/** * Read a text file from HDFS, a local file system (available on all nodes), or any * Hadoop-supported file system URI, and return it as an RDD of Strings. */ def textFile( path: String, minPartitions: Int = defaultMinPartitions): RDD[String] = wi
#_*_coding:utf-8_*_ # spark读取csv文件 #指定schema: schema = StructType([ # true代表不为null StructField("column_1", StringType(), True), # nullable=True, this field can not be null StructField("column_2", StringType(), True), StructField("