demographics section done

plots.py

@@ -1,6 +1,7 @@
 """Plotting functions for Voice Branding analysis using Altair."""
 
 import re
+import math
 from pathlib import Path
 
 import altair as alt
@@ -728,8 +729,6 @@ class JPMCPlotsMixin:
             },
             width=width or 800,
             height=height or getattr(self, 'plot_height', 400)
-        ).configure_view(
-            strokeWidth=0  # Remove frame which might obscure labels
         )
 
         chart = self._save_plot(chart, title)
@@ -794,6 +793,101 @@ class JPMCPlotsMixin:
         chart = self._save_plot(chart, title)
         return chart
 
+    def plot_demographic_distribution(
+        self,
+        column: str,
+        data: pl.LazyFrame | pl.DataFrame | None = None,
+        title: str | None = None,
+        height: int | None = None,
+        width: int | str | None = None,
+        show_counts: bool = True,
+    ) -> alt.Chart:
+        """Create a horizontal bar chart showing the distribution of respondents by a demographic column.
+
+        Designed to be compact so multiple charts (approx. 6) can fit on one slide.
+        Uses horizontal bars for better readability with many categories.
+
+        Parameters:
+            column: The column name to analyze (e.g., 'Age', 'Gender', 'Race/Ethnicity').
+            data: Optional DataFrame. If None, uses self.data_filtered.
+            title: Chart title. If None, auto-generates based on column name.
+            height: Chart height in pixels (default: auto-sized based on categories).
+            width: Chart width in pixels (default: 280 for compact layout).
+            show_counts: If True, display count labels on the bars.
+
+        Returns:
+            alt.Chart: An Altair horizontal bar chart showing the distribution.
+        """
+        df = self._ensure_dataframe(data)
+
+        if column not in df.columns:
+            return alt.Chart(pd.DataFrame({'text': [f"Column '{column}' not found"]})).mark_text().encode(text='text:N')
+
+        # Count values in the column, including nulls
+        stats_df = (
+            df.select(pl.col(column))
+            .with_columns(pl.col(column).fill_null("(No Response)"))
+            .group_by(column)
+            .agg(pl.len().alias("count"))
+            .sort("count", descending=True)
+            .to_pandas()
+        )
+
+        if stats_df.empty:
+            return alt.Chart(pd.DataFrame({'text': ['No data']})).mark_text().encode(text='text:N')
+
+        # Calculate percentages
+        total = stats_df['count'].sum()
+        stats_df['percentage'] = (stats_df['count'] / total * 100).round(1)
+
+        # Generate title if not provided
+        if title is None:
+            clean_col = column.replace('_', ' ').replace('/', ' / ')
+            title = f"Distribution: {clean_col}"
+
+        # Calculate appropriate height based on number of categories
+        num_categories = len(stats_df)
+        bar_height = 18  # pixels per bar
+        calculated_height = max(120, num_categories * bar_height + 40)  # min 120px, +40 for title/padding
+
+        # Horizontal bar chart - categories on Y axis, counts on X axis
+        bars = alt.Chart(stats_df).mark_bar(color=ColorPalette.PRIMARY).encode(
+            x=alt.X('count:Q', title='Count', axis=alt.Axis(grid=False)),
+            y=alt.Y(f'{column}:N', title=None, sort='-x', axis=alt.Axis(labelLimit=150)),
+            tooltip=[
+                alt.Tooltip(f'{column}:N', title=column.replace('_', ' ')),
+                alt.Tooltip('count:Q', title='Count'),
+                alt.Tooltip('percentage:Q', title='Percentage', format='.1f')
+            ]
+        )
+
+        # Add count labels at end of bars
+        if show_counts:
+            text = alt.Chart(stats_df).mark_text(
+                align='left',
+                baseline='middle',
+                dx=3,  # Offset from bar end
+                fontSize=9,
+                color=ColorPalette.TEXT
+            ).encode(
+                x='count:Q',
+                y=alt.Y(f'{column}:N', sort='-x'),
+                text='count:Q'
+            )
+            chart = (bars + text)
+        else:
+            chart = bars
+
+        # Compact dimensions for 6-per-slide layout
+        chart = chart.properties(
+            title=self._process_title(title),
+            width=width or 200,
+            height=height or calculated_height
+        )
+
+        chart = self._save_plot(chart, title)
+        return chart
+
     def plot_speaking_style_ranking_correlation(
         self,
         style_color: str,