demo-model

README.md

@@ -1,26 +1,17 @@
 # Your Terms: A text classifier that identifies potentially unfair or exploitative clauses in Terms and Conditions agreements
 
-It's no secret that 
-- A simple web UI using Flask to support a demo of the project
-- A command-line interface to support running different stages of the project's pipeline
-- The ability to easily reproduce your work on another machine by using virtualenv and providing access to external data sources.
+It's no secret that peopledon't read their terms and conditions agreements. Rather than spending hours reading through dense legal document, a vast majority of people will simply click agree and move on with their day. That's why we built Your Terms, a text classifier that
 
 ### Exeriments
-
+In the Notebooks module you can view all of the different experiments we ran. 
 
 ### Demo
 To run the demo:
-Move into the app directory with ```cd app```
-Run the app with ```flask run```
-This should run the flask app locally on your computer, so you should be able to use the demo at http://127.0.0.1:5000 (the port number may differ depending on your computer)
-
+Move into the app directory with by using ```cd app``` in your command line
+To run the app use ```flask run```
+This should run the flask app locally on your computer, so you should be able to use the demo in your web browser at http://127.0.0.1:5000 (the port number may differ depending on your computer)
+Press ```ctrl + C``` in your command line to shut down the demo
 
-### Contents
 
-- [docs](docs): template to create slides for project presentations
-- [nlp](nlp): Python project code
-- [notebooks](notebooks): Jupyter notebooks for project development and experimentation
-- [report](report): LaTeX report
-- [tests](tests): unit tests for project code
 
 

app/app.py

@@ -55,8 +55,9 @@ def forward(self, attention_mask = None, token_type_ids = None,input_ids = None)
 # model.load_state_dict(torch.load(MODEL_PATH))
 # model.eval()
 # tokenizer = BertTokenizer.from_pretrained('distilbert/distilbert-base-uncased')
+tokenizer = None
 stemmer = PorterStemmer()
-bow_model = joblib.load('../models/logistic_regression_bow.pkl')
+bow_model = joblib.load('../demo-model/logistic_regression_bow.pkl')
 nltk.download('stopwords')
 nltk.download('punkt')
 stop_words = set(stopwords.words('english'))