[SPARK-19969][ML] Imputer doc and example

## What changes were proposed in this pull request?

Add docs and examples for spark.ml.feature.Imputer. Currently scala and Java examples are included. Python example will be added after https://github.com/apache/spark/pull/17316

## How was this patch tested?

local doc generation and example execution

Author: Yuhao Yang <yuhao.yang@intel.com>

Closes #17324 from hhbyyh/imputerdoc.

1 files changed, 50 insertions, 0 deletions

diff --git a/examples/src/main/python/ml/imputer_example.py b/examples/src/main/python/ml/imputer_example.py
new file mode 100644
index 0000000000..b8437f827e
--- /dev/null
+++ b/examples/src/main/python/ml/imputer_example.py
@@ -0,0 +1,50 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+# $example on$
+from pyspark.ml.feature import Imputer
+# $example off$
+from pyspark.sql import SparkSession
+
+"""
+An example demonstrating Imputer.
+Run with:
+  bin/spark-submit examples/src/main/python/ml/imputer_example.py
+"""
+
+if __name__ == "__main__":
+    spark = SparkSession\
+        .builder\
+        .appName("ImputerExample")\
+        .getOrCreate()
+
+    # $example on$
+    df = spark.createDataFrame([
+        (1.0, float("nan")),
+        (2.0, float("nan")),
+        (float("nan"), 3.0),
+        (4.0, 4.0),
+        (5.0, 5.0)
+    ], ["a", "b"])
+
+    imputer = Imputer(inputCols=["a", "b"], outputCols=["out_a", "out_b"])
+    model = imputer.fit(df)
+
+    model.transform(df).show()
+    # $example off$
+
+    spark.stop()