PySpark - Union (combine two data frames)

from pyspark.sql import SparkSession
# Create a Spark session
spark = SparkSession.builder.appName("example").getOrCreate()
# Sample data for DataFrame 1
data1 = [("Alice", 25, "New York"),
("Bob", 30, "Los Angeles"),
("Charlie", 35, "Chicago")]

# Sample data for DataFrame 2
data2 = [("David", 40, "San Francisco"),
("Eve", 45, "Miami"),
("Frank", 50, "Seattle")]


# Create DataFrames
columns = ["Name", "Age", "City"]
df1 = spark.createDataFrame(data1, columns)
df2 = spark.createDataFrame(data2, columns)
# Show the DataFrames
df1.show()
df2.show()
# Perform a union operation
union_df = df1.union(df2)
# Show the result
union_df.show()