Update app.py

app.py

@@ -2,12 +2,13 @@ import pandas as pd
 import numpy as np
 from sklearn.ensemble import RandomForestClassifier
 import gradio as gr
+import zipfile
 
 def load_and_train_model():
-    # Load data
-    train_data = pd.read_csv('train.csv.zip')
+    with zipfile.ZipFile('train.csv.zip') as z:
+        with z.open('train.csv') as f:
+            train_data = pd.read_csv(f)
     
-    # Select important features
     important_features = ['Elevation', 'Horizontal_Distance_To_Roadways', 
                          'Horizontal_Distance_To_Fire_Points', 
                          'Horizontal_Distance_To_Hydrology',
@@ -16,25 +17,20 @@ def load_and_train_model():
     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 input array
+def predict(elevation, distance_to_roads, distance_to_fire, distance_to_water, vertical_distance):
     input_data = np.array([[
         elevation,
-        horizontal_distance_to_roadways,
-        horizontal_distance_to_fire_points,
-        horizontal_distance_to_hydrology,
-        vertical_distance_to_hydrology
+        distance_to_roads,
+        distance_to_fire,
+        distance_to_water,
+        vertical_distance
     ]])
     
-    # Make prediction
     prediction = model.predict(input_data)[0]
     
     forest_types = {
@@ -47,31 +43,69 @@ def predict(elevation, horizontal_distance_to_roadways, horizontal_distance_to_f
         7: "Krummholz"
     }
     
-    return forest_types[prediction]
+    confidence = max(model.predict_proba(input_data)[0]) * 100
+    
+    return f"{forest_types[prediction]} (Confidence: {confidence:.1f}%)"
 
 # Train model at startup
+print("Loading and training model...")
 model = load_and_train_model()
+print("Model training completed!")
 
-# Create Gradio interface
+# Create Gradio interface with improved inputs
 inputs = [
-    gr.Number(label="Elevation (meters)", minimum=1800, maximum=4000),
-    gr.Number(label="Distance to Roadways (meters)", minimum=0, maximum=8000),
-    gr.Number(label="Distance to Fire Points (meters)", minimum=0, maximum=8000),
-    gr.Number(label="Distance to Hydrology (meters)", minimum=0, maximum=1000),
-    gr.Number(label="Vertical Distance to Hydrology (meters)", minimum=-500, maximum=500)
+    gr.Slider(
+        minimum=1800, maximum=4000, step=10,
+        label="Elevation (meters above sea level)",
+        info="Height of the location above sea level",
+        value=2500
+    ),
+    gr.Slider(
+        minimum=0, maximum=8000, step=50,
+        label="Distance to Nearest Road (meters)",
+        info="How far is the nearest road?",
+        value=500
+    ),
+    gr.Slider(
+        minimum=0, maximum=8000, step=50,
+        label="Distance to Fire Points (meters)",
+        info="Distance to nearest fire ignition points",
+        value=1000
+    ),
+    gr.Slider(
+        minimum=0, maximum=1000, step=10,
+        label="Distance to Water (meters)",
+        info="Distance to nearest water source",
+        value=200
+    ),
+    gr.Slider(
+        minimum=-500, maximum=500, step=10,
+        label="Vertical Distance to Water (meters)",
+        info="Vertical distance to nearest water source (negative means below)",
+        value=0
+    )
 ]
 
-output = gr.Text(label="Predicted Forest Cover Type")
+output = gr.Text(
+    label="Predicted Forest Type",
+    info="Prediction with confidence level"
+)
 
 interface = gr.Interface(
     fn=predict,
     inputs=inputs,
     outputs=output,
-    title="Forest Cover Type Prediction",
-    description="Predict forest cover type using the most important environmental features.",
+    title="🌲 Forest Cover Type Predictor",
+    description="""
+    Predict the type of forest cover based on environmental features.
+    Just adjust the sliders to match your location's characteristics!
+    """,
     examples=[
-        [2596, 510, 6279, 258, 0]  # Sample values
-    ]
+        [2596, 510, 6279, 258, 0],
+        [2300, 300, 1500, 100, -50],
+        [3500, 1000, 2000, 500, 200]
+    ],
+    theme="soft"
 )
 
 if __name__ == "__main__":