Update app.py

app.py

@@ -1,19 +1,22 @@
 import streamlit as st
 
-# Library for Sentence Similarity
-import pandas as pd
-from sentence_transformers import SentenceTransformer
-from sklearn.metrics.pairwise import cosine_similarity
+# # Library for Sentence Similarity
+# import pandas as pd
+# from sentence_transformers import SentenceTransformer
+# from sklearn.metrics.pairwise import cosine_similarity
 
 # Library for Entailment
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
 
+# # Library for keyword extraction
+# import yake
+
 
 # Load models and tokenisers for both sentence transformers and text classification
 
-sentence_transformer_model = SentenceTransformer('all-MiniLM-L6-v2')
+# sentence_transformer_model = SentenceTransformer('all-MiniLM-L6-v2')
 
 tokenizer = AutoTokenizer.from_pretrained("roberta-large-mnli")
 
@@ -49,29 +52,29 @@ if sidebar_selectbox == "Compare two sentences":
 
               print("Comparing sentences...")
 
-              ### Compare Sentence Similarity ###
+              # ### Compare Sentence Similarity ###
        
-              # Perform calculations
+              # # Perform calculations
               
-              #Initialise sentences
-              sentences = []
+              # #Initialise sentences
+              # sentences = []
               
-              # Append input sentences to 'sentences' list
-              sentences.append(sentence_1)
-              sentences.append(sentence_2)
+              # # Append input sentences to 'sentences' list
+              # sentences.append(sentence_1)
+              # sentences.append(sentence_2)
               
-              # Create embeddings for both sentences
-              sentence_embeddings = sentence_transformer_model.encode(sentences)
+              # # Create embeddings for both sentences
+              # sentence_embeddings = sentence_transformer_model.encode(sentences)
               
-              cos_sim = cosine_similarity(sentence_embeddings[0].reshape(1, -1), sentence_embeddings[1].reshape(1, -1))[0][0]
-              cos_sim = round(cos_sim * 100) # Convert to percentage and round-off
+              # cos_sim = cosine_similarity(sentence_embeddings[0].reshape(1, -1), sentence_embeddings[1].reshape(1, -1))[0][0]
+              # cos_sim = round(cos_sim * 100) # Convert to percentage and round-off
              
                      
-              # st.write('Similarity between "{}" and "{}" is {}%'.format(sentence_1,
-              #        sentence_2, cos_sim))
+              # # st.write('Similarity between "{}" and "{}" is {}%'.format(sentence_1,
+              # #        sentence_2, cos_sim))
 
-              st.subheader("Similarity")
-              st.write(f"Similarity between the two sentences is {cos_sim}%.")
+              # st.subheader("Similarity")
+              # st.write(f"Similarity between the two sentences is {cos_sim}%.")
 
 
               ### Text classification - entailment, neutral or contradiction ###
@@ -100,6 +103,22 @@ if sidebar_selectbox == "Compare two sentences":
               st.write(text_classification_model.config.id2label[2], ":", round(outputs[0][2].item()*100,2),"%")
 
 
+              ### Extract keywords with YAKE ### (might make more sense with word cloud)
+
+              st.subheader("Keywords:")
+
+              kw_extractor = yake.KeywordExtractor(top=10, stopwords=None)
+              keywords = kw_extractor.extract_keywords(sentence_2)
+
+              # keywords_array = []
+
+              for kw, v in keywords:
+                # print("Keyphrase: ", kw, ": score", v)
+                # keywords_array.append(kw)
+
+                st.write(kw)
+
+