Update visualization.py

visualization.py

@@ -127,101 +127,6 @@ def plot_mse(df, mse_values, title, color='navy', time_threshold=3, anomaly_thre
     plt.close()
     return fig, anomaly_frames
 
-def plot_combined_mse(df, mse_embeddings, mse_posture, mse_voice, title, anomaly_threshold=4, time_threshold=3):
-    plt.figure(figsize=(16, 8), dpi=300)
-    fig, ax = plt.subplots(figsize=(16, 8))
-
-    if 'Seconds' not in df.columns:
-        df['Seconds'] = df['Timecode'].apply(
-            lambda x: sum(float(t) * 60 ** i for i, t in enumerate(reversed(x.split(':')))))
-
-    # Ensure the lengths of the DataFrame and MSE values are consistent
-    min_length = min(len(df), len(mse_embeddings), len(mse_posture), len(mse_voice))
-    df = df.iloc[:min_length].copy()
-    mse_embeddings = mse_embeddings[:min_length]
-    mse_posture = mse_posture[:min_length]
-    mse_voice = mse_voice[:min_length]
-
-    # Remove NaN values
-    valid_mask = ~np.isnan(mse_embeddings) & ~np.isnan(mse_posture) & ~np.isnan(mse_voice)
-    df = df[valid_mask]
-    mse_embeddings = mse_embeddings[valid_mask]
-    mse_posture = mse_posture[valid_mask]
-    mse_voice = mse_voice[valid_mask]
-
-    # Function to identify continuous segments
-    def get_continuous_segments(seconds, values, max_gap=1):
-        segments = []
-        current_segment = []
-        for i, (sec, val) in enumerate(zip(seconds, values)):
-            if not current_segment or (sec - current_segment[-1][0] <= max_gap):
-                current_segment.append((sec, val))
-            else:
-                segments.append(current_segment)
-                current_segment = [(sec, val)]
-        if current_segment:
-            segments.append(current_segment)
-        return segments
-
-    # Scale all MSE values to the same range (0 to 1)
-    def scale_mse(mse_values):
-        min_val = np.min(mse_values)
-        max_val = np.max(mse_values)
-        return (mse_values - min_val) / (max_val - min_val)
-
-    mse_embeddings_scaled = scale_mse(mse_embeddings)
-    mse_posture_scaled = scale_mse(mse_posture)
-    mse_voice_scaled = scale_mse(mse_voice)
-
-    # Plot each data series
-    for mse_values, color, label in zip([mse_embeddings_scaled, mse_posture_scaled, mse_voice_scaled], 
-                                        ['navy', 'purple', 'green'], 
-                                        ['Facial Features', 'Body Posture', 'Voice']):
-        segments = get_continuous_segments(df['Seconds'], mse_values)
-        
-        for segment in segments:
-            segment_seconds, segment_mse = zip(*segment)
-            ax.scatter(segment_seconds, segment_mse, color=color, alpha=0.3, s=5, label=label if segment == segments[0] else "")
-            
-            if len(segment) > 1:
-                segment_df = pd.DataFrame({'Seconds': segment_seconds, 'MSE': segment_mse})
-                segment_df = segment_df.sort_values('Seconds')
-                mean = segment_df['MSE'].rolling(window=min(10, len(segment)), min_periods=1, center=True).mean()
-                std = segment_df['MSE'].rolling(window=min(10, len(segment)), min_periods=1, center=True).std()
-                
-                ax.plot(segment_df['Seconds'], mean, color=color, linewidth=0.5)
-                ax.fill_between(segment_df['Seconds'], mean - std, mean + std, color=color, alpha=0.1)
-
-        # Plot median baseline for each series
-        median = np.median(mse_values)
-        ax.axhline(y=median, color=color, linestyle=':', alpha=0.5, label=f'{label} Baseline Median')
-
-        # Plot threshold for each series
-        threshold = np.mean(mse_values) + anomaly_threshold * np.std(mse_values)
-        ax.axhline(y=threshold, color=color, linestyle='--', alpha=1, label=f'{label} Anomaly Threshold')
-
-        # Plot anomalies in red
-        anomalies = mse_values > threshold
-        ax.scatter(df['Seconds'][anomalies], mse_values[anomalies], color='red', s=20, zorder=5)
-
-    max_seconds = df['Seconds'].max()
-    num_ticks = 100
-    tick_locations = np.linspace(0, max_seconds, num_ticks)
-    tick_labels = [seconds_to_timecode(int(s)) for s in tick_locations]
-
-    ax.set_xticks(tick_locations)
-    ax.set_xticklabels(tick_labels, rotation=90, ha='center', fontsize=6)
-
-    ax.set_xlabel('Timecode')
-    ax.set_ylabel('Scaled Mean Squared Error')
-    ax.set_title(title)
-
-    ax.grid(True, linestyle='--', alpha=0.7)
-    ax.legend()
-    plt.tight_layout()
-    plt.close()
-    return fig
-
 
 def plot_mse_histogram(mse_values, title, anomaly_threshold, color='blue'):
     plt.figure(figsize=(16, 3), dpi=300)