dwd_amazon_report.py
3.43 KB
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
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
class DwdAmazonReport(Templates):
def __init__(self, site_name='us', date_type="month", date_info='2021-10'):
super().__init__()
self.site_name = site_name
self.date_type = date_type
self.date_info = date_info
self.db_save = f'dwd_amazon_report'
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_buy_data = self.spark.sql(f"select 1+1;")
self.df_st_count = self.spark.sql(f"select 1+1;")
self.df_save = self.spark.sql(f"select 1+1;")
def read_data(self):
# 读取asin的月销数据
sql1 = f"""
select
asin,
asin_amazon_orders as monthly_sales
from
dim_asin_amorders_info
where
site_name = '{self.site_name}'
and date_type = '{self.date_type}'
and date_info = '{self.date_info}';
"""
print(sql1)
self.df_buy_data = self.spark.sql(sqlQuery=sql1).repartition(15, 'asin').cache()
self.df_buy_data.show(10, truncate=True)
sql2 = f"""
select
asin,
asin_zr_counts as zr_count,
asin_sp_counts as sp_count,
asin_st_counts as total_count
from
dwd_asin_measure
where
site_name = '{self.site_name}'
and date_type = '{self.date_type}'
and date_info = '{self.date_info}';
"""
print(sql2)
self.df_st_count = self.spark.sql(sqlQuery=sql2).repartition(15, 'asin').cache()
self.df_st_count.show(10, truncate=True)
def handle_data(self):
hdfs_path = f"/home/{SparkUtil.DEF_USE_DB}/dwd/{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)
self.df_save = self.df_buy_data.join(
self.df_st_count, on='asin', how='full'
)
columns = self.df_save.columns
for col_name in columns:
self.df_save = self.df_save.withColumn(
col_name, self.df_save[col_name].cast('string')
)
self.df_save = self.df_save.fillna('-1')
self.df_save = self.df_save.withColumn(
"weekly_sales", F.lit(None)
).withColumn(
"weekly_views", F.lit(None)
).withColumn(
"monthly_views", F.lit(None)
).withColumn(
"site_name", F.lit(self.site_name)
).withColumn(
"date_type", F.lit(self.date_type)
).withColumn(
"date_info", F.lit(self.date_info)
)
if __name__ == '__main__':
site_name = sys.argv[1]
date_type = sys.argv[2]
date_info = sys.argv[3]
if (site_name in ['us', 'uk', 'de']) and (date_type == 'month') and (date_info >= '2024-04'):
handle_obj = DwdAmazonReport(site_name=site_name, date_type=date_type, date_info=date_info)
handle_obj.run()
else:
print("暂不计算该维度数据！")
quit()