require(A.rows == C.rows, "A & C Dimension mismatch!")
+    require(B.cols == C.cols, "A & C Dimension mismatch!")
+    NativeBLAS.dgemm(transposeString(A), transposeString(B), C.rows, C.cols, A.cols,
+      alpha, A.data, A.offset, A.majorStride, B.data, B.offset, B.majorStride,
+      beta, C.data, C.offset, C.rows)
   }
 
   /**
    * DGEMV: y := alpha * A * x + beta * y
    * @param alpha alpha
-   * @param a A
+   * @param A A
    * @param x x
    * @param beta beta
    * @param y y
    */
-  def dgemv(alpha: Double, a: BDM[Double], x: BDV[Double], beta: Double, y: BDV[Double]): Unit = {
-    require(a.cols == x.length, "A & b Dimension mismatch!")
-    NativeBLAS.dgemv(transposeString(a), a.rows, a.cols,
-      alpha, a.data, a.offset, a.majorStride, x.data, x.offset, x.stride,
+  def dgemv(alpha: Double, A: BDM[Double], x: BDV[Double], beta: Double, y: BDV[Double]): Unit = {
+    require(A.cols == x.length, "A & x Dimension mismatch!")
+    require(A.rows == y.length, "A & y Dimension mismatch!")
+    NativeBLAS.dgemv(transposeString(A), A.rows, A.cols,
+      alpha, A.data, A.offset, A.majorStride, x.data, x.offset, x.stride,
       beta, y.data, y.offset, y.stride)
   }
 }

mllib/src/main/scala/org/apache/spark/ml/ann/Layer.scala

@@ -64,8 +64,9 @@ private[ann] trait Layer extends Serializable {
    * @return the layer model
    */
   def createModel(initialWeights: BDV[Double]): LayerModel
+
   /**
-   * Returns the instance of the layer with random generated weights
+   * Returns the instance of the layer with random generated weights.
    *
    * @param weights vector for weights initialization, must be equal to weightSize
    * @param random random number generator
@@ -83,23 +84,23 @@ private[ann] trait LayerModel extends Serializable {
 
   val weights: BDV[Double]
   /**
-   * Evaluates the data (process the data through the layer)
+   * Evaluates the data (process the data through the layer).
    * Output is allocated based on the size provided by the
-   * LayerModel implementation and the stack (batch) size
+   * LayerModel implementation and the stack (batch) size.
    * Developer is responsible for checking the size of output
-   * when writing to it
+   * when writing to it.
    *
    * @param data data
    * @param output output (modified in place)
    */
   def eval(data: BDM[Double], output: BDM[Double]): Unit
 
   /**
-   * Computes the delta for back propagation
+   * Computes the delta for back propagation.
    * Delta is allocated based on the size provided by the
-   * LayerModel implementation and the stack (batch) size
+   * LayerModel implementation and the stack (batch) size.
    * Developer is responsible for checking the size of
-   * prevDelta when writing to it
+   * prevDelta when writing to it.
    *
    * @param delta delta of this layer
    * @param output output of this layer
@@ -108,10 +109,10 @@ private[ann] trait LayerModel extends Serializable {
   def computePrevDelta(delta: BDM[Double], output: BDM[Double], prevDelta: BDM[Double]): Unit
 
   /**
-   * Computes the gradient
-   * cumGrad is a wrapper on the part of the weight vector
-   * size of cumGrad is based on weightSize provided by
-   * implementation of LayerModel
+   * Computes the gradient.
+   * cumGrad is a wrapper on the part of the weight vector.
+   * Size of cumGrad is based on weightSize provided by
+   * implementation of LayerModel.
    *
    * @param delta delta for this layer
    * @param input input data
@@ -197,11 +198,11 @@ private[ann] object AffineLayerModel {
   }
 
   /**
-   * Initialize weights randomly in the interval
-   * Uses [Bottou-88] heuristic [-a/sqrt(in); a/sqrt(in)]
-   * where a is chosen in a such way that the weight variance corresponds
+   * Initialize weights randomly in the interval.
+   * Uses [Bottou-88] heuristic [-a/sqrt(in); a/sqrt(in)],
+   * where `a` is chosen in such a way that the weight variance corresponds
    * to the points to the maximal curvature of the activation function
-   * (which is approximately 2.38 for a standard sigmoid)
+   * (which is approximately 2.38 for a standard sigmoid).
    *
    * @param numIn number of inputs
    * @param numOut number of outputs
@@ -306,7 +307,7 @@ private[ann] class FunctionalLayer (val activationFunction: ActivationFunction)
 /**
  * Functional layer model. Holds no weights.
  *
- * @param layer functiona layer
+ * @param layer functional layer
  */
 private[ann] class FunctionalLayerModel private[ann] (val layer: FunctionalLayer)
   extends LayerModel {
@@ -352,6 +353,7 @@ private[ann] trait TopologyModel extends Serializable {
    * Array of layer models
    */
   val layerModels: Array[LayerModel]
+
   /**
    * Forward propagation
    *
@@ -410,7 +412,7 @@ private[ml] object FeedForwardTopology {
    * Creates a multi-layer perceptron
    *
    * @param layerSizes sizes of layers including input and output size
-   * @param softmaxOnTop wether to use SoftMax or Sigmoid function for an output layer.
+   * @param softmaxOnTop whether to use SoftMax or Sigmoid function for an output layer.
    *                Softmax is default
    * @return multilayer perceptron topology
    */

sql/core/src/main/scala/org/apache/spark/sql/SparkSession.scala

@@ -39,7 +39,7 @@ import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan,
 import org.apache.spark.sql.execution._
 import org.apache.spark.sql.execution.datasources.LogicalRelation
 import org.apache.spark.sql.execution.ui.SQLListener
-import org.apache.spark.sql.internal.{CatalogImpl, SessionState, SharedState, SQLConf}
+import org.apache.spark.sql.internal.{CatalogImpl, SessionState, SharedState}
 import org.apache.spark.sql.sources.BaseRelation
 import org.apache.spark.sql.types.{DataType, LongType, StructType}
 import org.apache.spark.sql.util.ExecutionListenerManager

sql/core/src/main/scala/org/apache/spark/sql/api/r/SQLUtils.scala

@@ -26,9 +26,7 @@ import org.apache.spark.api.r.SerDe
 import org.apache.spark.broadcast.Broadcast
 import org.apache.spark.rdd.RDD
 import org.apache.spark.sql.{DataFrame, Row, SaveMode, SQLContext}
-import org.apache.spark.sql.catalyst.encoders.RowEncoder
 import org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema
-import org.apache.spark.sql.Encoder
 import org.apache.spark.sql.types._
 
 private[sql] object SQLUtils {
@@ -75,19 +73,19 @@ private[sql] object SQLUtils {
         org.apache.spark.sql.types.MapType(getSQLDataType(keyType), getSQLDataType(valueType))
       case r"\Astruct<(.+)${fieldsStr}>\Z" =>
         if (fieldsStr(fieldsStr.length - 1) == ',') {
-          throw new IllegalArgumentException(s"Invaid type $dataType")
+          throw new IllegalArgumentException(s"Invalid type $dataType")
         }
         val fields = fieldsStr.split(",")
         val structFields = fields.map { field =>
           field match {
             case r"\A(.+)${fieldName}:(.+)${fieldType}\Z" =>
               createStructField(fieldName, fieldType, true)
 
-            case _ => throw new IllegalArgumentException(s"Invaid type $dataType")
+            case _ => throw new IllegalArgumentException(s"Invalid type $dataType")
           }
         }
         createStructType(structFields)
-      case _ => throw new IllegalArgumentException(s"Invaid type $dataType")
+      case _ => throw new IllegalArgumentException(s"Invalid type $dataType")
     }
   }
 

sql/core/src/main/scala/org/apache/spark/sql/expressions/scalalang/typed.scala

@@ -38,7 +38,7 @@ object typed {
   // The reason we have separate files for Java and Scala is because in the Scala version, we can
   // use tighter types (primitive types) for return types, whereas in the Java version we can only
   // use boxed primitive types.
-  // For example, avg in the Scala veresion returns Scala primitive Double, whose bytecode
+  // For example, avg in the Scala version returns Scala primitive Double, whose bytecode
   // signature is just a java.lang.Object; avg in the Java version returns java.lang.Double.
 
   // TODO: This is pretty hacky. Maybe we should have an object for implicit encoders.