Update app.py

app.py

@@ -6,35 +6,22 @@ from collections import defaultdict
 
 # Page configuration
 st.set_page_config(
-    page_title="Text Similarity Explorer",
-    page_icon="📝",
+    page_title="Address Similarity Explorer",
+    page_icon="🏠",
     layout="wide"
 )
 
-# Custom CSS
-st.markdown("""
-    <style>
-    .title-font {
-        font-size: 28px !important;
-        font-weight: bold;
-        color: #2c3e50;
-    }
-    </style>
-""", unsafe_allow_html=True)
-
 class ShingleSimilarity:
     def __init__(self, k=3):
-        self.k = k  # shingle size
+        self.k = k
         
     def get_shingles(self, text):
-        """Convert text to k-shingles"""
         text = text.lower().strip()
         if len(text) < self.k:
             return {text}
         return {text[i:i+self.k] for i in range(len(text) - self.k + 1)}
     
     def similarity(self, text1, text2):
-        """Calculate Jaccard similarity between two texts using shingles"""
         shingles1 = self.get_shingles(text1)
         shingles2 = self.get_shingles(text2)
         
@@ -43,196 +30,86 @@ class ShingleSimilarity:
         
         return intersection / union if union > 0 else 0.0
 
-def create_similarity_based_visualization(texts, shingle_sim):
-    """Create visualization based on shingle similarity distances"""
+def create_similarity_visualization(texts, shingle_sim):
     n = len(texts)
-    
-    # Create similarity matrix
     similarity_matrix = np.zeros((n, n))
+    
     for i in range(n):
         for j in range(n):
             similarity_matrix[i][j] = shingle_sim.similarity(texts[i], texts[j])
     
-    # Convert similarities to distances
-    distance_matrix = 1 - similarity_matrix
+    # Create visualization
+    fig = go.Figure(data=go.Heatmap(
+        z=similarity_matrix,
+        x=texts,
+        y=texts,
+        colorscale='Viridis',
+        text=np.round(similarity_matrix, 4),
+        texttemplate='%{text}',
+        textfont={"size": 12},
+    ))
     
-    if n == 2:
-        # For 2 texts, create a simple 2D visualization
-        fig = go.Figure()
-        similarity = similarity_matrix[0][1]
-        
-        fig.add_trace(go.Scatter(
-            x=[0, 1-similarity],
-            y=[0, 0],
-            mode='markers+text',
-            text=texts,
-            textposition='top center',
-            marker=dict(size=10, color=['blue', 'red'])
-        ))
-        
-        fig.update_layout(
-            title=f"Text Similarity Visualization (Similarity: {similarity:.3f})",
-            xaxis_title="Relative Distance",
-            yaxis_title="",
-            height=400,
-            showlegend=False,
-            xaxis=dict(range=[-0.1, 1.1]),
-            yaxis=dict(range=[-0.5, 0.5])
-        )
-    else:
-        # For 3 or more texts, use MDS for 3D visualization
-        mds = MDS(n_components=3, dissimilarity='precomputed', random_state=42)
-        coords = mds.fit_transform(distance_matrix)
-        
-        fig = go.Figure()
-        
-        # Add points
-        fig.add_trace(go.Scatter3d(
-            x=coords[:, 0],
-            y=coords[:, 1],
-            z=coords[:, 2],
-            mode='markers+text',
-            text=texts,
-            textposition='top center',
-            marker=dict(
-                size=10,
-                color=list(range(len(texts))),
-                colorscale='Viridis',
-                opacity=0.8
-            ),
-            name='Texts'
-        ))
-        
-        # Add lines between points
-        for i in range(n):
-            for j in range(i+1, n):
-                opacity = max(0.1, min(1.0, similarity_matrix[i,j]))
-                fig.add_trace(go.Scatter3d(
-                    x=[coords[i,0], coords[j,0]],
-                    y=[coords[i,1], coords[j,1]],
-                    z=[coords[i,2], coords[j,2]],
-                    mode='lines',
-                    line=dict(color='gray', width=2),
-                    opacity=opacity,
-                    showlegend=False,
-                    hoverinfo='skip'
-                ))
-        
-        fig.update_layout(
-            title="3D Similarity Visualization",
-            scene=dict(
-                xaxis_title="Dimension 1",
-                yaxis_title="Dimension 2",
-                zaxis_title="Dimension 3",
-                camera=dict(
-                    up=dict(x=0, y=0, z=1),
-                    center=dict(x=0, y=0, z=0),
-                    eye=dict(x=1.5, y=1.5, z=1.5)
-                )
-            ),
-            height=700,
-            showlegend=True
-        )
+    fig.update_layout(
+        title="Address Similarity Matrix",
+        height=600,
+        width=800
+    )
     
     return fig
 
 def main():
-    st.title("📝 Text Similarity Explorer")
-    st.markdown("<p class='title-font'>Analyze text similarities using k-shingles</p>", unsafe_allow_html=True)
+    st.title("🏠 Address Similarity Analyzer")
     
-    # Shingle size configuration
-    shingle_size = st.sidebar.slider("Shingle Size (k)", 2, 5, 3)
-    shingle_sim = ShingleSimilarity(k=shingle_size)
+    # Example addresses from the image
+    example_addresses = [
+        "123 North Hampton Blvd",
+        "123 N Hampton Blvd",
+        "123 North Hampton Boulevard",
+        "123 N. Hampton Blvd",
+        "123 N. Hampton Boulevard",
+        "65 South Hampton Blvd"
+    ]
     
-    with st.expander("ℹ️ About Shingle-based Similarity", expanded=True):
-        st.markdown("""
-        - **Shingles** are consecutive character sequences of length k
-        - **Higher k** means more precise matching
-        - **Lower k** captures more general similarities
-        - Similarity is calculated using Jaccard similarity of shingle sets
-        """)
+    st.markdown("### Address Similarity Analysis")
+    st.info("If the similarity score is over 0.4, addresses are considered to be the same location")
     
-    tabs = st.tabs(["💫 Text Similarity", "🎯 Multi-Text Analysis"])
+    # Initialize shingle similarity with k=3
+    shingle_sim = ShingleSimilarity(k=3)
     
-    with tabs[0]:
-        st.markdown("### Compare Two Texts")
-        col1, col2 = st.columns(2)
-        
-        with col1:
-            text1 = st.text_area("First Text", value="I love programming in Python", height=100)
-            st.markdown("#### Shingles:")
-            st.write(sorted(shingle_sim.get_shingles(text1)))
-            
-        with col2:
-            text2 = st.text_area("Second Text", value="Coding with Python is amazing", height=100)
-            st.markdown("#### Shingles:")
-            st.write(sorted(shingle_sim.get_shingles(text2)))
-        
-        if st.button("Analyze Similarity", key="sim_button"):
-            similarity = shingle_sim.similarity(text1, text2)
-            
-            col1, col2 = st.columns(2)
-            with col1:
-                st.metric(
-                    label="Similarity Score",
-                    value=f"{similarity:.4f}",
-                    help="1.0 = identical, 0.0 = completely different"
-                )
-                interpretation = (
-                    "🟢 Very Similar" if similarity > 0.8
-                    else "🟡 Moderately Similar" if similarity > 0.5
-                    else "🔴 Different"
-                )
-                st.info(f"Interpretation: {interpretation}")
-            
-            with col2:
-                st.plotly_chart(
-                    create_similarity_based_visualization([text1, text2], shingle_sim),
-                    use_container_width=True
-                )
+    # Display similarity matrix
+    fig = create_similarity_visualization(example_addresses, shingle_sim)
+    st.plotly_chart(fig)
+    
+    # Interactive comparison
+    st.markdown("### Compare Two Addresses")
+    col1, col2 = st.columns(2)
+    
+    with col1:
+        addr1 = st.selectbox("Select first address:", example_addresses)
+    with col2:
+        addr2 = st.selectbox("Select second address:", example_addresses, index=1)
     
-    with tabs[1]:
-        st.markdown("### Analyze Multiple Texts")
-        num_texts = st.slider("Number of texts:", 2, 6, 3)
-        texts = []
+    if st.button("Compare Addresses"):
+        similarity = shingle_sim.similarity(addr1, addr2)
         
-        for i in range(num_texts):
-            text = st.text_area(
-                f"Text {i+1}",
-                value=f"Example text {i+1}",
-                height=100,
-                key=f"text_{i}"
-            )
-            texts.append(text)
+        st.metric(
+            label="Similarity Score",
+            value=f"{similarity:.4f}"
+        )
+        
+        is_same = similarity > 0.4
+        status = "✅ Same Location" if is_same else "❌ Different Locations"
+        color = "success" if is_same else "error"
+        st.markdown(f"**Status:** :{color}[{status}]")
         
-        if st.button("Analyze Texts", key="analyze_button"):
-            st.plotly_chart(
-                create_similarity_based_visualization(texts, shingle_sim),
-                use_container_width=True
-            )
-            
-            # Show similarity matrix
-            st.markdown("### Similarity Matrix")
-            similarity_matrix = np.zeros((len(texts), len(texts)))
-            for i in range(len(texts)):
-                for j in range(len(texts)):
-                    similarity_matrix[i][j] = shingle_sim.similarity(texts[i], texts[j])
-            
-            fig = go.Figure(data=go.Heatmap(
-                z=similarity_matrix,
-                x=[f"Text {i+1}" for i in range(len(texts))],
-                y=[f"Text {i+1}" for i in range(len(texts))],
-                colorscale='Viridis',
-                text=np.round(similarity_matrix, 3),
-                texttemplate='%{text}',
-                textfont={"size": 12},
-            ))
-            
-            fig.update_layout(
-                title="Similarity Matrix",
-                height=400
-            )
-            st.plotly_chart(fig, use_container_width=True)
+        # Show shingles comparison
+        col1, col2 = st.columns(2)
+        with col1:
+            st.markdown(f"**Shingles for Address 1:**")
+            st.write(sorted(shingle_sim.get_shingles(addr1)))
+        with col2:
+            st.markdown(f"**Shingles for Address 2:**")
+            st.write(sorted(shingle_sim.get_shingles(addr2)))
 
 if __name__ == "__main__":
     main()