all plots offline update

.vscode/settings.json

@@ -0,0 +1,5 @@
+{
+    "chat.tools.terminal.autoApprove": {
+        "/home/luigi/Documents/VoiceBranding/JPMC/Phase-3/.venv/bin/python": true
+    }
+}

03_quant_report.script.py

@@ -7,7 +7,7 @@ import polars as pl
 from pathlib import Path
 import argparse
 import json
-
+import re
 from validation import check_progress, duration_validation, check_straight_liners
 from utils import QualtricsSurvey, combine_exclusive_columns, calculate_weighted_ranking_scores
 import utils
@@ -69,7 +69,7 @@ cli_args = parse_cli_args()
 # mo.stop(file_browser.path(index=0) is None, mo.md("**⚠️ Please select a `_Labels.csv` file above to proceed**"))
 # RESULTS_FILE = Path(file_browser.path(index=0))
 
-RESULTS_FILE = 'data/exports/2-3-26_Copy-2-2-26/JPMC_Chase Brand Personality_Quant Round 1_February 2, 2026_Labels.csv'
+RESULTS_FILE = 'data/exports/debug/JPMC_Chase Brand Personality_Quant Round 1_February 2, 2026_Labels.csv'
 QSF_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase_Brand_Personality_Quant_Round_1.qsf'
 
 # %%
@@ -114,14 +114,11 @@ BEST_CHOSEN_CHARACTER = "the_coach"
 
 # %%
 # mo.stop(filter_form.value is None, mo.md("**Please submit filter above to proceed**"))
-# CLI args: None means "all options selected" (use S.options_* defaults)
+# CLI args: None means "no filter applied" - filter_data() will skip None filters
 # Build filter values dict dynamically from FILTER_CONFIG
-_active_filters = {}
+_active_filters = {filter_name: getattr(cli_args, filter_name) for filter_name in FILTER_CONFIG}
-for filter_name, options_attr in FILTER_CONFIG.items():
-    cli_value = getattr(cli_args, filter_name)
-    all_options = getattr(S, options_attr)
-    _active_filters[filter_name] = cli_value if cli_value is not None else all_options
 
+# %%
 _d = S.filter_data(data_all, **_active_filters)
 
 # Write filter description file if filter-name is provided
@@ -142,14 +139,17 @@ if cli_args.filter_name and S.fig_save_dir:
         all_options = getattr(S, options_attr)
         values = _active_filters[filter_name]
         display_name = filter_name.replace('_', ' ').title()
-        if values != all_options:
+        # None means no filter applied (same as "All")
+        if values is not None and values != all_options:
             _short_desc_parts.append(f"{display_name}: {', '.join(values)}")
             _filter_desc_lines.append(f"  {display_name}: {', '.join(values)}")
         else:
             _filter_desc_lines.append(f"  {display_name}: All")
     
     # Write detailed description INSIDE the filter-slug directory
-    _filter_file = _filter_slug_dir / f"{cli_args.filter_name}.txt"
+    # Sanitize filter name for filename usage (replace / and other chars)
+    _safe_filter_name = re.sub(r'[^\w\s-]', '_', cli_args.filter_name)
+    _filter_file = _filter_slug_dir / f"{_safe_filter_name}.txt"
     _filter_file.write_text('\n'.join(_filter_desc_lines))
     
     # Append to summary index file at figures/<export_date>/filter_index.txt

04_PPTX_Update_Images.py

@@ -21,9 +21,14 @@ def _():
 
 @app.cell
 def _():
-    TAG_SOURCE = Path('data/reports/Perception-Research-Report_2-2.pptx')
+    return
+
+
+@app.cell
+def _():
+    TAG_SOURCE = Path('/home/luigi/Documents/VoiceBranding/JPMC/Phase-3/data/reports/VOICE_Perception-Research-Report_3-2-26.pptx')
     # TAG_TARGET = Path('data/reports/Perception-Research-Report_2-2_tagged.pptx')
-    TAG_IMAGE_DIR = Path('figures/2-2-26')
+    TAG_IMAGE_DIR = Path('figures/debug')
     return TAG_IMAGE_DIR, TAG_SOURCE
 
 
@@ -47,10 +52,10 @@ def _():
 
 @app.cell
 def _():
-    REPLACE_SOURCE = Path('data/reports/Perception-Research-Report_2-2.pptx')
+    REPLACE_SOURCE = Path('/home/luigi/Documents/VoiceBranding/JPMC/Phase-3/data/reports/VOICE_Perception-Research-Report_3-2-26.pptx')
-    REPLACE_TARGET = Path('data/reports/Perception-Research-Report_2-2_updated.pptx')
+    # REPLACE_TARGET = Path('data/reports/Perception-Research-Report_2-2_updated.pptx')
 
-    NEW_IMAGES_DIR = Path('figures/2-2-26')
+    NEW_IMAGES_DIR = Path('figures/debug')
     return NEW_IMAGES_DIR, REPLACE_SOURCE
 
 

plots.py

@@ -2,6 +2,7 @@
 
 import re
 import math
+import textwrap
 from pathlib import Path
 
 import altair as alt
@@ -97,7 +98,11 @@ class QualtricsPlotsMixin:
         return "_".join(parts)
 
     def _get_filter_description(self) -> str:
-        """Generate a human-readable description of active filters."""
+        """Generate a human-readable description of active filters.
+        
+        Includes sample size (from _last_sample_size) prepended to the filter text.
+        Format: "Sample size: <n> | Filters: ..." or "Sample size: <n>" if no filters.
+        """
         parts = []
         
         # Mapping of attribute name to (display_name, value, options_attr)
@@ -131,17 +136,62 @@ class QualtricsPlotsMixin:
             if master_list and set(value) == set(master_list):
                  continue
             
+            # Special handling for Ethnicity: detect single-value ethnicity filters
+            # When filtering by one ethnicity (e.g., "White or Caucasian"), multiple options
+            # may be selected (all options containing that value). Display just the common value
+            # only if ALL options containing that value are selected.
+            if display_name.lower() == 'ethnicity' and len(value) > 1 and master_list:
+                # Find common individual ethnicity values across all selected options
+                # Each option may be comma-separated (e.g., "White or Caucasian, Hispanic or Latino")
+                value_sets = [
+                    set(v.strip() for v in opt.split(','))
+                    for opt in value
+                ]
+                # Intersect all sets to find common values
+                common_values = value_sets[0]
+                for vs in value_sets[1:]:
+                    common_values = common_values.intersection(vs)
+                
+                # If exactly one common value, check if ALL options containing it are selected
+                if len(common_values) == 1:
+                    common_val = common_values.pop()
+                    # Find all options in master list that contain this common value
+                    all_options_with_value = [
+                        opt for opt in master_list
+                        if common_val in [v.strip() for v in opt.split(',')]
+                    ]
+                    # Only simplify if we selected ALL options containing this value
+                    if set(value) == set(all_options_with_value):
+                        val_str = common_val
+                    else:
+                        clean_values = [str(v) for v in value]
+                        val_str = ", ".join(clean_values)
+                else:
+                    # No single common value - fall back to full list
+                    clean_values = [str(v) for v in value]
+                    val_str = ", ".join(clean_values)
+            else:
                 # Use original values for display (full list)
                 clean_values = [str(v) for v in value]
                 val_str = ", ".join(clean_values)
+            
             # Use UPPERCASE for category name to distinguish from values
             parts.append(f"{display_name.upper()}: {val_str}")
         
+        # Get sample size from the filtered dataset (not from transformed plot data)
+        sample_size = self._get_filtered_sample_size()
+        sample_prefix = f"Sample size: {sample_size}" if sample_size is not None else ""
+        
         if not parts:
-            return ""
+            # No filters active - return just sample size (or empty string if no sample size)
+            return sample_prefix
             
         # Join with clear separator - double space for visual break
-        return "Filters:  " + "  —  ".join(parts)
+        filter_text = "Filters:  " + "  —  ".join(parts)
+        
+        if sample_prefix:
+            return f"{sample_prefix}  |  {filter_text}"
+        return filter_text
 
     def _add_filter_footnote(self, chart: alt.Chart) -> alt.Chart:
         """Add a footnote with active filters to the chart.
@@ -253,9 +303,24 @@ class QualtricsPlotsMixin:
              raise ValueError("No data provided and self.data_filtered is None.")
         
         if isinstance(df, pl.LazyFrame):
-            return df.collect()
+            df = df.collect()
+        
         return df
     
+    def _get_filtered_sample_size(self) -> int | None:
+        """Get the sample size from the filtered dataset (self.data_filtered).
+        
+        This returns the number of respondents in the filtered dataset,
+        not the size of any transformed/aggregated data passed to plot functions.
+        """
+        data_filtered = getattr(self, 'data_filtered', None)
+        if data_filtered is None:
+            return None
+        
+        if isinstance(data_filtered, pl.LazyFrame):
+            return data_filtered.select(pl.len()).collect().item()
+        return data_filtered.height
+
     def _clean_voice_label(self, col_name: str) -> str:
         """Extract and clean voice name from column name for display.
         
@@ -370,8 +435,8 @@ class QualtricsPlotsMixin:
         # Base bar chart - use y2 to explicitly start bars at domain minimum
         if color_gender:
             bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X('voice:N', title=x_label, sort='-y'),
+                x=alt.X('voice:N', title=x_label, sort='-y', axis=alt.Axis(grid=False)),
-                y=alt.Y('average:Q', title=y_label, scale=alt.Scale(domain=domain)),
+                y=alt.Y('average:Q', title=y_label, scale=alt.Scale(domain=domain), axis=alt.Axis(grid=True)),
                 y2=alt.datum(domain[0]),  # Bars start at domain minimum (bottom edge)
                 color=alt.Color('gender:N',
                                scale=alt.Scale(domain=['Male', 'Female'],
@@ -384,10 +449,15 @@ class QualtricsPlotsMixin:
                     alt.Tooltip('gender:N', title='Gender')
                 ]
             )
+            
+            # Text overlay - inherit color from bars via mark_text
+            text = bars.mark_text(dy=-5, fontSize=10).encode(
+                text=alt.Text('count:Q')
+            )
         else:
             bars = alt.Chart(stats_df).mark_bar(color=color).encode(
-                x=alt.X('voice:N', title=x_label, sort='-y'),
+                x=alt.X('voice:N', title=x_label, sort='-y', axis=alt.Axis(grid=False)),
-                y=alt.Y('average:Q', title=y_label, scale=alt.Scale(domain=domain)),
+                y=alt.Y('average:Q', title=y_label, scale=alt.Scale(domain=domain), axis=alt.Axis(grid=True)),
                 y2=alt.datum(domain[0]),  # Bars start at domain minimum (bottom edge)
                 tooltip=[
                     alt.Tooltip('voice:N', title='Voice'),
@@ -447,13 +517,16 @@ class QualtricsPlotsMixin:
         # Convert to long format, sort by total
         stats_df = pl.DataFrame(stats).to_pandas()
         
+        # Compute explicit sort order by total (descending)
+        sort_order = stats_df.drop_duplicates('voice').sort_values('total', ascending=False)['voice'].tolist()
+        
         # Interactive legend selection - click to filter
         selection = alt.selection_point(fields=['rank'], bind='legend')
         
         # Create stacked bar chart with interactive legend
-        chart = alt.Chart(stats_df).mark_bar().encode(
+        bars = alt.Chart(stats_df).mark_bar().encode(
-            x=alt.X('voice:N', title=x_label, sort=alt.EncodingSortField(field='total', op='sum', order='descending')),
+            x=alt.X('voice:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-            y=alt.Y('count:Q', title=y_label, stack='zero'),
+            y=alt.Y('count:Q', title=y_label, stack='zero', axis=alt.Axis(grid=True)),
             color=alt.Color('rank:N',
                            scale=alt.Scale(domain=['Rank 1 (1st Choice)', 'Rank 2 (2nd Choice)', 'Rank 3 (3rd Choice)'],
                                          range=[ColorPalette.RANK_1, ColorPalette.RANK_2, ColorPalette.RANK_3]),
@@ -465,7 +538,18 @@ class QualtricsPlotsMixin:
                 alt.Tooltip('rank:N', title='Rank'),
                 alt.Tooltip('count:Q', title='Count')
             ]
-        ).add_params(selection).properties(
+        )
+        
+        # Text layer showing totals on top of bars
+        text = alt.Chart(stats_df).transform_filter(
+            alt.datum.rank == 'Rank 1 (1st Choice)'
+        ).mark_text(dy=-10, color='black').encode(
+            x=alt.X('voice:N', sort=sort_order),
+            y=alt.Y('total:Q'),
+            text=alt.Text('total:Q')
+        )
+        
+        chart = alt.layer(bars, text).add_params(selection).properties(
             title=self._process_title(title),
             width=width or 800,
             height=height or getattr(self, 'plot_height', 400)
@@ -518,6 +602,9 @@ class QualtricsPlotsMixin:
         # Interactive legend selection - click to filter
         selection = alt.selection_point(fields=['rank'], bind='legend')
 
+        # Compute explicit sort order by total (descending)
+        sort_order = stats_df.drop_duplicates('item').sort_values('total', ascending=False)['item'].tolist()
+
         if color_gender:
             # Add gender_rank column for combined color encoding
             stats_df['gender_rank'] = stats_df['gender'] + ' - ' + stats_df['rank']
@@ -532,9 +619,9 @@ class QualtricsPlotsMixin:
                 ColorPalette.GENDER_FEMALE_RANK_1, ColorPalette.GENDER_FEMALE_RANK_2, ColorPalette.GENDER_FEMALE_RANK_3
             ]
             
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X('item:N', title=x_label, sort=alt.EncodingSortField(field='total', order='descending')),
+                x=alt.X('item:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label, stack='zero'),
+                y=alt.Y('count:Q', title=y_label, stack='zero', axis=alt.Axis(grid=True)),
                 color=alt.Color('gender_rank:N',
                                scale=alt.Scale(domain=domain, range=range_colors),
                                legend=alt.Legend(orient='top', direction='horizontal', title=None, columns=3)),
@@ -546,15 +633,11 @@ class QualtricsPlotsMixin:
                     alt.Tooltip('count:Q', title='Count'),
                     alt.Tooltip('gender:N', title='Gender')
                 ]
-            ).add_params(selection).properties(
-                title=self._process_title(title),
-                width=width or 800,
-                height=height or getattr(self, 'plot_height', 400)
             )
         else:
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X('item:N', title=x_label, sort=alt.EncodingSortField(field='total', order='descending')),
+                x=alt.X('item:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label, stack='zero'),
+                y=alt.Y('count:Q', title=y_label, stack='zero', axis=alt.Axis(grid=True)),
                 color=alt.Color('rank:N',
                                scale=alt.Scale(domain=['Rank 1 (Best)', 'Rank 2', 'Rank 3'],
                                              range=[ColorPalette.RANK_1, ColorPalette.RANK_2, ColorPalette.RANK_3]),
@@ -566,7 +649,32 @@ class QualtricsPlotsMixin:
                     alt.Tooltip('rank:N', title='Rank'),
                     alt.Tooltip('count:Q', title='Count')
                 ]
-            ).add_params(selection).properties(
+            )
+
+        # Text layer showing totals on top of bars
+        if color_gender:
+            # Create a separate chart for totals with gender coloring
+            text_df = stats_df.drop_duplicates('item')[['item', 'total', 'gender']]
+            text = alt.Chart(text_df).mark_text(dy=-10).encode(
+                x=alt.X('item:N', sort=sort_order),
+                y=alt.Y('total:Q'),
+                text=alt.Text('total:Q'),
+                color=alt.condition(
+                    alt.datum.gender == 'Female',
+                    alt.value(ColorPalette.GENDER_FEMALE),
+                    alt.value(ColorPalette.GENDER_MALE)
+                )
+            )
+        else:
+            text = alt.Chart(stats_df).transform_filter(
+                alt.datum.rank_order == 1
+            ).mark_text(dy=-10, color='black').encode(
+                x=alt.X('item:N', sort=sort_order),
+                y=alt.Y('total:Q'),
+                text=alt.Text('total:Q')
+            )
+
+        chart = alt.layer(bars, text).add_params(selection).properties(
             title=self._process_title(title),
             width=width or 800,
             height=height or getattr(self, 'plot_height', 400)
@@ -604,6 +712,7 @@ class QualtricsPlotsMixin:
 
         # Convert and sort
         stats_df = pl.DataFrame(stats).sort('count', descending=True)
+        sort_order = stats_df['item'].to_list()
         
         # Add rank column for coloring (1-3 vs 4+)
         stats_df = stats_df.with_row_index('rank_index')
@@ -625,9 +734,9 @@ class QualtricsPlotsMixin:
                 ColorPalette.GENDER_FEMALE, ColorPalette.GENDER_FEMALE_NEUTRAL
             ]
             
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X('item:N', title=x_label, sort='-y'),
+                x=alt.X('item:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label),
+                y=alt.Y('count:Q', title=y_label, axis=alt.Axis(grid=True)),
                 color=alt.Color('gender_category:N',
                                scale=alt.Scale(domain=domain, range=range_colors),
                                legend=alt.Legend(orient='top', direction='horizontal', title=None)),
@@ -636,16 +745,30 @@ class QualtricsPlotsMixin:
                     alt.Tooltip('count:Q', title='1st Place Votes'),
                     alt.Tooltip('gender:N', title='Gender')
                 ]
-            ).properties(
+            )
+            
+            # Create text layer with gender coloring using conditional
+            text = alt.Chart(stats_df).mark_text(dy=-5, fontSize=10).encode(
+                x=alt.X('item:N', sort=sort_order),
+                y=alt.Y('count:Q'),
+                text=alt.Text('count:Q'),
+                color=alt.condition(
+                    alt.datum.gender == 'Female',
+                    alt.value(ColorPalette.GENDER_FEMALE),
+                    alt.value(ColorPalette.GENDER_MALE)
+                )
+            )
+            
+            chart = (bars + text).properties(
                 title=self._process_title(title),
                 width=width or 800,
                 height=height or getattr(self, 'plot_height', 400)
             )
         else:
             # Bar chart with conditional color
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X('item:N', title=x_label, sort='-y'),
+                x=alt.X('item:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label),
+                y=alt.Y('count:Q', title=y_label, axis=alt.Axis(grid=True)),
                 color=alt.Color('category:N',
                                scale=alt.Scale(domain=['Top 3', 'Other'],
                                              range=[ColorPalette.PRIMARY, ColorPalette.NEUTRAL]),
@@ -654,7 +777,20 @@ class QualtricsPlotsMixin:
                     alt.Tooltip('item:N', title='Item'),
                     alt.Tooltip('count:Q', title='1st Place Votes')
                 ]
-            ).properties(
+            )
+            
+            # Text overlay for counts
+            text = alt.Chart(stats_df).mark_text(
+                dy=-5,
+                color='black',
+                fontSize=10
+            ).encode(
+                x=alt.X('item:N', sort=sort_order),
+                y=alt.Y('count:Q'),
+                text=alt.Text('count:Q')
+            )
+            
+            chart = (bars + text).properties(
                 title=self._process_title(title),
                 width=width or 800,
                 height=height or getattr(self, 'plot_height', 400)
@@ -680,6 +816,8 @@ class QualtricsPlotsMixin:
             color_gender: If True, color bars by voice gender (blue=male, pink=female).
         """
         weighted_df = self._ensure_dataframe(data).to_pandas()
+        weighted_df.sort_values('Weighted Score', ascending=False, inplace=True)
+        sort_order = weighted_df['Character'].tolist()
 
         if color_gender:
             # Add gender column based on Character name
@@ -687,8 +825,8 @@ class QualtricsPlotsMixin:
             
             # Bar chart with gender coloring
             bars = alt.Chart(weighted_df).mark_bar().encode(
-                x=alt.X('Character:N', title=x_label, sort='-y'),
+                x=alt.X('Character:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('Weighted Score:Q', title=y_label),
+                y=alt.Y('Weighted Score:Q', title=y_label, axis=alt.Axis(grid=True)),
                 color=alt.Color('gender:N',
                                scale=alt.Scale(domain=['Male', 'Female'],
                                              range=[ColorPalette.GENDER_MALE, ColorPalette.GENDER_FEMALE]),
@@ -702,8 +840,8 @@ class QualtricsPlotsMixin:
         else:
             # Bar chart
             bars = alt.Chart(weighted_df).mark_bar(color=color).encode(
-                x=alt.X('Character:N', title=x_label, sort='-y'),
+                x=alt.X('Character:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('Weighted Score:Q', title=y_label),
+                y=alt.Y('Weighted Score:Q', title=y_label, axis=alt.Axis(grid=True)),
                 tooltip=[
                     alt.Tooltip('Character:N'),
                     alt.Tooltip('Weighted Score:Q', title='Score')
@@ -713,7 +851,7 @@ class QualtricsPlotsMixin:
         # Text overlay
         text = bars.mark_text(
             dy=-5,
-            color='white',
+            color='black',
             fontSize=11
         ).encode(
             text='Weighted Score:Q'
@@ -771,8 +909,11 @@ class QualtricsPlotsMixin:
             .to_pandas()
         )
 
+        # Compute explicit sort order by count (descending)
+        sort_order = stats_df.sort_values('count', ascending=False)[target_column].tolist()
+
+        # Add gender column for all cases when color_gender is True (needed for text layer)
         if color_gender:
-            # Add gender column based on voice label
             stats_df['gender'] = stats_df[target_column].apply(self._get_voice_gender)
             # Add gender_category column for combined color encoding
             stats_df['gender_category'] = stats_df['gender'] + ' - ' + stats_df['category']
@@ -784,9 +925,9 @@ class QualtricsPlotsMixin:
                 ColorPalette.GENDER_FEMALE, ColorPalette.GENDER_FEMALE_NEUTRAL
             ]
             
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
+                x=alt.X(f'{target_column}:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label),
+                y=alt.Y('count:Q', title=y_label, axis=alt.Axis(grid=True)),
                 color=alt.Color('gender_category:N',
                                scale=alt.Scale(domain=domain, range=range_colors),
                                legend=alt.Legend(orient='top', direction='horizontal', title=None)),
@@ -795,15 +936,23 @@ class QualtricsPlotsMixin:
                     alt.Tooltip('count:Q', title='Selections'),
                     alt.Tooltip('gender:N', title='Gender')
                 ]
-            ).properties(
+            )
-                title=self._process_title(title),
+            
-                width=width or 800,
+            # Text layer with gender coloring using conditional
-                height=height or getattr(self, 'plot_height', 400)
+            text = alt.Chart(stats_df).mark_text(dy=-10).encode(
+                x=alt.X(f'{target_column}:N', sort=sort_order),
+                y=alt.Y('count:Q'),
+                text=alt.Text('count:Q'),
+                color=alt.condition(
+                    alt.datum.gender == 'Female',
+                    alt.value(ColorPalette.GENDER_FEMALE),
+                    alt.value(ColorPalette.GENDER_MALE)
+                )
             )
         else:
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
+                x=alt.X(f'{target_column}:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label),
+                y=alt.Y('count:Q', title=y_label, axis=alt.Axis(grid=True)),
                 color=alt.Color('category:N',
                                scale=alt.Scale(domain=['Top 8', 'Other'],
                                              range=[ColorPalette.PRIMARY, ColorPalette.NEUTRAL]),
@@ -812,7 +961,16 @@ class QualtricsPlotsMixin:
                     alt.Tooltip(f'{target_column}:N', title='Voice'),
                     alt.Tooltip('count:Q', title='Selections')
                 ]
-            ).properties(
+            )
+            
+            # Text layer with black color
+            text = alt.Chart(stats_df).mark_text(dy=-10, color='black').encode(
+                x=alt.X(f'{target_column}:N', sort=sort_order),
+                y=alt.Y('count:Q'),
+                text=alt.Text('count:Q')
+            )
+
+        chart = alt.layer(bars, text).properties(
             title=self._process_title(title),
             width=width or 800,
             height=height or getattr(self, 'plot_height', 400)
@@ -863,8 +1021,11 @@ class QualtricsPlotsMixin:
             .to_pandas()
         )
 
+        # Compute explicit sort order by count (descending)
+        sort_order = stats_df.sort_values('count', ascending=False)[target_column].tolist()
+
+        # Add gender column for all cases when color_gender is True (needed for text layer)
         if color_gender:
-            # Add gender column based on voice label
             stats_df['gender'] = stats_df[target_column].apply(self._get_voice_gender)
             # Add gender_category column for combined color encoding
             stats_df['gender_category'] = stats_df['gender'] + ' - ' + stats_df['category']
@@ -876,9 +1037,9 @@ class QualtricsPlotsMixin:
                 ColorPalette.GENDER_FEMALE, ColorPalette.GENDER_FEMALE_NEUTRAL
             ]
             
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
+                x=alt.X(f'{target_column}:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label),
+                y=alt.Y('count:Q', title=y_label, axis=alt.Axis(grid=True)),
                 color=alt.Color('gender_category:N',
                                scale=alt.Scale(domain=domain, range=range_colors),
                                legend=alt.Legend(orient='top', direction='horizontal', title=None)),
@@ -887,15 +1048,23 @@ class QualtricsPlotsMixin:
                     alt.Tooltip('count:Q', title='In Top 3'),
                     alt.Tooltip('gender:N', title='Gender')
                 ]
-            ).properties(
+            )
-                title=self._process_title(title),
+            
-                width=width or 800,
+            # Text layer with gender coloring using conditional
-                height=height or getattr(self, 'plot_height', 400)
+            text = alt.Chart(stats_df).mark_text(dy=-10).encode(
+                x=alt.X(f'{target_column}:N', sort=sort_order),
+                y=alt.Y('count:Q'),
+                text=alt.Text('count:Q'),
+                color=alt.condition(
+                    alt.datum.gender == 'Female',
+                    alt.value(ColorPalette.GENDER_FEMALE),
+                    alt.value(ColorPalette.GENDER_MALE)
+                )
             )
         else:
-            chart = alt.Chart(stats_df).mark_bar().encode(
+            bars = alt.Chart(stats_df).mark_bar().encode(
-                x=alt.X(f'{target_column}:N', title=x_label, sort='-y'),
+                x=alt.X(f'{target_column}:N', title=x_label, sort=sort_order, axis=alt.Axis(grid=False)),
-                y=alt.Y('count:Q', title=y_label),
+                y=alt.Y('count:Q', title=y_label, axis=alt.Axis(grid=True)),
                 color=alt.Color('category:N',
                                scale=alt.Scale(domain=['Top 3', 'Other'],
                                              range=[ColorPalette.PRIMARY, ColorPalette.NEUTRAL]),
@@ -904,7 +1073,16 @@ class QualtricsPlotsMixin:
                     alt.Tooltip(f'{target_column}:N', title='Voice'),
                     alt.Tooltip('count:Q', title='In Top 3')
                 ]
-            ).properties(
+            )
+            
+            # Text layer with black color
+            text = alt.Chart(stats_df).mark_text(dy=-10, color='black').encode(
+                x=alt.X(f'{target_column}:N', sort=sort_order),
+                y=alt.Y('count:Q'),
+                text=alt.Text('count:Q')
+            )
+
+        chart = alt.layer(bars, text).properties(
             title=self._process_title(title),
             width=width or 800,
             height=height or getattr(self, 'plot_height', 400)
@@ -965,9 +1143,9 @@ class QualtricsPlotsMixin:
 
         # Horizontal bar chart - use x2 to explicitly start bars at x=1
         bars = alt.Chart(stats).mark_bar(color=ColorPalette.PRIMARY).encode(
-            x=alt.X('mean_score:Q', title='Average Score (1-5)', scale=alt.Scale(domain=[1, 5])),
+            x=alt.X('mean_score:Q', title='Average Score (1-5)', scale=alt.Scale(domain=[1, 5]), axis=alt.Axis(grid=True)),
             x2=alt.datum(1),  # Bars start at x=1 (left edge of domain)
-            y=alt.Y('Voice:N', title='Voice', sort='-x'),
+            y=alt.Y('Voice:N', title='Voice', sort='-x', axis=alt.Axis(grid=False)),
             tooltip=[
                 alt.Tooltip('Voice:N'),
                 alt.Tooltip('mean_score:Q', title='Average', format='.2f'),
@@ -1040,8 +1218,8 @@ class QualtricsPlotsMixin:
 
         # Conditional color based on sign
         chart = alt.Chart(plot_df).mark_bar().encode(
-            x=alt.X('trait_display:N', title=None, axis=alt.Axis(labelAngle=0)),
+            x=alt.X('trait_display:N', title=None, axis=alt.Axis(labelAngle=0, grid=False)),
-            y=alt.Y('correlation:Q', title='Correlation', scale=alt.Scale(domain=[-1, 1])),
+            y=alt.Y('correlation:Q', title='Correlation', scale=alt.Scale(domain=[-1, 1]), axis=alt.Axis(grid=True)),
             color=alt.condition(
                 alt.datum.correlation >= 0,
                 alt.value('green'),
@@ -1089,11 +1267,12 @@ class QualtricsPlotsMixin:
         chart = alt.Chart(df.to_pandas()).mark_bar().encode(
             x=alt.X('Color:N', 
                     title=None, 
-                    axis=alt.Axis(labelAngle=0),
+                    axis=alt.Axis(labelAngle=0, grid=False),
                     sort=["Green", "Blue", "Orange", "Red"]),
             y=alt.Y('correlation:Q', 
                     title='Average Correlation',
-                    scale=alt.Scale(domain=[-1, 1])),
+                    scale=alt.Scale(domain=[-1, 1]),
+                    axis=alt.Axis(grid=True)),
             color=alt.condition(
                 alt.datum.correlation >= 0,
                 alt.value('green'),
@@ -1149,10 +1328,23 @@ class QualtricsPlotsMixin:
             .with_columns(pl.col(column).fill_null("(No Response)"))
             .group_by(column)
             .agg(pl.len().alias("count"))
-            .sort("count", descending=True)
             .to_pandas()
         )
 
+        # Apply sorting logic
+        if column == 'Age':
+            # Custom sort for Age ranges
+            # Example values: "18 to 21 years", "25 to 34 years", "70 years or more"
+            # Extract first number to sort by
+            stats_df['sort_key'] = stats_df[column].apply(
+                lambda x: int(re.search(r'\d+', str(x)).group()) if re.search(r'\d+', str(x)) else 999
+            )
+            # Use EncodingSortField for Age to avoid schema issues with list-based labels
+            sort_order = alt.EncodingSortField(field="sort_key", order="ascending")
+        else:
+            # Default sort by count descending
+            sort_order = '-x'
+
         if stats_df.empty:
             return alt.Chart(pd.DataFrame({'text': ['No data']})).mark_text().encode(text='text:N')
 
@@ -1160,22 +1352,31 @@ class QualtricsPlotsMixin:
         total = stats_df['count'].sum()
         stats_df['percentage'] = (stats_df['count'] / total * 100).round(1)
 
+        # Clean y-labels by replacing underscores and wrapping long text
+        import textwrap
+        stats_df['clean_label'] = stats_df[column].astype(str).str.replace('_', ' ').apply(
+            lambda x: textwrap.wrap(x, width=25) if isinstance(x, str) else [str(x)]
+        )
+
+        # Calculate max lines for height adjustment
+        max_lines = stats_df['clean_label'].apply(len).max() if not stats_df.empty else 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
+        # Calculate appropriate height based on number of categories and wrapping
         num_categories = len(stats_df)
-        bar_height = 18  # pixels per bar
+        bar_height = max(20, max_lines * 15)  # pixels per bar, scale with lines
         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)),
+            x=alt.X('count:Q', title='Count', axis=alt.Axis(grid=True)),
-            y=alt.Y(f'{column}:N', title=None, sort='-x', axis=alt.Axis(labelLimit=150)),
+            y=alt.Y('clean_label:N', title=None, sort=sort_order, axis=alt.Axis(labelLimit=300, grid=False)),
             tooltip=[
-                alt.Tooltip(f'{column}:N', title=column.replace('_', ' ')),
+                alt.Tooltip('clean_label:N', title=column.replace('_', ' ')),
                 alt.Tooltip('count:Q', title='Count'),
                 alt.Tooltip('percentage:Q', title='Percentage', format='.1f')
             ]
@@ -1191,7 +1392,7 @@ class QualtricsPlotsMixin:
                 color=ColorPalette.TEXT
             ).encode(
                 x='count:Q',
-                y=alt.Y(f'{column}:N', sort='-x'),
+                y=alt.Y('clean_label:N', sort=sort_order),
                 text='count:Q'
             )
             chart = (bars + text)
@@ -1244,8 +1445,8 @@ class QualtricsPlotsMixin:
         plot_df = pl.DataFrame(trait_correlations).to_pandas()
 
         chart = alt.Chart(plot_df).mark_bar().encode(
-            x=alt.X('trait_display:N', title=None, axis=alt.Axis(labelAngle=0)),
+            x=alt.X('trait_display:N', title=None, axis=alt.Axis(labelAngle=0, grid=False)),
-            y=alt.Y('correlation:Q', title='Correlation', scale=alt.Scale(domain=[-1, 1])),
+            y=alt.Y('correlation:Q', title='Correlation', scale=alt.Scale(domain=[-1, 1]), axis=alt.Axis(grid=True)),
             color=alt.condition(
                 alt.datum.correlation >= 0,
                 alt.value('green'),
@@ -1349,9 +1550,14 @@ class QualtricsPlotsMixin:
         # Add title with filter subtitle (similar to _add_filter_footnote for Altair charts)
         filter_text = self._get_filter_description()
         if filter_text:
-            # Title on top, filter subtitle below in light grey
+            # Wrap filter text to prevent excessively long lines
-            fig.suptitle(title, fontsize=16, y=0.98, color=ColorPalette.TEXT)
+            wrapped_lines = textwrap.wrap(filter_text, width=100)
-            ax.set_title(filter_text, fontsize=10, pad=10, color='lightgrey', loc='left')
+            wrapped_text = '\n'.join(wrapped_lines)
+            
+            # Use suptitle for main title (auto-positioned above axes)
+            fig.suptitle(title, fontsize=16, color=ColorPalette.TEXT, y=1.02)
+            # Use ax.set_title for filter text (positioned relative to axes, not figure)
+            ax.set_title(wrapped_text, fontsize=10, color='lightgrey', loc='left', pad=5)
         else:
             ax.set_title(title, fontsize=16, pad=20, color=ColorPalette.TEXT)
         
@@ -1420,8 +1626,8 @@ class QualtricsPlotsMixin:
             x=alt.X('Trait:N', 
                     title=x_label, 
                     sort=trait_order,
-                    axis=alt.Axis(labelAngle=-45, labelLimit=200)),
+                    axis=alt.Axis(labelAngle=-45, labelLimit=200, grid=False)),
-            y=alt.Y('Count:Q', title=y_label),
+            y=alt.Y('Count:Q', title=y_label, axis=alt.Axis(grid=True)),
             xOffset='Character:N',
             color=alt.Color('Character:N',
                            scale=alt.Scale(domain=characters,
@@ -1537,8 +1743,8 @@ class QualtricsPlotsMixin:
             y=alt.Y('trait:N',
                     title=x_label,
                     sort=reversed_sort,
-                    axis=alt.Axis(labelLimit=200)),
+                    axis=alt.Axis(labelLimit=200, grid=False)),
-            x=alt.X('count:Q', title=y_label),
+            x=alt.X('count:Q', title=y_label, axis=alt.Axis(grid=True)),
             color=alt.Color('category:N',
                            scale=alt.Scale(
                                domain=['Original Trait', 'Other Trait'],
@@ -1877,8 +2083,8 @@ class QualtricsPlotsMixin:
         tooltip_title = 'Mean Score' if has_means else 'Rank 1 %' if has_ranks else 'Score'
         
         bars = alt.Chart(summary_df).mark_bar(color=ColorPalette.PRIMARY).encode(
-            x=alt.X('group:N', title='Group', sort='-y'),
+            x=alt.X('group:N', title='Group', sort='-y', axis=alt.Axis(grid=False)),
-            y=alt.Y('sig_count:Q', title='# of Significant Differences'),
+            y=alt.Y('sig_count:Q', title='# of Significant Differences', axis=alt.Axis(grid=True)),
             tooltip=[
                 alt.Tooltip('group:N', title='Group'),
                 alt.Tooltip('sig_count:Q', title='Sig. Differences'),

run_filter_combinations.py

@@ -12,6 +12,8 @@ Runs 03_quant_report.script.py for each single-filter combination:
 Usage:
     uv run python run_filter_combinations.py
     uv run python run_filter_combinations.py --dry-run  # Preview combinations without running
+    uv run python run_filter_combinations.py --category age  # Only run age combinations
+    uv run python run_filter_combinations.py --category consumer  # Only run consumer segment combinations
 """
 
 import subprocess
@@ -31,22 +33,33 @@ QSF_FILE = 'data/exports/OneDrive_2026-01-21/Soft Launch Data/JPMC_Chase_Brand_P
 REPORT_SCRIPT = Path(__file__).parent / '03_quant_report.script.py'
 
 
-def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
+def get_filter_combinations(survey: QualtricsSurvey, category: str = None) -> list[dict]:
     """
     Generate all single-filter combinations.
     
     Each combination isolates ONE filter value while keeping all others at "all selected".
-    Returns list of dicts with filter kwargs for each run.
+    
+    Args:
+        survey: QualtricsSurvey instance with loaded data
+        category: Optional filter category to limit combinations to.
+                  Valid values: 'all', 'age', 'gender', 'ethnicity', 'income', 'consumer',
+                               'business_owner', 'ai_user', 'investable_assets', 'industry'
+                  If None or 'all', generates all combinations.
+    
+    Returns:
+        List of dicts with filter kwargs for each run.
     """
     combinations = []
     
     # Add "All Respondents" run (no filters = all options selected)
+    if not category or category in ['all_filters', 'all']:
         combinations.append({
             'name': 'All_Respondents',
             'filters': {}  # Empty = use defaults (all selected)
         })
     
     # Age groups - one at a time
+    if not category or category in ['all_filters', 'age']:
         for age in survey.options_age:
             combinations.append({
                 'name': f'Age-{age}',
@@ -54,6 +67,7 @@ def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
             })
     
     # Gender - one at a time
+    if not category or category in ['all_filters', 'gender']:
         for gender in survey.options_gender:
             combinations.append({
                 'name': f'Gender-{gender}',
@@ -61,6 +75,7 @@ def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
             })
     
     # Ethnicity - grouped by individual values
+    if not category or category in ['all_filters', 'ethnicity']:
         # Ethnicity options are comma-separated (e.g., "White or Caucasian, Hispanic or Latino")
         # Create filters that include ALL options containing each individual ethnicity value
         ethnicity_values = set()
@@ -81,6 +96,7 @@ def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
             })
     
     # Income - one at a time
+    if not category or category in ['all_filters', 'income']:
         for income in survey.options_income:
             combinations.append({
                 'name': f'Income-{income}',
@@ -88,6 +104,7 @@ def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
             })
     
     # Consumer segments - combine _A and _B options, and also include standalone
+    if not category or category in ['all_filters', 'consumer']:
         # Group options by base name (removing _A/_B suffix)
         consumer_groups = {}
         for consumer in survey.options_consumer:
@@ -117,6 +134,7 @@ def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
             })
     
     # Business Owner - one at a time
+    if not category or category in ['all_filters', 'business_owner']:
         for business_owner in survey.options_business_owner:
             combinations.append({
                 'name': f'BusinessOwner-{business_owner}',
@@ -124,13 +142,29 @@ def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
             })
     
     # AI User - one at a time
+    if not category or category in ['all_filters', 'ai_user']:
         for ai_user in survey.options_ai_user:
             combinations.append({
                 'name': f'AIUser-{ai_user}',
                 'filters': {'ai_user': [ai_user]}
             })
         
+        # AI user daily, more than once daily, en multiple times a week = frequent
+        combinations.append({
+            'name': 'AIUser-Frequent',
+            'filters': {'ai_user': [
+                'Daily', 'More than once daily', 'Multiple times per week'
+            ]}
+        })
+        combinations.append({
+            'name': 'AIUser-RarelyNever',
+            'filters': {'ai_user': [
+                'Once a month', 'Less than once a month', 'Once a week', 'Rarely/Never'
+            ]}
+        })
+    
     # Investable Assets - one at a time
+    if not category or category in ['all_filters', 'investable_assets']:
         for investable_assets in survey.options_investable_assets:
             combinations.append({
                 'name': f'Assets-{investable_assets}',
@@ -138,6 +172,7 @@ def get_filter_combinations(survey: QualtricsSurvey) -> list[dict]:
             })
     
     # Industry - one at a time
+    if not category or category in ['all_filters', 'industry']:
         for industry in survey.options_industry:
             combinations.append({
                 'name': f'Industry-{industry}',
@@ -193,6 +228,12 @@ def main():
     import argparse
     parser = argparse.ArgumentParser(description='Run quant report for all filter combinations')
     parser.add_argument('--dry-run', action='store_true', help='Preview combinations without running')
+    parser.add_argument(
+        '--category',
+        choices=['all_filters', 'all', 'age', 'gender', 'ethnicity', 'income', 'consumer', 'business_owner', 'ai_user', 'investable_assets', 'industry'],
+        default='all_filters',
+        help='Filter category to run combinations for (default: all_filters)'
+    )
     args = parser.parse_args()
     
     # Load survey to get available filter options
@@ -200,9 +241,10 @@ def main():
     survey = QualtricsSurvey(RESULTS_FILE, QSF_FILE)
     survey.load_data()  # Populates options_* attributes
     
-    # Generate all combinations
+    # Generate combinations for specified category
-    combinations = get_filter_combinations(survey)
+    combinations = get_filter_combinations(survey, category=args.category)
-    print(f"Generated {len(combinations)} filter combinations")
+    category_desc = f" for category '{args.category}'" if args.category != 'all' else ''
+    print(f"Generated {len(combinations)} filter combinations{category_desc}")
     
     if args.dry_run:
         print("\nDRY RUN - Commands that would be executed:")

utils.py

@@ -879,40 +879,42 @@ class QualtricsSurvey(QualtricsPlotsMixin):
         """
         
         # Apply filters - skip if empty list (columns with all NULLs produce empty options)
+        # OR if all options are selected (to avoid dropping NULLs)
+        
         self.filter_age = age
-        if age is not None and len(age) > 0:
+        if age is not None and len(age) > 0 and set(age) != set(self.options_age):
             q = q.filter(pl.col('QID1').is_in(age))
         
         self.filter_gender = gender
-        if gender is not None and len(gender) > 0:
+        if gender is not None and len(gender) > 0 and set(gender) != set(self.options_gender):
             q = q.filter(pl.col('QID2').is_in(gender))
         
         self.filter_consumer = consumer
-        if consumer is not None and len(consumer) > 0:
+        if consumer is not None and len(consumer) > 0 and set(consumer) != set(self.options_consumer):
             q = q.filter(pl.col('Consumer').is_in(consumer))
         
         self.filter_ethnicity = ethnicity
-        if ethnicity is not None and len(ethnicity) > 0:
+        if ethnicity is not None and len(ethnicity) > 0 and set(ethnicity) != set(self.options_ethnicity):
             q = q.filter(pl.col('QID3').is_in(ethnicity))
         
         self.filter_income = income
-        if income is not None and len(income) > 0:
+        if income is not None and len(income) > 0 and set(income) != set(self.options_income):
             q = q.filter(pl.col('QID15').is_in(income))
         
         self.filter_business_owner = business_owner
-        if business_owner is not None and len(business_owner) > 0:
+        if business_owner is not None and len(business_owner) > 0 and set(business_owner) != set(self.options_business_owner):
             q = q.filter(pl.col('QID4').is_in(business_owner))
         
         self.filter_ai_user = ai_user
-        if ai_user is not None and len(ai_user) > 0:
+        if ai_user is not None and len(ai_user) > 0 and set(ai_user) != set(self.options_ai_user):
             q = q.filter(pl.col('QID22').is_in(ai_user))
         
         self.filter_investable_assets = investable_assets
-        if investable_assets is not None and len(investable_assets) > 0:
+        if investable_assets is not None and len(investable_assets) > 0 and set(investable_assets) != set(self.options_investable_assets):
             q = q.filter(pl.col('QID16').is_in(investable_assets))
         
         self.filter_industry = industry
-        if industry is not None and len(industry) > 0:
+        if industry is not None and len(industry) > 0 and set(industry) != set(self.options_industry):
             q = q.filter(pl.col('QID17').is_in(industry))
         
         self.data_filtered = q