Skip to content
GitLab
Menu
Projects
Groups
Snippets
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Sign in
Toggle navigation
Menu
Open sidebar
pse-trapp-public
IntentFinder
Commits
f53e017d
Commit
f53e017d
authored
Jun 02, 2021
by
Ala Rouis
Committed by
Patrick Schlindwein
Jun 02, 2021
Browse files
#28
überarbeitung id generierung
parent
bcca6a60
Changes
2
Show whitespace changes
Inline
Side-by-side
src/nlp/app/tests/test_utilities.py
View file @
f53e017d
...
...
@@ -8,3 +8,9 @@ class TestIntentHandler(TestCase):
" über das Virus informieren?"
)
id
=
obj
.
generate_intent_id
(
3
)
assert
id
==
"buergerinnen_virus_informieren"
def
test_normalize
(
self
):
obj
=
generator
.
IntentHandler
(
"Wo können sich hessische Bürger*Innen"
" über das Virus informieren?"
)
verb
=
obj
.
normalize
(
"Ich bin test."
)
assert
verb
[
1
]
==
"sein"
src/nlp/app/utilities/generator.py
View file @
f53e017d
...
...
@@ -10,6 +10,7 @@ class IntentHandler:
def
__init__
(
self
,
intent
:
str
):
self
.
intent
=
intent
self
.
nlp
=
spacy
.
load
(
"de_core_news_md"
)
self
.
doc
=
IntentHandler
.
nlp
(
intent
)
def
generate_intent_id
(
self
,
max_tokens
:
int
):
...
...
@@ -44,6 +45,13 @@ class IntentHandler:
text
=
re
.
sub
(
'[^a-zA-Z0-9]+'
,
''
,
text
)
return
text
def
normalize
(
self
,
text
):
doc
=
self
.
nlp
(
text
)
return_list
=
[]
for
token
in
doc
:
return_list
.
append
((
token
.
lemma_
).
replace
(
"ß"
,
"ss"
))
return
return_list
# def removeStopWords(tokens: []):
# filtered = []
# nlp = German()
...
...
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