hepatitis_c.py

import pandas as pd
import numpy as np
from pycaret.classification import *

# load data
data = pd.read_csv("HepatitisCdata.csv")
data = data.drop(labels='Unnamed: 0', axis=1)
data.head(10)

# clean data

# pd.Series(data["Category"], dtype="category")
# ['0=Blood Donor', '0s=suspect Blood Donor', '1=Hepatitis', '2=Fibrosis', '3=Cirrhosis']

data["Category"] = [0 if x == "0=Blood Donor" else x for x in data["Category"]]
data["Category"] = [1 if x == "0s=suspect Blood Donor" else x for x in data["Category"]]
data["Category"] = [2 if x == "1=Hepatitis" else x for x in data["Category"]]
data["Category"] = [3 if x == "2=Fibrosis" else x for x in data["Category"]]
data["Category"] = [4 if x == "3=Cirrhosis" else x for x in data["Category"]]

# pd.Series(data["Sex"], dtype="category")
# ['f', 'm']

data["Sex"] = [0 if x == "f" else 1 for x in data["Sex"]]
data.head(10)

# pycaret setup
s = setup(data, target = "Category")

# model training and selection
best = compare_models()

# model evaluation analytics
evaluate_model(best)

# save model to disk "hepatitis_model.pkl"
save_model(best, "hepatitis_model")

# load pickle file
from pycaret.classification import load_model

# load model
hepatitis_model = load_model('hepatitis_model')

# classes and sample
classes = ['Blood Donor', 'Suspect Blood Donor', 'Hepatitis', 'Fibrosis', 'Cirrhosis']
patient_data = data.iloc[10,1:]
patient_class = data.iloc[10,0]
print(patient_data, "\n")
print("Patient was labeled as:", classes[patient_class])

# perform the prediction
patient_data = pd.DataFrame()
patient_data = patient_data.append({
    'Age': 32.00,
    'Sex': 1.00,
    'ALB': 44.30,
    'ALP': 52.30,
    'ALT': 21.70,
    'AST': 22.40,
    'BIL': 17.20,
    'CHE': 4.15,
    'CHOL': 3.57,
    'CREA': 78.00,
    'GGT': 24.10,
    'PROT': 75.40
}, ignore_index=True)

# perform prediction
prediction = predict_model(hepatitis_model, data = patient_data)
print('Patient was CLASSIFIED as:', classes[prediction.Label[0]])