Two ways to transform RDD to DataFrame in Spark

gistfile1.txt

1. Add schema after becoming DataFrame 

sqlCtx.inferSchema(rdd1)

1. Add schema after becoming DataFrame

from pyspark.sql import Row
import os

current_path = os.getcwd()

rdd = sc.textFile("current_path" + '//class.txt')

def transform(x):
    y = x.split()
    return str(y[0]), str(y[1]), int(y[2]), float(y[3]), float(y[4])


varnames = Row("name", "sex", "age", "height", "weight")


df = rdd.map(transform).map(lambda x: varnames(*x)).toDF()