statistical significance

XX_statistical_significance.script.py

@@ -186,6 +186,20 @@ S.plot_significance_heatmap(_pairwise_df, metadata=_meta, title="Statistical Sig
 Yes, "The Coach" can be considered statistically more significant than the other options. It is clearly superior to the bottom two options and holds a statistically significant lead over the runner-up ("Personal Assistant") in direct comparison.
 """
 
+# %% Mentions significance analysis
+
+char_pairwise_df_mentions, _meta_mentions = S.compute_mentions_significance(
+    char_rank,
+    alpha=0.05,
+    correction="none",
+)
+
+S.plot_significance_heatmap(
+    char_pairwise_df_mentions,
+    metadata=_meta_mentions,
+    title="Statistical Significance: Character Total Mentions (Top 3 Visibility)"
+)
+
 
 # %% voices analysis
 top3_voices = S.get_top_3_voices(data)[0]
@@ -200,4 +214,119 @@ S.plot_significance_heatmap(
     metadata=_metadata,
     title="Statistical Significance: Voice Top Choice Preference"
 )
+# %% Total Mentions Significance (Rank 1+2+3 Combined)
+# This tests "Quantity" (Visibility) instead of "Quality" (Preference)
+
+_pairwise_df_mentions, _meta_mentions = S.compute_mentions_significance(
+    top3_voices,
+    alpha=0.05,
+    correction="none"
+)
+
+S.plot_significance_heatmap(
+    _pairwise_df_mentions,
+    metadata=_meta_mentions,
+    title="Statistical Significance: Voice Total Mentions (Top 3 Visibility)"
+)
+# %% Male Voices Only Analysis
+import reference
+
+def filter_voices_by_gender(df: pl.DataFrame, target_gender: str) -> pl.DataFrame:
+    """Filter ranking columns to keep only those matching target gender."""
+    cols_to_keep = []
+    
+    # Always keep identifier if present
+    if '_recordId' in df.columns:
+        cols_to_keep.append('_recordId')
+        
+    for col in df.columns:
+        # Check if column is a voice column (contains Vxx)
+        # Format is typically "Top_3_Voices_ranking__V14"
+        if '__V' in col:
+            voice_id = col.split('__')[1]
+            if reference.VOICE_GENDER_MAPPING.get(voice_id) == target_gender:
+                cols_to_keep.append(col)
+                
+    return df.select(cols_to_keep)
+
+# Get full ranking data as DataFrame
+df_voices = top3_voices.collect()
+
+# Filter for Male voices
+df_male_voices = filter_voices_by_gender(df_voices, 'Male')
+
+# 1. Male Voices: Top Choice Preference (Rank 1)
+_pairwise_male_pref, _meta_male_pref = S.compute_ranking_significance(
+    df_male_voices,
+    alpha=0.05,
+    correction="none"
+)
+
+S.plot_significance_heatmap(
+    _pairwise_male_pref,
+    metadata=_meta_male_pref,
+    title="Male Voices Only: Top Choice Preference Significance"
+)
+
+# 2. Male Voices: Total Mentions (Visibility)
+_pairwise_male_vis, _meta_male_vis = S.compute_mentions_significance(
+    df_male_voices,
+    alpha=0.05,
+    correction="none"
+)
+
+S.plot_significance_heatmap(
+    _pairwise_male_vis,
+    metadata=_meta_male_vis,
+    title="Male Voices Only: Total Mentions Significance"
+)
+# %% Male Voices (Excluding Bottom 3: V88, V86, V81)
+
+# Start with the male voices dataframe from the previous step
+voices_to_exclude = ['V88', 'V86', 'V81']
+
+def filter_exclude_voices(df: pl.DataFrame, exclude_list: list[str]) -> pl.DataFrame:
+    """Filter ranking columns to exclude specific voices."""
+    cols_to_keep = []
+    
+    # Always keep identifier if present
+    if '_recordId' in df.columns:
+        cols_to_keep.append('_recordId')
+        
+    for col in df.columns:
+        # Check if column is a voice column (contains Vxx)
+        if '__V' in col:
+            voice_id = col.split('__')[1]
+            if voice_id not in exclude_list:
+                cols_to_keep.append(col)
+                
+    return df.select(cols_to_keep)
+
+df_male_top = filter_exclude_voices(df_male_voices, voices_to_exclude)
+
+# 1. Male Top Candidates: Top Choice Preference
+_pairwise_male_top_pref, _meta_male_top_pref = S.compute_ranking_significance(
+    df_male_top,
+    alpha=0.05,
+    correction="none"
+)
+
+S.plot_significance_heatmap(
+    _pairwise_male_top_pref,
+    metadata=_meta_male_top_pref,
+    title="Male Voices (Excl. Bottom 3): Top Choice Preference Significance"
+)
+
+# 2. Male Top Candidates: Total Mentions
+_pairwise_male_top_vis, _meta_male_top_vis = S.compute_mentions_significance(
+    df_male_top,
+    alpha=0.05,
+    correction="none"
+)
+
+S.plot_significance_heatmap(
+    _pairwise_male_top_vis,
+    metadata=_meta_male_top_vis,
+    title="Male Voices (Excl. Bottom 3): Total Mentions Significance"
+)
 # %%