在 Amazon Redshift 中讀取和寫入

下列程式碼範例用 PySpark 於透過資料來源 API 和 SparkSQL，從 Amazon Redshift 資料庫讀取和寫入範例資料。

Data source API

用 PySpark 於使用資料來源 API 從 Amazon Redshift 資料庫讀取和寫入範例資料。

import boto3
from pyspark.sql import SQLContext

sc = # existing SparkContext
sql_context = SQLContext(sc)

url = "jdbc:redshift:iam://redshifthost:5439/database"
aws_iam_role_arn = "arn:aws:iam::accountID:role/roleName"

df = sql_context.read \
    .format("io.github.spark_redshift_community.spark.redshift") \
    .option("url", url) \
    .option("dbtable", "tableName") \
    .option("tempdir", "s3://path/for/temp/data") \
    .option("aws_iam_role", "aws_iam_role_arn") \
    .load()

df.write \
    .format("io.github.spark_redshift_community.spark.redshift") \
    .option("url", url) \
    .option("dbtable", "tableName_copy") \
    .option("tempdir", "s3://path/for/temp/data") \
    .option("aws_iam_role", "aws_iam_role_arn") \
    .mode("error") \
    .save()

SparkSQL

用於 PySpark 使用 SparkSQL 從 Amazon Redshift 資料庫讀取和寫入範例資料。

import boto3
import json
import sys
import os
from pyspark.sql import SparkSession

spark = SparkSession \
    .builder \
    .enableHiveSupport() \
    .getOrCreate()
    
url = "jdbc:redshift:iam://redshifthost:5439/database"
aws_iam_role_arn = "arn:aws:iam::accountID:role/roleName"
    
bucket = "s3://path/for/temp/data"
tableName = "tableName" # Redshift table name

s = f"""CREATE TABLE IF NOT EXISTS {tableName} (country string, data string) 
    USING io.github.spark_redshift_community.spark.redshift 
    OPTIONS (dbtable '{tableName}', tempdir '{bucket}', url '{url}', aws_iam_role '{aws_iam_role_arn}' ); """

spark.sql(s)
         
columns = ["country" ,"data"]
data = [("test-country","test-data")]
df = spark.sparkContext.parallelize(data).toDF(columns)

# Insert data into table
df.write.insertInto(tableName, overwrite=False)
df = spark.sql(f"SELECT * FROM {tableName}")
df.show()