Update app.py

app.py

@@ -245,6 +245,29 @@ def determine_optimal_anomalies(anomaly_scores, z_threshold=3):
     anomalies = anomaly_scores > threshold
     return anomalies, np.where(anomalies)[0]
 
+
+def timecode_to_seconds(timecode):
+    h, m, s = map(float, timecode.split(':'))
+    return h * 3600 + m * 60 + s
+
+
+def group_similar_timecodes(timecodes, scores, threshold_seconds=5):
+    grouped = []
+    current_group = []
+
+    for i, (timecode, score) in enumerate(zip(timecodes, scores)):
+        if not current_group or abs(
+                timecode_to_seconds(timecode) - timecode_to_seconds(current_group[0][0])) <= threshold_seconds:
+            current_group.append((timecode, score, i))
+        else:
+            grouped.append(current_group)
+            current_group = [(timecode, score, i)]
+
+    if current_group:
+        grouped.append(current_group)
+
+    return grouped
+
 class LSTMAutoencoder(nn.Module):
     def __init__(self, input_size, hidden_size=64, num_layers=2):
         super(LSTMAutoencoder, self).__init__()
@@ -349,7 +372,6 @@ def normalize_scores(scores):
         return np.full_like(scores, 100)
     return ((scores - min_score) / (max_score - min_score)) * 100
 
-
 def plot_anomaly_scores(df, anomaly_scores, top_indices, title, timecodes):
     plt.figure(figsize=(16, 8), dpi=500)
     fig, ax = plt.subplots(figsize=(16, 8))
@@ -371,10 +393,16 @@ def plot_anomaly_scores(df, anomaly_scores, top_indices, title, timecodes):
     top_indices = [idx for idx in top_indices if idx > 0]
     ax.scatter(df['Seconds'].iloc[top_indices], normalized_scores[top_indices], color='red', s=50, zorder=5)
 
-    # Add timecode annotations
-    for idx, timecode in zip(top_indices, timecodes):
+    # Group similar timecodes
+    grouped_timecodes = group_similar_timecodes([df['Timecode'].iloc[idx] for idx in top_indices],
+                                                normalized_scores[top_indices])
+
+    # Add timecode annotations for grouped timecodes
+    for group in grouped_timecodes:
+        max_score_idx = max(range(len(group)), key=lambda i: group[i][1])
+        timecode, score, idx = group[max_score_idx]
         ax.annotate(timecode,
-                    (df['Seconds'].iloc[idx], normalized_scores[idx]),
+                    (df['Seconds'].iloc[top_indices[idx]], score),
                     xytext=(5, 5), textcoords='offset points',
                     fontsize=6, color='red')
 
@@ -411,10 +439,16 @@ def plot_emotion(df, emotion, anomaly_scores, top_indices, color, timecodes):
     top_indices = [idx for idx in top_indices if idx > 0]
     ax.scatter(df['Seconds'].iloc[top_indices], anomaly_scores[top_indices], color='red', s=50, zorder=5)
 
-    # Add timecode annotations
-    for idx, timecode in zip(top_indices, timecodes):
+    # Group similar timecodes
+    grouped_timecodes = group_similar_timecodes([df['Timecode'].iloc[idx] for idx in top_indices],
+                                                anomaly_scores[top_indices])
+
+    # Add timecode annotations for grouped timecodes
+    for group in grouped_timecodes:
+        max_score_idx = max(range(len(group)), key=lambda i: group[i][1])
+        timecode, score, idx = group[max_score_idx]
         ax.annotate(timecode,
-                    (df['Seconds'].iloc[idx], anomaly_scores[idx]),
+                    (df['Seconds'].iloc[top_indices[idx]], score),
                     xytext=(5, 5), textcoords='offset points',
                     fontsize=6, color='red')
 
@@ -534,9 +568,9 @@ def process_video(video_path, num_components, desired_fps, batch_size, progress=
 
         progress(0.95, "Generating plots")
         try:
-            anomaly_plot_all = plot_anomaly_scores(df, anomaly_scores_all, top_indices_all, "All Features",
+            anomaly_plot_all = plot_anomaly_scores(df, anomaly_scores_all, top_indices_all, "Facial Features + Emotions",
                                                    df['Timecode'].iloc[top_indices_all].values)
-            anomaly_plot_comp = plot_anomaly_scores(df, anomaly_scores_comp, top_indices_comp, "Components Only",
+            anomaly_plot_comp = plot_anomaly_scores(df, anomaly_scores_comp, top_indices_comp, "Facial Features",
                                                     df['Timecode'].iloc[top_indices_comp].values)
             emotion_plots = [
                 plot_emotion(df, emotion,
@@ -596,7 +630,7 @@ iface = gr.Interface(
         gr.Plot(label="Happy Anomalies"),
         gr.Plot(label="Surprise Anomalies"),
         gr.Plot(label="Neutral Anomalies"),
-        gr.Gallery(label="Detected Persons", columns=[5], rows=[2], height="auto")
+        gr.Gallery(label="Random Samples of Detected Persons", columns=[5], rows=[2], height="auto")
     ],
     title="Facial Expressions Anomaly Detection",
     description="""