Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Contribute to GitLab
Sign in / Register
Toggle navigation
E
exa_news_classificator
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
Vasyl Bodnaruk
exa_news_classificator
Commits
1c4f3d4d
Commit
1c4f3d4d
authored
Aug 15, 2017
by
Tags
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Connect new data from esi.wp_esi_ml_data.
parent
07129d22
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
22 additions
and
10 deletions
+22
-10
model_data_analysis.py
model_data_analysis.py
+1
-1
news_classify_tag.py
news_classify_tag.py
+21
-9
No files found.
model_data_analysis.py
View file @
1c4f3d4d
...
...
@@ -148,7 +148,7 @@ if __name__ == '__main__':
# !!!!graph results
frequency
=
list
(
words_frequency
.
values
())
#
graph_results(frequency, "The Words Frequencies")
graph_results
(
frequency
,
"The Words Frequencies"
)
# the are some words with great frequency
...
...
news_classify_tag.py
View file @
1c4f3d4d
...
...
@@ -26,7 +26,7 @@ class Classifier:
self
.
train_data
=
corpus
return
# load external
f=
dictionary
# load external dictionary
file_name_dictionary
=
'large.txt'
file_dict
=
open
(
file_name_dictionary
,
"r"
)
self
.
correct_words
=
set
()
...
...
@@ -49,14 +49,26 @@ class Classifier:
train_data
=
[]
# text_id = []
sql1
=
'''SELECT wp_esi_tag_news.tag_id, wp_esi_news.title, wp_esi_news.description
FROM wp_esi_news, wp_esi_tag_news WHERE wp_esi_tag_news.news_id=wp_esi_news.id
ORDER BY wp_esi_tag_news.tag_id LIMIT 1000 '''
self
.
db
.
query
(
sql1
)
result
=
self
.
db
.
store_result
()
data
=
list
()
for
tag_id
,
title
,
description
in
result
.
fetch_row
(
maxrows
=
0
):
data
.
append
((
tag_id
,
title
,
description
))
# sql1 = '''SELECT wp_esi_tag_news.tag_id, wp_esi_news.title, wp_esi_news.description
# FROM wp_esi_news, wp_esi_tag_news WHERE wp_esi_tag_news.news_id=wp_esi_news.id
# ORDER BY wp_esi_tag_news.tag_id LIMIT 1000 '''
# self.db.query(sql1)
# result = self.db.store_result()
# data = list()
# for tag_id, title, description in result.fetch_row(maxrows=0):
# data.append((tag_id, title, description))
sql1
=
'''SELECT wp_esi_ml_data.tag_id, wp_esi_news_accept.title, wp_esi_news_accept.description, wp_esi_news_accept.text
FROM wp_esi_news_accept, wp_esi_ml_data WHERE wp_esi_ml_data.news_id=wp_esi_news_accept.id
ORDER BY wp_esi_ml_data.tag_id'''
self
.
db
.
query
(
sql1
)
result
=
self
.
db
.
store_result
()
data
=
list
()
for
tag_id
,
title
,
description
,
text
in
result
.
fetch_row
(
maxrows
=
0
):
if
description
is
not
None
:
data
.
append
((
tag_id
,
title
,
description
+
text
))
else
:
data
.
append
((
tag_id
,
title
,
text
))
for
tag_id
,
_
in
self
.
tags
:
texts
=
''
...
...
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