voice plots

03_quant_report.py

@@ -255,7 +255,7 @@ def _():
     mo.md(r"""
     ---
 
-    # Brand Character Results (overall)
+    # Brand Character Results
     """)
     return
 
@@ -276,7 +276,7 @@ def _(S, data):
     return
 
 
-@app.cell
+@app.cell(disabled=True)
 def _():
     mo.md(r"""
     ## Character ranking points
@@ -311,7 +311,7 @@ def _(S, char_rank):
     return
 
 
-@app.cell(disabled=True)
+@app.cell
 def _():
     mo.md(r"""
     ### Statistical Significance Character Ranking
@@ -335,7 +335,7 @@ def _(S, char_rank):
     return
 
 
-@app.cell
+@app.cell(disabled=True)
 def _():
     mo.md(r"""
     ## Character Ranking: times 1st place
@@ -438,7 +438,7 @@ def _():
     return
 
 
-@app.cell
+@app.cell(disabled=True)
 def _():
     return
 
@@ -461,20 +461,34 @@ def _():
 @app.cell
 def _():
     mo.md(r"""
-    ## 8 Most Chosen
+    ## Top 8 Most Chosen out of 18
     """)
     return
 
 
 @app.cell
 def _(S, data):
-    v_18_8_3 = S.get_18_8_3(data)[0].collect()
+    v_18_8_3 = S.get_18_8_3(data)[0]
     return (v_18_8_3,)
 
 
 @app.cell
 def _(S, v_18_8_3):
-    S.plot_voice_selection_counts(v_18_8_3)
+    S.plot_voice_selection_counts(v_18_8_3, title="Top 8 Voice Selection from 18 Voices", x_label='Voice')
+    return
+
+
+@app.cell
+def _():
+    mo.md(r"""
+    ## Top 3 most chosen out of 8
+    """)
+    return
+
+
+@app.cell
+def _(S, v_18_8_3):
+    S.plot_top3_selection_counts(v_18_8_3, title="Top 3 Voice Selection Counts from 8 Voices", x_label='Voice')
     return
 
 
@@ -497,10 +511,7 @@ def _(S, data):
 
 @app.cell
 def _(S, top3_voices):
-    _plot = S.plot_ranking_distribution(top3_voices, x_label='Voice')
+    S.plot_ranking_distribution(top3_voices, x_label='Voice', title="Distribution of Voice Rankings (1st, 2nd, 3rd)")
-    mo.md(f"""
-    {mo.ui.altair_chart(_plot)}
-    """)
     return
 
 
@@ -548,7 +559,7 @@ def _():
     return
 
 
-@app.cell
+@app.cell(hide_code=True)
 def _():
     mo.md(r"""
     ## Weighted Popularity Scores
@@ -568,6 +579,7 @@ def _(S, top3_voices_weighted):
 
 @app.cell
 def _():
+    ## Voice Ranked 1st the most
     return
 
 
@@ -578,7 +590,8 @@ def _(top3_voices_weighted):
 
 
 @app.cell
-def _():
+def _(S, top3_voices):
+    S.plot_most_ranked_1(top3_voices, title="Most Popular Voice<br>(Number of Times Ranked 1st)", x_label='Voice')
     return
 
 
@@ -597,13 +610,13 @@ def _(S, data):
     return (voice_1_10,)
 
 
-@app.cell(hide_code=True)
+@app.cell(disabled=True)
 def _(S, voice_1_10):
-    S.plot_average_scores_with_counts(voice_1_10, x_label='Voice', width=1000, domain=[1,10], title="Voice General Impression (Scale 1-10)")
+    S.plot_average_scores_with_counts(voice_1_10, x_label='Voice', domain=[1,10], title="Voice General Impression (Scale 1-10)")
     return
 
 
-@app.cell
+@app.cell(disabled=True)
 def _():
     mo.md(r"""
     ### Statistical Significance (Scale 1-10)
@@ -687,5 +700,60 @@ def _(S, voice_1_10):
     return
 
 
+@app.cell
+def _(S, data):
+    # Get your voice scale data (from notebook)
+    voice_1_10, _ = S.get_voice_scale_1_10(data)
+    return (voice_1_10,)
+
+
+@app.cell
+def _(S, voice_1_10):
+    S.plot_average_scores_with_counts(voice_1_10, x_label='Voice', domain=[1,10], title="Voice General Impression (Scale 1-10)")
+    return
+
+
+@app.cell(disabled=True)
+def _():
+    mo.md(r"""
+    ### Statistical Significance (Scale 1-10)
+    """)
+    return
+
+
+@app.cell(disabled=True)
+def _(S, voice_1_10):
+    # Compute pairwise significance tests
+    pairwise_df, metadata = S.compute_pairwise_significance(
+        voice_1_10,
+        test_type="mannwhitney",  # or "ttest", "chi2", "auto"
+        alpha=0.05,
+        correction="bonferroni"   # or "holm", "none"
+    )
+
+    # View significant pairs
+    # print(pairwise_df.filter(pl.col('significant') == True))
+
+    # Create heatmap visualization
+    _heatmap = S.plot_significance_heatmap(
+        pairwise_df, 
+        metadata=metadata,
+        title="Voice Rating Significance<br>(Pairwise Comparisons)"
+    )
+
+    # Create summary bar chart
+    _summary = S.plot_significance_summary(
+        pairwise_df,
+        metadata=metadata
+    )
+
+    mo.md(f"""
+    {mo.ui.altair_chart(_heatmap)}
+
+    {mo.ui.altair_chart(_summary)}
+    """)
+    return
+
+
 if __name__ == "__main__":
     app.run()

plots.py

@@ -385,13 +385,13 @@ class QualtricsPlotsMixin:
     def plot_ranking_distribution(
         self,
         data: pl.LazyFrame | pl.DataFrame | None = None,
-        title: str = "Rankings Distribution\n(1st to 4th Place)",
+        title: str = "Rankings Distribution\n(1st to 3rd Place)",
         x_label: str = "Item",
         y_label: str = "Number of Votes",
         height: int | None = None,
         width: int | str | None = None,
     ) -> alt.Chart:
-        """Create a stacked bar chart showing the distribution of rankings (1st to 4th)."""
+        """Create a stacked bar chart showing the distribution of rankings (1st to 3rd)."""
         df = self._ensure_dataframe(data)
 
         stats = []
@@ -401,15 +401,15 @@ class QualtricsPlotsMixin:
             r1 = df.filter(pl.col(col) == 1).height
             r2 = df.filter(pl.col(col) == 2).height
             r3 = df.filter(pl.col(col) == 3).height
-            r4 = df.filter(pl.col(col) == 4).height
+            # r4 = df.filter(pl.col(col) == 4).height
-            total = r1 + r2 + r3 + r4
+            total = r1 + r2 + r3 
 
             if total > 0:
                 label = self._clean_voice_label(col)
                 stats.append({'item': label, 'rank': 'Rank 1 (Best)', 'count': r1, 'rank1': r1})
                 stats.append({'item': label, 'rank': 'Rank 2', 'count': r2, 'rank1': r1})
                 stats.append({'item': label, 'rank': 'Rank 3', 'count': r3, 'rank1': r1})
-                stats.append({'item': label, 'rank': 'Rank 4 (Worst)', 'count': r4, 'rank1': r1})
+                # stats.append({'item': label, 'rank': 'Rank 4 (Worst)', 'count': r4, 'rank1': r1})
 
         if not stats:
             return alt.Chart(pd.DataFrame({'text': ['No data']})).mark_text().encode(text='text:N')
@@ -423,8 +423,8 @@ class QualtricsPlotsMixin:
             x=alt.X('item:N', title=x_label, sort=alt.EncodingSortField(field='rank1', order='descending')),
             y=alt.Y('count:Q', title=y_label, stack='zero'),
             color=alt.Color('rank:N',
-                           scale=alt.Scale(domain=['Rank 1 (Best)', 'Rank 2', 'Rank 3', 'Rank 4 (Worst)'],
+                           scale=alt.Scale(domain=['Rank 1 (Best)', 'Rank 2', 'Rank 3'],
-                                         range=[ColorPalette.RANK_1, ColorPalette.RANK_2, ColorPalette.RANK_3, ColorPalette.RANK_4]),
+                                         range=[ColorPalette.RANK_1, ColorPalette.RANK_2, ColorPalette.RANK_3]),
                            legend=alt.Legend(orient='top', direction='horizontal', title=None)),
             order=alt.Order('rank:N', sort='ascending'),
             opacity=alt.condition(selection, alt.value(1), alt.value(0.2)),

reference.py

@@ -36,3 +36,24 @@ ORIGINAL_CHARACTER_TRAITS = {
         "Efficient",
     ]
 }
+
+VOICE_GENDER_MAPPING = {
+    "V14": "Female",
+    "V04": "Female",
+    "V08": "Female",
+    "V77": "Female",
+    "V48": "Female",
+    "V82": "Female",
+    "V89": "Female",
+    "V91": "Female",
+    "V34": "Male",
+    "V69": "Male",
+    "V45": "Male",
+    "V46": "Male",
+    "V54": "Male",
+    "V74": "Male",
+    "V81": "Male",
+    "V86": "Male",
+    "V88": "Male",
+    "V16": "Male",
+}