data = [
("John","Doe",28,45000,1,0,1),
("Jane","Doe",26,52000,1,1,1),
("Matt","Anderson",34,62000,1,0,0),
("Ashley","James",30,58000,1,1,0),
("Amber","Murray",24,48000,1,0,0)
]
schema = StructType([
StructField("FirstName",StringType(),True),
StructField("LastName",StringType(),True),
StructField("Age",IntegerType(),True),
StructField("Salary", IntegerType(), True),
StructField("Checking", IntegerType(), True),
StructField("Savings", IntegerType(), True),
StructField("CreditCard", IntegerType(), True)
])
df = spark.createDataFrame(data=data, schema=schema)
df.show()
|