diff options
Diffstat (limited to 'mllib/src/main')
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala | 9 | ||||
-rw-r--r-- | mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala | 17 |
2 files changed, 23 insertions, 3 deletions
diff --git a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala b/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala index f71726f110..a1d36c4bec 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/evaluation/BinaryClassificationEvaluator.scala @@ -29,6 +29,8 @@ import org.apache.spark.sql.types.DoubleType /** * :: Experimental :: * Evaluator for binary classification, which expects two input columns: rawPrediction and label. + * The rawPrediction column can be of type double (binary 0/1 prediction, or probability of label 1) + * or of type vector (length-2 vector of raw predictions, scores, or label probabilities). */ @Since("1.2.0") @Experimental @@ -78,13 +80,14 @@ class BinaryClassificationEvaluator @Since("1.4.0") (@Since("1.4.0") override va @Since("1.2.0") override def evaluate(dataset: DataFrame): Double = { val schema = dataset.schema - SchemaUtils.checkColumnType(schema, $(rawPredictionCol), new VectorUDT) + SchemaUtils.checkColumnTypes(schema, $(rawPredictionCol), Seq(DoubleType, new VectorUDT)) SchemaUtils.checkColumnType(schema, $(labelCol), DoubleType) // TODO: When dataset metadata has been implemented, check rawPredictionCol vector length = 2. val scoreAndLabels = dataset.select($(rawPredictionCol), $(labelCol)) - .map { case Row(rawPrediction: Vector, label: Double) => - (rawPrediction(1), label) + .map { + case Row(rawPrediction: Vector, label: Double) => (rawPrediction(1), label) + case Row(rawPrediction: Double, label: Double) => (rawPrediction, label) } val metrics = new BinaryClassificationMetrics(scoreAndLabels) val metric = $(metricName) match { diff --git a/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala b/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala index 76f651488a..e71dd9eee0 100644 --- a/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala +++ b/mllib/src/main/scala/org/apache/spark/ml/util/SchemaUtils.scala @@ -44,6 +44,23 @@ private[spark] object SchemaUtils { } /** + * Check whether the given schema contains a column of one of the require data types. + * @param colName column name + * @param dataTypes required column data types + */ + def checkColumnTypes( + schema: StructType, + colName: String, + dataTypes: Seq[DataType], + msg: String = ""): Unit = { + val actualDataType = schema(colName).dataType + val message = if (msg != null && msg.trim.length > 0) " " + msg else "" + require(dataTypes.exists(actualDataType.equals), + s"Column $colName must be of type equal to one of the following types: " + + s"${dataTypes.mkString("[", ", ", "]")} but was actually of type $actualDataType.$message") + } + + /** * Appends a new column to the input schema. This fails if the given output column already exists. * @param schema input schema * @param colName new column name. If this column name is an empty string "", this method returns |