Upload 3 files

app.py

@@ -0,0 +1,9 @@
+import gradio as gr
+
+iface = gr.Interface(
+    fn="inference.predict.predict",  # Assuming predict.py is in the 'inference' folder
+    inputs=["number", "number", "number", "number", "number", "number"],
+    outputs=["text"],
+)
+
+iface.launch(share=True)

inference/predict.py

@@ -8,35 +8,34 @@ def preprocess_input(input_data):
     input_data['rain'] = boxcox(input_data['rain'] + 1)[0]
     return input_data
 
-def load_model(model_path='lgbm_model.txt'):
+def load_model(model_path='inference/lgbm_model.txt'):
     # Load the trained LightGBM model
     model = lgb.Booster(model_file=model_path)
     return model
 
 def predict(input_data, model):
+    # Preprocess the input data
+    preprocessed_data = preprocess_input(pd.DataFrame([input_data]))
+
     # Make predictions using the loaded model
-    prediction = model.predict(input_data, num_iteration=model.best_iteration)
+    prediction = model.predict(preprocessed_data, num_iteration=model.best_iteration)
     predicted_class = prediction.argmax(axis=1)
-    return predicted_class
+
+    # Decode the predicted class (inverse transform)
+    label_encoder = LabelEncoder()
+    predicted_label = label_encoder.inverse_transform(predicted_class)[0]
+
+    return predicted_label
 
 if __name__ == "__main__":
     # Example usage
-    input_data_path = 'path_to_input_data.xlsx'  # Replace with the path to your input data file
-    input_data = pd.read_excel(input_data_path)
-
-    # Preprocess the input data
-    preprocessed_data = preprocess_input(input_data)
+    input_data = {'wind': 10, 'rain': 5, 'humidity': 60, 'cloud': 2, 'pressure': 1015, 'avg_temp': 25}
 
     # Load the trained model
     trained_model = load_model()
 
     # Make predictions
-    predictions = predict(preprocessed_data, trained_model)
-
-    # Decode the predictions (inverse transform)
-    label_encoder = LabelEncoder()
-    predicted_labels = label_encoder.inverse_transform(predictions)
+    prediction = predict(input_data, trained_model)
 
-    # Display the predictions
-    print("Predicted Labels:")
-    print(predicted_labels)
+    # Display the prediction
+    print("Predicted Label:", prediction)