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
46f27a5c
Commit
46f27a5c
authored
Feb 18, 2019
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
修改文件写入路径
parent
7086c675
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
3 additions
and
3 deletions
+3
-3
to_database.py
tensnsorflow/es/to_database.py
+3
-3
No files found.
tensnsorflow/es/to_database.py
View file @
46f27a5c
...
...
@@ -40,7 +40,7 @@ def main():
df2
=
pd
.
read_csv
(
'/data/esmm/native.csv'
)
df2
[
'cid_id'
]
=
df2
[
'cid_id'
]
.
astype
(
str
)
df1
=
pd
.
read_csv
(
"/
home/gmuser/esmm_data
/native/pred.txt"
,
sep
=
'
\t
'
,
header
=
None
,
names
=
[
"ctr"
,
"cvr"
,
"ctcvr"
])
df1
=
pd
.
read_csv
(
"/
data/esmm
/native/pred.txt"
,
sep
=
'
\t
'
,
header
=
None
,
names
=
[
"ctr"
,
"cvr"
,
"ctcvr"
])
df2
[
"ctr"
],
df2
[
"cvr"
],
df2
[
"ctcvr"
]
=
df1
[
"ctr"
],
df1
[
"cvr"
],
df1
[
"ctcvr"
]
df3
=
df2
.
groupby
(
by
=
[
"uid"
,
"city"
])
.
apply
(
lambda
x
:
x
.
sort_values
(
by
=
"ctcvr"
,
ascending
=
False
))
.
reset_index
(
drop
=
True
)
.
groupby
(
by
=
[
"uid"
,
"city"
])
.
agg
({
'cid_id'
:
native_set_join
})
.
reset_index
(
drop
=
False
)
df3
.
columns
=
[
"device_id"
,
"city_id"
,
"native_queue"
]
...
...
@@ -48,10 +48,10 @@ def main():
# nearby queue
df2
=
pd
.
read_csv
(
'/
home/gmuser/esmm_data
/nearby.csv'
)
df2
=
pd
.
read_csv
(
'/
data/esmm
/nearby.csv'
)
df2
[
'cid_id'
]
=
df2
[
'cid_id'
]
.
astype
(
str
)
df1
=
pd
.
read_csv
(
"/
home/gmuser/esmm_data
/nearby/pred.txt"
,
sep
=
'
\t
'
,
header
=
None
,
names
=
[
"ctr"
,
"cvr"
,
"ctcvr"
])
df1
=
pd
.
read_csv
(
"/
data/esmm
/nearby/pred.txt"
,
sep
=
'
\t
'
,
header
=
None
,
names
=
[
"ctr"
,
"cvr"
,
"ctcvr"
])
df2
[
"ctr"
],
df2
[
"cvr"
],
df2
[
"ctcvr"
]
=
df1
[
"ctr"
],
df1
[
"cvr"
],
df1
[
"ctcvr"
]
df4
=
df2
.
groupby
(
by
=
[
"uid"
,
"city"
])
.
apply
(
lambda
x
:
x
.
sort_values
(
by
=
"ctcvr"
,
ascending
=
False
))
.
reset_index
(
drop
=
True
)
.
groupby
(
by
=
[
"uid"
,
"city"
])
.
agg
({
'cid_id'
:
nearby_set_join
})
.
reset_index
(
drop
=
False
)
df4
.
columns
=
[
"device_id"
,
"city_id"
,
"nearby_queue"
]
...
...
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