xxxxxxxxxx
from pyspark.sql import SparkSession
# Create SparkSession
spark = SparkSession.builder.getOrCreate()
# Read existing data into DataFrame
df = spark.read.csv("path/to/input.csv", header=True, inferSchema=True)
# Add a new column named "new_column" with default values
df = df.withColumn("new_column", lit("default_value"))
# Alternatively, add a new column based on some transformation
df = df.withColumn("new_column", col("existing_column") + 1)
# View the updated DataFrame
df.show()