Update app.py

app.py

@@ -10,16 +10,18 @@ def load_model():
   return model
   
 model = load_model()
+
+
 st.title("Patent Text Extractor")
 placeholder = st.empty()
 text_input = placeholder.text_area("Paste or write text", height=300)
 button = st.button("Extract Keywords")
-top_n = st.sidebar.slider("Select a number of keywords", 1, 10, 50,20)
+#top_n = st.sidebar.slider("Select a number of keywords", 1, 10, 50,20)
 #min_ngram = st.sidebar.number_input("Minimum number of words in each keyword", 1)
 #max_ngram = st.sidebar.number_input("Maximum number of words in each keyword", 3)
 #st.sidebar.code(f"ngram_range=({min_ngram}, {max_ngram})")
 
-params = {"docs": text_input, "top_n": top_n, "keyphrase_ngram_range":(1, 3), "stop_words": 'english',"vectorizer":KeyphraseCountVectorizer()}
+params = {"docs": text_input, "top_n": top_n, "stop_words": 'english',"vectorizer":KeyphraseCountVectorizer()}
 
 #add_diversity = st.sidebar.checkbox("Adjust diversity of keywords")
 
@@ -34,10 +36,13 @@ params = {"docs": text_input, "top_n": top_n, "keyphrase_ngram_range":(1, 3), "s
         #diversity = st.sidebar.slider("diversity", 0.1, 1.0, 0.6, 0.01)
         #params["use_mmr"] = True
         #params["diversity"] = diversity
-
-keywords = model.extract_keywords(**params)
+kw_extractor = yake.KeywordExtractor(top=50)
+candidates = kw_extractor.extract_keywords(text_input)
+keyphrases = [candidate[0] for candidate in candidates]
+kw_model = KeyBERT(model=model)
 
 if keywords != []:
     st.info("Extracted keywords")
-    keywords = pd.DataFrame(keywords, columns=["Keyword", "Score"])
+    keywords = kw_model.extract_keywords(text_input,candidates, keyphrase_ngram_range=(1, 3), 
+                       top_n=50,stop_words='english',vectorizer=KeyphraseCountVectorizer())
     st.table(keywords)