Notes

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler

# Load the disease dataset
df = pd.read_csv("disease.csv")

# Extract the features and target values
X = df[['age', 'bmi', 'bp']].values
y = df['disease'].values

# Split the data into training and testing sets
train_features = X[:int(0.8 * X.shape[0])]
train_target = y[:int(0.8 * y.shape[0])]
test_features = X[int(0.8 * X.shape[0]):]
test_target = y[int(0.8 * y.shape[0]):]

# Normalize the data using StandardScaler
scaler = StandardScaler()
train_features = scaler.fit_transform(train_features)
test_features = scaler.transform(test_features)

# Train a logistic regression classifier on the training data
clf = LogisticRegression(random_state=42)
clf.fit(train_features, train_target)

# Evaluate the classifier on the test data
accuracy = clf.score(test_features, test_target)
print("Accuracy: {:.2f}%".format(accuracy * 100))