Update app.py

app.py

@@ -531,7 +531,6 @@ elif app_mode == "Advanced EDA":
             'plot_type': "Histogram",
             'x_col': df.columns[0] if len(df.columns) > 0 else None,
             'y_col': df.columns[1] if len(df.columns) > 1 else None,
-            'z_col': df.columns[2] if len(df.columns) > 2 else None,
             'color_col': None,
             'size_col': None,
             'time_col': None,
@@ -568,9 +567,8 @@ elif app_mode == "Advanced EDA":
     st.sidebar.header("📊 Visualization Configuration")
     plot_types = [
         "Histogram", "Scatter Plot", "Box Plot", "Violin Plot",
-        "Correlation Heatmap", "Parallel Coordinates", "Andrews Curves",
-        "Pair Plot", "Density Contour", "3D Scatter", "Time Series",
-        "Sunburst Chart", "Funnel Chart", "Clustering Analysis"
+        "Correlation Heatmap", "Parallel Coordinates", "Pair Plot", "Density Contour",
+        "3D Scatter", "Time Series", "Bar Chart", "Pie Chart",  "Line Chart" # Removed the computationally expensive ones
     ]
     st.session_state.eda_config['plot_type'] = st.sidebar.selectbox(
         "Choose Visualization",
@@ -579,33 +577,49 @@ elif app_mode == "Advanced EDA":
     )
 
     # Dynamic Controls Based on Plot Type
-    if st.session_state.eda_config['plot_type'] != "Correlation Heatmap":
-        st.session_state.eda_config['x_col'] = st.sidebar.selectbox(
-            "X Axis",
-            df.columns,
-            index=df.columns.get_loc(st.session_state.eda_config['x_col'])
-            if st.session_state.eda_config['x_col'] in df.columns else 0
-        )
+    plot_type = st.session_state.eda_config['plot_type']
+
+    def show_column_selectors(plot_type, df, config):
+        """Helper function to display column selectors based on plot type."""
+        if plot_type != "Correlation Heatmap":
+            config['x_col'] = st.sidebar.selectbox(
+                "X Axis",
+                df.columns,
+                index=df.columns.get_loc(config['x_col']) if config['x_col'] in df.columns else 0
+            )
 
-    if st.session_state.eda_config['plot_type'] in ["Scatter Plot", "Box Plot", "Violin Plot", "Time Series", "3D Scatter", "Histogram"]:
-        st.session_state.eda_config['y_col'] = st.sidebar.selectbox(
-            "Y Axis",
-            df.columns,
-            index=df.columns.get_loc(st.session_state.eda_config['y_col'])
-            if st.session_state.eda_config['y_col'] in df.columns else 0
-        )
+        if plot_type in ["Scatter Plot", "Box Plot", "Violin Plot", "Time Series", "3D Scatter", "Histogram", "Line Chart"]:
+            config['y_col'] = st.sidebar.selectbox(
+                "Y Axis",
+                df.columns,
+                index=df.columns.get_loc(config['y_col']) if config['y_col'] in df.columns else 0
+            )
+            
+        if plot_type == "Time Series":
+            config['time_col'] = st.sidebar.selectbox(
+                "Time Column",
+                df.columns,
+                index=df.columns.get_loc(config['time_col']) if config['time_col'] in df.columns else 0
+            )
+            config['value_col'] = st.sidebar.selectbox(
+                "Value Column",
+                df.columns,
+                index=df.columns.get_loc(config['value_col']) if config['value_col'] in df.columns else 0
+            )
 
-    if st.session_state.eda_config['plot_type'] == "3D Scatter":
-        st.session_state.eda_config['z_col'] = st.sidebar.selectbox(
-            "Z Axis",
-            df.columns,
-            index=df.columns.get_loc(st.session_state.eda_config['z_col'])
-            if st.session_state.eda_config['z_col'] in df.columns else 0
-        )
-        st.session_state.eda_config['color_col'] = st.sidebar.selectbox(
-            "Color by",
-            [None] + list(df.columns)
-        )
+        if plot_type == "3D Scatter":
+            config['z_col'] = st.sidebar.selectbox(
+                "Z Axis",
+                df.columns,
+                index=df.columns.get_loc(config['z_col']) if config['z_col'] in df.columns else 0
+            )
+            config['color_col'] = st.sidebar.selectbox(
+                "Color by",
+                [None] + list(df.columns)
+            )
+        return config
+
+    st.session_state.eda_config = show_column_selectors(plot_type, df, st.session_state.eda_config)
 
     # Advanced Plot Customization
     with st.expander("🎨 Advanced Customization", expanded=False):
@@ -623,7 +637,14 @@ elif app_mode == "Advanced EDA":
         fig = None
         config = st.session_state.eda_config
 
-        if config['plot_type'] == "Histogram":
+        # Numeric Column Validation Helper
+        def check_numeric(col):
+            if not pd.api.types.is_numeric_dtype(df[col]):
+                st.error(f"Column '{col}' must be numeric for this plot type.")
+                st.stop()
+
+        if plot_type == "Histogram":
+            check_numeric(config['x_col'])
             color_palette = config['color_palette']
             colors = getattr(pc.sequential, color_palette)
             fig = px.histogram(
@@ -633,7 +654,9 @@ elif app_mode == "Advanced EDA":
                 color_discrete_sequence = [colors[0]]
             )
 
-        elif config['plot_type'] == "Scatter Plot":
+        elif plot_type == "Scatter Plot":
+            check_numeric(config['x_col'])
+            check_numeric(config['y_col'])
             fig = px.scatter(
                 df, x=config['x_col'], y=config['y_col'],
                 color=config['color_col'],
@@ -641,14 +664,17 @@ elif app_mode == "Advanced EDA":
                 hover_data=config['hover_data_cols']
             )
 
-        elif config['plot_type'] == "3D Scatter":
+        elif plot_type == "3D Scatter":
+            check_numeric(config['x_col'])
+            check_numeric(config['y_col'])
+            check_numeric(config['z_col'])
             fig = px.scatter_3d(
                 df, x=config['x_col'], y=config['y_col'], z=config['z_col'],
                 color=config['color_col'],
                 color_discrete_sequence=[config['color_palette']]
             )
 
-        elif config['plot_type'] == "Correlation Heatmap":
+        elif plot_type == "Correlation Heatmap":
             numeric_df = df.select_dtypes(include=np.number)
             if not numeric_df.empty:
                 corr = numeric_df.corr()
@@ -659,37 +685,67 @@ elif app_mode == "Advanced EDA":
             else:
                 st.warning("No numerical columns found for correlation heatmap.")
 
-        elif config['plot_type'] == "Box Plot":
+        elif plot_type == "Box Plot":
             fig = px.box(
                 df, x=config['x_col'], y=config['y_col'],
                 color=config['color_col']
             )
 
-        elif config['plot_type'] == "Violin Plot":
+        elif plot_type == "Violin Plot":
             fig = px.violin(
                 df, x=config['x_col'], y=config['y_col'],
                 box=True, points="all",
                 color=config['color_col']
             )
 
-        elif config['plot_type'] == "Time Series":
-            df = df.sort_values(by=config['time_col'])
+        elif plot_type == "Time Series":
+             # Time Series plots now require time_col and value_col
             fig = px.line(
                 df, x=config['time_col'], y=config['value_col'],
                 color=config['color_col']
             )
 
-        elif config['plot_type'] == "Scatter Matrix":
-            fig = px.scatter_matrix(
-                df, dimensions=config['scatter_matrix_cols'],
+        elif plot_type == "Parallel Coordinates":
+            numeric_df = df.select_dtypes(include=np.number)
+            if not numeric_df.empty:
+                fig = px.parallel_coordinates(numeric_df, color_continuous_scale=config['color_palette'])
+            else:
+                st.warning("No numerical columns found for parallel coordinates plot.")
+
+        elif plot_type == "Pair Plot":
+            numeric_cols = df.select_dtypes(include=np.number).columns
+            if len(numeric_cols) >= 2:
+                dimensions = st.multiselect("Select Columns for Pair Plot", numeric_cols, default=numeric_cols[:2])
+                fig = px.scatter_matrix(df[dimensions], color=config['color_col'])
+            else:
+                st.warning("Need at least 2 numeric columns for pair plot.")
+
+        elif plot_type == "Density Contour":
+            check_numeric(config['x_col'])
+            check_numeric(config['y_col'])
+            fig = px.density_contour(df, x=config['x_col'], y=config['y_col'], color=config['color_col'])
+
+        elif plot_type == "Bar Chart":
+            fig = px.bar(
+                df, x=config['x_col'], y=config['y_col'],
                 color=config['color_col']
             )
 
+        elif plot_type == "Pie Chart":
+            fig = px.pie(
+                df, values=config['y_col'], names=config['x_col'],
+                color_discrete_sequence=px.colors.sequential.RdBu
+            )
+        elif plot_type == "Line Chart":
+            fig = px.line(
+                df, x=config['x_col'], y=config['y_col'],
+                color=config['color_col']
+            )
         if fig:
             st.plotly_chart(fig, use_container_width=True)
     except Exception as e:
         st.error(f"An error occurred while generating the plot: {e}")
-                
+        
 # Model Training Section
 elif app_mode == "Model Training":
     st.title("🚂 Model Training Studio")