import pandas as pd
from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder,StandardScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.keras import Input
from sklearn.metrics import classification_report
from tensorflow.keras.callbacks import EarlyStopping
import keras_tuner as kt
df = pd.read_csv('Disease_symptom_and_patient_profile_dataset.csv',dtype={'Outcome Variable':str})
df['Outcome Variable'] = df['Outcome Variable'].map({'Positive':1,'Negative':0})
num_features = df.select_dtypes(include=['int64']).columns.drop('Outcome Variable').to_list()
cat_features = df.select_dtypes(include=['object']).columns.to_list()
preprocess = ColumnTransformer(transformers=[
    ('num',StandardScaler(),num_features),
    ('cat',OneHotEncoder(handle_unknown='ignore',drop='first'),cat_features)
])
from sklearn.model_selection import train_test_split
x= df.drop(columns=['Outcome Variable'])
y= df['Outcome Variable']
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state= 42)
x_train_scaled = preprocess.fit_transform(x_train)
x_test_scaled = preprocess.transform(x_test)
def build_model(hp):
    model = Sequential([
    Input(shape=(x_test_scaled.shape[1],)),
    Dense(units=hp.Int('u1',32,256,step=32),activation='relu'),
    Dense(units=hp.Int('u2',16,128,step=16),activation='relu'),
    Dense(units=hp.Int('u3',8,64,step=8),activation='relu'),
    Dense(1,activation='sigmoid')])
    model.compile(optimizer='adam',loss='binary_crossentropy',metrics=['accuracy'])
    return model
tuner = kt.RandomSearch(build_model,objective='val_loss',max_trials=20)
early_stop = EarlyStopping(monitor='val_loss',patience=20,restore_best_weights=True)
tuner.search(x_train_scaled,y_train,epochs=400,batch_size=32,callbacks=[early_stop],validation_split=0.4,verbose=1)
best_model = tuner.get_best_models(1)[0]
y_pred = (best_model.predict(x_test_scaled).flatten()>=0.5).astype(int)
for pre,ac in zip(y_pred[:5],y_test[:5]):
    print(f'Predict: {pre} - Actual: {ac}')
print(f'Report: {classification_report(y_test,y_pred)}')
def pre_desease(Disease,Fever,Cough,Fatigue,Breathing,Age,Gender,Blood,Cholesterol):
    cols = x.columns
    vals = [Disease,Fever,Cough,Fatigue,Breathing,Age,Gender,Blood,Cholesterol]
    user = pd.DataFrame([dict(zip(cols,vals))])
    prediction = best_model.predict(preprocess.transform(user)).item()
    decision = 'POSITIVE' if prediction >=0.5 else 'NEGATIVE'
    return f'Result: {decision}'
import gradio as gr

inputs = [
    gr.Text(label='Disease'),
    gr.Radio(choices=['Yes', 'No'],label='Fever'),
    gr.Radio(choices=['Yes', 'No'],label='Cough'),
    gr.Radio(choices=['Yes', 'No'],label='Fatigue'),
    gr.Radio(choices=['Yes', 'No'],label='Difficulty Breathing'),
    gr.Number(label='Age'),
    gr.Radio(choices=['Female', 'Male'],label='Gender'),
    gr.Radio(choices=['Low', 'Normal', 'High'],label='Blood Pressure'),
    gr.Radio(choices=['Normal', 'Low', 'High'],label='Cholesterol Level'),
]
demo = gr.Interface(fn=pre_desease,inputs=inputs,outputs='text',title='Predict Desease')
demo.launch()