Scikit-learn 기본 사용법

1. Scikit-learn 시작

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

https://scikit-learn.org/stable/getting_started.html

Getting Started

 

2. 데이터 분할 (Train/Test Split)

# 데이터 준비
X = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
y = np.array([1, 2, 3, 4])

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

https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html

train_test_split

 

3. 데이터 스케일링 (Standard Scaling)

# 스케일러 초기화
scaler = StandardScaler()

# 스케일링 적용 (학습 데이터에 맞춰)
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html

StandardScaler

 

4. 선형 회귀 모델 (Linear Regression)

# 모델 초기화
model = LinearRegression()

# 모델 학습
model.fit(X_train, y_train)

# 예측
y_pred = model.predict(X_test)

https://scikit-learn.org/stable/modules/linear_model.html#ordinary-least-squares

1.1. Linear Models

 

5. 모델 평가 (Model Evaluation)

# MSE 계산
mse = mean_squared_error(y_test, y_pred)
print(f'Mean Squared Error: {mse}')

# R^2 계산
r2 = r2_score(y_test, y_pred)
print(f'R^2 Score: {r2}')

https://scikit-learn.org/stable/modules/model_evaluation.html#regression-metrics

3.4. Metrics and scoring: quantifying the quality of predictions

 

6. 분류 모델 (Classification)

from sklearn.datasets import load_iris
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score

# 데이터 준비
iris = load_iris()
X = iris.data
y = iris.target

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

# 모델 초기화
clf = SVC()

# 모델 학습
clf.fit(X_train, y_train)

# 예측
y_pred = clf.predict(X_test)

# 정확도 평가
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy}')

https://scikit-learn.org/stable/modules/svm.html

1.4. Support Vector Machines

 

7. 교차 검증 (Cross-Validation)

from sklearn.model_selection import cross_val_score

# 교차 검증
scores = cross_val_score(clf, X, y, cv=5)
print(f'Cross-Validation Scores: {scores}')
print(f'Average CV Score: {np.mean(scores)}')

https://scikit-learn.org/stable/modules/cross_validation.html

3.1. Cross-validation: evaluating estimator performance

 

8. 하이퍼파라미터 튜닝 (Hyperparameter Tuning)

from sklearn.model_selection import GridSearchCV

# 파라미터 그리드 설정
param_grid = {'C': [0.1, 1, 10], 'gamma': [1, 0.1, 0.01]}

# 그리드 서치
grid = GridSearchCV(SVC(), param_grid, refit=True, verbose=2)
grid.fit(X_train, y_train)

# 최적 파라미터 및 점수 출력
print(f'Best Parameters: {grid.best_params_}')
print(f'Best Score: {grid.best_score_}')

https://scikit-learn.org/stable/modules/grid_search.html

3.2. Tuning the hyper-parameters of an estimator

 

9. 파이프라인 (Pipeline)

from sklearn.pipeline import Pipeline

# 파이프라인 설정
pipeline = Pipeline([
    ('scaler', StandardScaler()),
    ('svc', SVC())
])

# 파이프라인 학습
pipeline.fit(X_train, y_train)

# 예측
y_pred = pipeline.predict(X_test)

https://scikit-learn.org/stable/modules/compose.html#pipeline

6.1. Pipelines and composite estimators

 

10. 데이터셋 로드 (Loading Datasets)

from sklearn.datasets import load_iris, load_boston

# 아이리스 데이터셋 로드
iris = load_iris()
X_iris, y_iris = iris.data, iris.target

# 보스턴 주택 가격 데이터셋 로드
boston = load_boston()
X_boston, y_boston = boston.data, boston.target

https://scikit-learn.org/stable/datasets/toy_dataset.html

7.1. Toy datasets