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
6f1e60af
Commit
6f1e60af
authored
Jan 03, 2019
by
高雅喆
Browse files
Options
Browse Files
Download
Plain Diff
Merge branch 'master' of git.wanmeizhensuo.com:ML/ffm-baseline
rm 2018 to 201
parents
337a29da
ede972bc
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
7 additions
and
5 deletions
+7
-5
feature_engineering.py
tensnsorflow/feature_engineering.py
+0
-0
ffm.py
tensnsorflow/ffm.py
+7
-5
No files found.
tensnsorflow/feature_engineering.py
View file @
6f1e60af
This diff is collapsed.
Click to expand it.
tensnsorflow/ffm.py
View file @
6f1e60af
...
...
@@ -156,14 +156,15 @@ def get_data():
df
=
df
.
rename
(
columns
=
{
0
:
"y"
,
1
:
"z"
,
2
:
"stat_date"
,
3
:
"ucity_id"
,
4
:
"clevel1_id"
,
5
:
"ccity_name"
,
6
:
"device_type"
,
7
:
"manufacturer"
,
8
:
"channel"
,
9
:
"top"
,
10
:
"time"
,
11
:
"device_id"
})
print
(
"esmm data ok"
)
print
(
df
.
head
(
2
)
)
# print(df.head(2
)
df
[
"clevel1_id"
]
=
df
[
"clevel1_id"
]
.
astype
(
"str"
)
df
[
"y"
]
=
df
[
"y"
]
.
astype
(
"str"
)
df
[
"z"
]
=
df
[
"z"
]
.
astype
(
"str"
)
df
[
"top"
]
=
df
[
"top"
]
.
astype
(
"str"
)
df
[
"y"
]
=
df
[
"stat_date"
]
.
str
.
cat
([
df
[
"device_id"
]
.
values
.
tolist
(),
df
[
"y"
]
.
values
.
tolist
(),
df
[
"z"
]
.
values
.
tolist
()],
sep
=
","
)
df
=
df
.
drop
([
"z"
,
"stat_date"
,
"device_id"
],
axis
=
1
)
.
fillna
(
0.0
)
df
=
df
.
drop
([
"z"
,
"stat_date"
,
"device_id"
,
"time"
],
axis
=
1
)
.
fillna
(
"na"
)
print
(
df
.
head
(
2
))
features
=
0
for
i
in
[
"ucity_id"
,
"clevel1_id"
,
"ccity_name"
,
"device_type"
,
"manufacturer"
,
"channel"
]:
...
...
@@ -210,7 +211,8 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
sql
=
"select e.y,e.z,e.label,e.ucity_id,e.clevel1_id,e.ccity_name,"
\
"u.device_type,u.manufacturer,u.channel,c.top,cid_time.time,e.device_id,e.cid_id "
\
"from esmm_pre_data 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 on e.cid_id = cid_time.cid_id"
"left join cid_type_top c on e.device_id = c.device_id left join cid_time on e.cid_id = cid_time.cid_id "
\
"where e.device_id = '358035085192742'"
df
=
con_sql
(
db
,
sql
)
df
=
df
.
rename
(
columns
=
{
0
:
"y"
,
1
:
"z"
,
2
:
"label"
,
3
:
"ucity_id"
,
4
:
"clevel1_id"
,
5
:
"ccity_name"
,
6
:
"device_type"
,
7
:
"manufacturer"
,
8
:
"channel"
,
9
:
"top"
,
10
:
"time"
,
...
...
@@ -244,7 +246,7 @@ def get_predict_set(ucity_id,model,ccity_name,manufacturer,channel):
df
[
"y"
]
=
df
[
"label"
]
.
str
.
cat
(
[
df
[
"device_id"
]
.
values
.
tolist
(),
df
[
"ucity_id"
]
.
values
.
tolist
(),
df
[
"cid_id"
]
.
values
.
tolist
(),
df
[
"y"
]
.
values
.
tolist
(),
df
[
"z"
]
.
values
.
tolist
()],
sep
=
","
)
df
=
df
.
drop
([
"z"
,
"label"
,
"device_id"
,
"cid_id"
],
axis
=
1
)
.
fillna
(
0.0
)
df
=
df
.
drop
([
"z"
,
"label"
,
"device_id"
,
"cid_id"
,
"time"
],
axis
=
1
)
.
fillna
(
0.0
)
print
(
"before transform"
)
print
(
df
.
shape
)
temp_series
=
model
.
transform
(
df
,
n
=
160000
,
processes
=
22
)
...
...
@@ -289,7 +291,7 @@ if __name__ == "__main__":
a
=
time
.
time
()
temp
,
validate_date
,
ucity_id
,
ccity_name
,
manufacturer
,
channel
=
get_data
()
model
=
transform
(
temp
,
validate_date
)
#
get_predict_set(ucity_id,model,ccity_name,manufacturer,channel)
get_predict_set
(
ucity_id
,
model
,
ccity_name
,
manufacturer
,
channel
)
b
=
time
.
time
()
print
(
"cost(分钟)"
)
print
((
b
-
a
)
/
60
)
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