开始

from pyspark.sql import SparkSession

spark = SparkSession \
    .builder \
    .appName("Python Spark SQL basic example") \
    .config("spark.some.config.option", "some-value") \
    .getOrCreate()

创建DataFrame

# spark is an existing SparkSession
df = spark.read.json("/yx/people.json") 
# Displays the content of the DataFrame to stdout
df.show()
# +----+-------+
# | age|   name|
# +----+-------+
# |null|Michael|
# |  30|   Andy|
# |  19| Justin|
# +----+-------+

数据操作（类型化）

df.printSchema() #

'''
结果：
root
 |-- age: long (nullable = true)
 |-- name: string (nullable = true)
'''
df.select('name').show() #

'''
结果：
+-------+
|   name|
+-------+
|Michael|
|   Andy|
| Justin|
+-------+
'''

df.select(df['name'],df['age'] + 10).show()

'''
结果：
+-------+----------+
|   name|(age + 10)|
+-------+----------+
|Michael|      null|
|   Andy|        40|
| Justin|        29|
+-------+----------+
'''

sql化编程

df.createOrReplaceTempView('people') #创建一张临时表，只在当前会话生效
df.createGlobalTempView("people1") # 创建一张全局临时表，在所有会话中生效


sqlDF = spark.sql('select * from people')
sqlDF1 = spark.sql('select * from global_temp.people1')
sqlDF2 = spark.newSession().sql('select * from people')# 
sqlDF3 = spark.newSession().sql('select * from global_temp.people')# 成功
sqlDF.show()  #成功
sqlDF1.show() #成功
sqlDF2.show() #失败：'Table or view not found: people; line 1 pos 14'
sqlDF3.show() #成功
'''
结果：
+----+-------+
| age|   name|
+----+-------+
|null|Michael|
|  30|   Andy|
|  19| Justin|
+----+-------+
'''