Update app.py

app.py

@@ -9,6 +9,30 @@ import cv2
 import constants as const
 from get_drive_model import ensure_model_download
 import atexit  # Import atexit module
+from simple_salesforce import Salesforce
+from datetime import datetime
+
+# Salesforce login
+sf = Salesforce(
+    username='karthikm@sathkrutha.com',
+    password='Navya@1223',
+    security_token='FDWBkm0pbrNFkv6bwznbW1SKn',
+    domain='login'  # use 'test' for sandbox, 'login' for production
+)
+
+# Salesforce object API name
+SALESFORCE_OBJECT = 'Anomaly_Result__c'
+
+def log_to_salesforce(video_path, prediction_text):
+    try:
+        result = sf.__getattr__(SALESFORCE_OBJECT).create({
+            'Video_Name__c': os.path.basename(video_path),
+            'Prediction_Result__c': prediction_text,
+            'Timestamp__c': datetime.utcnow().isoformat()
+        })
+        print("Salesforce Record Created:", result)
+    except Exception as e:
+        print("Salesforce Logging Failed:", e)
 
 # Define the path for the directory
 FRAMES_FOLDER = 'static/frames'
@@ -30,7 +54,6 @@ FRAMES_FOLDER = 'static/frames'
 def process_video(filepath):
     print(f"Processing video: {filepath}")
 
-    # Example: Read video frames and make predictions
     frames_for_prediction, frames_for_display = preprocess(filepath)
 
     print(f"Shape of frames for prediction: {frames_for_prediction.shape}")
@@ -38,7 +61,6 @@ def process_video(filepath):
 
     print(first_model.summary())
 
-    # Anomaly detection prediction
     anomaly_prediction = first_model.predict(frames_for_prediction)[0][0]
     print(f"Anomaly Prediction: {anomaly_prediction}")
 
@@ -52,6 +74,10 @@ def process_video(filepath):
         prediction_label = f'No Anomalous Activity with {anomaly_prediction * 100:.2f}% confidence.'
 
     frame_paths = save_frames_to_filesystem(frames_for_display)
+
+    # Log prediction to Salesforce
+    log_to_salesforce(filepath, prediction_label)
+
     return prediction_label, frame_paths
 
 def save_frames_to_filesystem(frames):
@@ -65,40 +91,37 @@ def save_frames_to_filesystem(frames):
     return frame_paths
 
 def cleanup_uploads_folder():
-    # Clean up the UPLOAD_FOLDER
     if os.path.exists(UPLOAD_FOLDER):
         for filename in os.listdir(UPLOAD_FOLDER):
             file_path = os.path.join(UPLOAD_FOLDER, filename)
             try:
                 if os.path.isfile(file_path) or os.path.islink(file_path):
-                    os.unlink(file_path)  # Remove file or symbolic link
+                    os.unlink(file_path)
                 elif os.path.isdir(file_path):
-                    shutil.rmtree(file_path)  # Remove directory and its contents
+                    shutil.rmtree(file_path)
             except Exception as e:
                 print(f'Failed to delete {file_path}. Reason: {e}')
 
-    # Clean up the FRAMES_FOLDER
     if os.path.exists(FRAMES_FOLDER):
         for filename in os.listdir(FRAMES_FOLDER):
             file_path = os.path.join(FRAMES_FOLDER, filename)
             try:
                 if os.path.isfile(file_path) or os.path.islink(file_path):
-                    os.unlink(file_path)  # Remove file or symbolic link
+                    os.unlink(file_path)
                 elif os.path.isdir(file_path):
-                    shutil.rmtree(file_path)  # Remove directory and its contents
+                    shutil.rmtree(file_path)
             except Exception as e:
                 print(f'Failed to delete {file_path}. Reason: {e}')
 
     print("Uploads and frames folders cleaned")
 
-
 # Register the cleanup function
 atexit.register(cleanup_uploads_folder)
 
 # Create Gradio Interface
 iface = gr.Interface(
     fn=process_video,
-    inputs=gr.File(type="filepath"),  # Add file upload for all detections
+    inputs=gr.File(type="filepath"),
     outputs=[
         gr.Textbox(label="Prediction", elem_id="prediction-box"),
         gr.Gallery(label="Video Frames", elem_id="frame-gallery", columns=5, rows=10)
@@ -147,11 +170,10 @@ iface = gr.Interface(
     """
 )
 
-# Additional interfaces for individual triggers (with file upload option)
-
+# Additional interfaces for individual triggers
 violent_iface = gr.Interface(
-    fn=process_video,  # Use the same process_video for Violent Detection
-    inputs=gr.File(type="filepath"),  # File upload for violent detection
+    fn=process_video,
+    inputs=gr.File(type="filepath"),
     outputs=[
         gr.Textbox(label="Prediction"),
         gr.Gallery(label="Video Frames", columns=5, rows=10)
@@ -160,8 +182,8 @@ violent_iface = gr.Interface(
 )
 
 explosion_iface = gr.Interface(
-    fn=process_video,  # Use the same process_video for Explosion Detection
-    inputs=gr.File(type="filepath"),  # File upload for explosion detection
+    fn=process_video,
+    inputs=gr.File(type="filepath"),
     outputs=[
         gr.Textbox(label="Prediction"),
         gr.Gallery(label="Video Frames", columns=5, rows=10)
@@ -170,8 +192,8 @@ explosion_iface = gr.Interface(
 )
 
 normal_iface = gr.Interface(
-    fn=process_video,  # Use the same process_video for Normal Detection
-    inputs=gr.File(type="filepath"),  # File upload for normal detection
+    fn=process_video,
+    inputs=gr.File(type="filepath"),
     outputs=[
         gr.Textbox(label="Prediction"),
         gr.Gallery(label="Video Frames", columns=5, rows=10)
@@ -181,9 +203,10 @@ normal_iface = gr.Interface(
 
 # Combine all interfaces into a single application
 combined_iface = gr.TabbedInterface([iface, violent_iface, explosion_iface, normal_iface],
-                                    ["Upload Video", "Violent Detection", "Explosion Detection", "suspicious activities"])
+                                    ["Upload Video", "Violent Detection", "Explosion Detection", "Suspicious Activities"])
 
 if __name__ == "__main__":
     combined_iface.launch()
 
 
+