Update app.py

app.py

@@ -349,7 +349,7 @@ def normalize_scores(scores):
     return ((scores - min_score) / (max_score - min_score)) * 100
 
 
-def plot_anomaly_scores(df, anomaly_scores, top_indices, title):
+def plot_anomaly_scores(df, anomaly_scores, top_indices, title, timecodes):
     plt.figure(figsize=(16, 8), dpi=400)
     fig, ax = plt.subplots(figsize=(16, 8))
 
@@ -363,12 +363,19 @@ def plot_anomaly_scores(df, anomaly_scores, top_indices, title):
     seconds = df['Seconds'].values[1:]
     scores = normalized_scores[1:]
 
-    # Create bar plot
-    ax.bar(seconds, scores, width=1, color='blue', alpha=0.7)
+    # Create scatter plot
+    ax.scatter(seconds, scores, color='blue', alpha=0.7, s=10)
 
     # Highlight top anomalies (excluding the first data point)
     top_indices = [idx for idx in top_indices if idx > 0]
-    ax.bar(df['Seconds'].iloc[top_indices], normalized_scores[top_indices], width=1, color='red', alpha=0.7)
+    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):
+        ax.annotate(timecode,
+                    (df['Seconds'].iloc[idx], normalized_scores[idx]),
+                    xytext=(5, 5), textcoords='offset points',
+                    fontsize=6, color='red')
 
     max_seconds = df['Seconds'].max()
     ax.set_xlim(0, max_seconds)
@@ -385,8 +392,7 @@ def plot_anomaly_scores(df, anomaly_scores, top_indices, title):
     plt.tight_layout()
     return fig
 
-
-def plot_emotion(df, emotion, anomaly_scores, top_indices, num_anomalies, color):
+def plot_emotion(df, emotion, anomaly_scores, top_indices, num_anomalies, color, timecodes):
     plt.figure(figsize=(16, 8), dpi=400)
     fig, ax = plt.subplots(figsize=(16, 8))
 
@@ -397,12 +403,19 @@ def plot_emotion(df, emotion, anomaly_scores, top_indices, num_anomalies, color)
     seconds = df['Seconds'].values[1:]
     scores = anomaly_scores[1:]
 
-    # Create bar plot
-    ax.bar(seconds, scores, width=1, color=color, alpha=0.7)
+    # Create scatter plot
+    ax.scatter(seconds, scores, color=color, alpha=0.7, s=10)
 
     # Highlight top anomalies (excluding the first data point)
     top_indices = [idx for idx in top_indices if idx > 0]
-    ax.bar(df['Seconds'].iloc[top_indices], anomaly_scores[top_indices], width=1, color='red', alpha=0.7)
+    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):
+        ax.annotate(timecode,
+                    (df['Seconds'].iloc[idx], anomaly_scores[idx]),
+                    xytext=(5, 5), textcoords='offset points',
+                    fontsize=6, color='red')
 
     max_seconds = df['Seconds'].max()
     ax.set_xlim(0, max_seconds)
@@ -419,7 +432,6 @@ def plot_emotion(df, emotion, anomaly_scores, top_indices, num_anomalies, color)
     plt.tight_layout()
     return fig
 
-
 def get_random_face_samples(organized_faces_folder, output_folder):
     face_samples = []
     for cluster_folder in os.listdir(organized_faces_folder):
@@ -432,7 +444,7 @@ def get_random_face_samples(organized_faces_folder, output_folder):
                 output_path = os.path.join(output_folder, f"face_sample_{cluster_folder}.jpg")
                 face_img = cv2.imread(face_path)
                 if face_img is not None:
-                    small_face = cv2.resize(face_img, (160, 160))
+                    small_face = cv2.resize(face_img, (224, 224))
                     cv2.imwrite(output_path, small_face)
                     face_samples.append(output_path)
     return face_samples
@@ -514,11 +526,17 @@ def process_video(video_path, num_anomalies, num_components, desired_fps, batch_
 
         progress(0.95, "Generating plots")
         try:
-            anomaly_plot_all = plot_anomaly_scores(df, anomaly_scores_all, top_indices_all, "All Features")
-            anomaly_plot_comp = plot_anomaly_scores(df, anomaly_scores_comp, top_indices_comp, "Components Only")
+            anomaly_plot_all = plot_anomaly_scores(df, anomaly_scores_all, top_indices_all, "All Features",
+                                                   df['Timecode'].iloc[top_indices_all].values)
+            anomaly_plot_comp = plot_anomaly_scores(df, anomaly_scores_comp, top_indices_comp, "Components Only",
+                                                    df['Timecode'].iloc[top_indices_comp].values)
             emotion_plots = [
-                plot_emotion(df, emotion, emotion_anomalies[emotion]['scores'], emotion_anomalies[emotion]['indices'],
-                             num_anomalies, color)
+                plot_emotion(df, emotion,
+                             emotion_anomalies[emotion]['scores'],
+                             emotion_anomalies[emotion]['indices'],
+                             num_anomalies,
+                             color,
+                             df['Timecode'].iloc[emotion_anomalies[emotion]['indices']].values)
                 for emotion, color in zip(['fear', 'sad', 'angry', 'happy', 'surprise', 'neutral'],
                                           ['purple', 'green', 'orange', 'darkblue', 'gold', 'grey'])
             ]
@@ -530,11 +548,11 @@ def process_video(video_path, num_anomalies, num_components, desired_fps, batch_
         results += f"Breakdown of persons/clusters:\n"
         for cluster_id in range(num_clusters):
             results += f"Person/Cluster {cluster_id + 1}: {len([c for c in clusters if c == cluster_id])} frames\n"
-        results += f"\nTop {num_anomalies} anomalies (All Features):\n"
+        results += f"\nTop {num_anomalies} anomalies (Facial Features + Emotions):\n"
         results += "\n".join([f"{score:.2f} at {timecode}" for score, timecode in
                               zip(anomaly_scores_all[top_indices_all[1:]],
                                   df['Timecode'].iloc[top_indices_all[1:]].values)])
-        results += f"\n\nTop {num_anomalies} anomalies (Components Only):\n"
+        results += f"\n\nTop {num_anomalies} anomalies (Facial Features):\n"
         results += "\n".join([f"{score:.2f} at {timecode}" for score, timecode in
                               zip(anomaly_scores_comp[top_indices_comp[1:]],
                                   df['Timecode'].iloc[top_indices_comp[1:]].values)])