from pyspark.sql.functions import col @time_decorator def no_broadcast_var(data): # Create small dataframe small_data = [("CA", "California"), ("TX", "Texas"), ("FL", "Florida")] small_df = spark.createDataFrame(small_data, ["state", "stateLF"]) # Perform joining result_no_broadcast = data.join(small_df, "state") return result_no_broadcast.count() display(no_broadcast_var(df))