sparksql

上传文件到hdfs：

hadoop fs -put /root/people.json /

/root/people.json：本地路径

/：hdfs路径

from pyspark.sql import SparkSession
spark = SparkSession \
    .builder \
    .appName("Python Spark SQL basic example") \
    .config("spark.some.config.option", "some-value") \
    .getOrCreate()
------------------
df = spark.read.json("/people.json")
df.show()

df.printSchema()
df.select("name").show()

df.select(df['name'], df['age'] + 1).show()

df.filter(df['age'] > 21).show()

df.groupBy("age").count().show()
--------------------------------

df.createOrReplaceTempView("people")

sqlDF = spark.sql("SELECT * FROM people")
sqlDF.show()