drop voice46 from scales 1-10. fix plots breakline in title

utils.py

@@ -351,18 +351,22 @@ def calculate_weighted_ranking_scores(df: pl.LazyFrame) -> pl.DataFrame:
 
 def normalize_row_values(df: pl.DataFrame, target_cols: list[str]) -> pl.DataFrame:
     """
-    Normalizes values in the specified columns row-wise (Standardization: (x - mean) / std).
-    Ignores null values (NaNs). Only applied if there are at least 2 non-null values in the row.
+    Normalizes values in the specified columns row-wise to 0-10 scale (Min-Max normalization).
+    Formula: ((x - min) / (max - min)) * 10
+    Ignores null values (NaNs).
     """
     
     # Using list evaluation for row-wise stats
     # We create a temporary list column containing values from all target columns
+    # Ensure columns are cast to Float64 to avoid type errors with mixed/string data
     df_norm = df.with_columns(
-        pl.concat_list(target_cols)
+        pl.concat_list([pl.col(c).cast(pl.Float64) for c in target_cols])
         .list.eval(
-            # Apply standardization: (x - mean) / std
-            # std(ddof=1) is the sample standard deviation
-            (pl.element() - pl.element().mean()) / pl.element().std(ddof=1)
+            # Apply Min-Max scaling to 0-10
+            (
+                (pl.element() - pl.element().min()) / 
+                (pl.element().max() - pl.element().min())
+            ) * 10
         )
         .alias("_normalized_values")
     )
@@ -377,8 +381,8 @@ def normalize_row_values(df: pl.DataFrame, target_cols: list[str]) -> pl.DataFra
 
 def normalize_global_values(df: pl.DataFrame, target_cols: list[str]) -> pl.DataFrame:
     """
-    Normalizes values in the specified columns globally (Standardization: (x - global_mean) / global_std).
-    Computes a single mean and standard deviation across ALL values in the target_cols and applies it.
+    Normalizes values in the specified columns globally to 0-10 scale.
+    Formula: ((x - global_min) / (global_max - global_min)) * 10
     Ignores null values (NaNs).
     """
     # Ensure eager for scalar extraction
@@ -390,19 +394,23 @@ def normalize_global_values(df: pl.DataFrame, target_cols: list[str]) -> pl.Data
         return df.lazy() if was_lazy else df
 
     # Calculate global stats efficiently by stacking all columns
-    stats = df.select(target_cols).melt().select([
-        pl.col("value").mean().alias("mean"),
-        pl.col("value").std().alias("std")
+    # Cast to Float64 to ensure numeric calculations
+    stats = df.select([pl.col(c).cast(pl.Float64) for c in target_cols]).melt().select([
+        pl.col("value").min().alias("min"),
+        pl.col("value").max().alias("max")
     ])
     
-    global_mean = stats["mean"][0]
-    global_std = stats["std"][0]
+    global_min = stats["min"][0]
+    global_max = stats["max"][0]
     
-    if global_std is None or global_std == 0:
+    # Handle edge case where all values are same or none exist
+    if global_min is None or global_max is None or global_max == global_min:
         return df.lazy() if was_lazy else df
 
+    global_range = global_max - global_min
+
     res = df.with_columns([
-        ((pl.col(col) - global_mean) / global_std).alias(col)
+        (((pl.col(col).cast(pl.Float64) - global_min) / global_range) * 10).alias(col)
         for col in target_cols
     ])
     
@@ -649,10 +657,12 @@ class JPMCSurvey(JPMCPlotsMixin):
         return subset, None
     
     
-    def get_voice_scale_1_10(self, q: pl.LazyFrame) -> Union[pl.LazyFrame, None]:
+    def get_voice_scale_1_10(self, q: pl.LazyFrame, drop_cols=['Voice_Scale_1_10__V46']) -> Union[pl.LazyFrame, None]:
         """Extract columns containing the Voice Scale 1-10 ratings for the Chase virtual assistant. 
         
         Returns subquery that can be chained with other polars queries.
+        
+        Drops scores for V46 as it was improperly configured in the survey and thus did not show up for respondents.
         """
         
         QIDs_map = {}
@@ -662,6 +672,12 @@ class JPMCSurvey(JPMCPlotsMixin):
                 # Convert "Voice 16 Scale 1-10_1" to "Scale_1_10__Voice_16"
                 QIDs_map[qid] = f"Voice_Scale_1_10__V{val['QName'].split()[1]}"
         
+        for col in drop_cols:
+            if col in QIDs_map.values():
+                # remove from QIDs_map
+                qid_to_remove = [k for k,v in QIDs_map.items() if v == col][0]
+                del QIDs_map[qid_to_remove]
+        
         return self._get_subset(q, list(QIDs_map.keys()), rename_cols=False).rename(QIDs_map), None