โมเดลเชิงเส้น: การถดถอยและการจำแนกประเภท

การถดถอยเชิงเส้น

from sklearn.linear_model import LinearRegression
from sklearn.datasets import make_regression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

X, y = make_regression(n_samples=200, n_features=5, noise=10, random_state=0)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, random_state=0)

model = LinearRegression().fit(X_tr, y_tr)
print("RMSE:", mean_squared_error(y_te, model.predict(X_te))**0.5)

สัมประสิทธิ์ของแบบจำลอง

from sklearn.linear_model import LinearRegression
import numpy as np

X = np.array([[1],[2],[3]])
y = np.array([2, 4, 6])

model = LinearRegression().fit(X, y)
print("Coef:", model.coef_)       # [2.]
print("Intercept:", model.intercept_)  # ~0

การถดถอยแบบริดจ์และลาสโซ

from sklearn.linear_model import Ridge, Lasso
from sklearn.datasets import make_regression

X, y = make_regression(n_features=20, noise=15, random_state=0)

ridge = Ridge(alpha=1.0).fit(X, y)
lasso = Lasso(alpha=0.1).fit(X, y)
print("Ridge coef[:5]:", ridge.coef_[:5])
print("Lasso coef[:5]:", lasso.coef_[:5])  # some are 0 (sparse)

การถดถอยโลจิสติก

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

X, y = make_classification(random_state=0)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, random_state=0)
model = LogisticRegression().fit(X_tr, y_tr)
print("Accuracy:", accuracy_score(y_te, model.predict(X_te)))

การถดถอยโลจิสติกหลายคลาส

from sklearn.linear_model import LogisticRegression
from sklearn.datasets import load_iris

X, y = load_iris(return_X_y=True)
model = LogisticRegression(max_iter=200).fit(X, y)
print("Classes:", model.classes_)   # [0 1 2]
print("Accuracy:", model.score(X, y))

การปรับสเกลคุณลักษณะสำหรับแบบจำลองเชิงเส้น

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression

pipe = Pipeline([
    ("scale", StandardScaler()),
    ("clf",   LogisticRegression())
])
pipe.fit(X_tr, y_tr)
print(pipe.score(X_te, y_te))

เส้นโค้งการเรียนรู้

from sklearn.model_selection import learning_curve
import numpy as np

train_sizes, train_scores, val_scores = learning_curve(
    LogisticRegression(), X, y, cv=5,
    train_sizes=np.linspace(0.1, 1.0, 5)
)
print("Val mean:", val_scores.mean(axis=1))

คะแนน R² สำหรับการถดถอย

from sklearn.metrics import r2_score
from sklearn.linear_model import LinearRegression
from sklearn.datasets import make_regression

X, y = make_regression(noise=20, random_state=0)
model = LinearRegression().fit(X, y)
print("R²:", r2_score(y, model.predict(X)))

คุณลักษณะพหุนาม

from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LinearRegression
import numpy as np

X = np.array([[1],[2],[3],[4],[5]])
y = np.array([1, 4, 9, 16, 25])  # y = x^2

pipe = Pipeline([
    ("poly", PolynomialFeatures(degree=2)),
    ("lr",   LinearRegression())
])
pipe.fit(X, y)
print(pipe.predict([[6]]))   # ~36

SGDClassifier และ SGDRegressor

from sklearn.linear_model import SGDClassifier
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.datasets import make_classification

X, y = make_classification(n_samples=100_000, random_state=0)
pipe = Pipeline([("sc", StandardScaler()), ("sgd", SGDClassifier())])
pipe.fit(X, y)
print(pipe.score(X, y))

เส้นทางการทำให้เป็นระเบียบ

from sklearn.linear_model import RidgeCV, LassoCV
from sklearn.datasets import make_regression

X, y = make_regression(n_features=20, noise=10, random_state=0)
ridge = RidgeCV(alphas=[0.1, 1, 10]).fit(X, y)
print("Best alpha:", ridge.alpha_)

ตรวจสอบความเข้าใจ

สรุปทบทวน