1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
import os
import sys
sys.path.append(os.path.dirname(sys.path[0])) # 上级目录
from utils.hdfs_utils import HdfsUtils
from utils.spark_util import SparkUtil
from utils.templates import Templates
from pyspark.sql import functions as F, Window
class DwtTitleMatchingDegree(Templates):
def __init__(self, site_name='us', date_type="month", date_info='2023-01'):
super().__init__()
self.site_name = site_name
self.date_type = date_type
self.date_info = date_info
self.db_save = f'dwt_title_matching_degree'
self.spark = self.create_spark_object(
app_name=f"{self.db_save}: {self.site_name}, {self.date_type}, {self.date_info}")
self.reset_partitions(partitions_num=5)
self.partitions_by = ['site_name', 'date_type', 'date_info']
self.df_dwd = self.spark.sql(f"select 1+1;")
self.df_save = self.spark.sql(f"select 1+1;")
def read_data(self):
# 读取dwd_title_matching_degree
sql = f"""
select
asin,
asin_title,
search_term,
contains_flag
from
dwd_title_matching_degree
where
site_name = '{self.site_name}'
and date_type = '{self.date_type}'
and date_info = '{self.date_info}';
"""
print(sql)
self.df_dwd = self.spark.sql(sqlQuery=sql).cache()
def handle_data(self):
hdfs_path = f"/home/{SparkUtil.DEF_USE_DB}/dwt/{self.db_save}/site_name={self.site_name}/date_type={self.date_type}/date_info={self.date_info}"
print(f"清除hdfs目录中.....{hdfs_path}")
HdfsUtils.delete_hdfs_file(hdfs_path)
# 按照asin分区统计asin的数量
window = Window.partitionBy("asin")
self.df_dwd = self.df_dwd.withColumn("asin_count", F.count("asin").over(window))
# 统计每个asin中，flag为1的数量
self.df_dwd = self.df_dwd.withColumn("contains_count", F.sum("contains_flag").over(window))
self.df_dwd = self.df_dwd.withColumn("proportion", F.round(F.col("contains_count") / F.col("asin_count"), 4))
self.df_dwd = self.df_dwd.withColumn("site_name", F.lit(self.site_name))
self.df_dwd = self.df_dwd.withColumn("date_type", F.lit(self.date_type))
self.df_dwd = self.df_dwd.withColumn("date_info", F.lit(self.date_info))
self.df_save = self.df_dwd
if __name__ == '__main__':
site_name = sys.argv[1]
date_type = sys.argv[2]
date_info = sys.argv[3]
handle_obj = DwtTitleMatchingDegree(site_name=site_name, date_type=date_type, date_info=date_info)
handle_obj.run()