问AWS胶黏剂

EN

toFahrenheit = udf(lambda x: '-1' if x in not_found else x * 9 / 5 + 32, StringType())

weather_df.withColumn("new_tmax", toFahrenheit(weather_df["tmax"])).drop("tmax").withColumnRenamed("new_tmax","tmax")

IllegalArgumentException: u"requirement failed: The number of columns doesn't match.\nOld column names (11): station, name, latitude, longitude, elevation, date, awnd, prcp, snow, tmin, tmax\nNew column names (0): "

%pyspark
import sys
from pyspark.context import SparkContext
from awsglue.context import GlueContext
from awsglue.context import DynamicFrame
from awsglue.transforms import *
from awsglue.utils import getResolvedOptions
from awsglue.job import Job
from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.types import StringType

glueContext = GlueContext(SparkContext.getOrCreate())

weather_raw = glueContext.create_dynamic_frame.from_catalog(database = "ohare-airport-2006", table_name = "ohare_intl_airport_2006_08_climate_csv")
print "cpnt : ", weather_raw.count()
weather_raw.printSchema()
weather_raw.toDF().show(10)

#UDF to convert the air temperature from celsius to fahrenheit (For sample transformation)
#toFahrenheit = udf((lambda c: c[1:], c * 9 / 5 + 32)
toFahrenheit = udf(lambda x: '-1' if x in not_found_cat else x * 9 / 5 + 32, StringType())

#Apply the UDF to maximum and minimum air temperature
wthdf = weather_df.withColumn("new_tmin", toFahrenheit(weather_df["tmin"])).withColumn("new_tmax", toFahrenheit(weather_df["tmax"])).drop("tmax").drop("tmin").withColumnRenamed("new_tmax","tmax").withColumnRenamed("new_tmin","tmin")

wthdf.toDF().show(5)

 weather_df:
root
|-- station: string
|-- name: string
|-- latitude: double
|-- longitude: double
|-- elevation: double
|-- date: string
|-- awnd: double
|-- fmtm: string
|-- pgtm: string
|-- prcp: double
|-- snow: double
|-- snwd: long
|-- tavg: string
|-- tmax: long
|-- tmin: long

Traceback (most recent call last):
  File "/tmp/zeppelin_pyspark-3684249459612979499.py", line 349, in <module>
    raise Exception(traceback.format_exc())
Exception: Traceback (most recent call last):
  File "/tmp/zeppelin_pyspark-3684249459612979499.py", line 342, in <module>
    exec(code)
  File "<stdin>", line 3, in <module>
  File "/usr/lib/spark/python/pyspark/sql/dataframe.py", line 1558, in toDF
    jdf = self._jdf.toDF(self._jseq(cols))
  File "/usr/lib/spark/python/lib/py4j-0.10.4-src.zip/py4j/java_gateway.py", line 1133, in __call__
    answer, self.gateway_client, self.target_id, self.name)
  File "/usr/lib/spark/python/pyspark/sql/utils.py", line 79, in deco
    raise IllegalArgumentException(s.split(': ', 1)[1], stackTrace)
IllegalArgumentException: u"requirement failed: The number of columns doesn't match.\nOld column names (11): station, name, latitude, longitude, elevation, date, awnd, prcp, snow, tmin, tmax\nNew column names (0): "