'''import gradio as gr
import pickle
import pandas as pd

# Load the saved model
with open("model_AD.pkl", "rb") as f:
    model = pickle.load(f)

def predict_pcos(input_features):
    # Convert input features into a DataFrame (assuming 8 features here)
    input_data = pd.DataFrame([input_features], columns=["Age (yrs)", "BMI", "Weight (Kg)", "Cycle length(days)", "Follicle No. (L)", "Follicle No. (R)", "AMH(ng/mL)", "beta-HCG(mIU/mL)"])

    # Predict using the loaded model
    prediction = model.predict(input_data)

    return "PCOS Positive" if prediction[0] == 1 else "PCOS Negative"

# Define Gradio inputs and outputs
iface = gr.Interface(
    fn=predict_pcos,
    inputs=[
        gr.inputs.Number(label="Age (yrs)"),
        gr.inputs.Number(label="BMI"),
        gr.inputs.Number(label="Weight (Kg)"),
        gr.inputs.Number(label="Cycle length(days)"),
        gr.inputs.Number(label="Follicle No. (L)"),
        gr.inputs.Number(label="Follicle No. (R)"),
        gr.inputs.Number(label="AMH(ng/mL)"),
        gr.inputs.Number(label="beta-HCG(mIU/mL)")
    ],
    outputs="text",
    title="PCOS Detection",
    description="Predicts PCOS based on user-provided medical data."
)

# Launch the Gradio interface
iface.launch()

import gradio as gr
import pickle
import numpy as np

# Load the trained model
with open("model_AD.pkl", "rb") as f:
    model = pickle.load(f)

def predict_pcos(age, weight, height, bmi, pulse_rate, cycle_length):
    input_data = np.array([[age, weight, height, bmi, pulse_rate, cycle_length]])
    prediction = model.predict(input_data)
    return "Positive" if prediction[0] == 1 else "Negative"

# Define the Gradio interface
interface = gr.Interface(
    fn=predict_pcos,
    inputs=[
        gr.Number(label="Age (yrs)"),
        gr.Number(label="Weight (Kg)"),
        gr.Number(label="Height (Cm)"),
        gr.Number(label="BMI"),
        gr.Number(label="Pulse rate(bpm)"),
        gr.Number(label="Cycle length(days)")
    ],
    outputs=gr.Textbox(label="PCOS Prediction"),
    title="PCOS Detection Model",
    description="Predicts the likelihood of PCOS based on user input features."
)

# Launch the Gradio app
interface.launch()
'''
import gradio as gr
import pickle
import numpy as np

# Load the model
with open('model_AD.pkl', 'rb') as f:
    loaded_model = pickle.load(f)

# Define the prediction function
def predict_pcos(
    age, weight, height, bmi, blood_group, pulse_rate, rr, hb, cycle_ri,
    cycle_length, marriage_status, pregnant, no_of_abortions, fsh, lh, fsh_lh, 
    hip, waist, waist1, tsh, prl, vit_d3, prg, rbs, weight_gain, hair_growth, 
    skin_darkening, hair_loss, pimples, fast_food, reg_exercise, bp_systolic, 
    bp_diastolic, follicle_no_l, follicle_no_r, avg_f_size_l, avg_f_size_r, endometrium):
    
    # Prepare the input data as a single-row array
    input_data = np.array([[
        age, weight, height, bmi, blood_group, pulse_rate, rr, hb, cycle_ri,
        cycle_length, marriage_status, pregnant, no_of_abortions, fsh, lh, fsh_lh, 
        hip, waist, waist1, tsh, prl, vit_d3, prg, rbs, weight_gain, hair_growth, 
        skin_darkening, hair_loss, pimples, fast_food, reg_exercise, bp_systolic, 
        bp_diastolic, follicle_no_l, follicle_no_r, avg_f_size_l, avg_f_size_r, endometrium
    ]])

    # Get prediction
    prediction = loaded_model.predict(input_data)[0]
    return "PCOS Detected" if prediction == 1 else "No PCOS"

# Define the Gradio interface
inputs = [
    gr.Number(label="Age (yrs)"),
    gr.Number(label="Weight (Kg)"),
    gr.Number(label="Height (Cm)"),
    gr.Number(label="BMI"),
    gr.Number(label="Blood Group"),  # Convert categorical data appropriately if needed
    gr.Number(label="Pulse rate (bpm)"),
    gr.Number(label="RR (breaths/min)"),
    gr.Number(label="Hb (g/dl)"),
    gr.Number(label="Cycle (R/I)"),
    gr.Number(label="Cycle length (days)"),
    gr.Number(label="Marriage Status (Yrs)"),
    gr.Number(label="Pregnant (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="No. of abortions"),
    gr.Number(label="FSH (mIU/mL)"),
    gr.Number(label="LH (mIU/mL)"),
    gr.Number(label="FSH/LH"),
    gr.Number(label="Hip (inch)"),
    gr.Number(label="Waist (inch)"),
    gr.Number(label="Waist1 (inch)"),
    gr.Number(label="TSH (mIU/L)"),
    gr.Number(label="PRL (ng/mL)"),
    gr.Number(label="Vit D3 (ng/mL)"),
    gr.Number(label="PRG (ng/mL)"),
    gr.Number(label="RBS (mg/dl)"),
    gr.Number(label="Weight gain (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="Hair growth (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="Skin darkening (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="Hair loss (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="Pimples (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="Fast food (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="Regular Exercise (Y/N)"),  # 1 for Yes, 0 for No
    gr.Number(label="BP Systolic (mmHg)"),
    gr.Number(label="BP Diastolic (mmHg)"),
    gr.Number(label="Follicle No. (L)"),
    gr.Number(label="Follicle No. (R)"),
    gr.Number(label="Avg. F size (L) (mm)"),
    gr.Number(label="Avg. F size (R) (mm)"),
    gr.Number(label="Endometrium (mm)")
]

outputs = gr.Textbox(label="PCOS Prediction")
custom_css = """
    body {
        background-color: #eafaf8;
        color: #333333;
        font-family: Arial, sans-serif;
    }
    .gradio-container {
        background: #ffffff;
        border: 2px solid #d4efdf;
        border-radius: 15px;
        padding: 20px;
        box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
    }
    .input, .output {
        font-size: 16px;
        color: #2e4053;
    }
    .gr-button {
        background-color: #76d7c4;
        color: white;
        border: none;
        padding: 10px 20px;
        text-align: center;
        font-size: 14px;
        font-weight: bold;
        cursor: pointer;
        border-radius: 8px;
        transition: background-color 0.3s ease;
    }
    .gr-button:hover {
        background-color: #48c9b0;
    }
    .gr-input, .gr-textbox {
        border: 1px solid #a9dfbf;
        border-radius: 5px;
        padding: 8px;
        font-size: 14px;
    }
    .gr-title {
        font-size: 24px;
        font-weight: bold;
        color: #1abc9c;
        text-align: center;
        margin-bottom: 10px;
    }
    .gr-description {
        font-size: 16px;
        color: #5d6d7e;
        text-align: center;
        margin-bottom: 20px;
    }
"""

# Create and launch the app
app = gr.Interface(
    fn=predict_pcos, 
    inputs=inputs, 
    outputs=outputs, 
    title="PCOS Prediction Model",
    description="Enter the patient's information to predict PCOS.",
    css=custom_css
)

app.launch()