Fix: Add missing session state logic and file upload processing

app.py

@@ -34,7 +34,102 @@ st.title("Entity Resolution on CSV (Network Graph)")
 # SIDEBAR: CSV UPLOAD
 # ----------------------
 st.sidebar.header("Upload CSV for Entity Resolution")
-uploaded_file = st.sidebar.file_uploader("Choose a CSV file", type=["csv"])
+uploaded_file = st.sidebar.file_uploader(
+    "📁 Choose a CSV file",
+    type=["csv"],
+    help="Drag and drop your CSV file here or click to browse",
+    accept_multiple_files=False,
+    key="csv_uploader",
+    label_visibility="visible"
+)
+
+# File upload status info
+if uploaded_file is None:
+    st.sidebar.info("👆 **Drag & drop** your CSV file above or click to browse")
+    st.sidebar.markdown("**Supported formats:** `.csv` files")
+    st.sidebar.markdown("**Max size:** 200MB")
+
+# Initialize session state for data
+if 'uploaded_data_df' not in st.session_state:
+    st.session_state.uploaded_data_df = None
+if 'last_uploaded_file' not in st.session_state:
+    st.session_state.last_uploaded_file = None
+
+# Enhanced file upload processing
+if uploaded_file is not None:
+    try:
+        # Get file info
+        file_details = {
+            "filename": uploaded_file.name,
+            "size": uploaded_file.size,
+            "type": uploaded_file.type
+        }
+        
+        st.sidebar.success(f"📁 **{file_details['filename']}** ({file_details['size']} bytes)")
+        
+        # Process immediately if it's a new file
+        file_id = f"{file_details['filename']}_{file_details['size']}"
+        
+        if 'current_file_id' not in st.session_state:
+            st.session_state.current_file_id = None
+        
+        if st.session_state.current_file_id != file_id:
+            st.sidebar.info("🔄 Processing uploaded file...")
+            
+            try:
+                # Read the file
+                if uploaded_file.type == "text/csv" or uploaded_file.name.endswith('.csv'):
+                    df = pd.read_csv(uploaded_file)
+                else:
+                    # Try reading as CSV anyway
+                    df = pd.read_csv(uploaded_file)
+                
+                # Store in session state
+                st.session_state.uploaded_data_df = df
+                st.session_state.current_file_id = file_id
+                st.session_state.last_uploaded_file = uploaded_file.name
+                
+                st.sidebar.success(f"✅ **Successfully loaded!**")
+                st.sidebar.metric("📊 Dataset", f"{len(df)} rows × {len(df.columns)} cols")
+                
+            except Exception as e:
+                st.sidebar.error(f"❌ **Error:** {str(e)}")
+                st.sidebar.info("💡 Make sure your file is a valid CSV format")
+                st.session_state.uploaded_data_df = None
+        else:
+            st.sidebar.success("✅ **File already loaded**")
+            if st.session_state.uploaded_data_df is not None:
+                df = st.session_state.uploaded_data_df
+                st.sidebar.metric("📊 Current Dataset", f"{len(df)} rows × {len(df.columns)} cols")
+
+    except Exception as e:
+        st.sidebar.error(f"❌ **Upload Error:** {str(e)}")
+        st.session_state.uploaded_data_df = None
+
+# Show current data status
+if st.session_state.uploaded_data_df is not None:
+    st.sidebar.write(f"**Current Data:** {len(st.session_state.uploaded_data_df)} rows loaded")
+else:
+    st.sidebar.write("**Current Data:** None")
+
+# Clear data button
+if st.sidebar.button("🗑️ Clear All Data"):
+    st.session_state.uploaded_data_df = None
+    st.session_state.last_uploaded_file = None
+    st.sidebar.success("Data cleared!")
+
+# Generate sample data option
+st.sidebar.markdown("**Or use sample data:**")
+if st.sidebar.button("Use Sample Data"):
+    # Create simple sample data for testing
+    st.session_state.uploaded_data_df = pd.DataFrame({
+        'first_name': ['John', 'Jon', 'Jane', 'Jain', 'Mike', 'Michael'],
+        'last_name': ['Smith', 'Smith', 'Doe', 'Doe', 'Johnson', 'Johnson'], 
+        'email_address': ['john.smith@email.com', 'j.smith@gmail.com', 'jane.doe@company.com', 'jdoe@company.com', 'mike.j@work.com', 'michael.johnson@work.com'],
+        'phone_number': ['555-0123', '555-0123', '555-0456', '(555) 456-0000', '555-0789', '5550789']
+    })
+    st.session_state.last_uploaded_file = "sample_data"
+    st.sidebar.success("Sample data loaded!")
 
 similarity_threshold = st.sidebar.slider(
     "Similarity Threshold",
@@ -148,10 +243,12 @@ def find_connected_components_manual(nodes, edges):
 # ----------------------
 # LOAD CSV & PROCESS
 # ----------------------
-if uploaded_file is not None:
-    st.markdown("### Preview of Uploaded CSV Data")
-    df = pd.read_csv(uploaded_file)
+# Use the unified session state data
+if st.session_state.uploaded_data_df is not None:
+    st.markdown("### Preview of Data")
+    df = st.session_state.uploaded_data_df
     st.dataframe(df.head(10))
+    st.info(f"📊 Dataset contains {len(df)} rows and {len(df.columns)} columns")
 
     # Provide a "Run Entity Resolution" button
     if st.button("Run Entity Resolution"):