app.py

#!/usr/bin/env python
# coding: utf-8

# In[1]:


import warnings
warnings.simplefilter("ignore")
import pandas as pd
import numpy as np
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.model_selection import train_test_split
import xgboost as xgb
from sklearn.preprocessing import LabelEncoder
import joblib
import gradio as gr
import joblib

# Define the Gradio input and output interfaces
inputs = [
    gr.inputs.Dropdown(choices=["0", "1"], label="Gender"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you smoke?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have Yellow Fingers?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have Anxiety?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you get influenced by Peer Pressure?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have any Chronic Disease?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have Fatigue?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have an Allergy?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you experience Wheezing?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you drink alcohol?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Are you Coughing?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have Shortness of Breath?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have Swallowing Difficulty?"),
    gr.inputs.Dropdown(choices=["0", "1"], label="Do you have Chest Pain?"),
    gr.inputs.Number(label='What is your Age')
]

output = gr.outputs.Label(num_top_classes=2)

# Define the predict function
def predict(gender, smoking, yellow_fingers, anxiety, peer_pressure,
            chronic_disease, fatigue, allergy, wheezing, alcohol_consuming,
            coughing, shortness_of_breath, swallowing_difficulty, chest_pain,
            age):
    # Create a dataframe with the input values
    input_dict = {'GENDER': gender, 'SMOKING': smoking, 'YELLOW_FINGERS': yellow_fingers,
                  'ANXIETY': anxiety, 'PEER_PRESSURE': peer_pressure,
                  'CHRONIC DISEASE': chronic_disease, 'FATIGUE ': fatigue,
                  'ALLERGY ': allergy, 'WHEEZING': wheezing,
                  'ALCOHOL CONSUMING': alcohol_consuming, 'COUGHING': coughing,
                  'SHORTNESS OF BREATH': shortness_of_breath,
                  'SWALLOWING DIFFICULTY': swallowing_difficulty,
                  'CHEST PAIN': chest_pain, 'AGE': age}
    input_df = pd.DataFrame.from_dict([input_dict]).astype("int")
    
    dtest = xgb.DMatrix(input_df)
    
    
    #make predictions
    #load model
    model = joblib.load("model.pkl")
    prediction = model.predict(dtest)
    
    # Return prediction
    return "You exhibit symptomps of Lung cancer,you might want to see the Doctor for proper diagnosis ❤." if prediction >0.99 else "You don't seem to have Lung Cancer, Enjoy and take good care of yourself❤"

# Create and launch the interface
interface = gr.Interface(fn=predict, inputs=inputs, outputs=output, 
                     title='Lung Cancer Prediction', description='Predicting lung cancer using XGBoost Classifier.\nPlease Note:\nFemale = 0, Male= 1\nNo = 0, Yes = 1',
                        theme = 'darkhuggingface')
interface.launch()