Update pages/Comparision.py

pages/Comparision.py

@@ -1,145 +1,126 @@
 import streamlit as st
 import requests
-import nltk
 from transformers import pipeline
-from rake_nltk import Rake
-from nltk.corpus import stopwords
-from fuzzywuzzy import fuzz
-import openai
+import concurrent.futures
 import os
+import json
 from dotenv import load_dotenv
+from requests.exceptions import JSONDecodeError
 
-# Load environment variables for Llama 3
+# Load environment variables
 load_dotenv()
 
-# Title of the app
-st.title("Sentiment Analysis Comparison: Transformers vs Llama 3")
+# Initialize Hugging Face API for Llama 3
+HF_API_URL = "https://api-inference.huggingface.co/v1"
+HF_API_KEY = os.getenv('HFSecret')
 
-# Define the options for the dropdown menu, selecting a remote txt file already created to analyze the text
-options = ['None', 'Appreciation Letter', 'Regret Letter', 'Kindness Tale', 'Lost Melody Tale', 'Twitter Example 1', 'Twitter Example 2']
+# Initialize pipelines for Transformers
+pipe_sent_transformers = pipeline('sentiment-analysis')
+pipe_summ_transformers = pipeline("summarization", model="facebook/bart-large-cnn")
 
-# Create a dropdown menu to select options
-selected_option = st.selectbox("Select a preset option", options)
+# Define the Llama 3 model ID
+LLAMA_MODEL_ID = "meta-llama/Meta-Llama-3-8B-Instruct"
 
-# Define URLs for different options
-urls = {
-    'Appreciation 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"
-}
-
-# Function to fetch text content based on selected option
+# Function to fetch text content from Transformers app
 def fetch_text_content(selected_option):
-    return requests.get(urls[selected_option]).text if selected_option in urls else ""
-
-# Fetch text content based on selected option
-text = fetch_text_content(selected_option)
-
-# Display text content in a text area
-text = st.text_area('Enter the text to analyze', text)
-
-# Download NLTK resources
-nltk.download('punkt')
-nltk.download('stopwords')
-
-# Initialize sentiment, summarization, and keyword extraction pipelines for Transformers
-pipe_sent = pipeline('sentiment-analysis')
-pipe_summ = pipeline("summarization", model="facebook/bart-large-cnn")
-
-# Llama 3 initialization
-llama_api_key = os.getenv('HFSecret')
-llama_base_url = "https://api-inference.huggingface.co/v1"
-llama_repo_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+    options_urls = {
+        'Appreciation 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"
+    }
+    return requests.get(options_urls[selected_option]).text if selected_option in options_urls else ""
 
-# Function to use Llama 3 for sentiment analysis, summarization, and keyword extraction
+# Function to analyze sentiment using Llama
 def analyze_with_llama(text):
-    headers = {
-        "Authorization": f"Bearer {llama_api_key}"
-    }
+    headers = {"Authorization": f"Bearer {HF_API_KEY}"}
     data = {
         "inputs": text,
-        "parameters": {
-            "max_new_tokens": 200
+        "options": {
+            "use_cache": False,
+            "wait_for_model": True
         }
     }
-    # Perform the request
-    response = requests.post(f"{llama_base_url}/models/{llama_repo_id}", headers=headers, json=data)
-    return response.json()
-
-# Function to extract keywords using RAKE and remove duplicates
-def extract_keywords(text):
-    r = Rake()
-    r.extract_keywords_from_text(text)
-    phrases_with_scores = r.get_ranked_phrases_with_scores()
-    stop_words = set(stopwords.words('english'))
-    keywords = [(score, phrase) for score, phrase in phrases_with_scores if phrase.lower() not in stop_words]
-    keywords.sort(key=lambda x: x[0], reverse=True)
-    unique_keywords = []
-    seen_phrases = set()
-    for score, phrase in keywords:
-        if phrase not in seen_phrases:
-            similar_phrases = [seen_phrase for seen_phrase in seen_phrases if fuzz.ratio(phrase, seen_phrase) > 70]
-            if similar_phrases:
-                merged_phrase = max([phrase] + similar_phrases, key=len)
-                unique_keywords.append((score, merged_phrase))
-            else:
-                unique_keywords.append((score, phrase))
-            seen_phrases.add(phrase)
-    return unique_keywords[:10]
-
-# Create two columns
-col1, col2 = st.columns(2)
-
-# Transformer-based analysis in the first column
-with col1:
-    st.header("Transformer-based Analysis")
-    if st.button("Analyze with Transformers"):
-        with st.spinner("Analyzing with Transformers..."):
-            # Sentiment analysis
-            out_sentiment = pipe_sent(text)
-            sentiment_score = out_sentiment[0]['score']
-            sentiment_label = out_sentiment[0]['label']
-            sentiment_emoji = '😊' if sentiment_label == 'POSITIVE' else '😞'
-            sentiment_text = f"Sentiment Score: {sentiment_score}, Sentiment Label: {sentiment_label.capitalize()} {sentiment_emoji}"
-            
-            with st.expander("Sentiment Analysis (Transformers)"):
-                st.write(sentiment_text)
-            
-            # Summarization
-            out_summ = pipe_summ(text)
-            summarized_text = out_summ[0]['summary_text']
-            
-            with st.expander("Summarization (Transformers)"):
-                st.write(summarized_text)
-            
-            # Keyword extraction
-            keywords = extract_keywords(text)
-            keyword_list = [keyword[1] for keyword in keywords]
-            
-            with st.expander("Keywords (Transformers)"):
-                st.write(keyword_list)
-
-# Llama 3-based analysis in the second column
-with col2:
-    st.header("Llama 3-based Analysis")
-    if st.button("Analyze with Llama 3"):
-        with st.spinner("Analyzing with Llama 3..."):
-            llama_response = analyze_with_llama(text)
-            
-            if llama_response:
-                # Assuming the response returns in the same format, adjust if needed
-                sentiment_text = llama_response.get('sentiment_analysis', 'No sentiment detected')
-                summarized_text = llama_response.get('summarization', 'No summary available')
-                keywords = llama_response.get('keywords', 'No keywords available')
-                
-                with st.expander("Sentiment Analysis (Llama 3)"):
-                    st.write(sentiment_text)
-                
-                with st.expander("Summarization (Llama 3)"):
-                    st.write(summarized_text)
-                
-                with st.expander("Keywords (Llama 3)"):
-                    st.write(keywords)
+    
+    try:
+        response = requests.post(f"{HF_API_URL}/models/{LLAMA_MODEL_ID}", headers=headers, json=data)
+        response.raise_for_status()
+        return response.json()  # Ensure valid JSON
+    except (requests.RequestException, json.JSONDecodeError):
+        return {"error": "Error occurred while processing Llama model response."}
+
+# Function to run Transformer-based analysis
+def transformer_analysis(text):
+    # Sentiment analysis
+    sentiment_result = pipe_sent_transformers(text)
+    sentiment_score = sentiment_result[0]['score']
+    sentiment_label = sentiment_result[0]['label']
+    
+    # Summarization
+    summary_result = pipe_summ_transformers(text)
+    summary = summary_result[0]['summary_text']
+    
+    return sentiment_score, sentiment_label, summary
+
+# Function to run Llama-based analysis
+def llama_analysis(text):
+    llama_response = analyze_with_llama(text)
+    
+    if "error" in llama_response:
+        return "Error", "Error", "Error"
+    
+    # Extract sentiment and summary if valid JSON
+    sentiment_label = llama_response.get('sentiment', 'UNKNOWN')
+    sentiment_score = llama_response.get('sentiment_score', 0.0)
+    summary = llama_response.get('summary', 'No summary available.')
+    
+    return sentiment_score, sentiment_label, summary
+
+# Streamlit app layout with two columns
+st.title("Parallel Sentiment Analysis with Transformers and Llama")
+
+# Select text to analyze from dropdown
+options = ['None', 'Appreciation Letter', 'Regret Letter', 'Kindness Tale', 'Lost Melody Tale', 'Twitter Example 1', 'Twitter Example 2']
+selected_option = st.selectbox("Select a preset option", options)
+
+# Fetch text content for analysis
+jd = fetch_text_content(selected_option)
+text = st.text_area('Enter the text to analyze', jd)
+
+if st.button("Start Analysis"):
+    # Set up the two columns for parallel analysis
+    col1, col2 = st.columns(2)
+
+    with st.spinner("Running sentiment analysis..."):
+        with concurrent.futures.ThreadPoolExecutor() as executor:
+            # Execute analyses in parallel
+            future_transformer = executor.submit(transformer_analysis, text)
+            future_llama = executor.submit(llama_analysis, text)
+
+            # Retrieve results from both transformers and Llama
+            sentiment_score_transformer, sentiment_label_transformer, summary_transformer = future_transformer.result()
+            sentiment_score_llama, sentiment_label_llama, summary_llama = future_llama.result()
+
+    # Display results for Transformers-based analysis in the first column
+    with col1:
+        st.subheader("Transformers Analysis")
+        with st.expander("Sentiment Analysis - Transformers"):
+            sentiment_emoji = '😊' if sentiment_label_transformer == 'POSITIVE' else '😞'
+            st.write(f"Sentiment: {sentiment_label_transformer} ({sentiment_emoji})")
+            st.write(f"Score: {sentiment_score_transformer:.2f}")
+        
+        with st.expander("Summarization - Transformers"):
+            st.write(summary_transformer)
+
+    # Display results for Llama-based analysis in the second column
+    with col2:
+        st.subheader("Llama Analysis")
+        with st.expander("Sentiment Analysis - Llama"):
+            sentiment_emoji = '😊' if sentiment_label_llama == 'POSITIVE' else '😞'
+            st.write(f"Sentiment: {sentiment_label_llama} ({sentiment_emoji})")
+            st.write(f"Score: {sentiment_score_llama:.2f}")
+        
+        with st.expander("Summarization - Llama"):
+            st.write(summary_llama)