import gradio as gr
import joblib
import numpy as np
import pandas as pd
import tensorflow as tf

# Assuming you have a function that creates the same model architecture
def create_model(input_shape):
    model = tf.keras.models.Sequential([
        tf.keras.layers.Flatten(input_shape=input_shape),
        tf.keras.layers.BatchNormalization(),
        tf.keras.layers.Dense(1000, activation='relu'),
        tf.keras.layers.BatchNormalization(),
        tf.keras.layers.Dropout(0.8),
        tf.keras.layers.Dense(1000, activation='relu'),
        tf.keras.layers.BatchNormalization(),
        tf.keras.layers.Dropout(0.8),
        tf.keras.layers.Dense(1, activation='sigmoid')
    ])
    model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=3e-6),
                  loss='binary_crossentropy',
                  metrics=['accuracy'])
    return model

# Load model weights
input_shape = [18]  # Adjust based on your feature count
model = create_model(input_shape)
model.load_weights('model_2.h5')

# Load the scaler
scaler = joblib.load('scaler.joblib')

features = [
    'PRNCPTX_HEPATECTOMY RESCJ TOTAL RIGHT LOBECTOMY', 'OPTIME', 'HYPERMED_Yes',
    'PRNCPTX_HEPATECTOMY RESCJ TRISEGMENTECTOMY', 'PRPLATE', 'PRINR',
    'HEP_APPROACH_Laparoscopic', 'PRALKPH', 'HEP_PRINGLE_Yes',
    'HEP_SEC_HISTOLOGIC_Colorectal metastasis', 'HEP_CON_PARTRES', 'SEX_male',
    'ASACLAS', 'HEP_SEC_TUMORSIZE', 'HEP_SEC_NUMTUMORS', 'PRSGOT', 'HEP_VIRAL_None',
    'HEP_NEOTHERAPY_140101_Preoperative systemic chemotherapy'
]

categorical_features = [
    'HYPERMED_Yes', 'HEP_APPROACH_Laparoscopic', 'HEP_PRINGLE_Yes',
    'SEX_male', 'HEP_VIRAL_None'
]

def predict_outcome(*args):
    inputs = list(args)
    # Convert 'Yes'/'No' inputs to 1/0 for the model
    for i, feature in enumerate(features):
        if feature in categorical_features:
            inputs[i] = 1 if inputs[i] == 'Yes' else 0
    input_data = np.array(inputs).reshape(1, -1)
    # Scale inputs
    inputs_scaled = scaler.transform(input_data)
    # Predict
    prediction = model.predict(inputs_scaled)
    outcome_probability = prediction.flatten()[0]
    return f'Probability of Post Hepatectomy Liver Failure: {outcome_probability:.2%}'

# Define Gradio inputs
inputs = []
for feature in features:
    if feature in categorical_features:
        inputs.append(gr.Radio(label=feature, choices=['Yes', 'No']))
    else:
        inputs.append(gr.Number(label=feature))

# Set up and launch the Gradio interface
iface = gr.Interface(fn=predict_outcome, inputs=inputs, outputs='text')
iface.launch()