Commit 45302231 authored by 张彦钊's avatar 张彦钊

add

parent 42843dd9
...@@ -15,6 +15,14 @@ def position(x,y): ...@@ -15,6 +15,14 @@ def position(x,y):
sum = sum + 1 sum = sum + 1
return sum return sum
def cpc(x,y):
sum = 0
for i in x:
if int(i['absolute_position']) <= y and i["is_cpc"] == 1:
sum = sum + 1
return sum
if __name__ == '__main__': if __name__ == '__main__':
sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \ sparkConf = SparkConf().set("spark.hive.mapred.supports.subdirectories", "true") \
...@@ -32,8 +40,16 @@ if __name__ == '__main__': ...@@ -32,8 +40,16 @@ if __name__ == '__main__':
df = spark.sql(sql) df = spark.sql(sql)
# # df.show(6) # # df.show(6)
# # params['exposure_cards'], # # params['exposure_cards'],
df.persist()
rdd = df.rdd.map(lambda x:("a",position(eval(x[0]),10))).reduceByKey(lambda x,y:x+y).map(lambda x:x[1]) rdd = df.rdd.map(lambda x:("a",position(eval(x[0]),10))).reduceByKey(lambda x,y:x+y).map(lambda x:x[1])
print(rdd.collect()) print("<=10")
print(rdd.collect()[0])
rdd = df.rdd.map(lambda x: ("a", cpc(eval(x[0]), 10))).reduceByKey(lambda x, y: x + y).map(lambda x: x[1])
print("<=10 cpc ==1 ")
print(rdd.collect()[0])
df.unpersist()
......
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