Update app.py

app.py

@@ -14,31 +14,39 @@ for i in range(3):
     model.load_model(f'./model_{i}.cbm')
     modelos_cargados.append(model)
 
-# Function to process the soil image
-def process_soil_image(image):
-    # Here you would implement the logic to process the image
-    # For example, converting the image to a format suitable for your model
-    # Assuming it results in properties similar to your earlier functions
+# Define your array columns as before
+array_cols = ['array_area', *[f'mean_{i}' for i in range(1, 151)],
+              *[f'std_{i}' for i in range(1, 151)],
+              *[f'med_{i}' for i in range(1, 151)],
+              *[f'q1_{i}' for i in range(1, 151)],
+              *[f'q3_{i}' for i in range(1, 151)],
+              *[f'max_{i}' for i in range(1, 151)],
+              *[f'range_{i}' for i in range(1, 151)],
+              *[f'D1_{i}' for i in range(1, 151)],
+              *[f'D10_{i}' for i in range(1, 151)],
+              *[f'IQR_{i}' for i in range(1, 151)]]
 
-    # This is a placeholder for the actual image processing logic
-    # Replace with actual image processing steps and prediction logic
-    arr = np.array(image)
-    # Dummy properties extraction
-    properties = np.random.rand(150)  # Simulated properties for example
+def process_soil_image(image):
+    # Dummy properties extraction (simulate the real extraction)
+    arr = np.array(image)  # Convert the image to a numpy array
+    if arr.ndim != 3:
+        raise ValueError("Expected a 3-dimensional array (height, width, channels).")
+    
+    # Simulated property extraction (ensure you have 150 properties)
+    properties = np.random.rand(150)  # Simulated for demonstration
     return properties
 
-def get_array_properties(arr):
-    # Implement the same properties calculation as before
-    area_arr = arr.size
-    mean_arr = arr.mean()
-    std_arr = arr.std()
-    return np.array([area_arr, mean_arr, std_arr])
-
 def predecir_desde_imagen(image, modelos, array_cols):
     # Process the soil image to extract properties
     properties = process_soil_image(image)
+    print(f"Extracted properties shape: {properties.shape}")  # Debug statement
     datos_df = pd.DataFrame([properties], columns=array_cols)
+    print(f"DataFrame shape: {datos_df.shape}")  # Debug statement
     
+    # Make sure properties have the same length as array_cols
+    if datos_df.shape[1] != len(array_cols):
+        raise ValueError(f"Expected {len(array_cols)} columns, but got {datos_df.shape[1]}.")
+
     # Apply PCA and predict as before
     pca_datos = get_pca_dataset(datos_df)
 
@@ -52,7 +60,6 @@ def predecir_desde_imagen(image, modelos, array_cols):
 
 def predecir_desde_imagen_interface(image):
     # Ensure the image is in the expected format
-    image = Image.fromarray(image)  # Convert to PIL Image if necessary
     predicciones = predecir_desde_imagen(image, modelos_cargados, array_cols)
     
     return {
@@ -62,18 +69,6 @@ def predecir_desde_imagen_interface(image):
         'pH': float(predicciones[3])
     }
 
-# Define your array columns as before
-array_cols = ['array_area', *[f'mean_{i}' for i in range(1, 151)],
-              *[f'std_{i}' for i in range(1, 151)],
-              *[f'med_{i}' for i in range(1, 151)],
-              *[f'q1_{i}' for i in range(1, 151)],
-              *[f'q3_{i}' for i in range(1, 151)],
-              *[f'max_{i}' for i in range(1, 151)],
-              *[f'range_{i}' for i in range(1, 151)],
-              *[f'D1_{i}' for i in range(1, 151)],
-              *[f'D10_{i}' for i in range(1, 151)],
-              *[f'IQR_{i}' for i in range(1, 151)]]
-
 demo = gr.Interface(
     fn=predecir_desde_imagen_interface,
     inputs=gr.Image(label="Upload Soil Image"),