Add: Comprehensive window functions guide with examples

pyspark_window_functions_complete_guide.py

@@ -0,0 +1,54 @@
+"""
+PySpark Window Functions - Complete Guide
+Author: Sharukh Malik
+Description: Comprehensive examples of window functions in PySpark
+"""
+
+from pyspark.sql import SparkSession
+from pyspark.sql.window import Window
+from pyspark.sql import functions as F
+
+
+
+# Create Spark session
+spark = SparkSession.builder.appName("WindowFunctionExample").getOrCreate()
+
+# Sample data
+data = [
+    ("Sales", "John", 5000, "2024-01"),
+    ("Sales", "Jane", 6000, "2024-01"),
+    ("Sales", "John", 5500, "2024-02"),
+    ("IT", "Bob", 7000, "2024-01"),
+    ("IT", "Alice", 7500, "2024-01"),
+]
+
+
+df = spark.createDataFrame(data,["Department","Employee","Salary","Month"])
+
+
+df.show()
+
+
+# Example 1: Rank by salary within each department
+window_spec = Window.partitionBy("Department").orderBy(F.desc("Salary"))
+df_ranked = df.withColumn("Rank", F.rank().over(window_spec))
+df_ranked.show()
+
+
+# Example 2: Running total
+
+window_running = Window.partitionBy("Department").orderBy("month").rowsBetween(Window.unboundedPreceding,Window.currentRow)
+df_running = df.withColumn("Running_Total",F.sum("Salary").over(window_running))
+df_running.show()
+
+
+# Example 3: Lead and Lag
+window_order = Window.partitionBy("Employee").orderBy("Month")
+df_lead_lag = df.withColumn("Previous_Salary", F.lag("Salary", 1).over(window_order)) \
+                .withColumn("Next_Salary", F.lead("Salary", 1).over(window_order))
+df_lead_lag.show()
+
+
+# Example 4: Percent rank
+df_percent = df.withColumn("Percent_Rank", F.percent_rank().over(window_spec))
+df_percent.show()