Update stats_data.py

stats_data.py

@@ -1,6 +1,6 @@
 import pandas as pd
 
-# Standardized metadata based on your training configuration
+# Metadata lookup for UI and filtering
 SPEAKER_META = {
     "F01": {"Gender": "Female", "Severity": "Severe", "Dataset": "Torgo"},
     "F03": {"Gender": "Female", "Severity": "Mild", "Dataset": "Torgo"},
@@ -10,30 +10,48 @@ SPEAKER_META = {
     "M03": {"Gender": "Male", "Severity": "Mild", "Dataset": "Torgo"},
     "M04": {"Gender": "Male", "Severity": "Moderate", "Dataset": "Torgo"},
     "M05": {"Gender": "Male", "Severity": "Severe", "Dataset": "Torgo"},
-    "F02": {"Gender": "Female", "Severity": "Severe (Isolated)", "Dataset": "UA-Speech"}
+    "F02 (UA)": {"Gender": "Female", "Severity": "Severe", "Dataset": "UA-Speech"}
 }
 
 def get_indomain_breakdown():
+    # Performance on Seen Torgo Speakers
     data = {
         "Speaker": ["M05", "F01", "M01", "M04", "M02", "M03", "F03", "F04"],
         "Severity": ["Severe", "Severe", "Moderate", "Moderate", "Mild", "Mild", "Mild", "Mild"],
         "Whisper Tiny": [12.1, 12.6, 32.7, 31.8, 62.1, 58.4, 61.2, 59.1],
         "5K Pure Model": [33.1, 34.2, 47.2, 45.6, 84.5, 81.8, 83.5, 82.8],
-        "10K Triple-Mix": [25.4, 24.1, 44.1, 41.2, 79.1, 77.5, 79.0, 78.2]
+        "10K Triple-Mix": ["25.4%", "24.1% (LOSO)", "44.1%", "41.2%", "79.1%", "77.5%", "79.0%", "78.2%"]
     }
     df = pd.DataFrame(data)
-    df["Relative Gain (5K vs Tiny)"] = (((df["5K Pure Model"] - df["Whisper Tiny"]) / df["Whisper Tiny"]) * 100).round(1)
-    for col in ["Whisper Tiny", "5K Pure Model", "10K Triple-Mix"]:
-        df[col] = df[col].astype(str) + "%"
-    df["Relative Gain (5K vs Tiny)"] = "+" + df["Relative Gain (5K vs Tiny)"].astype(str) + "%"
+    
+    # Calculate Relative Gain from the best model (usually 5K for in-domain)
+    df["Relative Gain (Best)"] = (((df["5K Pure Model"] - df["Whisper Tiny"]) / df["Whisper Tiny"]) * 100).round(1)
+    
+    # Formatting
+    df["Whisper Tiny"] = df["Whisper Tiny"].astype(str) + "%"
+    df["5K Pure Model"] = df["5K Pure Model"].astype(str) + "%"
+    df["Relative Gain (Best)"] = "+" + df["Relative Gain (Best)"].astype(str) + "%"
     return df
 
 def get_experimental_summary():
+    # Summary of the three primary research conditions
     data = {
-        "Experiment Condition": ["In-Domain (Seen Torgo)", "LOSO (Unseen Torgo F01)", "Zero-Shot (UA-Speech F02)"],
-        "Whisper Tiny": ["41.50%", "12.38%", "4.33%"],
-        "5K Pure Model": ["58.77%", "N/A", "6.19%"],
-        "10K Triple-Mix": ["54.67%", "24.76%", "5.98%"],
-        "Best Relative Improvement": ["+41.6%", "+100.0%", "+42.9%"]
+        "Condition": ["In-Domain (Seen Torgo)", "LOSO (Unseen Torgo F01)", "Zero-Shot (UA-Speech F02)"],
+        "Whisper Tiny": [41.50, 12.38, 4.33],
+        "5K Pure Model": [58.77, "N/A", 6.19],
+        "10K Triple-Mix": [54.67, 24.76, 5.98]
     }
-    return pd.DataFrame(data)
+    df = pd.DataFrame(data)
+    
+    # Calculate Best Relative Gain
+    best_scores = [58.77, 24.76, 6.19]
+    whisper_base = [41.50, 12.38, 4.33]
+    gains = [f"+{round(((b-w)/w)*100, 1)}%" for b, w in zip(best_scores, whisper_base)]
+    df["Relative Gain (Best)"] = gains
+
+    # Formatting for display
+    df["Whisper Tiny"] = df["Whisper Tiny"].astype(str) + "%"
+    df["5K Pure Model"] = df["5K Pure Model"].apply(lambda x: f"{x}%" if x != "N/A" else x)
+    df["10K Triple-Mix"] = df["10K Triple-Mix"].astype(str) + "%"
+    
+    return df