Update stats_data.py

stats_data.py

@@ -1,6 +1,6 @@
 import pandas as pd
 
-# Speaker meta remains the same for UI lookups
+# Speaker meta lookup
 SPEAKER_META = {
     "M05": {"Gender": "Male", "Severity": "Severe", "Dataset": "Torgo"},
     "F01": {"Gender": "Female", "Severity": "Severe", "Dataset": "Torgo"},
@@ -14,46 +14,29 @@ SPEAKER_META = {
 }
 
 def get_indomain_breakdown():
+    # Individual speaker results for In-Domain Torgo
     data = {
         "Speaker": ["M05", "F01", "M01", "M04", "M02", "M03", "F03", "F04"],
         "Severity": ["Severe", "Severe", "Moderate", "Moderate", "Mild", "Mild", "Mild", "Mild"],
         "Whisper Baseline": [12.1, 12.6, 32.7, 31.8, 62.1, 58.4, 61.2, 59.1],
-        "Correction Layer (5K)": [33.1, 34.2, 47.2, 45.6, 84.5, 81.8, 83.5, 82.8]
+        "5K Pure Model": [33.1, 34.2, 47.2, 45.6, 84.5, 81.8, 83.5, 82.8]
     }
     df = pd.DataFrame(data)
-    # Relative Gain calculation: ((Ours - Whisper) / Whisper) * 100
-    df["Relative Gain"] = (((df["Correction Layer (5K)"] - df["Whisper Baseline"]) / df["Whisper Baseline"]) * 100).round(1)
+    df["Relative Gain"] = (((df["5K Pure Model"] - df["Whisper Baseline"]) / df["Whisper Baseline"]) * 100).round(1)
     
-    # Add percentage signs for display
-    for col in ["Whisper Baseline", "Correction Layer (5K)"]:
+    # Formatting
+    for col in ["Whisper Baseline", "5K Pure Model"]:
         df[col] = df[col].astype(str) + "%"
     df["Relative Gain"] = "+" + df["Relative Gain"].astype(str) + "%"
-    
     return df
 
 def get_experimental_summary():
+    # Comparing 5K and 10K across the three specific research conditions
     data = {
-        "Experiment Condition": ["In-Domain (Seen Torgo)", "LOSO (Unseen Torgo F01)", "Zero-Shot (UA-Speech F02)"],
-        "Whisper Baseline": [41.50, 12.38, 4.33],
-        "5K Model Score": [58.77, "N/A", 6.19],
-        "10K Model Score": [54.67, 24.76, 5.98]
+        "Condition": ["In-Domain (Seen Torgo)", "LOSO (Unseen Torgo F01)", "Zero-Shot (UA-Speech F02)"],
+        "Whisper Baseline": ["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 Gain": ["+41.6%", "+100.0%", "+42.9%"]
     }
-    df = pd.DataFrame(data)
-    # Calculate gain based on the best performing model in that row
-    best_scores = [58.77, 24.76, 6.19]
-    whisper_base = [41.50, 12.38, 4.33]
-    gains = []
-    for b, w in zip(best_scores, whisper_base):
-        gains.append(f"+{round(((b-w)/w)*100, 1)}%")
-    
-    df["Relative Gain (Best)"] = gains
-    
-    # Formatting
-    df["Whisper Baseline"] = df["Whisper Baseline"].astype(str) + "%"
-    df.at[0, "5K Model Score"] = "58.77%"
-    df.at[2, "5K Model Score"] = "6.19%"
-    df.at[0, "10K Model Score"] = "54.67%"
-    df.at[1, "10K Model Score"] = "24.76%"
-    df.at[2, "10K Model Score"] = "5.98%"
-    
-    return df
+    return pd.DataFrame(data)