[GitHub] [spark] HyukjinKwon commented on a diff in pull request #38013: [SPARK-40509][SS][PYTHON] add example for applyInPandasWithState

[GitBox <gi...@apache.org>]

HyukjinKwon commented on code in PR #38013:
URL: https://github.com/apache/spark/pull/38013#discussion_r981247894


##########
examples/src/main/python/sql/streaming/structured_network_wordcount_session_window.py:
##########
@@ -0,0 +1,114 @@
+#
+# 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.
+#
+
+r"""
+ split lines into words, group by words as key and use the state per key to track session of each key.
+
+ Usage: structured_network_wordcount_windowed.py <hostname> <port>
+ <hostname> and <port> describe the TCP server that Structured Streaming
+ would connect to receive data.
+
+ To run this on your local machine, you need to first run a Netcat server
+    `$ nc -lk 9999`
+ and then run the example
+    `$ bin/spark-submit
+    examples/src/main/python/sql/streaming/structured_network_wordcount_session_window.py
+    localhost 9999`
+"""
+import sys
+
+from pyspark.sql import SparkSession
+from pyspark.sql.functions import explode
+from pyspark.sql.functions import split
+from pyspark.sql.functions import window
+from pyspark.sql.types import (
+    LongType,
+    StringType,
+    StructType,
+    StructField,
+    Row,
+)
+from pyspark.sql.streaming.state import GroupStateTimeout, GroupState
+import pandas as pd
+
+if __name__ == "__main__":
+    if len(sys.argv) != 3:
+        msg = ("Usage: structured_network_wordcount_session_window.py <hostname> <port>")
+        print(msg, file=sys.stderr)
+        sys.exit(-1)
+
+    host = sys.argv[1]
+    port = int(sys.argv[2])
+
+    spark = SparkSession\
+        .builder\
+        .appName("StructuredNetworkWordCountSessionWindow")\
+        .getOrCreate()
+
+    spark.sparkContext.setLogLevel("WARN")
+
+    # Create DataFrame representing the stream of input lines from connection to host:port
+    lines = spark\
+        .readStream\
+        .format('socket')\
+        .option('host', host)\
+        .option('port', port)\
+        .option('includeTimestamp', 'true')\
+        .load()
+
+    # Split the lines into words, retaining timestamps
+    # split() splits each line into an array, and explode() turns the array into multiple rows
+    events = lines.select(
+        explode(split(lines.value, ' ')).alias('sessionId'),
+        lines.timestamp.cast("long")
+    )
+
+    session_type = StructType(
+    [StructField("sessionId", StringType()), StructField("count", LongType()),
+    StructField("start", LongType()), StructField("end", LongType())]
+    )
+
+    def func(key, pdf_iter, state):
+        if state.hasTimedOut:
+            finished_session = state.get
+            state.remove()
+            yield pd.DataFrame({"sessionId": [finished_session[0]], "count": [finished_session[1]], "start": [finished_session[2]], "end": [finished_session[3]]})

Review Comment:
   I would do this more in a Pythonic way. e.g.)
   
   ```python
   session_id, count, start, end = state.get
   pd.DataFrame({"sessionId": session_id, "count": count, "start": start, "end", end})
   ```
   
   or
   
   ```python
   pd.DataFrame(dict(zip(("sessionId", "count", "start", "end"), state.get)))
   ```



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org