Skip to content
Projects
Groups
Snippets
Help
This project
Loading...
Sign in / Register
Toggle navigation
A
Amazon-Selection-Data
Overview
Overview
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
abel_cjy
Amazon-Selection-Data
Commits
fec40875
Commit
fec40875
authored
Feb 06, 2026
by
fangxingjun
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
no message
parent
c023bddc
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
15 additions
and
0 deletions
+15
-0
dwd_nsr_bsr_keepa_asin.py
Pyspark_job/dwd/dwd_nsr_bsr_keepa_asin.py
+15
-0
No files found.
Pyspark_job/dwd/dwd_nsr_bsr_keepa_asin.py
View file @
fec40875
...
@@ -104,6 +104,21 @@ class DwdNsrBsrKeepaAsin(Templates):
...
@@ -104,6 +104,21 @@ class DwdNsrBsrKeepaAsin(Templates):
df_result
.
show
(
10
,
truncate
=
False
)
df_result
.
show
(
10
,
truncate
=
False
)
df_result
.
groupBy
(
"asin_cate_flag"
)
.
count
()
.
orderBy
(
"count"
,
ascending
=
False
)
.
show
(
truncate
=
False
)
df_result
.
groupBy
(
"asin_cate_flag"
)
.
count
()
.
orderBy
(
"count"
,
ascending
=
False
)
.
show
(
truncate
=
False
)
self
.
df_save_asin_cate
=
df_result
self
.
df_save_asin_cate
=
df_result
df_bsr_agg
=
self
.
df_asin_bsr
.
groupBy
([
'asin'
])
.
agg
(
F
.
max
(
"date_info"
)
.
alias
(
"bsr_latest_date"
),
# F.count("date_info").alias("bsr_30day_count"),
F
.
countDistinct
(
"date_info"
)
.
alias
(
"bsr_30day_count"
),
)
df_nsr_agg
=
self
.
df_asin_nsr
.
groupBy
([
'asin'
])
.
agg
(
F
.
max
(
"date_info"
)
.
alias
(
"nsr_latest_date"
),
# F.count("date_info").alias("nsr_30day_count"),
F
.
countDistinct
(
"date_info"
)
.
alias
(
"nsr_30day_count"
),
)
self
.
df_save_asin_cate
=
self
.
df_save_asin_cate
.
join
(
df_bsr_agg
,
on
=
[
'asin'
],
how
=
'left'
)
.
join
(
df_nsr_agg
,
on
=
[
'asin'
],
how
=
'left'
)
self
.
df_save_asin_cate
=
self
.
df_save_asin_cate
.
withColumn
(
"site_name"
,
F
.
lit
(
self
.
site_name
))
self
.
df_save_asin_cate
=
self
.
df_save_asin_cate
.
withColumn
(
"site_name"
,
F
.
lit
(
self
.
site_name
))
self
.
df_save_asin_cate
.
show
(
10
,
truncate
=
False
)
self
.
df_save_asin_cate
.
show
(
10
,
truncate
=
False
)
self
.
save_data_common
(
self
.
save_data_common
(
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment