[SPARK-26315][PySpark] auto cast threshold from Integer to Float in a…

…pproxSimilarityJoin of BucketedRandomProjectionLSHModel

python/pyspark/ml/feature.py

@@ -192,6 +192,7 @@ def approxSimilarityJoin(self, datasetA, datasetB, threshold, distCol="distCol")
                  "datasetA" and "datasetB", and a column "distCol" is added to show the distance
                  between each pair.
         """
+        threshold = TypeConverters.toFloat(threshold)
         return self._call_java("approxSimilarityJoin", datasetA, datasetB, threshold, distCol)
 
 
@@ -239,6 +240,16 @@ class BucketedRandomProjectionLSH(JavaEstimator, LSHParams, HasInputCol, HasOutp
     |  3|  6| 2.23606797749979|
     +---+---+-----------------+
     ...
+    >>> model.approxSimilarityJoin(df, df2, 3, distCol="EuclideanDistance").select(
+    ...     col("datasetA.id").alias("idA"),
+    ...     col("datasetB.id").alias("idB"),
+    ...     col("EuclideanDistance")).show()
+    +---+---+-----------------+
+    |idA|idB|EuclideanDistance|
+    +---+---+-----------------+
+    |  3|  6| 2.23606797749979|
+    +---+---+-----------------+
+    ...
     >>> brpPath = temp_path + "/brp"
     >>> brp.save(brpPath)
     >>> brp2 = BucketedRandomProjectionLSH.load(brpPath)