def _task_run(self):
super(_InlineSparkTask, self)._task_run()
if self._get_spark_ctrl().stop_spark_session_on_finish:
session = get_spark_session()
logger.info("Stopping spark session: %s")
session.stop()
def word_count_inline(text=parameter.data.txt[spark.DataFrame],
counters=output.txt.data):
# type: (spark.DataFrame, PathStr) -> spark.DataFrame
from operator import add
from dbnd._core.commands import get_spark_session
lines = text.rdd.map(lambda r: r[0])
counts = (lines.flatMap(lambda x: x.split(" ")).map(
lambda x: (x, 1)).reduceByKey(add))
counts.saveAsTextFile(str(counters))
df = get_spark_session().createDataFrame(counts)
output = counts.collect()
for (word, count) in output:
print("%s: %i" % (word, count))
return df
def target_to_value(self, target, **kwargs):
path = _target_to_path(target)
schema = kwargs["schema"] if "schema" in kwargs else None
return (get_spark_session().read.format(
self.file_format).options(**kwargs).load(path, schema=schema))
