stats_data.py

import pandas as pd

# Speaker meta lookup
SPEAKER_META = {
    "M05": {"Gender": "Male", "Severity": "Severe", "Dataset": "Torgo"},
    "F01": {"Gender": "Female", "Severity": "Severe", "Dataset": "Torgo"},
    "M01": {"Gender": "Male", "Severity": "Moderate", "Dataset": "Torgo"},
    "M04": {"Gender": "Male", "Severity": "Moderate", "Dataset": "Torgo"},
    "M02": {"Gender": "Male", "Severity": "Mild", "Dataset": "Torgo"},
    "M03": {"Gender": "Male", "Severity": "Mild", "Dataset": "Torgo"},
    "F03": {"Gender": "Female", "Severity": "Mild", "Dataset": "Torgo"},
    "F04": {"Gender": "Female", "Severity": "Mild", "Dataset": "Torgo"},
    "F02 (UA)": {"Gender": "Female", "Severity": "Severe (Isolated)", "Dataset": "UA-Speech"}
}

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],
        "5K Pure Model": [33.1, 34.2, 47.2, 45.6, 84.5, 81.8, 83.5, 82.8]
    }
    df = pd.DataFrame(data)
    df["Relative Gain"] = (((df["5K Pure Model"] - df["Whisper Baseline"]) / df["Whisper Baseline"]) * 100).round(1)
    
    # 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 = {
        "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%"]
    }
    return pd.DataFrame(data)