import numpy as np
import pandas as pd 
dataset=pd.read_csv("hcvdat0.csv")
dataset.head()

#Drop the unnecessary column
dataset = dataset.drop(columns=(['Unnamed: 0']))
#Identify Null Values
dataset.isnull().sum()
#Handling Null Values
from sklearn.impute import SimpleImputer

imputer1 = SimpleImputer(missing_values=np.nan,strategy="median")
imputer1.fit(dataset.iloc[:,[3,4,5,9,12]])
dataset.iloc[:,[3,4,5,9,12]]=imputer1.transform(dataset.iloc[:,[3,4,5,9,12]])
dataset.isnull().sum()
#Convert Categorical Data to Numerical Data
from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
dataset["Sex"]=le.fit_transform(dataset["Sex"]) #1 = m(male); 0 = f(female)

dataset['Category'] = dataset['Category'].map({'0=Blood Donor': 0,'0s=suspect Blood Donor': 0,'1=Hepatitis': 1,'2=Fibrosis': 2,'3=Cirrhosis': 3}) #0 = Healthy; 1 = Hepatitis; 2 = Fibrosis; 3 = Cirrhosis

# select features ALB, ALP, AST, BIL, CHE, CHOL and GGT as X into the model
# Select category as target features y
dataset_feature = ['ALB','ALP','ALT','AST','BIL','CHE','CHOL','GGT']

X = dataset.loc[:,dataset_feature]
y = dataset.Category
#split the data into train and test with portion 70,30
from sklearn.model_selection import train_test_split
X_train,X_test, y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=10)

from sklearn.naive_bayes import GaussianNB
NB = GaussianNB()
#fit model
NB=NB.fit(X_train, y_train)
NB_pred = NB.predict(X_test)

def HCV(ALB,ALP,ALT,AST,BIL,CHE,CHOL,GGT):
  x = np.array([ALB,ALP,ALT,AST,BIL,CHE,CHOL,GGT])
  prediction = NB.predict(x.reshape(1,-1))
  if prediction == 0:
    result ="Healthy"
  elif prediction ==1:
    result="Hepatitis"
  elif prediction ==2:
    result="Fibrosis"
  elif prediction ==3:
    result="Cirrhosis"
  return result

import gradio as gr
outputs = gr.outputs.Textbox()
app = gr.Interface(fn=HCV, inputs=['number','number','number','number','number','number','number','number'], outputs=outputs,description="This is a HCV model")

app.launch()