Spark DataFrame API练习与功能介绍

1 DataFrame API练习

基于RDD创建

from pyspark.sql import SparkSession
from pyspark.sql import Row

spark = SparkSession.builder.appName('test').getOrCreate()
sc = spark.sparkContext
# spark.conf.set("spark.sql.shuffle.partitions", 6)
# ================直接创建==========================
l = [('Ankit',25),('Jalfaizy',22),('saurabh',20),('Bala',26)]
rdd = sc.parallelize(l)
#为数据添加列名
people = rdd.map(lambda x: Row(name=x[0], age=int(x[1])))
#创建DataFrame
schemaPeople = spark.createDataFrame(people)

从csv中读取数据

# ==================从csv读取======================
#加载csv类型的数据并转换为DataFrame
df = spark.read.format