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
587bc6b2
Commit
587bc6b2
authored
Dec 25, 2018
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
add app list
parent
f679f172
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
43 additions
and
7 deletions
+43
-7
applist.py
tensnsorflow/applist.py
+43
-7
No files found.
tensnsorflow/applist.py
View file @
587bc6b2
...
@@ -21,14 +21,50 @@ def json_format(x):
...
@@ -21,14 +21,50 @@ def json_format(x):
def
sort_app
():
def
sort_app
():
db
=
pymysql
.
connect
(
host
=
'10.66.157.22'
,
port
=
4000
,
user
=
'root'
,
passwd
=
'3SYz54LS9#^9sBvC'
,
db
=
'jerry_prod'
)
db
=
pymysql
.
connect
(
host
=
'10.66.157.22'
,
port
=
4000
,
user
=
'root'
,
passwd
=
'3SYz54LS9#^9sBvC'
,
db
=
'jerry_prod'
)
sql
=
"select device_id,app_list from device_id_applist limit
6
"
sql
=
"select device_id,app_list from device_id_applist limit
20000
"
df
=
con_sql
(
db
,
sql
)
df
=
con_sql
(
db
,
sql
)
a
=
df
[
1
]
.
values
.
tolist
()
df
=
df
.
rename
(
columns
=
{
0
:
"device_id"
,
1
:
"app_list"
})
print
(
type
(
a
[
0
]))
df
[
1
]
=
df
[
1
]
.
apply
(
json_format
)
category
=
{
"competitor"
:{
"新氧微整形"
,
"新氧SoYoung"
},
dianshang
=
{
"美团"
,
"京东"
,
"淘宝"
}
"dianshang"
:{
"京东"
,
"淘宝"
,
"唯品会"
,
"天猫"
,
"苏宁易购"
,
"国美"
,
"当当"
,
"亚马逊"
,
"网易严选"
,
"小米有品"
},
df
[
2
]
=
df
[
1
]
.
apply
(
lambda
x
:
1
if
len
(
x
&
dianshang
)
>
0
else
0
)
"kuajing_dianshang"
:
{
"小红书"
,
"网易考拉"
,
"洋码头"
,
"达令全球好货"
,
"海狐海淘"
,
print
(
df
[
2
]
.
unique
())
"HIG0"
,
"豌豆公主"
,
"尚品网"
,
"丰趣海淘"
,
"比呀比海外购"
},
"zhibo"
:
{
"YY直播"
,
"映客直播"
,
"花椒直播"
,
"NOW直播"
,
"小米直播"
,
"一直播"
,
"KK直播"
,
"酷狗直播"
,
"来疯直播"
,
"喵播"
},
"youxizhibo"
:
{
"虎牙直播"
,
"斗鱼直播"
,
"熊猫直播"
,
"触手直播"
,
"企鹅电竞"
,
"龙珠直播"
,
"战旗直播"
,
"全民直播"
,
"CC直播"
,
"火猫直播"
},
"short_video"
:
{
"抖音短视频"
,
"快手"
,
"西瓜视频"
,
"火山小视频"
,
"秒拍"
,
"快视频"
,
"小影"
,
"蛙趣视频"
,
"最右"
,
"小咖秀"
},
"meitu"
:
{
"美图秀秀"
,
"美颜相机"
,
"天天P图"
,
"Faceu激萌"
,
"B612咔叽"
,
"in"
,
"相机360"
,
"潮自拍"
,
"玩图"
,
"nice"
},
"tiyu"
:
{
"直播吧"
,
"腾讯体育"
,
"新浪体育"
,
"虎扑体育"
,
"懂球帝"
,
"CCTV5"
,
"疯狂体育"
,
"球探体育比分"
,
"PP体育"
,
"A8体育直播"
},
"read"
:{
"掌阅"
,
"QQ阅读"
,
"咪咕阅读"
,
"书旗小说"
,
"多看阅读"
,
"追书神器"
,
"搜狗阅读"
,
"微信读书"
,
"起点小说"
,
"宜搜小说"
},
"finance"
:
{
"21财经"
,
"华尔街见闻"
,
"新浪财经"
,
"时代财经"
,
"和讯财经"
,
"第一财经"
,
"FT中文网"
,
"财经杂志"
,
"财新"
,
"央视财经"
},
"fashion_clothes"
:
{
"蘑菇街"
,
"聚美优品"
,
"美丽说"
,
"楚楚街"
,
"穿衣助手"
,
"有货"
,
"优品惠"
,
"优购时尚商城"
,
"走秀奢侈品"
},
"muying"
:
{
"贝贝网"
,
"蜜芽"
,
"孩子王"
,
"妈妈100"
,
"大V店"
,
"宝贝格子"
,
"乐友"
,
"母婴之家"
,
"国际妈咪海淘母婴商城"
,
"美囤妈妈"
,
"妈妈网孕育"
,
"宝宝树孕育"
,
"辣妈帮"
,
"亲宝宝"
,
"宝宝知道"
,
"妈妈社区"
,
"妈妈帮"
,
"柚宝宝"
,
"育儿宝"
},
"fresh"
:
{
"每日优鲜"
,
"京东到家"
,
"天天果园"
,
"中粮我买网"
,
"本来生活"
,
"手机惠农"
,
"盒马"
,
"顺丰优选"
,
"百果园"
,
"易果生鲜"
},
"bijia"
:
{
"美团"
,
"拼多多"
,
"折800"
,
"返利网"
,
"卷皮折扣"
,
"淘粉吧"
,
"聚划算"
,
"一淘"
,
"网购联盟"
,
"返利淘联盟"
,
"什么值得买"
,
"花生日记"
},
"travel"
:
{
"携程旅行"
,
"去哪儿旅行"
,
"同程旅游"
,
"途牛旅游"
,
"飞猪"
,
"马蜂窝旅游"
,
"艺龙旅行"
,
"驴妈妈旅游"
,
"TripAdvisor猫途鹰"
,
"美团旅行"
},
"airplane"
:
{
"航班管家"
,
"飞常准"
,
"航旅纵横"
,
"春秋航空"
,
"南方航空"
,
"中国国航"
,
"东方航空"
,
"海南航空"
,
"深圳航空"
,
"四川航空"
},
"love"
:
{
"百合婚恋"
,
"世纪佳缘"
,
"珍爱网"
,
"牵手婚恋"
,
"探探"
,
"热恋"
,
"有缘网"
,
"约会吧"
,
"约爱"
,
"快约爱"
},
"stock"
:
{
"同花顺炒股票"
,
"大智慧"
,
"涨乐财富通"
,
"腾讯自选股"
,
"广发证券易淘金"
,
"金太阳"
,
"国泰君安君弘"
,
"海通e海通财"
,
"平安证券"
,
"同花顺"
},
"car"
:
{
"平安好车主"
,
"途虎养车"
,
"车主无忧"
,
"汽车超人"
,
"车e族"
,
"汽修宝"
,
"车点点"
,
"汽车大师"
,
"乐车邦"
,
"车享家"
},
"child"
:
{
"小伴龙"
,
"儿歌多多"
,
"宝宝巴士奇妙屋"
,
"智慧树"
,
"贝瓦儿歌"
,
"儿歌点点"
,
"宝贝听听"
,
"宝宝小厨房"
,
"宝宝游乐园"
,
"叽里呱啦"
},
"homework"
:
{
"作业帮"
,
"小猿搜题"
,
"一起作业学生端"
,
"学霸君"
,
"互动作业"
,
"猿题库"
,
"纳米盒"
,
"阿凡题"
,
"洋葱数学"
},
"work"
:
{
"钉钉"
,
"企业微信"
,
"移动彩云"
,
"云之家"
,
"今目标"
,
"口袋助理"
,
"推事本"
,
"奇鱼微办公"
,
"工作圈"
,
"明道"
},
"home"
:
{
"最美装修"
,
"齐家网"
,
"土巴兔装修"
,
"装修头条"
,
"装修管家"
,
"窝牛装修"
,
"丽芙家居"
,
"酷家乐装修"
,
"惠装装修"
,
"房天下装修"
},
"job"
:
{
"智联招聘"
,
"前程无忧"
,
"斗米"
,
"拉勾"
,
"Boss直聘"
,
"猎聘同道"
,
"智联招聘"
}
}
df
[
"app_list"
]
=
df
[
"app_list"
]
.
apply
(
json_format
)
for
i
in
category
.
keys
():
df
[
i
]
=
df
[
"app_list"
]
.
apply
(
lambda
x
:
1
if
len
(
x
&
category
[
i
])
>
0
else
0
)
print
(
i
)
print
(
df
[
i
]
.
unique
())
if
__name__
==
"__main__"
:
if
__name__
==
"__main__"
:
sort_app
()
sort_app
()
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