'''Simple HIV prediction using Logistic Regression'''
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

#Load Data

data = {
    'Age': [25, 35, 45, 28, 50, 30, 40, 23, 60, 33],
    'CD4_Count': [500, 350, 200, 450, 180, 320, 250, 600, 150, 400],
    'Viral_load': [10, 20, 50, 15, 60, 25, 40, 12, 70, 30],
    'HIV_status': [0, 1, 1, 0, 1, 0, 1, 0, 1, 0]
}

#Convert to DataFrame

df = pd.DataFrame(data)

#Split into Features and Target

X = df[['Age', 'CD4_Count', 'Viral_load']]
y = df['HIV_status']

#Split into Train and Test

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 42)

#Train the model

model = LogisticRegression()
model.fit(X_train, y_train)

#predicting

y_pred = model.predict(X_test)


#New data prediction

new_data = np.array([20, 480, 12])
new_prediction = model.predict(new_data.reshape(1, -1))
for i, (input_data, prediction) in enumerate(zip(new_data, new_prediction)):
  status = "Positive" if prediction == 1 else "Negative"
  print(f"predicted HIV status: {status}")