Commit 67921e0f authored by 张彦钊's avatar 张彦钊

change

parent 7cf96872
...@@ -127,7 +127,7 @@ if __name__ == '__main__': ...@@ -127,7 +127,7 @@ if __name__ == '__main__':
spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate() spark = SparkSession.builder.config(conf=sparkConf).enableHiveSupport().getOrCreate()
clicks = [] clicks = []
cpcs = [] cpcs = []
for i in range(1,3): for i in range(1,26):
clicks.append(all_click(i)) clicks.append(all_click(i))
cpcs.append(cpc_click(i)) cpcs.append(cpc_click(i))
print("clicks") print("clicks")
...@@ -135,13 +135,13 @@ if __name__ == '__main__': ...@@ -135,13 +135,13 @@ if __name__ == '__main__':
print("cpcs") print("cpcs")
print(cpcs) print(cpcs)
rdd = spark.sparkContext.parallelize(cpcs) # rdd = spark.sparkContext.parallelize(cpcs)
df = spark.createDataFrame(rdd).toDF.toPandas() # df = spark.createDataFrame(rdd).toDF.toPandas()
df.to_csv('/home/gmuser/cpc.csv',index=False) # df.to_csv('/home/gmuser/cpc.csv',index=False)
#
rdd = spark.sparkContext.parallelize(clicks) # rdd = spark.sparkContext.parallelize(clicks)
df = spark.createDataFrame(rdd).toDF.toPandas() # df = spark.createDataFrame(rdd).toDF.toPandas()
df.to_csv('/home/gmuser/clicks.csv', index=False) # df.to_csv('/home/gmuser/clicks.csv', index=False)
spark.stop() spark.stop()
......
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