Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
F
ffm-baseline
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
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
ML
ffm-baseline
Commits
91a4256d
Commit
91a4256d
authored
Apr 12, 2019
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
esmm 测试项目增加知识图谱特征
parent
25c95f53
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
8 additions
and
3 deletions
+8
-3
feature.py
tensnsorflow/es/feature.py
+8
-3
No files found.
tensnsorflow/es/feature.py
View file @
91a4256d
...
...
@@ -41,21 +41,26 @@ def get_data():
print
(
start
)
db
=
pymysql
.
connect
(
host
=
'10.66.157.22'
,
port
=
4000
,
user
=
'root'
,
passwd
=
'3SYz54LS9#^9sBvC'
,
db
=
'jerry_test'
)
sql
=
"select e.y,e.z,e.stat_date,e.ucity_id,feat.level2_ids,e.ccity_name,u.device_type,u.manufacturer,"
\
"u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids "
\
"u.channel,c.top,e.device_id,cut.time,dl.app_list,e.diary_service_id,feat.level3_ids,"
\
"k.treatment_method,k.price_min,k.price_max,k.treatment_time,k.maintain_time,k.recover_time "
\
"from {} e left join user_feature u on e.device_id = u.device_id "
\
"left join cid_type_top c on e.device_id = c.device_id "
\
"left join cid_time_cut cut on e.cid_id = cut.cid "
\
"left join device_app_list dl on e.device_id = dl.device_id "
\
"left join diary_feat feat on e.cid_id = feat.diary_id "
\
"left join train_Knowledge_network_data k on SUBSTRING_INDEX(feat.level2_ids,"
,
",1) = k.level2_id "
\
"where e.stat_date >= '{}'"
.
format
(
train_data_set
,
start
)
df
=
con_sql
(
db
,
sql
)
# print(df.shape)
df
=
df
.
rename
(
columns
=
{
0
:
"y"
,
1
:
"z"
,
2
:
"stat_date"
,
3
:
"ucity_id"
,
4
:
"clevel2_id"
,
5
:
"ccity_name"
,
6
:
"device_type"
,
7
:
"manufacturer"
,
8
:
"channel"
,
9
:
"top"
,
10
:
"device_id"
,
11
:
"time"
,
12
:
"app_list"
,
13
:
"service_id"
,
14
:
"level3_ids"
})
11
:
"time"
,
12
:
"app_list"
,
13
:
"service_id"
,
14
:
"level3_ids"
,
15
:
"method"
,
16
:
"min"
,
17
:
"max"
,
18
:
"treatment_time"
,
19
:
"maintain_time"
,
20
:
"recover_time"
})
print
(
"esmm data ok"
)
print
(
df
.
head
(
2
))
print
(
df
[[
"method"
,
"min"
,
"max"
,
"treatment_time"
,
"maintain_time"
,
"recover_time"
]]
.
head
(
6
))
print
(
df
.
count
(
axis
=
1
))
service_id
=
tuple
(
df
[
"service_id"
]
.
unique
())
db
=
pymysql
.
connect
(
host
=
'rdsfewzdmf0jfjp9un8xj.mysql.rds.aliyuncs.com'
,
port
=
3306
,
user
=
'work'
,
passwd
=
'BJQaT9VzDcuPBqkd'
,
db
=
'zhengxing'
)
...
...
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