Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 import numpy as np
 import pandas as pd
 from catboost import CatBoostRegressor
+from sklearn.decomposition import PCA
 
 # Load CatBoost models
 modelos_cargados = []
@@ -25,17 +26,27 @@ array_cols = ['array_area', *[f'mean_{i}' for i in range(1, 151)],
 # Total expected columns
 expected_columns_count = len(array_cols)  # This should be 1501
 
+# Initialize PCA
+pca = PCA(n_components=10)  # Adjust n_components as needed
+
+def get_pca_dataset(datos_df):
+    """Fit PCA on the given DataFrame and return transformed data."""
+    pca.fit(datos_df)  # Fit PCA on the training data (do this once on your training dataset)
+    transformed_data = pca.transform(datos_df)  # Transform the new data
+    return transformed_data
+
 def process_soil_image(image):
-    # Dummy properties extraction (simulate the real extraction)
+    """Extract properties from the uploaded soil image."""
     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
-    properties = np.random.rand(1500)  # Simulated for demonstration, should match expected_columns_count - 1
+    # Simulated property extraction (replace with actual logic)
+    properties = np.random.rand(1500)  # Simulated for demonstration
     return properties
 
 def predecir_desde_imagen(image, modelos, array_cols):
+    """Predict soil properties from the uploaded image."""
     # Process the soil image to extract properties
     properties = process_soil_image(image)
     print(f"Extracted properties shape: {properties.shape}")  # Debug statement
@@ -60,6 +71,7 @@ def predecir_desde_imagen(image, modelos, array_cols):
     return mediana_predicciones
 
 def predecir_desde_imagen_interface(image):
+    """Gradio interface function to handle the prediction request."""
     # Ensure the image is in the expected format
     predicciones = predecir_desde_imagen(image, modelos_cargados, array_cols)
     
@@ -70,10 +82,12 @@ def predecir_desde_imagen_interface(image):
         'pH': float(predicciones[3])
     }
 
+# Create Gradio interface
 demo = gr.Interface(
     fn=predecir_desde_imagen_interface,
     inputs=gr.Image(label="Upload Soil Image"),
     outputs=gr.JSON(label="Predictions")
 )
 
+# Launch the Gradio application
 demo.launch()  # No share=True since it's not supported in Hugging Face Spaces