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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
"""
计算买家搜索词
"""
import os
import sys
sys.path.append(os.path.dirname(sys.path[0])) # 上级目录
from utils.templates import Templates
from utils.spark_util import SparkUtil
from pyspark.sql.window import Window
from pyspark.sql import functions as F
from utils.common_util import CommonUtil
from utils.DorisHelper import DorisHelper
class DwdBuyerSt(Templates):
def __init__(self, site_name='us', date_type="month", date_info='2022-1'):
super().__init__()
self.site_name = site_name
self.date_type = date_type
self.date_info = date_info
self.db_save = f'dwd_buyer_st'
self.start_day = ''
self.end_day = ''
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=10)
self.partitions_by = ['site_name', 'date_type', 'date_info']
self.get_date_info()
self.df_search_for_buyer_term = self.spark.sql(f"select 1+1;")
self.df_positioning_for_buyer_term = self.spark.sql(f"select 1+1;")
self.site_dict = {
"us": 3,
"uk": 4,
"de": 6,
"fr": 1,
"es": 7,
"it": 8
}
def get_date_info(self):
df_date = self.spark.sql(f"select * from dim_date_20_to_30;")
df = df_date.toPandas()
if self.date_type == 'week':
df_week_start_day = df.loc[(df.year_week == f'{self.date_info}') & (df.week_day == 1)]
self.start_day = str(list(df_week_start_day.date)[0]).replace("-", "")
df_week_end_day = df.loc[(df.year_week == f'{self.date_info}') & (df.week_day == 7)]
self.end_day = str(list(df_week_end_day.date)[0]).replace("-", "")
def read_data(self):
# 1.读取搜索词买家词信息
sql = f"""
SELECT replace(replace(replace(customerSearchText, '\\t', ' '), '\\n', ' '), '\\001', ' ') as search_term, attributedSales7d as sales,
attributedConversions7d as orders, clicks, startDate as report_date
from advertising_manager.customer_search_report where site={self.site_dict[f'{self.site_name}']} and LENGTH(customerSearchText) <100
and startDate >= '{self.start_day}' and startDate <= '{self.end_day}'
and customerSearchText is not null and trim(customerSearchText) != ''
"""
print("sql = " + sql)
self.df_search_for_buyer_term = DorisHelper.spark_import_with_sql(session=self.spark, query=sql, use_type='adv')
# 2.读取定位买家词
sql = f"""
SELECT replace(replace(replace(`query`, '\\t', ' '), '\\n', ' '), '\\001', ' ') as search_term, attributedSales7d as sales,
attributedConversions7d as orders, clicks, startDate as report_date
from advertising_manager.customer_search_target_report where site={self.site_dict[f'{self.site_name}']} and targetingExpression
in('close-match','loose-match') and LENGTH(query) >10 and LENGTH(query) < 100 and
startDate >= '{self.start_day}' and startDate <= '{self.end_day}'
and `query` is not null and trim(`query`) != ''
"""
print("sql = " + sql)
self.df_positioning_for_buyer_term = DorisHelper.spark_import_with_sql(session=self.spark, query=sql, use_type='adv')
def handle_data(self):
df_all_search_term = self.df_search_for_buyer_term.unionByName(
self.df_positioning_for_buyer_term)
window = Window.partitionBy(['search_term', 'report_date']).orderBy(
df_all_search_term.orders.desc()
)
df_all_search_term = df_all_search_term.withColumn("st_rank", F.row_number().over(window=window))
self.df_save = df_all_search_term.filter("st_rank = 1")
self.df_save = self.df_save.select("search_term", F.col("sales").cast("double").alias("sales"),
"orders", "clicks", "report_date")
self.df_save = self.df_save.withColumn("created_time",
F.date_format(F.current_timestamp(), 'yyyy-MM-dd HH:mm:SS')). \
withColumn("updated_time", F.date_format(F.current_timestamp(), 'yyyy-MM-dd HH:mm:SS'))
self.df_save = self.df_save.withColumn("string_field1", F.lit("null"))
self.df_save = self.df_save.withColumn("string_field2", F.lit("null"))
self.df_save = self.df_save.withColumn("string_field3", F.lit("null"))
self.df_save = self.df_save.withColumn("int_field1", F.lit(0))
self.df_save = self.df_save.withColumn("int_field2", F.lit(0))
self.df_save = self.df_save.withColumn("int_field3", F.lit(0))
self.df_save = self.df_save.withColumn("site_name", F.lit(self.site_name))
self.df_save = self.df_save.withColumn("date_type", F.lit(self.date_type))
self.df_save = self.df_save.withColumn("date_info", F.lit(self.date_info))
if __name__ == '__main__':
site_name = sys.argv[1] # 参数1：站点
date_type = sys.argv[2] # 参数2：类型：week/4_week/month/quarter
date_info = sys.argv[3] # 参数3：年-周/年-月/年-季, 比如: 2022-1
handle_obj = DwdBuyerSt(site_name=site_name, date_type=date_type, date_info=date_info)
handle_obj.run()
cmd = f"""
set mapred.output.compress=true;
set hive.exec.compress.output=true;
set mapred.output.compression.codec=com.hadoop.compression.lzo.LzopCodec;
insert overwrite table big_data_selection.dwd_buyer_st partition(site_name="{site_name}", date_type="{date_type}", date_info="{date_info}") select search_term, sales, orders, clicks, report_date, created_time, updated_time, string_field1, string_field2, string_field3, int_field1, int_field2, int_field3 from big_data_selection.dwd_buyer_st where site_name="{site_name}" and date_type="{date_type}" and date_info="{date_info}" and report_date is not null;
msck repair table big_data_selection.dwd_buyer_st;
"""
print("cmd=", cmd)
CommonUtil.hive_cmd_exec(cmd)