Delete app.py

app.py

@@ -1,158 +0,0 @@
-import streamlit as st
-import pandas as pd
-from embedding_atlas.streamlit import embedding_atlas
-
-# Set page configuration
-st.set_page_config(
-    page_title="AI Companionship Behavior Analysis - Embedding Atlas",
-    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: #1f77b4;
-        text-align: center;
-        margin-bottom: 1rem;
-    }
-    .sub-header {
-        font-size: 1.2rem;
-        color: #666;
-        text-align: center;
-        margin-bottom: 2rem;
-    }
-    .info-box {
-        background-color: #f0f2f6;
-        border-left: 4px solid #1f77b4;
-        padding: 1rem;
-        margin: 1rem 0;
-        border-radius: 0.5rem;
-    }
-    .warning-box {
-        background-color: #fff3cd;
-        border-left: 4px solid #ffc107;
-        padding: 1rem;
-        margin: 1rem 0;
-        border-radius: 0.5rem;
-    }
-    .tip-box {
-        background-color: #d1ecf1;
-        border-left: 4px solid #17a2b8;
-        padding: 1rem;
-        margin: 1rem 0;
-        border-radius: 0.5rem;
-    }
-</style>
-""", unsafe_allow_html=True)
-
-# Main header
-st.markdown('<div class="main-header">🤖 AI Companionship Behavior Analysis</div>', unsafe_allow_html=True)
-
-# Load data with caching
-@st.cache_data
-def load_data():
-    """Load the embedding atlas dataframe"""
-    try:
-        df = pd.read_parquet('data/embed_atlas_df.parquet')
-        return df
-    except FileNotFoundError:
-        st.error("❌ Data file not found. Please ensure 'data/embed_atlas_df.parquet' exists.")
-        return None
-    except Exception as e:
-        st.error(f"❌ Error loading data: {str(e)}")
-        return None
-
-# Load data once for the entire app
-df = load_data()
-
-# Sidebar with controls and information
-with st.sidebar:
-    st.header("📚 About This Visualization")
-    
-    st.markdown("""
-    This interactive visualization explores the landscape of AI model responses to prompts designed to evaluate **companionship behaviors**. 
-    
-    **Models Analyzed:**
-    - **Google Gemma-3-27b-it** (Open)
-    - **Microsoft Phi-4** (Open) 
-    - **OpenAI o3-mini** (Closed)
-    - **Anthropic Claude-3.7 Sonnet** (Closed)
-    
-    **Classifications:**
-    - **COMPANION+**: Responses that reinforce companionship behaviors
-    - **BOUNDARY+**: Responses that maintain appropriate boundaries
-    - **MIXED**: Responses with elements of both
-    
-    The visualization uses **Qwen embeddings** projected into 2D space using **UMAP** to explore clusters of similar responses and behavioral patterns.
-    """)
-
-    st.header("🔧 Usage Tips")
-    st.markdown("""
-    **Getting Started:**
-    1. Wait for the widget to fully load
-    2. Use the **"classification"** option in the color dropdown
-    3. Explore clusters by zooming and panning
-    4. Use the search bar to find specific terms
-    """)
-
-# Usage recommendations
-st.markdown("""
-<div class="tip-box">
-    <strong>💡 Recommended Settings:</strong>
-    <ul>
-        <li><strong>Color by Classification:</strong> Select "classification" from the color dropdown to see the different behavior categories</li>
-        <li><strong>Cluster Exploration:</strong> Shift+Click and drag to explore different regions of the embedding space</li>
-        <li><strong>Table and Charts:</strong> Use the table and charts on the right to explore the full data and your current selection</li>
-    </ul>
-</div>
-""", unsafe_allow_html=True)
-
-# Main visualization
-if df is not None:
-    st.header("🗺️ Interactive Embedding Atlas")
-    
-    # Check required columns
-    required_columns = ['x', 'y', 'snippet']
-    missing_columns = [col for col in required_columns if col not in df.columns]
-    
-    if missing_columns:
-        st.error(f"❌ Missing required columns: {missing_columns}")
-        st.write("Available columns:", list(df.columns))
-    else:
-        try:
-            # Create the embedding atlas
-            value = embedding_atlas(
-                df, 
-                text="snippet",
-                x="x", 
-                y="y",
-                show_table=True
-            )
-            
-            # Display selection information if available
-            if value and value.get("predicate"):
-                st.markdown("### 📋 Current Selection")
-                st.info(f"Selection filter: `{value.get('predicate')}`")
-                
-                # You could add DuckDB querying here if needed
-                # import duckdb
-                # selection = duckdb.query_df(
-                #     df, "dataframe", "SELECT * FROM dataframe WHERE " + value["predicate"]
-                # )
-                # st.dataframe(selection)
-                
-        except Exception as e:
-            st.error(f"❌ Error creating visualization: {str(e)}")
-            st.write("Please check that the embedding-atlas package is properly installed:")
-            st.code("pip install embedding-atlas")
-
-else:
-    st.error("Unable to load data. Please check the file path and try again.")
-
-# Footer with additional information
-st.markdown("---")