Github user yanboliang commented on a diff in the pull request: https://github.com/apache/spark/pull/19204#discussion_r139312388 --- Diff: python/pyspark/ml/evaluation.py --- @@ -328,6 +329,86 @@ def setParams(self, predictionCol="prediction", labelCol="label", kwargs = self._input_kwargs return self._set(**kwargs) + +@inherit_doc +class ClusteringEvaluator(JavaEvaluator, HasPredictionCol, HasFeaturesCol, + JavaMLReadable, JavaMLWritable): + """ + .. note:: Experimental + + Evaluator for Clustering results, which expects two input + columns: prediction and features. + + >>> from sklearn import datasets + >>> from pyspark.sql.types import * + >>> from pyspark.ml.linalg import Vectors, VectorUDT + >>> from pyspark.ml.evaluation import ClusteringEvaluator + ... + >>> iris = datasets.load_iris() + >>> iris_rows = [(Vectors.dense(x), int(iris.target[i])) + ... for i, x in enumerate(iris.data)] + >>> schema = StructType([ + ... StructField("features", VectorUDT(), True), + ... StructField("cluster_id", IntegerType(), True)]) --- End diff -- ```cluster_id``` -> ```prediction``` to emphasize this is the prediction value, not ground truth.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org