Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| import pandas as pd | |
| import tempfile | |
| import os | |
| # Page configuration | |
| st.set_page_config( | |
| page_title="📊 LLM Data Analyzer", | |
| page_icon="📊", | |
| layout="wide", | |
| initial_sidebar_state="expanded" | |
| ) | |
| st.title("📊 LLM Data Analyzer") | |
| st.write("*Analyze data and chat with AI - Powered by Hugging Face Spaces*") | |
| # Simple AI responses without API calls | |
| def get_ai_response(prompt): | |
| """Generate simple AI-like responses without external API""" | |
| prompt_lower = prompt.lower() | |
| # Data analysis responses | |
| if "average" in prompt_lower or "mean" in prompt_lower: | |
| return "Based on the data summary, the average values can be calculated from the statistical measures shown. For more detailed analysis, look at the mean values in the data description." | |
| elif "trend" in prompt_lower or "pattern" in prompt_lower: | |
| return "The data shows various patterns. Examine the min, max, and std deviation values to understand the distribution and trends in your dataset." | |
| elif "correlation" in prompt_lower or "relationship" in prompt_lower: | |
| return "To understand relationships between columns, look at how values change together. The standard deviation and percentiles in the summary can give insights." | |
| elif "outlier" in prompt_lower or "unusual" in prompt_lower: | |
| return "Check the min/max values and compare them to the mean and median. Large differences suggest outliers in your data." | |
| elif "summary" in prompt_lower or "overview" in prompt_lower: | |
| return "The data summary shows key statistics including count, mean, standard deviation, min, 25%, 50%, 75%, and max values for each column." | |
| # General chat responses | |
| elif "hello" in prompt_lower or "hi" in prompt_lower: | |
| return "Hello! I'm the LLM Data Analyzer. I can help you understand your data better. Upload a CSV or Excel file and ask me questions about it!" | |
| elif "what can you do" in prompt_lower or "help" in prompt_lower: | |
| return "I can help you: 1) Upload and preview data 2) View statistics 3) Answer questions about your data 4) Have conversations. Try uploading a CSV or Excel file!" | |
| elif "thank" in prompt_lower: | |
| return "You're welcome! Feel free to ask more questions about your data anytime." | |
| else: | |
| return "That's an interesting question! To get the most accurate analysis, please upload your data and ask specific questions about the columns and values. I can then provide detailed insights based on your actual dataset." | |
| # Create tabs | |
| tab1, tab2, tab3 = st.tabs(["📤 Upload & Analyze", "💬 Chat", "📊 About"]) | |
| # ============================================================================ | |
| # TAB 1: Upload & Analyze | |
| # ============================================================================ | |
| with tab1: | |
| st.header("📤 Upload and Analyze Data") | |
| st.info("💡 Tip: CSV files work best. If upload fails, try saving your Excel file as CSV first.") | |
| uploaded_file = st.file_uploader( | |
| "Upload a CSV or Excel file", | |
| type=["csv", "xlsx", "xls"], | |
| help="Supported formats: CSV, Excel" | |
| ) | |
| if uploaded_file is not None: | |
| try: | |
| st.success(f"✅ File received: {uploaded_file.name}") | |
| # Save to temp file to avoid streaming issues | |
| with tempfile.NamedTemporaryFile(delete=False, suffix=os.path.splitext(uploaded_file.name)[1]) as tmp_file: | |
| tmp_file.write(uploaded_file.getbuffer()) | |
| tmp_path = tmp_file.name | |
| # Read file | |
| try: | |
| if uploaded_file.name.lower().endswith('.csv'): | |
| df = pd.read_csv(tmp_path, on_bad_lines='skip') | |
| else: | |
| # Try multiple engines for Excel | |
| try: | |
| df = pd.read_excel(tmp_path, engine='openpyxl') | |
| except: | |
| try: | |
| df = pd.read_excel(tmp_path, engine='xlrd') | |
| except: | |
| df = pd.read_excel(tmp_path) | |
| except Exception as read_error: | |
| st.error("❌ Could not read file. Try converting to CSV format.") | |
| st.info("**Solution:** Open in Excel → File → Save As → CSV → Upload again") | |
| st.stop() | |
| finally: | |
| # Clean up temp file | |
| try: | |
| os.unlink(tmp_path) | |
| except: | |
| pass | |
| # Validate dataframe | |
| if df.empty: | |
| st.error("❌ File is empty. Make sure it contains data rows.") | |
| st.stop() | |
| # Display data preview | |
| st.subheader("📋 Data Preview") | |
| st.dataframe(df.head(10), use_container_width=True) | |
| # Display statistics | |
| st.subheader("📊 Data Statistics") | |
| col1, col2, col3 = st.columns(3) | |
| with col1: | |
| st.metric("Rows", len(df)) | |
| with col2: | |
| st.metric("Columns", len(df.columns)) | |
| with col3: | |
| st.metric("Columns", ", ".join(df.columns[:3].tolist()) + "...") | |
| # Detailed statistics | |
| try: | |
| numeric_df = df.select_dtypes(include=['number']) | |
| if not numeric_df.empty: | |
| st.write("### Numeric Columns Summary") | |
| st.write(numeric_df.describe().T) | |
| else: | |
| st.info("No numeric columns found in dataset.") | |
| except: | |
| st.info("Could not generate statistics for this data.") | |
| # Ask AI about the data | |
| st.subheader("❓ Ask AI About Your Data") | |
| question = st.text_input( | |
| "What would you like to know about this data?", | |
| placeholder="e.g., What is the average? What patterns do you see?", | |
| key="data_question" | |
| ) | |
| if question: | |
| response = get_ai_response(question) | |
| st.success("✅ Analysis Complete") | |
| st.write(response) | |
| except Exception as e: | |
| st.error(f"❌ Unexpected error: {str(e)[:50]}") | |
| st.info("**Try this:** Save your Excel file as CSV, then upload again.") | |
| # ============================================================================ | |
| # TAB 2: Chat | |
| # ============================================================================ | |
| with tab2: | |
| st.header("💬 Chat with AI Assistant") | |
| st.write("Have a conversation about data analysis and AI.") | |
| # Initialize session state for chat history | |
| if "messages" not in st.session_state: | |
| st.session_state.messages = [] | |
| # Display chat history | |
| for message in st.session_state.messages: | |
| with st.chat_message(message["role"]): | |
| st.markdown(message["content"]) | |
| # Chat input | |
| user_input = st.text_input( | |
| "Type your message:", | |
| placeholder="Ask me anything...", | |
| key="chat_input" | |
| ) | |
| if user_input: | |
| # Add user message immediately | |
| st.session_state.messages.append({"role": "user", "content": user_input}) | |
| # Get response | |
| response = get_ai_response(user_input) | |
| # Add assistant message | |
| st.session_state.messages.append({ | |
| "role": "assistant", | |
| "content": response | |
| }) | |
| # Display latest messages | |
| st.divider() | |
| with st.chat_message("assistant"): | |
| st.markdown(response) | |
| # ============================================================================ | |
| # TAB 3: About | |
| # ============================================================================ | |
| with tab3: | |
| st.header("ℹ️ About This App") | |
| st.markdown(""" | |
| ### 🎯 What is this? | |
| **LLM Data Analyzer** is a tool for analyzing data and having conversations about your datasets. | |
| ### 🔧 Technology Stack | |
| - **Framework:** Streamlit | |
| - **Hosting:** Hugging Face Spaces (Free Tier) | |
| - **Language:** Python | |
| ### ⚡ Features | |
| 1. **Data Analysis**: Upload CSV/Excel and ask questions about your data | |
| 2. **Chat**: Have conversations about data insights | |
| 3. **Statistics**: View comprehensive data summaries | |
| ### 📝 How to Use | |
| 1. **Upload Data** - Start by uploading a CSV or Excel file | |
| 2. **Preview** - Review your data and statistics | |
| 3. **Ask Questions** - Ask about patterns, averages, outliers, etc. | |
| 4. **Chat** - Have conversations about your analysis | |
| ### 🌐 Powered By | |
| - [Hugging Face](https://huggingface.co/) - AI platform and hosting | |
| - [Streamlit](https://streamlit.io/) - Web framework | |
| - [Pandas](https://pandas.pydata.org/) - Data analysis | |
| ### 📖 Troubleshooting | |
| **File upload fails with 403 error?** | |
| - Convert Excel to CSV first (File → Save As → CSV format) | |
| - Upload the CSV file instead | |
| - This solves 99% of upload issues | |
| **Still having issues?** | |
| - Make sure file has valid data | |
| - File size should be under 50MB | |
| - Try a simpler file first to test | |
| ### 🔗 Links | |
| - [GitHub Repository](https://github.com/Arif-Badhon/LLM-Data-Analyzer) | |
| - [Hugging Face Hub](https://huggingface.co/) | |
| --- | |
| **Version:** 1.1 | **Last Updated:** Dec 2025 | |
| 💡 **Note:** This version uses intelligent pattern matching for responses. | |
| """) |