Spaces:
Runtime error
Runtime error
| import streamlit as st | |
| import requests | |
| import pandas as pd | |
| import io | |
| import os | |
| from PIL import Image | |
| import time | |
| # Configure page | |
| st.set_page_config( | |
| page_title="PromptPrepML - Auto ML Data Preprocessing", | |
| page_icon="🤖", | |
| layout="wide", | |
| initial_sidebar_state="expanded" | |
| ) | |
| # Custom CSS for better styling | |
| st.markdown(""" | |
| <style> | |
| .main-header { | |
| font-size: 2.5rem; | |
| font-weight: bold; | |
| color: #1f2937; | |
| text-align: center; | |
| margin-bottom: 2rem; | |
| } | |
| .step-header { | |
| font-size: 1.5rem; | |
| font-weight: 600; | |
| color: #374151; | |
| margin: 1rem 0; | |
| } | |
| .success-box { | |
| background-color: #f0fdf4; | |
| border: 1px solid #bbf7d0; | |
| border-radius: 0.5rem; | |
| padding: 1rem; | |
| margin: 1rem 0; | |
| } | |
| .info-box { | |
| background-color: #eff6ff; | |
| border: 1px solid #bfdbfe; | |
| border-radius: 0.5rem; | |
| padding: 1rem; | |
| margin: 1rem 0; | |
| } | |
| .warning-box { | |
| background-color: #fffbeb; | |
| border: 1px solid #fed7aa; | |
| border-radius: 0.5rem; | |
| padding: 1rem; | |
| margin: 1rem 0; | |
| } | |
| </style> | |
| """, unsafe_allow_html=True) | |
| # API base URLs - try deployed backend first, fallback to localhost | |
| DEPLOYED_BACKEND = "https://promptprepml-backend.railway.app" | |
| LOCAL_BACKEND = "http://localhost:8000" | |
| def check_backend_health(): | |
| """Check if backend is running (try deployed first, then local)""" | |
| backends = [DEPLOYED_BACKEND, LOCAL_BACKEND] | |
| for backend_url in backends: | |
| try: | |
| response = requests.get(f"{backend_url}/health", timeout=5) | |
| if response.status_code == 200: | |
| st.session_state.backend_url = backend_url | |
| return True, backend_url | |
| except: | |
| continue | |
| return False, None | |
| def upload_dataset(uploaded_file): | |
| """Upload dataset to backend""" | |
| if 'backend_url' not in st.session_state: | |
| return None, "Backend not connected" | |
| try: | |
| files = {'file': uploaded_file} | |
| response = requests.post(f"{st.session_state.backend_url}/upload-dataset", files=files) | |
| if response.status_code == 200: | |
| return response.json(), None | |
| else: | |
| return None, f"Upload failed: {response.text}" | |
| except Exception as e: | |
| return None, f"Upload error: {str(e)}" | |
| def process_pipeline(uploaded_file, prompt): | |
| """Process dataset through ML pipeline""" | |
| if 'backend_url' not in st.session_state: | |
| return None, "Backend not connected" | |
| try: | |
| files = {'file': uploaded_file} | |
| data = {'prompt': prompt} | |
| response = requests.post(f"{st.session_state.backend_url}/process-pipeline", files=files, data=data) | |
| if response.status_code == 200: | |
| return response.json(), None | |
| else: | |
| return None, f"Processing failed: {response.text}" | |
| except Exception as e: | |
| return None, f"Processing error: {str(e)}" | |
| def download_file(filename): | |
| """Download processed file""" | |
| if 'backend_url' not in st.session_state: | |
| return None, "Backend not connected" | |
| try: | |
| response = requests.get(f"{st.session_state.backend_url}/api/download/{filename}") | |
| if response.status_code == 200: | |
| return response.content, None | |
| else: | |
| return None, f"Download failed: {response.text}" | |
| except Exception as e: | |
| return None, f"Download error: {str(e)}" | |
| def main(): | |
| # Main header | |
| st.markdown('<h1 class="main-header">🤖 PromptPrepML</h1>', unsafe_allow_html=True) | |
| st.markdown('<p style="text-align: center; color: #6b7280; font-size: 1.1rem;">Convert natural language prompts into ML-ready datasets</p>', unsafe_allow_html=True) | |
| # Check backend health | |
| backend_healthy, backend_url = check_backend_health() | |
| if not backend_healthy: | |
| st.error("❌ Backend is not running! Please start the backend:") | |
| st.code(""" | |
| cd promptprepml/backend | |
| venv\\Scripts\\activate | |
| python app/main.py | |
| # OR wait for deployed backend to be ready | |
| """) | |
| st.info("🚀 **Deploying backend to cloud...** This will make the app work standalone!") | |
| return | |
| st.success(f"✅ Backend connected at: {backend_url}") | |
| # Sidebar for navigation | |
| st.sidebar.title("📋 Processing Steps") | |
| # Initialize session state | |
| if 'step' not in st.session_state: | |
| st.session_state.step = 'upload' | |
| if 'upload_result' not in st.session_state: | |
| st.session_state.upload_result = None | |
| if 'processing_result' not in st.session_state: | |
| st.session_state.processing_result = None | |
| # Step indicators | |
| steps = ['📤 Upload', '⚙️ Configure', '🚀 Process', '📊 Results'] | |
| current_step_index = 0 | |
| if st.session_state.step == 'upload': | |
| current_step_index = 0 | |
| elif st.session_state.step == 'configure': | |
| current_step_index = 1 | |
| elif st.session_state.step == 'process': | |
| current_step_index = 2 | |
| elif st.session_state.step == 'results': | |
| current_step_index = 3 | |
| # Display step indicators | |
| for i, step in enumerate(steps): | |
| if i < current_step_index: | |
| st.sidebar.success(f"✅ {step}") | |
| elif i == current_step_index: | |
| st.sidebar.info(f"🔄 {step}") | |
| else: | |
| st.sidebar.write(f"⏳ {step}") | |
| # Step 1: Upload Dataset | |
| if st.session_state.step == 'upload': | |
| st.markdown('<h2 class="step-header">📤 Step 1: Upload Dataset</h2>', unsafe_allow_html=True) | |
| uploaded_file = st.file_uploader( | |
| "Choose a CSV file", | |
| type=['csv'], | |
| help="Upload your dataset for preprocessing" | |
| ) | |
| if uploaded_file is not None: | |
| st.info(f"📄 File uploaded: `{uploaded_file.name}`") | |
| # Show file preview | |
| try: | |
| df = pd.read_csv(uploaded_file) | |
| st.markdown('<div class="info-box">', unsafe_allow_html=True) | |
| st.markdown(f"**Dataset Shape:** {df.shape}") | |
| st.markdown(f"**Columns:** {', '.join(df.columns)}") | |
| st.dataframe(df.head()) | |
| st.markdown('</div>', unsafe_allow_html=True) | |
| if st.button("🚀 Continue to Configuration", type="primary"): | |
| # Upload to backend | |
| with st.spinner("Uploading dataset..."): | |
| result, error = upload_dataset(uploaded_file) | |
| if error: | |
| st.error(f"❌ Upload failed: {error}") | |
| else: | |
| st.session_state.upload_result = result | |
| st.session_state.step = 'configure' | |
| st.rerun() | |
| except Exception as e: | |
| st.error(f"❌ Error reading file: {str(e)}") | |
| # Step 2: Configure Processing | |
| elif st.session_state.step == 'configure': | |
| st.markdown('<h2 class="step-header">⚙️ Step 2: Configure Processing</h2>', unsafe_allow_html=True) | |
| if st.session_state.upload_result: | |
| file_info = st.session_state.upload_result | |
| st.markdown('<div class="info-box">', unsafe_allow_html=True) | |
| st.markdown(f"**File:** {file_info.get('filename', 'Unknown')}") | |
| st.markdown(f"**Size:** {file_info.get('size', 'Unknown')} bytes") | |
| st.markdown('</div>', unsafe_allow_html=True) | |
| # Processing options | |
| prompt = st.text_area( | |
| "Describe your preprocessing needs:", | |
| value="Prepare this dataset for machine learning. Handle missing values, remove identifier columns, extract date features, encode categorical variables, and scale numeric features.", | |
| height=100, | |
| help="Describe what you want to do with your dataset in natural language" | |
| ) | |
| col1, col2 = st.columns([1, 1]) | |
| with col1: | |
| if st.button("⬅️ Back", type="secondary"): | |
| st.session_state.step = 'upload' | |
| st.rerun() | |
| with col2: | |
| if st.button("🚀 Start Processing", type="primary"): | |
| if uploaded_file is not None: | |
| with st.spinner("Processing dataset... This may take a few minutes."): | |
| result, error = process_pipeline(uploaded_file, prompt) | |
| if error: | |
| st.error(f"❌ Processing failed: {error}") | |
| else: | |
| st.session_state.processing_result = result | |
| st.session_state.step = 'results' | |
| st.rerun() | |
| # Step 3: Results | |
| elif st.session_state.step == 'results': | |
| st.markdown('<h2 class="step-header">📊 Step 3: Results</h2>', unsafe_allow_html=True) | |
| if st.session_state.processing_result: | |
| result = st.session_state.processing_result | |
| # Success message | |
| st.markdown('<div class="success-box">', unsafe_allow_html=True) | |
| st.success("✅ Dataset processed successfully!") | |
| st.markdown('</div>', unsafe_allow_html=True) | |
| # Results summary | |
| col1, col2 = st.columns([2, 1]) | |
| with col1: | |
| st.markdown("### 📈 Processing Summary") | |
| dataset_info = result.get('dataset_info', {}) | |
| if dataset_info: | |
| basic_info = dataset_info.get('basic_info', {}) | |
| st.markdown(f"- **Original Shape:** {basic_info.get('shape', 'Unknown')}") | |
| st.markdown(f"- **Columns:** {basic_info.get('columns', 'Unknown')}") | |
| preprocessing_info = result.get('preprocessing_info', {}) | |
| if preprocessing_info: | |
| st.markdown(f"- **Processed Shape:** {preprocessing_info.get('processed_shape', 'Unknown')}") | |
| # Dataset preview | |
| st.markdown("### 👀 Dataset Preview") | |
| preview_data = result.get('preview_data', []) | |
| if preview_data: | |
| df_preview = pd.DataFrame(preview_data) | |
| st.dataframe(df_preview) | |
| with col2: | |
| st.markdown("### 📥 Download Files") | |
| download_links = [ | |
| ("Processed Dataset", "processed_dataset.csv"), | |
| ("Training Set", "train.csv"), | |
| ("Test Set", "test.csv"), | |
| ("Pipeline", "pipeline.pkl"), | |
| ("EDA Report", "eda_report.html") | |
| ] | |
| for name, filename in download_links: | |
| if st.button(f"📥 {name}", key=f"download_{filename}"): | |
| with st.spinner(f"Downloading {filename}..."): | |
| file_content, error = download_file(filename) | |
| if error: | |
| st.error(f"❌ Download failed: {error}") | |
| else: | |
| st.download_button( | |
| label=f"💾 Save {filename}", | |
| data=file_content, | |
| file_name=filename, | |
| mime="application/octet-stream" | |
| ) | |
| # Action buttons | |
| col1, col2 = st.columns([1, 1]) | |
| with col1: | |
| if st.button("🔄 Process New Dataset", type="secondary"): | |
| # Reset session state | |
| for key in list(st.session_state.keys()): | |
| del st.session_state[key] | |
| st.session_state.step = 'upload' | |
| st.rerun() | |
| with col2: | |
| if st.button("📈 View EDA Report", type="primary"): | |
| st.info("📊 EDA Report feature coming soon!") | |
| # Footer | |
| st.markdown("---") | |
| st.markdown(""" | |
| <div style="text-align: center; color: #6b7280; margin-top: 2rem;"> | |
| <p><strong>PromptPrepML</strong> - Automated ML Data Preprocessing</p> | |
| <p><small>Convert natural language prompts into ML-ready datasets</small></p> | |
| </div> | |
| """, unsafe_allow_html=True) | |
| if __name__ == "__main__": | |
| main() | |