Update func.py

func.py

@@ -1,26 +1,29 @@
-import streamlit as st
-import requests
-from bs4 import BeautifulSoup
 from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoModelForTokenClassification
+from bs4 import BeautifulSoup
+import requests
 
-# ---------------- Model Setup ----------------
-@st.cache_resource
-def load_sentiment_model():
-    model_id = "LinkLinkWu/Stock_Analysis_Test_Ahamed"
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    model = AutoModelForSequenceClassification.from_pretrained(model_id)
-    return pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
+# ----------- Lazy Initialization of Pipelines -----------
+_sentiment_pipeline = None
+_ner_pipeline = None
 
-@st.cache_resource
-def load_ner_model():
-    tokenizer = AutoTokenizer.from_pretrained("dslim/bert-base-NER")
-    model = AutoModelForTokenClassification.from_pretrained("dslim/bert-base-NER")
-    return pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True)
+def get_sentiment_pipeline():
+    global _sentiment_pipeline
+    if _sentiment_pipeline is None:
+        model_id = "LinkLinkWu/Stock_Analysis_Test_Ahamed"
+        tokenizer = AutoTokenizer.from_pretrained(model_id)
+        model = AutoModelForSequenceClassification.from_pretrained(model_id)
+        _sentiment_pipeline = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
+    return _sentiment_pipeline
 
-sentiment_pipeline = load_sentiment_model()
-ner_pipeline = load_ner_model()
+def get_ner_pipeline():
+    global _ner_pipeline
+    if _ner_pipeline is None:
+        tokenizer = AutoTokenizer.from_pretrained("dslim/bert-base-NER")
+        model = AutoModelForTokenClassification.from_pretrained("dslim/bert-base-NER")
+        _ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, grouped_entities=True)
+    return _ner_pipeline
 
-# ---------------- Helper Functions ----------------
+# ----------- Core Functions -----------
 def fetch_news(ticker):
     try:
         url = f"https://finviz.com/quote.ashx?t={ticker}"
@@ -33,18 +36,15 @@ def fetch_news(ticker):
         }
         response = requests.get(url, headers=headers)
         if response.status_code != 200:
-            st.error(f"Failed to fetch page for {ticker}: Status code {response.status_code}")
             return []
 
         soup = BeautifulSoup(response.text, 'html.parser')
         title = soup.title.text if soup.title else ""
         if ticker not in title:
-            st.error(f"Page for {ticker} not found or access denied.")
             return []
 
         news_table = soup.find(id='news-table')
         if news_table is None:
-            st.error(f"News table not found for {ticker}. The website structure might have changed.")
             return []
 
         news = []
@@ -55,19 +55,17 @@ def fetch_news(ticker):
                 link = a_tag['href']
                 news.append({'title': title, 'link': link})
         return news
-    except Exception as e:
-        st.error(f"Failed to fetch news for {ticker}: {e}")
+    except Exception:
         return []
 
-def analyze_sentiment(text):
+def analyze_sentiment(text, sentiment_pipeline):
     try:
         result = sentiment_pipeline(text)[0]
         return "Positive" if result['label'] == 'POSITIVE' else "Negative"
-    except Exception as e:
-        st.error(f"Sentiment analysis failed: {e}")
+    except Exception:
         return "Unknown"
 
-def extract_org_entities(text):
+def extract_org_entities(text, ner_pipeline):
     try:
         entities = ner_pipeline(text)
         org_entities = []
@@ -79,6 +77,5 @@ def extract_org_entities(text):
                 if len(org_entities) >= 5:
                     break
         return org_entities
-    except Exception as e:
-        st.error(f"NER entity extraction failed: {e}")
+    except Exception:
         return []