Repository: spark Updated Branches: refs/heads/branch-1.3 0040b6128 -> 40746749a
[MLlib] Minor: UDF style update. Author: Reynold Xin <[email protected]> Closes #4388 from rxin/mllib-style and squashes the following commits: 61d465b [Reynold Xin] oops 3364295 [Reynold Xin] Missed one .. 5e068e3 [Reynold Xin] [MLlib] Minor: UDF style update. (cherry picked from commit c3ba4d4cd032e376bfdf7ea7eaab65a79a771e7e) Signed-off-by: Reynold Xin <[email protected]> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/40746749 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/40746749 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/40746749 Branch: refs/heads/branch-1.3 Commit: 40746749a6670f43aece69fe1482e92fa87decf5 Parents: 0040b61 Author: Reynold Xin <[email protected]> Authored: Wed Feb 4 23:57:53 2015 -0800 Committer: Reynold Xin <[email protected]> Committed: Wed Feb 4 23:58:13 2015 -0800 ---------------------------------------------------------------------- .../apache/spark/ml/classification/LogisticRegression.scala | 8 +++++--- .../main/scala/org/apache/spark/ml/recommendation/ALS.scala | 4 ++-- 2 files changed, 7 insertions(+), 5 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/40746749/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala index df90078..b46a5cd 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/classification/LogisticRegression.scala @@ -132,12 +132,14 @@ class LogisticRegressionModel private[ml] ( override def transform(dataset: DataFrame, paramMap: ParamMap): DataFrame = { transformSchema(dataset.schema, paramMap, logging = true) val map = this.paramMap ++ paramMap - val scoreFunction = udf((v: Vector) => { + val scoreFunction = udf { v: Vector => val margin = BLAS.dot(v, weights) 1.0 / (1.0 + math.exp(-margin)) - } : Double) + } val t = map(threshold) - val predictFunction = udf((score: Double) => { if (score > t) 1.0 else 0.0 } : Double) + val predictFunction = udf { score: Double => + if (score > t) 1.0 else 0.0 + } dataset .select($"*", scoreFunction(col(map(featuresCol))).as(map(scoreCol))) .select($"*", predictFunction(col(map(scoreCol))).as(map(predictionCol))) http://git-wip-us.apache.org/repos/asf/spark/blob/40746749/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala ---------------------------------------------------------------------- diff --git a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala index 09456b2..bf57371 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/recommendation/ALS.scala @@ -129,13 +129,13 @@ class ALSModel private[ml] ( // Register a UDF for DataFrame, and then // create a new column named map(predictionCol) by running the predict UDF. - val predict = udf((userFeatures: Seq[Float], itemFeatures: Seq[Float]) => { + val predict = udf { (userFeatures: Seq[Float], itemFeatures: Seq[Float]) => if (userFeatures != null && itemFeatures != null) { blas.sdot(k, userFeatures.toArray, 1, itemFeatures.toArray, 1) } else { Float.NaN } - } : Float) + } dataset .join(users, dataset(map(userCol)) === users("id"), "left") .join(items, dataset(map(itemCol)) === items("id"), "left") --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
