Update app.py

app.py

@@ -1,27 +1,38 @@
 import pandas as pd
-import joblib
+import numpy as np
+from sklearn.ensemble import RandomForestClassifier
 import gradio as gr
 
-# Load the model
-model = joblib.load('forest_model.joblib')
+def load_and_train_model():
+    # Load data
+    train_data = pd.read_csv('train.csv')
+    
+    # Select important features
+    important_features = ['Elevation', 'Horizontal_Distance_To_Roadways', 
+                         'Horizontal_Distance_To_Fire_Points', 
+                         'Horizontal_Distance_To_Hydrology',
+                         'Vertical_Distance_To_Hydrology']
+    
+    X = train_data[important_features]
+    y = train_data['Cover_Type']
+    
+    # Train model
+    model = RandomForestClassifier(n_estimators=100, random_state=42)
+    model.fit(X, y)
+    
+    return model
 
 def predict(elevation, horizontal_distance_to_roadways, horizontal_distance_to_fire_points, 
             horizontal_distance_to_hydrology, vertical_distance_to_hydrology):
     
-    # Create a DataFrame with all features (initialized to 0)
-    input_data = pd.DataFrame(0, index=[0], columns=model.feature_names_in_)
-    
-    # Set the values for our important features
-    feature_values = {
-        'Elevation': elevation,
-        'Horizontal_Distance_To_Roadways': horizontal_distance_to_roadways,
-        'Horizontal_Distance_To_Fire_Points': horizontal_distance_to_fire_points,
-        'Horizontal_Distance_To_Hydrology': horizontal_distance_to_hydrology,
-        'Vertical_Distance_To_Hydrology': vertical_distance_to_hydrology
-    }
-    
-    for feature, value in feature_values.items():
-        input_data[feature] = value
+    # Create input array
+    input_data = np.array([[
+        elevation,
+        horizontal_distance_to_roadways,
+        horizontal_distance_to_fire_points,
+        horizontal_distance_to_hydrology,
+        vertical_distance_to_hydrology
+    ]])
     
     # Make prediction
     prediction = model.predict(input_data)[0]
@@ -38,6 +49,9 @@ def predict(elevation, horizontal_distance_to_roadways, horizontal_distance_to_f
     
     return forest_types[prediction]
 
+# Train model at startup
+model = load_and_train_model()
+
 # Create Gradio interface
 inputs = [
     gr.Number(label="Elevation (meters)", minimum=1800, maximum=4000),
@@ -56,7 +70,7 @@ interface = gr.Interface(
     title="Forest Cover Type Prediction",
     description="Predict forest cover type using the most important environmental features.",
     examples=[
-        [2596, 510, 6279, 258, 0]  # Sample values for the top 5 features
+        [2596, 510, 6279, 258, 0]  # Sample values
     ]
 )