Update pages/Comparision.py

pages/Comparision.py

@@ -5,53 +5,53 @@ from transformers import pipeline
 from rake_nltk import Rake
 from nltk.corpus import stopwords
 from fuzzywuzzy import fuzz
-from openai import OpenAI
-import os
-from dotenv import load_dotenv
 
-# Load environment variables for OpenAI
-load_dotenv()
+# Ensure NLTK resources are downloaded
+nltk.download('punkt', quiet=True)
+nltk.download('stopwords', quiet=True)
 
-# Initialize OpenAI client for Llama 3 model
-client = OpenAI(
-  base_url="https://api-inference.huggingface.co/v1",
-  api_key=os.environ.get('HFSecret')  # Replace with your token
-)
-repo_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+st.title("Exploring Torch, Transformers, Rake, and Others analyzing Text")
 
-st.title("Parallel Sentiment Analysis: Transformers vs. Llama 3")
-
-# Define the options for the dropdown menu, selecting a remote txt file already created to analyze the text
-options = ['None', 'Apprecitation Letter', 'Regret Letter', 'Kindness Tale', 'Lost Melody Tale', 'Twitter Example 1', 'Twitter Example 2']
+# Define the options for the dropdown menu, Selecting a remote txt file already created to analyze the text
+options = ['None','Apprecitation Letter', 'Regret Letter', 'Kindness Tale', 'Lost Melody Tale', 'Twitter Example 1', 'Twitter Example 2']
 
 # Create a dropdown menu to select options
 selected_option = st.selectbox("Select a preset option", options)
 
 # Define URLs for different options
-urls = {
-    "Apprecitation Letter": "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Appreciation_Letter.txt",
-    "Regret Letter": "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Regret_Letter.txt",
-    "Kindness Tale": "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Kindness_Tale.txt",
-    "Lost Melody Tale": "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Lost_Melody_Tale.txt",
-    "Twitter Example 1": "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_1.txt",
-    "Twitter Example 2": "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_2.txt"
-}
+url_option1 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Appreciation_Letter.txt"
+url_option2 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Regret_Letter.txt"
+url_option3 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Kindness_Tale.txt"
+url_option4 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Lost_Melody_Tale.txt"
+url_option5 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_1.txt"
+url_option6 = "https://raw.githubusercontent.com/peteciank/public_files/main/Transformers/Twitter_Example_2.txt"
 
 # Function to fetch text content based on selected option
 def fetch_text_content(selected_option):
-    return requests.get(urls.get(selected_option, "")).text if selected_option in urls else ""
-
-# Fetch text content
+    if selected_option == 'Apprecitation Letter':
+        return requests.get(url_option1).text
+    elif selected_option == 'Regret Letter':
+        return requests.get(url_option2).text
+    elif selected_option == 'Kindness Tale':
+        return requests.get(url_option3).text
+    elif selected_option == 'Lost Melody Tale':
+        return requests.get(url_option4).text
+    elif selected_option == 'Twitter Example 1':
+        return requests.get(url_option5).text
+    elif selected_option == 'Twitter Example 2':
+        return requests.get(url_option6).text
+    else:
+        return ""
+
+# Fetch text content based on selected option
 jd = fetch_text_content(selected_option)
 
-# Download NLTK resources
-nltk.download('punkt')
-nltk.download('stopwords')
-
-# Initialize transformer sentiment analysis pipeline
+# Initialize pipeline for sentiment analysis
 pipe_sent = pipeline('sentiment-analysis')
+# Initialize pipeline for summarization
+pipe_summ = pipeline("summarization", model="facebook/bart-large-cnn")
 
-# Function to extract keywords
+# Function to extract keywords and remove duplicates
 def extract_keywords(text):
     r = Rake()
     r.extract_keywords_from_text(text)
@@ -75,40 +75,28 @@ def extract_keywords(text):
             seen_phrases.add(phrase)
     return unique_keywords[:10]
 
-# Text input
+# Display text content in a text area
 text = st.text_area('Enter the text to analyze', jd)
 
+# Run analysis when button is pressed
 if st.button("Start Analysis"):
-    col1, col2 = st.columns(2)
-
-    # Transformers (Column 1)
-    with col1:
-        st.header("Transformers Model")
-        with st.spinner("Analyzing with Transformers..."):
+    with st.spinner("Analyzing Sentiment"):
+        with st.expander("Sentiment Analysis - ✅ Completed", expanded=False):
             out_sentiment = pipe_sent(text)
             sentiment_score = out_sentiment[0]['score']
             sentiment_label = out_sentiment[0]['label']
             sentiment_emoji = '😊' if sentiment_label == 'POSITIVE' else '😞'
-            st.write(f"Sentiment Score: {sentiment_score}, Sentiment Label: {sentiment_label.capitalize()} {sentiment_emoji}")
-
-        st.subheader("Keywords")
-        keywords = extract_keywords(text)
-        st.write([keyword[1] for keyword in keywords])
-
-    # Llama 3 Model (Column 2)
-    with col2:
-        st.header("Llama 3 Model")
-        with st.spinner("Analyzing with Llama 3..."):
-            try:
-                stream = client.chat.completions.create(
-                    model=repo_id,
-                    messages=[{"role": "user", "content": text}],
-                    temperature=0.5,
-                    stream=True,
-                    max_tokens=3000
-                )
-                response = ''.join([chunk['choices'][0]['text'] for chunk in stream])
-                st.write(response)
-            except Exception as e:
-                st.error("Error occurred while fetching response from Llama 3")
-
+            sentiment_text = f"Sentiment Score: {sentiment_score}, Sentiment Label: {sentiment_label.capitalize()} {sentiment_emoji}"
+            st.write(sentiment_text)
+
+    with st.spinner("Summarizing - This may take a while"):
+        with st.expander("Summarization - ✅ Completed", expanded=False):        
+            out_summ = pipe_summ(text)
+            summarized_text = out_summ[0]['summary_text']
+            st.write(summarized_text)
+
+    with st.spinner("Extracting Keywords"):
+        with st.expander("Keywords Extraction - ✅ Completed", expanded=False):
+            keywords = extract_keywords(text)
+            keyword_list = [keyword[1] for keyword in keywords]
+            st.write(keyword_list)