머신 러닝 (8) 분류

 import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

import koreanize_matplotlib

import seaborn as sns

from sklearn.datasets import load_diabetes

from sklearn.model_selection import train_test_split

from sklearn.linear_model import LogisticRegression

from sklearn.metrics import accuracy_score, confusion_matrix, classification_report

import warnings

warnings.filterwarnings('ignore')

pima_columns = ['pregnancies', 'glucose', 'blood_pressure', 'skin_thickness', 'insulin', 'bmi', 'diabetes_pedigree_function', 'age', 'outcome']

pima_data_url = 'https://raw.githubusercontent.com/jbrownlee/Datasets/master/pima-indians-diabetes.data.csv'

df = pd.read_csv(pima_data_url, names=pima_columns)

# 타겟 변수 확인 (outcome: 0=정상, 1=당뇨병)

print(df['outcome'].value_counts())

print(df['outcome'].value_counts(normalize=True))

# Feature(X)와 Target(y) 분리

X = df.drop('outcome', axis=1)

y = df['outcome']

# 학습용/테스트용 데이터 분할 (8:2)

# stratify=y: 타겟 변수의 클래스 비율을 유지하며 분할

X_train, X_test, y_train, y_test = train_test_split(

    X, y, test_size=0.2, random_state=42, stratify=y

)

print(f"학습 데이터: {X_train.shape}")

print(f"테스트 데이터: {X_test.shape}")

# max_iter=1000: 수렴을 위해 반복 횟수 충분히 설정

model = LogisticRegression(max_iter=1000, random_state=42)

model.fit(X_train, y_train)

# 테스트 데이터 예측

y_pred = model.predict(X_test)

# 정확도(Accuracy) 출력

accuracy = accuracy_score(y_test, y_pred)

print(f"Accuracy (정확도): {accuracy:.4f}")

# 정확도(Accuracy) 출력

y_pred = model.predict(X_test)

y_pred