Create app.py

app.py

@@ -0,0 +1,119 @@
+import gradio as gr
+import numpy as np
+from joblib import load
+from tensorflow.keras.models import load_model
+import tensorflow as tf
+import pickle
+
+# Load the LabelEncoder from Hugging Face Space
+with open('label_encoder.pkl', 'rb') as f:
+    label_encoder = pickle.load(f)
+
+# Assuming 'ct' is your ColumnTransformer (replace this with the actual loading code for your preprocessor)
+# If you have a preprocessor file (such as a pickle file), you can load it here, e.g.,
+# with open('column_transformer.pkl', 'rb') as f:
+#     ct = pickle.load(f)
+
+# UI Components for user input
+input_Gender = gr.Radio(["male", "female"], label="Gender")
+input_Race = gr.Dropdown(list(dict(df['Race (Reported)'].value_counts()).keys()), label="Race")
+input_Age = gr.Dropdown(list(dict(df['Age'].value_counts())), label='Age')
+input_Height = gr.Number(label='Height (cm)')
+input_Weight = gr.Number(label='Weight (kg)')
+input_Diabetes = gr.Radio([0.0, 1.0], label='Diabetes')
+input_Simvastatin = gr.Radio([0.0, 1.0], label='Simvastatin (Zocor)')
+input_Amiodarone = gr.Radio([0.0, 1.0], label='Amiodarone (Cordarone)')
+input_INR_reported = gr.Number(label='INR on Reported Therapeutic Dose of Warfarin')
+input_Cyp2C9_genotypes = gr.Dropdown(list(dict(df['Cyp2C9 genotypes'].value_counts())), label='Cyp2C9 genotypes')
+input_VKORC1_genotypes = gr.Radio(list(dict(df['VKORC1 genotype: -1639 G>A (3673); chr16:31015190; rs9923231; C/T'].value_counts())), label='VKORC1 genotypes')
+input_model = gr.Dropdown(['Decision Tree Regression', 'Support Vector Regression', 'Random Forest Regression', 'Deep Learning'], label='Model Selection')
+
+# Output textbox to display predicted dose
+output_warfarin_dosage = gr.Textbox(label='Therapeutic Dose of Warfarin')
+
+# Prediction function with renamed input variables
+def predict_dosage(gender, race, age, height, weight, diabetes, simvastatin, amiodarone, inr, cyp2c9, vkorc1, selected_model):
+    import numpy as np
+    from joblib import load
+    from tensorflow.keras.models import load_model
+    import tensorflow as tf
+
+    # Optional debug function to inspect data before prediction
+    def print_input_debug(transformed_input, final_array):
+        print("Transformed input shape:", transformed_input.shape)
+        print("Final input shape:", final_array.shape)
+        print("Input data type:", final_array.dtype)
+
+    try:
+        # Load the selected model
+        if selected_model == 'Deep Learning':
+            model = load_model('best_DeepLearning_model.h5')
+        elif selected_model == 'Support Vector Regression':
+            model = load('SVR_optimized.joblib')
+        elif selected_model == 'Random Forest Regression':
+            model = load('RandomForestRegressor_optimized.joblib')
+        else:
+            model = load("DecisionTreeRegressor_optimized.joblib")
+
+        # Handle unseen labels by attempting to map them to known labels
+        def safe_transform_label(encoder, label, default=None):
+            try:
+                return encoder.transform([label])[0]
+            except ValueError:
+                # If label is unseen, return default (e.g., most frequent label or a fallback value)
+                return default if default is not None else encoder.transform([encoder.classes_[0]])[0]
+
+        # Encode Age using LabelEncoder (catching unseen labels)
+        encoded_age = safe_transform_label(label_encoder, age, default=label_encoder.classes_[0])
+
+        # Ensure numerical inputs are valid floats
+        height = float(height) if height is not None else 0.0
+        weight = float(weight) if weight is not None else 0.0
+        inr = float(inr) if inr is not None else 0.0
+
+        # Assemble input for transformation
+        raw_inputs = [
+            str(gender),
+            str(race),
+            str(age),
+            height,
+            weight,
+            float(diabetes),
+            float(simvastatin),
+            float(amiodarone),
+            inr,
+            str(cyp2c9),
+            str(vkorc1)
+        ]
+
+        # Apply preprocessing pipeline (ct should be defined or loaded)
+        transformed_input = ct.transform([raw_inputs])
+        transformed_input[0][-7] = encoded_age  # Age is encoded, so replace it in the transformed input
+
+        # Convert to NumPy array for model input
+        input_array = np.array(transformed_input, dtype=np.float32)
+        print_input_debug(transformed_input, input_array)
+
+        # Predict using appropriate model type
+        if selected_model == 'Deep Learning':
+            tensor_input = tf.convert_to_tensor(input_array)
+            prediction = model.predict(tensor_input, verbose=0)
+            return float(prediction[0][0])
+        else:
+            prediction = model.predict(input_array)
+            return float(prediction[0])
+
+    except Exception as e:
+        print(f"Error in prediction: {str(e)}")
+        return f"Error in prediction: {str(e)}"
+
+# Launch Gradio app
+gr.Interface(
+    fn=predict_dosage,
+    inputs=[
+        input_Gender, input_Race, input_Age, input_Height, input_Weight,
+        input_Diabetes, input_Simvastatin, input_Amiodarone,
+        input_INR_reported, input_Cyp2C9_genotypes, input_VKORC1_genotypes, input_model
+    ],
+    outputs=[output_warfarin_dosage]
+).launch(debug=True)