Advent of 2021, Day 18 – Time windows for Spark streaming

Series of Apache Spark posts:

• Dec 01: What is Apache Spark
• Dec 02: Installing Apache Spark
• Dec 03: Getting around CLI and WEB UI in Apache Spark
• Dec 04: Spark Architecture – Local and cluster mode
• Dec 05: Setting up Spark Cluster
• Dec 06: Setting up IDE
• Dec 07: Starting Spark with R and Python
• Dec 08: Creating RDD files
• Dec 09: RDD Operations
• Dec 10: Working with data frames
• Dec 11: Working with packages and spark DataFrames
• Dec 12: Spark SQL
• Dec 13: Spark SQL Bucketing and partitioning
• Dec 14: Spark SQL query hints and executions
• Dec 15: Introduction to Spark Streaming
• Dec 16: Dataframe operations for Spark streaming
• Dec 17: Watermarking and joins for Spark streaming

Spark streaming support three types of time windows:
– tumbling windows (fixed time window)
– sliding windows
– session windows.

Tumbling windows are fixed sized and static. They are non-overlapping and are contiguous intervals. Every ingested data can be (must be) bound to a singled window.

Sliding windows are also fixed sized and also static. Windows will overlap when the duration of the slide is smaller than the duration of the window. Ingested data can therefore be bound to two or more windows

Session windows are dynamic in size of the window length. The size depends on the ingested data. A session starts with an input and expands if the following input expands if the next ingested record has fallen within the gap duration.

For static window duration, a session window closes when there is no input received within gap duration. Both tumbling and sliding windows session uses session_window function.

Example of using dynamic session window with Python:

from pyspark.sql import functions as F

events = DataFrame { timestamp: Timestamp, userId: String, Value: Integer }

session_window = session_window(events.timestamp, \
    F.when(events.userId == "user1", "5 seconds") \
    .when(events.userId == "user2", "20 seconds").otherwise("5 minutes"))

# Group the data by session window and userId, and compute the count of each group
sessionizedCounts = events \
    .withWatermark("timestamp", "10 minutes") \
    .groupBy(
        session_window,
        events.userId) \
    .count()

In case of static window function, the session_window will not be defined. Example with Python:

sessionizedCounts = events \
    .withWatermark("timestamp", "10 minutes") \
    .groupBy(
        session_window(events.timestamp, "5 minutes"),
        events.userId) \
    .count()

Time windows functions are mandatory to be defined when there are ingest records with different durations or any kind of instability with ingest itself.

Tomorrow we will look into data manipulation and data engineering for Spark Streaming.

Compete set of code, documents, notebooks, and all of the materials will be available at the Github repository: https://github.com/tomaztk/Spark-for-data-engineers

Happy Spark Advent of 2021! 🙂