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
dd6af371
Commit
dd6af371
authored
6 years ago
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
try to fix time
parent
c51d4fe8
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
8 additions
and
9 deletions
+8
-9
prepareData.py
prepareData.py
+8
-9
No files found.
prepareData.py
View file @
dd6af371
...
...
@@ -3,7 +3,6 @@ import datetime
def
fetch_data
(
start_date
,
end_date
):
# 获取点击表里的device_id
sql
=
"select distinct device_id from data_feed_click"
click_device_id
=
con_sql
(
sql
)[
0
]
.
values
.
tolist
()
...
...
@@ -13,12 +12,12 @@ def fetch_data(start_date, end_date):
sql
=
"select cid,device_id,time,stat_date from data_feed_click "
\
"where stat_date >= {0} and stat_date <= {1}"
.
format
(
start_date
,
end_date
)
click
=
con_sql
(
sql
)
click
=
click
.
rename
(
columns
=
{
0
:
"cid"
,
1
:
"device_id"
,
2
:
"time"
,
3
:
"stat_date"
})
click
=
click
.
rename
(
columns
=
{
0
:
"cid"
,
1
:
"device_id"
,
2
:
"time_date"
,
3
:
"stat_date"
})
print
(
"成功获取点击表里的数据"
)
# 从time特征中抽取hour
click
[
"hour"
]
=
click
[
"time
"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
hour
)
click
[
"minute"
]
=
click
[
"time
"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
minute
)
click
=
click
.
drop
(
"time
"
,
axis
=
1
)
click
[
"hour"
]
=
click
[
"time
_date"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
hour
)
click
[
"minute"
]
=
click
[
"time
_date"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
minute
)
click
=
click
.
drop
(
"time
_date"
,
axis
=
1
)
print
(
"点击表数据预览"
)
print
(
click
.
head
(
2
))
...
...
@@ -26,12 +25,12 @@ def fetch_data(start_date, end_date):
sql
=
"select cid,device_id,time,stat_date from data_feed_exposure "
\
"where stat_date >= {0} and stat_date <= {1}"
.
format
(
start_date
,
end_date
)
exposure
=
con_sql
(
sql
)
exposure
=
exposure
.
rename
(
columns
=
{
0
:
"cid"
,
1
:
"device_id"
,
2
:
"time"
,
3
:
"stat_date"
})
exposure
=
exposure
.
rename
(
columns
=
{
0
:
"cid"
,
1
:
"device_id"
,
2
:
"time_date"
,
3
:
"stat_date"
})
print
(
"成功获取曝光表里的数据"
)
# 从time特征中抽取hour
exposure
[
"hour"
]
=
exposure
[
"time
"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
hour
)
exposure
[
"minute"
]
=
exposure
[
"time
"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
minute
)
exposure
=
exposure
.
drop
(
"time
"
,
axis
=
1
)
exposure
[
"hour"
]
=
exposure
[
"time
_date"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
hour
)
exposure
[
"minute"
]
=
exposure
[
"time
_date"
]
.
apply
(
lambda
x
:
datetime
.
datetime
.
fromtimestamp
(
x
)
.
minute
)
exposure
=
exposure
.
drop
(
"time
_date"
,
axis
=
1
)
print
(
"曝光表数据预览"
)
print
(
exposure
.
head
(
2
))
...
...
This diff is collapsed.
Click to expand it.
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