Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
M
meta_base_code
Project
Project
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
宋柯
meta_base_code
Commits
b4f77d1a
Commit
b4f77d1a
authored
Sep 21, 2020
by
litaolemo
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update
parent
4bc5c3f0
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
16 additions
and
2 deletions
+16
-2
tractate_analysis_in_7000.py
task/tractate_analysis_in_7000.py
+16
-2
No files found.
task/tractate_analysis_in_7000.py
View file @
b4f77d1a
...
@@ -190,8 +190,9 @@ temp_null_count = 0
...
@@ -190,8 +190,9 @@ temp_null_count = 0
# 500: [0, 0, 0],
# 500: [0, 0, 0],
# 1000: [0, 0, 0],
# 1000: [0, 0, 0],
# }
# }
print
(
device_id_dict
)
for
redis_count
,
device_id
in
enumerate
(
device_id_dict
):
for
redis_count
,
device_id
in
enumerate
(
device_id_dict
):
# if redis_count >= 50:break
# if redis_count >= 50:break
second_demands
=
[]
second_demands
=
[]
projects
=
[]
projects
=
[]
...
@@ -262,7 +263,7 @@ exposure_sql = """
...
@@ -262,7 +263,7 @@ exposure_sql = """
print
(
exposure_sql
)
print
(
exposure_sql
)
exposure_df
=
spark
.
sql
(
exposure_sql
)
exposure_df
=
spark
.
sql
(
exposure_sql
)
exposure_df
.
createOrReplaceTempView
(
"exposure_df"
)
#
exposure_df.createOrReplaceTempView("exposure_df")
exposure_df
.
show
(
1
)
exposure_df
.
show
(
1
)
sql_res
=
exposure_df
.
collect
()
sql_res
=
exposure_df
.
collect
()
session_pv_all
=
0
session_pv_all
=
0
...
@@ -276,6 +277,7 @@ baoguang_dict = {}
...
@@ -276,6 +277,7 @@ baoguang_dict = {}
# 找出card_id 对应帖子的标签 并分类汇总 得到 标签-计数字段
# 找出card_id 对应帖子的标签 并分类汇总 得到 标签-计数字段
for
res
in
sql_res
:
for
res
in
sql_res
:
# partition_date = res.partition_date
# partition_date = res.partition_date
print
(
res
)
cl_id
=
res
.
cl_id
cl_id
=
res
.
cl_id
if
cl_id
in
device_id_dict
:
if
cl_id
in
device_id_dict
:
card_id
=
res
.
card_id
card_id
=
res
.
card_id
...
@@ -313,3 +315,14 @@ for tag_id in second_demands_id_count:
...
@@ -313,3 +315,14 @@ for tag_id in second_demands_id_count:
# "session_pv_count": len(set(second_demands_id_count[tag_id]))
# "session_pv_count": len(set(second_demands_id_count[tag_id]))
}
}
print
(
temp_dict
)
print
(
temp_dict
)
for
tag_id
in
projects_demands_id_count
:
temp_dict
=
{
"tag_name"
:
tag_id
,
"device_count"
:
projects_demands_tag_count
[
tag_id
],
"tractate_count"
:
tags_v3_count_dict
.
get
(
tag_id
),
"exporsure_count"
:
len
(
set
(
projects_demands_id_count
[
tag_id
])),
# "session_pv_count": len(set(second_demands_id_count[tag_id]))
}
print
(
temp_dict
)
\ No newline at end of file
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