Python에서 로지스틱 회귀 구현하기

라이브러리와 데이터 집합 가져오기

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# Generate dataset
X, y = make_classification(n_samples=100, n_features=2, n_classes=2, random_state=42)

# Split into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

로지스틱 회귀 모델 만들기

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

예측 수행하기

y_pred = model.predict(X_test)

모델 평가하기

accuracy = accuracy_score(y_test, y_pred)
print(f"Model Accuracy: {accuracy:.2f}")

결정 경계 시각화하기

import matplotlib.pyplot as plt
import numpy as np

# Define grid for plotting
def plot_decision_boundary(X, y, model):
    x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.1), np.arange(y_min, y_max, 0.1))

    Z = model.predict(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    
    plt.contourf(xx, yy, Z, alpha=0.8)
    plt.scatter(X[:, 0], X[:, 1], c=y, edgecolor='k')
    plt.title('Decision Boundary')
    plt.show()

plot_decision_boundary(X, y, model)

모델 조정하기

model = LogisticRegression(C=0.5)
model.fit(X_train, y_train)

로지스틱 회귀의 문제

요약 및 다음 단계