GitHub - huyquoctrinh/Web-app-psy-prediction-for-Vietnamese-Student: Web application apply Bert-NLP for psychological prediction base on chatbot and crawl by bot from data on Messenger

It is slightly simplified implementation of Kim's Convolutional Neural Networks for Sentence Classification paper in Tensorflow.

Requirements

With CNN train.py With Bert classify_text_with_bert.ipynb

./eval.py --eval_train --checkpoint_dir="./runs/1459637919/checkpoints/"

Replace the checkpoint dir with the output from the training. To use your own data, change the eval.py script to load your data.

API: sudo python3 bert_sv.py WEB U.I: npm start

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
__pycache__		__pycache__
data		data
database		database
node_modules		node_modules
public		public
static		static
templates		templates
views		views
5373468049359826.csv		5373468049359826.csv
README.md		README.md
app.js		app.js
bert_sv.py		bert_sv.py
classify_text_with_bert.ipynb		classify_text_with_bert.ipynb
client.py		client.py
config.js		config.js
db.js		db.js
eval.py		eval.py
kq.csv		kq.csv
kq.txt		kq.txt
kt.py		kt.py
main.py		main.py
module.py		module.py
package-lock.json		package-lock.json
package.json		package.json
prediction.csv		prediction.csv
routes.js		routes.js
server.py		server.py
tach_dau.py		tach_dau.py
test_plot.py		test_plot.py
test_sv.py		test_sv.py
tk.csv		tk.csv
train.py		train.py
train_plot.py		train_plot.py