我正在尝试从dstream中的json创建一个数据框,但是下面的代码似乎无法正确显示该数据框-
import sys
import json
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from pyspark.sql import SQLContext
def getSqlContextInstance(sparkContext):
if ('sqlContextSingletonInstance' not in globals()):
globals()['sqlContextSingletonInstance'] = SQLContext(sparkContext)
return globals()['sqlContextSingletonInstance']
if __name__ == "__main__":
if len(sys.argv) != 3:
raise IOError("Invalid usage; the correct format is:\nquadrant_count.py <hostname> <port>")
# Initialize a SparkContext with a name
spc = SparkContext(appName="jsonread")
sqlContext = SQLContext(spc)
# Create a StreamingContext with a batch interval of 2 seconds
stc = StreamingContext(spc, 2)
# Checkpointing feature
stc.checkpoint("checkpoint")
# Creating …
Run Code Online (Sandbox Code Playgroud)