first commit

.idea/.gitignore

@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml

.idea/Vietnamese_classification.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.9 (Vietnamese_classification)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Vietnamese_classification.iml" filepath="$PROJECT_DIR$/.idea/Vietnamese_classification.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

app.py

@@ -0,0 +1,18 @@
+import os
+
+from utils import *
+from transformers import pipeline
+import gradio as gr
+
+
+pipe = pipeline("text-classification", model="ShynBui/comment_classification_v2", token=os.environ['HF_TOKEN'])
+
+
+
+def classification(text):
+    classi = pipe(covert_pyVI(text))
+
+    return classi[0]['label'], classi[0]['score']
+
+iface = gr.Interface(fn=classification, inputs="text", outputs=["text", "text"])
+iface.launch()

requirements.txt

@@ -0,0 +1,84 @@
+## The following requirements were added by pip freeze:
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==4.3.0
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+colorama==0.4.6
+contourpy==1.2.1
+cycler==0.12.1
+exceptiongroup==1.2.1
+fastapi==0.110.2
+ffmpy==0.3.2
+filelock==3.13.4
+fonttools==4.51.0
+fsspec==2024.3.1
+gradio==4.27.0
+gradio_client==0.15.1
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.22.2
+idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.3
+joblib==1.4.0
+jsonschema==4.21.1
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+mdurl==0.1.2
+mpmath==1.3.0
+networkx==3.2.1
+numpy==1.26.4
+orjson==3.10.1
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+pydantic==2.7.0
+pydantic_core==2.18.1
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.2
+python-crfsuite==0.9.10
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+pyvi==0.1.1
+PyYAML==6.0.1
+referencing==0.34.0
+regex==2024.4.16
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+ruff==0.4.1
+safetensors==0.4.3
+scikit-learn==1.4.2
+scipy==1.13.0
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sklearn-crfsuite==0.3.6
+sniffio==1.3.1
+starlette==0.37.2
+sympy==1.12
+tabulate==0.9.0
+threadpoolctl==3.4.0
+tokenizers==0.19.1
+tomlkit==0.12.0
+toolz==0.12.1
+torch==2.2.2
+tqdm==4.66.2
+transformers==4.40.0
+typer==0.12.3
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+uvicorn==0.29.0
+websockets==11.0.3
+zipp==3.18.1

utils.py

@@ -0,0 +1,4 @@
+from pyvi import ViTokenizer, ViPosTagger
+
+def covert_pyVI(text):
+    return ViTokenizer.tokenize(text)