API ของ scikit-learn: fit, transform, predict

scikit-learn คืออะไร

from sklearn.linear_model import LinearRegression
import numpy as np

X = np.array([[1],[2],[3],[4],[5]])
y = np.array([2, 4, 6, 8, 10])

model = LinearRegression().fit(X, y)
print(model.predict([[6]]))   # [12.]

การแบ่งข้อมูลฝึกและทดสอบ

from sklearn.model_selection import train_test_split
import numpy as np

X = np.random.rand(100, 5)
y = (X[:,0] > 0.5).astype(int)

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42
)
print(X_train.shape, X_test.shape)   # (80,5) (20,5)

fit() — การฝึกโมเดล

from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification

X, y = make_classification(n_samples=200, random_state=0)
model = LogisticRegression()
model.fit(X, y)
print("Trained:", model.classes_)

predict() และ predict_proba()

from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification

X, y = make_classification(random_state=0)
model = LogisticRegression().fit(X, y)

print(model.predict(X[:5]))          # [0 1 0 ...]
print(model.predict_proba(X[:2]))    # [[0.7 0.3] ...]

ตัวแปลง: fit และ transform

from sklearn.preprocessing import StandardScaler
import numpy as np

X_train = np.array([[1,2],[3,4],[5,6]])
X_test  = np.array([[2,3],[4,5]])

scaler = StandardScaler()
X_train_s = scaler.fit_transform(X_train)   # fit + transform
X_test_s  = scaler.transform(X_test)        # transform only (using train stats)

กระบวนการประมวลผลต่อเนื่อง

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

pipe = Pipeline([
    ("scaler", StandardScaler()),
    ("clf", SVC())
])
pipe.fit(X_train, y_train)
print(pipe.score(X_test, y_test))

ความแม่นยำและตัวชี้วัดอื่น ๆ

from sklearn.metrics import accuracy_score, classification_report

y_pred = model.predict(X_test)
print(accuracy_score(y_test, y_pred))
print(classification_report(y_test, y_pred))

การตรวจสอบไขว้

from sklearn.model_selection import cross_val_score
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification

X, y = make_classification(random_state=0)
scores = cross_val_score(LogisticRegression(), X, y, cv=5)
print(f"CV scores: {scores.mean():.3f} ± {scores.std():.3f}")

การปรับไฮเปอร์พารามิเตอร์ด้วย GridSearchCV

from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
from sklearn.datasets import make_classification

X, y = make_classification(random_state=0)
param_grid = {"C": [0.1, 1, 10], "kernel": ["rbf", "linear"]}
gs = GridSearchCV(SVC(), param_grid, cv=5)
gs.fit(X, y)
print(gs.best_params_, gs.best_score_)

การเตรียมข้อมูล: LabelEncoder และ OneHotEncoder

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
import numpy as np

le = LabelEncoder()
print(le.fit_transform(["cat","dog","cat","fish"]))   # [0 1 0 2]

ohe = OneHotEncoder(sparse_output=False)
print(ohe.fit_transform([["red"],["green"],["blue"]]))

การบันทึกและโหลดโมเดล

import joblib
from sklearn.linear_model import LogisticRegression
from sklearn.datasets import make_classification

X, y = make_classification(random_state=0)
model = LogisticRegression().fit(X, y)

joblib.dump(model, "model.joblib")
loaded = joblib.load("model.joblib")
print(loaded.predict(X[:3]))

ตรวจสอบความเข้าใจ

สรุปทบทวน