Commit 88c19ef1 authored by 张彦钊's avatar 张彦钊

change test file

parent ea33c974
......@@ -147,13 +147,13 @@ if __name__ == '__main__':
# validate_date, value_map, app_list_map = feature()
# get_predict(validate_date, value_map, app_list_map)
spark = SparkSession.builder.getOrCreate()
b = [("a", 1), ("a", 1), ("b", 3), ("a", 2)]
rdd = spark.sparkContext.parallelize(b)
df = spark.createDataFrame(rdd).toDF("id","n")
df.show()
t = df.select("id").rdd.map(lambda x:x[0]).collect()
print(t)
from hdfs import *
client = Client("hdfs://172.16.32.4:8020")
path = "/strategy/esmm/tr"
for root, dir, files in client.walk(path):
for file in files:
if file[:4] == "part":
print(file)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment