Creating Spark DataFrame

create_spark_df1.md

data = [
    ('1990-05-03', 29, True),
    ('1994-09-23', 25, False)
]

df = spark.createDataFrame(data, ['dob', 'age', 'is_fan'])
df.printSchema()

root
 |-- dob: string (nullable = true)
 |-- age: long (nullable = true)
 |-- is_fan: boolean (nullable = true)

df.show()

+----------+---+------+
|       dob|age|is_fan|
+----------+---+------+
|1990-05-03| 29|  true|
|1994-09-23| 25| false|
+----------+---+------+

create_spark_df2.py

data_list = [
    ('1990-05-03', 29, True),
    ('1994-09-23', 25, False)
]

data = [ {'dob': r[0], 'age': r[1], 'is_fan': r[2]} for r in data_list  ]

user_df = spark.createDataFrame(data)

user_df.show()