Notebook Docker 安装spark环境

from pyspark import SparkContext     
from pyspark.sql import SparkSession 
from pyspark.sql.types import StructType, StructField, LongType, StringType
from pyspark.sql import Row
from pyspark.sql import Column
import pandas as pd
import numpy as np

spark=SparkSession .builder .appName(‘newapp‘) .getOrCreate()

stringCSVRDD = spark.sparkContext.parallelize([
                    (123, "Katie", 19, "brown"),
                    (456, "Michael", 22, "green"),
                    (789, "Simone", 23, "blue")])
schema = StructType([StructField("id", LongType(), True),
                        StructField("name", StringType(), True),
                        StructField("age", LongType(), True),
                        StructField("eyeColor", StringType(), True)])
swimmers = spark.createDataFrame(stringCSVRDD,schema)
swimmers.registerTempTable("swimmers")
# 使用Sql语句
data=spark.sql("select * from swimmers")
# 将数据转换List，这样就可以查看dataframe的数据元素的样式
print(data.collect())
# 以表格形式展示数据
data.show()