add tests

Author: Wayne Zhang

python/pyspark/ml/feature.py

@@ -2082,8 +2082,9 @@ class StringIndexer(JavaEstimator, HasInputCol, HasOutputCol, HasHandleInvalid,
     """
     A label indexer that maps a string column of labels to an ML column of label indices.
     If the input column is numeric, we cast it to string and index the string values.
-    The indices are in [0, numLabels), ordered by label frequencies.
-    So the most frequent label gets index 0.
+    The indices are in [0, numLabels). By default, this is ordered by label frequencies
+    so the most frequent label gets index 0. The ordering behavior is controlled by
+    setting stringOrderType.
 
     >>> stringIndexer = StringIndexer(inputCol="label", outputCol="indexed", handleInvalid='error')
     >>> model = stringIndexer.fit(stringIndDf)
@@ -2111,14 +2112,22 @@ class StringIndexer(JavaEstimator, HasInputCol, HasOutputCol, HasHandleInvalid,
     >>> loadedInverter = IndexToString.load(indexToStringPath)
     >>> loadedInverter.getLabels() == inverter.getLabels()
     True
+    >>> stringIndexer.getStringOrderType()
+    'frequencyDesc'
+    >>> stringIndexer.setStringOrderType("alphabetDesc")
+    >>> model = stringIndexer.fit(stringIndDf)
+    >>> td = model.transform(stringIndDf)
+    >>> sorted(set([(i[0], i[1]) for i in td.select(td.id, td.indexed).collect()]),
+    ...     key=lambda x: x[0])
+    [(0, 2.0), (1, 1.0), (2, 0.0), (3, 2.0), (4, 2.0), (5, 0.0)]
 
     .. versionadded:: 1.4.0
     """
 
     stringOrderType = Param(Params._dummy(), "stringOrderType",
                             "How to order labels of string column. The first label after " +
                             "ordering is assigned an index of 0. Supported options: " +
-                            "frequencyDesc, frequencyAsc, alphabetDsec, alphabetAsc.",
+                            "frequencyDesc, frequencyAsc, alphabetDesc, alphabetAsc.",
                             typeConverter=TypeConverters.toString)
 
     @keyword_only