split consumer groups best character

03_quant_report.py

@@ -174,6 +174,11 @@ def _(data_validated):
     return (data,)
 
 
+@app.cell
+def _():
+    return
+
+
 @app.cell
 def _():
     # Check if all business owners are missing a 'Consumer type' in demographics
@@ -404,6 +409,37 @@ def _():
     return
 
 
+@app.cell
+def _():
+    mo.md(r"""
+    ## Character Ranking Points (per customer segment)
+    """)
+    return
+
+
+@app.cell
+def _(S, data):
+    _content = ""
+    for _consumer_group, _consumer_df in utils.split_consumer_groups(data).items():
+
+        _char_rank = S.get_character_ranking(_consumer_df)[0]
+        _char_rank_weighted = calculate_weighted_ranking_scores(_char_rank)
+
+        _plot = S.plot_weighted_ranking_score(
+            _char_rank_weighted, 
+            title=f'Most Popular Character - Weighted Popularity Score - CONSUMER: "{_consumer_group.replace()}"<br>(1st=3pts, 2nd=2pts, 3rd=1pt)',
+            x_label='Voice'
+        )
+
+        _content += f"""
+        {mo.ui.altair_chart(_plot)}
+    
+        """
+
+    mo.md(_content)
+    return
+
+
 @app.cell(hide_code=True)
 def _():
     mo.md(r"""
@@ -579,7 +615,6 @@ def _(S, voice_1_10):
     {mo.ui.altair_chart(_summary)}
     """)
 
-
     return
 
 

utils.py

@@ -1716,3 +1716,37 @@ def process_voice_ranking_data(
     ])
     
     return result.collect()
+
+
+def split_consumer_groups(df: Union[pl.LazyFrame, pl.DataFrame]) -> dict[str, pl.DataFrame]:
+    """
+    Split dataframe into groups based on Consumer column, combining A/B subgroups.
+    
+    Mappings:
+    - Mass_A, Mass_B -> Mass
+    - Lower_Mass_A, Lower_Mass_B -> Lower_Mass
+    - MassAffluent_A, MassAffluent_B -> MassAffluent
+    - Mix_of_Affluent..._A, ..._B -> Mix_of_Affluent...
+    """
+    if isinstance(df, pl.LazyFrame):
+        df = df.collect()
+        
+    if "Consumer" not in df.columns:
+        raise ValueError("Column 'Consumer' not found in DataFrame")
+
+    # Clean Consumer column by removing _A or _B suffix
+    # Using regex replacement for trailing _A or _B
+    df_clean = df.with_columns(
+        pl.col("Consumer")
+        .str.replace(r"_[AB]$", "")
+        .alias("Consumer_Group")
+    )
+    
+    # Split into dict
+    groups = {}
+    unique_groups = df_clean["Consumer_Group"].drop_nulls().unique().to_list()
+    
+    for group in unique_groups:
+        groups[group] = df_clean.filter(pl.col("Consumer_Group") == group)
+        
+    return groups