Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
P
physical
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
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
alpha
physical
Commits
41e1a4e7
Commit
41e1a4e7
authored
Jun 26, 2019
by
kai
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
update
parent
67913a91
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
69 additions
and
81 deletions
+69
-81
Project.xml
.idea/codeStyles/Project.xml
+0
-25
collect_data.py
linucb/views/collect_data.py
+69
-56
No files found.
.idea/codeStyles/Project.xml
View file @
41e1a4e7
...
@@ -24,29 +24,5 @@
...
@@ -24,29 +24,5 @@
<option
name=
"ITERATION_ELEMENTS_WRAPPING"
value=
"chop_down_if_not_single"
/>
<option
name=
"ITERATION_ELEMENTS_WRAPPING"
value=
"chop_down_if_not_single"
/>
</formatting-settings>
</formatting-settings>
</DBN-SQL>
</DBN-SQL>
<DBN-PSQL>
<case-options
enabled=
"false"
>
<option
name=
"KEYWORD_CASE"
value=
"lower"
/>
<option
name=
"FUNCTION_CASE"
value=
"lower"
/>
<option
name=
"PARAMETER_CASE"
value=
"lower"
/>
<option
name=
"DATATYPE_CASE"
value=
"lower"
/>
<option
name=
"OBJECT_CASE"
value=
"preserve"
/>
</case-options>
<formatting-settings
enabled=
"false"
/>
</DBN-PSQL>
<DBN-SQL>
<case-options
enabled=
"false"
>
<option
name=
"KEYWORD_CASE"
value=
"lower"
/>
<option
name=
"FUNCTION_CASE"
value=
"lower"
/>
<option
name=
"PARAMETER_CASE"
value=
"lower"
/>
<option
name=
"DATATYPE_CASE"
value=
"lower"
/>
<option
name=
"OBJECT_CASE"
value=
"preserve"
/>
</case-options>
<formatting-settings
enabled=
"false"
>
<option
name=
"STATEMENT_SPACING"
value=
"one_line"
/>
<option
name=
"CLAUSE_CHOP_DOWN"
value=
"chop_down_if_statement_long"
/>
<option
name=
"ITERATION_ELEMENTS_WRAPPING"
value=
"chop_down_if_not_single"
/>
</formatting-settings>
</DBN-SQL>
</code_scheme>
</code_scheme>
</component>
</component>
\ No newline at end of file
linucb/views/collect_data.py
View file @
41e1a4e7
...
@@ -164,10 +164,23 @@ class CollectData(object):
...
@@ -164,10 +164,23 @@ class CollectData(object):
user_id
=
raw_val_dict
[
"user_id"
]
if
"user_id"
in
raw_val_dict
else
None
user_id
=
raw_val_dict
[
"user_id"
]
if
"user_id"
in
raw_val_dict
else
None
logging
.
info
(
"consume topic_id:
%
s,device_id:
%
s"
%
(
str
(
topic_id
),
str
(
device_id
)))
logging
.
info
(
"consume topic_id:
%
s,device_id:
%
s"
%
(
str
(
topic_id
),
str
(
device_id
)))
topic_tag_list
=
list
(
TopicTag
.
objects
.
using
(
settings
.
SLAVE_DB_NAME
)
.
filter
(
topic_id
=
topic_id
,
is_online
=
True
)
.
values_list
(
"tag_id"
,
flat
=
True
))
# topic_tag_list = list(TopicTag.objects.using(settings.SLAVE_DB_NAME).filter(topic_id=topic_id,is_online=True).values_list("tag_id",flat=True))
tag_query_results
=
Tag
.
objects
.
using
(
settings
.
SLAVE_DB_NAME
)
.
filter
(
id__in
=
topic_tag_list
,
is_online
=
True
,
is_deleted
=
False
)
.
values_list
(
"id"
,
"collection"
,
"is_ai"
)
# tag_query_results = Tag.objects.using(settings.SLAVE_DB_NAME).filter(id__in=topic_tag_list,is_online=True,is_deleted=False).values_list("id","collection","is_ai")
for
id
,
collection
,
is_ai
in
tag_query_results
:
# for id,collection,is_ai in tag_query_results:
if
collection
and
is_ai
:
# if collection and is_ai:
# click_topic_tag_list.append(id)
topic_tag_list
=
list
()
click_results
=
TopicTag
.
objects
.
using
(
settings
.
SLAVE_DB_NAME
)
.
filter
(
topic_id
=
topic_id
,
is_online
=
True
)
.
values_list
(
"tag_id"
,
"is_collection"
)
for
tag_id
,
is_collection
in
click_results
:
topic_tag_list
.
append
(
tag_id
)
if
is_collection
:
click_topic_tag_list
.
append
(
tag_id
)
tag_query_results
=
Tag
.
objects
.
using
(
settings
.
SLAVE_DB_NAME
)
.
filter
(
id__in
=
topic_tag_list
,
is_online
=
True
,
is_deleted
=
False
)
.
values_list
(
"id"
,
"is_ai"
)
for
id
,
is_ai
in
tag_query_results
:
if
is_ai
:
click_topic_tag_list
.
append
(
id
)
click_topic_tag_list
.
append
(
id
)
logging
.
info
(
"positive tag_list,device_id:
%
s,topic_id:
%
s,tag_list:
%
s"
%
(
logging
.
info
(
"positive tag_list,device_id:
%
s,topic_id:
%
s,tag_list:
%
s"
%
(
...
@@ -197,58 +210,58 @@ class CollectData(object):
...
@@ -197,58 +210,58 @@ class CollectData(object):
# 更新该用户的推荐tag数据,放在 更新完成user tag行为信息之后
# 更新该用户的推荐tag数据,放在 更新完成user tag行为信息之后
if
len
(
click_topic_tag_list
)
>
0
:
if
len
(
click_topic_tag_list
)
>
0
:
self
.
update_recommend_tag_list
(
device_id
,
user_feature
,
user_id
,
click_topic_tag_list
=
click_topic_tag_list
)
self
.
update_recommend_tag_list
(
device_id
,
user_feature
,
user_id
,
click_topic_tag_list
=
click_topic_tag_list
)
elif
"type"
in
raw_val_dict
and
"page_precise_exposure"
==
raw_val_dict
[
"type"
]:
#
elif "type" in raw_val_dict and "page_precise_exposure" == raw_val_dict["type"]:
if
isinstance
(
raw_val_dict
[
"params"
][
"exposure_cards"
],
str
):
#
if isinstance(raw_val_dict["params"]["exposure_cards"],str):
exposure_cards_list
=
json
.
loads
(
raw_val_dict
[
"params"
][
"exposure_cards"
])
#
exposure_cards_list = json.loads(raw_val_dict["params"]["exposure_cards"])
elif
isinstance
(
raw_val_dict
[
"params"
][
"exposure_cards"
],
list
):
#
elif isinstance(raw_val_dict["params"]["exposure_cards"],list):
exposure_cards_list
=
raw_val_dict
[
"params"
][
"exposure_cards"
]
#
exposure_cards_list = raw_val_dict["params"]["exposure_cards"]
else
:
#
else:
exposure_cards_list
=
list
()
#
exposure_cards_list = list()
device_id
=
raw_val_dict
[
"device"
][
"device_id"
]
#
device_id = raw_val_dict["device"]["device_id"]
user_id
=
raw_val_dict
[
"user_id"
]
if
"user_id"
in
raw_val_dict
else
None
#
user_id = raw_val_dict["user_id"] if "user_id" in raw_val_dict else None
logging
.
warning
(
"type msg:
%
s"
%
raw_val_dict
.
get
(
"type"
))
#
logging.warning("type msg:%s" % raw_val_dict.get("type"))
exposure_topic_id_list
=
list
()
#
exposure_topic_id_list = list()
for
item
in
exposure_cards_list
:
#
for item in exposure_cards_list:
if
"card_id"
not
in
item
:
#
if "card_id" not in item:
continue
#
continue
exposure_topic_id
=
item
[
"card_id"
]
#
exposure_topic_id = item["card_id"]
logging
.
info
(
#
logging.info(
"consume exposure topic_id:
%
s,device_id:
%
s"
%
(
str
(
exposure_topic_id
),
str
(
device_id
)))
#
"consume exposure topic_id:%s,device_id:%s" % (str(exposure_topic_id), str(device_id)))
if
exposure_topic_id
:
#
if exposure_topic_id:
exposure_topic_id_list
.
append
(
exposure_topic_id
)
#
exposure_topic_id_list.append(exposure_topic_id)
#
topic_tag_id_dict
=
dict
()
#
topic_tag_id_dict = dict()
tag_list
=
list
()
#
tag_list = list()
exposure_sql_query_results
=
TopicTag
.
objects
.
using
(
settings
.
SLAVE_DB_NAME
)
.
\
#
exposure_sql_query_results = TopicTag.objects.using(settings.SLAVE_DB_NAME).\
filter
(
topic_id__in
=
exposure_topic_id_list
)
.
\
#
filter(topic_id__in=exposure_topic_id_list).\
values_list
(
"topic_id"
,
"tag_id"
,
"is_online"
,
"is_collection"
)
#
values_list("topic_id","tag_id","is_online","is_collection")
# if len(exposure_sql_query_results)>0:
#
# if len(exposure_sql_query_results)>0:
for
topic_id
,
tag_id
,
is_online
,
is_collection
in
exposure_sql_query_results
:
#
for topic_id,tag_id,is_online,is_collection in exposure_sql_query_results:
if
is_online
and
is_collection
==
1
:
#
if is_online and is_collection == 1:
tag_list
.
append
(
tag_id
)
#
tag_list.append(tag_id)
if
is_online
:
#
if is_online:
tag_sql_query_results
=
Tag
.
objects
.
using
(
settings
.
SLAVE_DB_NAME
)
.
filter
(
#
tag_sql_query_results = Tag.objects.using(settings.SLAVE_DB_NAME).filter(
id
=
tag_id
)
.
values_list
(
"id"
,
"collection"
,
"is_ai"
)
#
id=tag_id).values_list("id", "collection", "is_ai")
for
id
,
collection
,
is_ai
in
tag_sql_query_results
:
#
for id, collection, is_ai in tag_sql_query_results:
if
(
is_ai
==
1
)
and
id
not
in
tag_list
:
#
if (is_ai == 1) and id not in tag_list:
tag_list
.
append
(
id
)
#
tag_list.append(id)
#
if
topic_id
not
in
topic_tag_id_dict
:
#
if topic_id not in topic_tag_id_dict:
topic_tag_id_dict
[
topic_id
]
=
list
()
#
topic_tag_id_dict[topic_id] = list()
topic_tag_id_dict
[
topic_id
]
.
append
(
tag_id
)
#
topic_tag_id_dict[topic_id].append(tag_id)
#
is_click
=
0
#
is_click = 0
is_vote
=
0
#
is_vote = 0
#
reward
=
1
if
is_click
or
is_vote
else
0
#
reward = 1 if is_click or is_vote else 0
#
logging
.
info
(
"negative tag_list,device_id:
%
s,topic_tag_id_dict:
%
s"
%
(
#
logging.info("negative tag_list,device_id:%s,topic_tag_id_dict:%s" % (
str
(
device_id
),
str
(
topic_tag_id_dict
)))
#
str(device_id), str(topic_tag_id_dict)))
for
tag_id
in
tag_list
:
#
for tag_id in tag_list:
self
.
update_user_linucb_tag_info
(
reward
,
device_id
,
tag_id
,
user_feature
)
#
self.update_user_linucb_tag_info(reward, device_id, tag_id, user_feature)
#
# 更新该用户的推荐tag数据,放在 更新完成user tag行为信息之后
#
# 更新该用户的推荐tag数据,放在 更新完成user tag行为信息之后
self
.
update_recommend_tag_list
(
device_id
,
user_feature
,
user_id
)
#
self.update_recommend_tag_list(device_id, user_feature, user_id)
elif
"type"
in
raw_val_dict
and
"interest_choice_click_next"
==
raw_val_dict
[
"type"
]:
elif
"type"
in
raw_val_dict
and
"interest_choice_click_next"
==
raw_val_dict
[
"type"
]:
if
isinstance
(
raw_val_dict
[
"params"
][
"tagid_list"
],
str
):
if
isinstance
(
raw_val_dict
[
"params"
][
"tagid_list"
],
str
):
tagid_list
=
json
.
loads
(
raw_val_dict
[
"params"
][
"tagid_list"
])
tagid_list
=
json
.
loads
(
raw_val_dict
[
"params"
][
"tagid_list"
])
...
...
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