PySpark でタイムスタンプを UTC から JST に変換する例。
# 文字列をタイムスタンプ型に変換 df = df.withColumn("timestamp", col("timestamp").cast("Timestamp")) # UTC から JST に変換 df = df.withColumn("timestamp", from_utc_timestamp(col("timestamp"),"Asia/Tokyo")) # タイムスタンプ型から文字列型に変換 df = df.withColumn("timestamp", date_format(col("timestamp"), 'yyyy-MM-dd HH:mm:ss.S'))
コードサンプル
- AWS Glue PySpark のコードサンプル
import sys from awsglue.transforms import * from awsglue.utils import getResolvedOptions from pyspark.context import SparkContext from awsglue.context import GlueContext from awsglue.job import Job from pyspark.sql.functions import from_utc_timestamp from awsglue.dynamicframe import DynamicFrame from pyspark.sql.functions import col from pyspark.sql.functions import * from pyspark.sql.functions import date_format ## @params: [JOB_NAME] args = getResolvedOptions(sys.argv, ['JOB_NAME']) sc = SparkContext() glueContext = GlueContext(sc) spark = glueContext.spark_session job = Job(glueContext) job.init(args['JOB_NAME'], args) ## @type: DataSource ## @args: [database = "default", table_name = "timestamp_test", transformation_ctx = "datasource0"] ## @return: datasource0 ## @inputs: [] datasource0 = glueContext.create_dynamic_frame.from_catalog(database = "default", table_name = "timestamp_test", transformation_ctx = "datasource0") ## @type: ApplyMapping ## @args: [mapping = [("timestamp", "string", "timestamp", "string"), ("col2", "string", "col2", "string"), ("col3", "string", "col3", "string"), ("col4", "string", "col4", "string")], transformation_ctx = "applymapping1"] ## @return: applymapping1 ## @inputs: [frame = datasource0] applymapping1 = ApplyMapping.apply(frame = datasource0, mappings = [("timestamp", "string", "timestamp", "string"), ("col2", "string", "col2", "string"), ("col3", "string", "col3", "string"), ("col4", "string", "col4", "string")], transformation_ctx = "applymapping1") df = DynamicFrame.toDF(applymapping1) df = df.withColumn("timestamp", col("timestamp").cast("Timestamp")) df = df.withColumn("timestamp", from_utc_timestamp(col("timestamp"),"Asia/Tokyo")) df = df.withColumn("timestamp", date_format(col("timestamp"), 'yyyy-MM-dd HH:mm:ss.S')) result = DynamicFrame.fromDF(df, glueContext, "result") result = DynamicFrame.fromDF(df, glueContext, "result") ## @type: DataSink ## @args: [connection_type = "s3", connection_options = {"path": "s3://dl-sfdc-dm/test/timestamp_test"}, format = "csv", transformation_ctx = "datasink2"] ## @return: datasink2 ## @inputs: [frame = applymapping1] datasink2 = glueContext.write_dynamic_frame.from_options(frame = result, connection_type = "s3", connection_options = {"path": "s3://dl-sfdc-dm/test/timestamp_test"}, format = "csv", transformation_ctx = "datasink2") job.commit()
"2021-05-07T04:59:43.000+0000","line1","line1","line1" "2021-05-07T05:59:43.000+0000","line2","line2","line2" "2021-05-07T06:59:43.000+0000","line3","line3","line3" "2021-05-07T07:59:43.000+0000","line4","line4","line4" "2021-05-07T08:59:43.000+0000","line5","line5","line5"
参考
UTCが入っているデータに対してJSTの列を追加してJSTの時間に変換してみます。
from pyspark.sql.functions import from_utc_timestamp df = spark.createDataFrame([ (1, "2020-12-19 00:00:00"), (2, "2020-12-19 20:00:00") ], ["id", "UTC"]) df = df.withColumn("UTC", col("UTC").cast("Timestamp")) df = df.withColumn("JST", from_utc_timestamp(col("UTC"),"Asia/Tokyo")) df.show()JSTの列が +9 されていることが分かります。
+---+-------------------+-------------------+ | id| UTC| JST| +---+-------------------+-------------------+ | 1|2020-12-19 00:00:00|2020-12-19 09:00:00| | 2|2020-12-19 20:00:00|2020-12-20 05:00:00| +---+-------------------+-------------------+PySparkでUTCで入っている時刻をJSTに変換する | Simple is Beautiful.