added var split_group

02_quant_analysis.py

@@ -1,6 +1,6 @@
 import marimo
 
-__generated_with = "0.19.2"
+__generated_with = "0.19.7"
 app = marimo.App(width="full")
 
 
@@ -285,7 +285,6 @@ def _(S, mo, v_18_8_3):
 def _(S, calculate_weighted_ranking_scores, data):
     top3_voices = S.get_top_3_voices(data)[0]
     top3_voices_weighted = calculate_weighted_ranking_scores(top3_voices)
-
     return top3_voices, top3_voices_weighted
 
 

03_quant_report.py

@@ -71,7 +71,6 @@ def _(S, data_all):
 
 
     mo.md(f"""
-    # Data Validation
 
     {check_progress(data_all)}
 
@@ -104,25 +103,23 @@ def _(data_all):
     return (data_validated,)
 
 
-@app.cell(hide_code=True)
+@app.cell
 def _():
 
 
     return
 
 
-@app.cell
+@app.cell(hide_code=True)
 def _():
     # 
     return
 
 
-@app.cell(hide_code=True)
+@app.cell
 def _():
     mo.md(r"""
-    ---
+    ## Lucia confirmation missing 'Consumer' data
-
-    # Introduction (Respondent Demographics)
     """)
     return
 
@@ -135,14 +132,6 @@ def _(S, data_validated):
 
 
 @app.cell(hide_code=True)
-def _():
-    mo.md(r"""
-    ## Lucia confirmation missing 'Consumer' data
-    """)
-    return
-
-
-@app.cell
 def _(demographics):
     # Demographics where 'Consumer' is null
     demographics_no_consumer = demographics.filter(pl.col('Consumer').is_null())['_recordId'].to_list()
@@ -189,7 +178,7 @@ def _():
 @app.cell
 def _():
     mo.md(r"""
-    ## Demographic Distributions
+    # Demographic Distributions
     """)
     return
 
@@ -209,7 +198,6 @@ def _():
 @app.cell
 def _(S, data, demo_plot_cols):
     _content = """
-    ## Demographic Distributions
 
     """
     for c in demo_plot_cols:
@@ -229,7 +217,7 @@ def _():
     mo.md(r"""
     ---
 
-    # Brand Character Results
+    # Brand Character Results (overall)
     """)
     return
 
@@ -400,7 +388,7 @@ def _(S, char_df):
     return character_colors, consistent_sort_order
 
 
-@app.cell(hide_code=True)
+@app.cell
 def _():
     mo.md(r"""
     ## Statistical significance best characters
@@ -412,15 +400,24 @@ def _():
     return
 
 
-@app.cell
+@app.cell(hide_code=True)
 def _():
+    mo.md(r"""
+    # BC per Consumer
+    """)
     return
 
 
 @app.cell
 def _():
-    mo.md(r"""
+    split_group = 'Consumer'
-    ## Character Ranking Points (per customer segment)
+    return (split_group,)
+
+
+@app.cell
+def _(split_group):
+    mo.md(rf"""
+    ## Character Ranking Points (per {split_group} segment)
     """)
     return
 
@@ -449,9 +446,9 @@ def _(S, data):
 
 
 @app.cell
-def _():
+def _(split_group):
-    mo.md(r"""
+    mo.md(rf"""
-    ## Character Ranking Place 1-2-3 in one (per consumer)
+    ## Character Ranking Place 1-2-3 in one (per {split_group})
     """)
     return
 
@@ -476,9 +473,9 @@ def _(S, data):
 
 
 @app.cell
-def _():
+def _(split_group):
-    mo.md(r"""
+    mo.md(rf"""
-    ## Character Ranking times 1st place (per consumer)
+    ## Character Ranking times 1st place (per {split_group})
     """)
     return
 
@@ -502,9 +499,9 @@ def _(S, data):
 
 
 @app.cell
-def _():
+def _(split_group):
-    mo.md(r"""
+    mo.md(rf"""
-    ## Predefined personality traits WordClouds per Consumer
+    ## Predefined personality traits WordClouds per {split_group}
     """)
     return
 
@@ -531,9 +528,9 @@ def _(S, data):
 
 
 @app.cell
-def _():
+def _(split_group):
-    mo.md(r"""
+    mo.md(rf"""
-    ## Frequency traits chosen - per consumer segment
+    ## Frequency traits chosen - per {split_group} segment
     """)
     return
 
@@ -565,7 +562,7 @@ def _(S, character_colors, consistent_sort_order, data):
     return
 
 
-@app.cell(hide_code=True)
+@app.cell
 def _():
     mo.md(r"""
     ---
@@ -582,7 +579,7 @@ def _(S, data):
     return top3_voices, top3_voices_weighted
 
 
-@app.cell
+@app.cell(hide_code=True)
 def _():
     mo.md(r"""
     ## Which voice is ranked best in the ranking question for top 3?
@@ -679,7 +676,7 @@ def _():
     return
 
 
-@app.cell(hide_code=True)
+@app.cell
 def _():
     mo.md(r"""
     ## Voice Scale 1-10
@@ -694,7 +691,7 @@ def _(S, data):
     return (voice_1_10,)
 
 
-@app.cell
+@app.cell(hide_code=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)")
     return
@@ -742,5 +739,47 @@ def _(S, voice_1_10):
     return
 
 
+@app.cell
+def _():
+    mo.md(r"""
+    ### Statistical Significance (Scale 1-10)
+    """)
+    return
+
+
+@app.cell
+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()