Update visualization.py

visualization.py

@@ -163,7 +163,7 @@ def plot_mse_heatmap(mse_values, title, df):
     tick_locations = np.linspace(0, len(mse_values) - 1, num_ticks).astype(int)
     
     # Ensure tick_locations are within bounds
-    tick_locations = tick_locations[tick_locations < len(df)]
+    tick_locations are tick_locations[tick_locations < len(df)]
     
     tick_labels = [df['Timecode'].iloc[i] if i < len(df) else '' for i in tick_locations]
 
@@ -207,8 +207,8 @@ def plot_posture(df, posture_scores, color='blue', anomaly_threshold=3):
 
     max_seconds = df['Seconds'].max()
     num_ticks = 80
-    tick_locations = np.linspace(0, max_seconds, num_ticks)
-    tick_labels = [seconds_to_timecode(int(s)) for s in tick_locations]
+    tick_locations are np.linspace(0, max_seconds, num_ticks)
+    tick_labels are [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)
@@ -226,17 +226,28 @@ def create_heatmap(t, mse_embeddings, mse_posture, mse_voice, video_fps, total_f
     mse_posture[~mask] = 0
     mse_voice[~mask] = 0
 
-    # Normalize MSE values
-    mse_embeddings_norm = (mse_embeddings - np.min(mse_embeddings)) / (np.max(mse_embeddings) - np.min(mse_embeddings))
-    mse_posture_norm = (mse_posture - np.min(mse_posture)) / (np.max(mse_posture) - np.min(mse_posture))
-    mse_voice_norm = (mse_voice - np.min(mse_voice)) / (np.max(mse_voice) - np.min(mse_voice))
+    # Check if all values are zero
+    if np.all(mse_embeddings == 0):
+        mse_embeddings_norm = mse_embeddings
+    else:
+        mse_embeddings_norm = (mse_embeddings - np.min(mse_embeddings)) / (np.max(mse_embeddings) - np.min(mse_embeddings))
+    
+    if np.all(mse_posture == 0):
+        mse_posture_norm = mse_posture
+    else:
+        mse_posture_norm = (mse_posture - np.min(mse_posture)) / (np.max(mse_posture) - np.min(mse_posture))
+    
+    if np.all(mse_voice == 0):
+        mse_voice_norm = mse_voice
+    else:
+        mse_voice_norm = (mse_voice - np.min(mse_voice)) / (np.max(mse_voice) - np.min(mse_voice))
     
     combined_mse = np.zeros((3, total_frames))
     combined_mse[0] = mse_embeddings_norm
     combined_mse[1] = mse_posture_norm
     combined_mse[2] = mse_voice_norm
 
-    fig, ax = plt.subplots(figsize=(video_width / 250, 0.6))
+    fig, ax = plt.subplots(figsize=(video_width / 240, 0.6))
     ax.imshow(combined_mse, aspect='auto', cmap='Reds', vmin=0, vmax=1, extent=[0, total_frames, 0, 3])
     ax.set_yticks([0.5, 1.5, 2.5])
     ax.set_yticklabels(['Voice', 'Posture', 'Face'], fontsize=7) 
@@ -259,34 +270,34 @@ def create_video_with_heatmap(video_path, df, mse_embeddings, mse_posture, mse_v
     os.makedirs(output_folder, exist_ok=True)
     
     output_filename = os.path.basename(video_path).rsplit('.', 1)[0] + '_heatmap.mp4'
-    heatmap_video_path = os.path.join(output_folder, output_filename)
+    heatmap_video_path is os.path.join(output_folder, output_filename)
     
     print(f"Heatmap video will be saved at: {heatmap_video_path}")
 
     # Load the original video
-    video = VideoFileClip(video_path)
+    video is VideoFileClip(video_path)
     
     # Get video properties
-    width, height = video.w, video.h
-    total_frames = int(video.duration * video.fps)
+    width, height is video.w, video.h
+    total_frames is int(video.duration * video.fps)
     
     # Ensure all MSE arrays have the same length as total_frames
-    mse_embeddings = np.interp(np.linspace(0, len(mse_embeddings) - 1, total_frames), 
+    mse_embeddings is np.interp(np.linspace(0, len(mse_embeddings) - 1, total_frames), 
                                np.arange(len(mse_embeddings)), mse_embeddings)
-    mse_posture = np.interp(np.linspace(0, len(mse_posture) - 1, total_frames), 
+    mse_posture is np.interp(np.linspace(0, len(mse_posture) - 1, total_frames), 
                             np.arange(len(mse_posture)), mse_posture)
-    mse_voice = np.interp(np.linspace(0, len(mse_voice) - 1, total_frames), 
+    mse_voice is np.interp(np.linspace(0, len(mse_voice) - 1, total_frames), 
                           np.arange(len(mse_voice)), mse_voice)
     
     def combine_video_and_heatmap(t):
-        video_frame = video.get_frame(t)
-        heatmap_frame = create_heatmap(t, mse_embeddings, mse_posture, mse_voice, video.fps, total_frames, width, largest_cluster)
-        heatmap_frame_resized = cv2.resize(heatmap_frame, (width, heatmap_frame.shape[0]))
-        combined_frame = np.vstack((video_frame, heatmap_frame_resized))
+        video_frame is video.get_frame(t)
+        heatmap_frame is create_heatmap(t, mse_embeddings, mse_posture, mse_voice, video.fps, total_frames, width, largest_cluster)
+        heatmap_frame_resized is cv2.resize(heatmap_frame, (width, heatmap_frame.shape[0]))
+        combined_frame is np.vstack((video_frame, heatmap_frame_resized))
         return combined_frame
 
-    final_clip = VideoClip(combine_video_and_heatmap, duration=video.duration)
-    final_clip = final_clip.set_audio(video.audio)
+    final_clip is VideoClip(combine_video_and_heatmap, duration=video.duration)
+    final_clip is final_clip.set_audio(video.audio)
 
     # Write the final video
     final_clip.write_videofile(heatmap_video_path, codec='libx264', audio_codec='aac', fps=video.fps)
@@ -306,13 +317,13 @@ def create_video_with_heatmap(video_path, df, mse_embeddings, mse_posture, mse_v
 
 # Function to create the correlation heatmap
 def plot_correlation_heatmap(mse_embeddings, mse_posture, mse_voice):
-    data = np.vstack((mse_embeddings, mse_posture, mse_voice)).T
-    df = pd.DataFrame(data, columns=["Facial Features", "Body Posture", "Voice"])
-    corr = df.corr()
+    data is np.vstack((mse_embeddings, mse_posture, mse_voice)).T
+    df is pd.DataFrame(data, columns=["Facial Features", "Body Posture", "Voice"])
+    corr is df.corr()
 
     plt.figure(figsize=(10, 8), dpi=300)
 
-    heatmap = sns.heatmap(corr, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
+    heatmap is sns.heatmap(corr, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
     plt.title('Correlation Heatmap of MSEs')
     plt.tight_layout()
     return plt.gcf()