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
import os
import sys
sys.path.append(os.path.dirname(sys.path[0])) # 上级目录
from utils.templates import Templates
# from ..utils.templates import Templates
from pyspark.sql import functions as F
class DwdStInfoDay(Templates):
def __init__(self, site_name='us', date_type="month", date_info='2022-1'):
super(DwdStInfoDay, self).__init__()
self.site_name = site_name
self.date_type = date_type
self.date_info = date_info
self.db_save = f'dwd_st_info_day_word'
self.spark = self.create_spark_object(app_name=f"{self.db_save}: {self.site_name}, {self.date_info}")
self.df_date = self.get_year_week_tuple()
self.df_save = self.spark.sql(f"select 1+1;")
self.df_brand_day = self.spark.sql(f"select 1+1;")
self.df_rank_repeat = self.spark.sql(f"select 1+1;")
self.partitions_by = ['site_name']
self.reset_partitions(partitions_num=5)
def read_data(self):
sql = f"select year, month, search_term, rank, report_date from ods_brand_analytics_day where site_name='{self.site_name}' " \
f"and dm in ('2021-9', '2021-10', '2021-11', '2021-12', '2022-1', '2022-2', '2022-3', '2022-4', '2022-5', '2022-6', '2022-7', '2022-8')"
self.df_brand_day = self.spark.sql(sqlQuery=sql)
self.df_brand_day = self.df_brand_day.withColumn("st_word", F.explode(F.split(self.df_brand_day.search_term, " ")))
print(self.df_brand_day.count())
quit()
self.df_brand_day = self.df_brand_day.groupby(['st_word']).count()
self.df_brand_day = self.df_brand_day.withColumnRenamed("count", "st_word_counts")
self.df_brand_day = self.df_brand_day.orderBy('st_word_counts', ascending=False)
self.df_brand_day = self.df_brand_day.withColumn('site_name', F.lit(self.site_name))
self.df_brand_day.show(20, truncate=False)
self.df_save = self.df_brand_day
if __name__ == '__main__':
handle_obj = DwdStInfoDay()
handle_obj.run()