Classification

Code

from sklearn.linear_model import LogisticRegression
from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
from sklearn.svm import SVC
from sklearn.neighbors import KNeighborsClassifier
from sklearn.datasets import make_classification
from sklearn.metrics import accuracy_score
from sklearn.model_selection import train_test_split

X, y = make_classification(n_samples=500, n_features=10, random_state=42)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.2, random_state=42)

models = {
    "logreg": LogisticRegression(max_iter=1000),
    "rf": RandomForestClassifier(n_estimators=100, random_state=42),
    "gb": GradientBoostingClassifier(random_state=42),
    "svc": SVC(kernel="rbf", probability=True),
    "knn": KNeighborsClassifier(n_neighbors=5),
}

for name, m in models.items():
    m.fit(X_tr, y_tr)
    acc = accuracy_score(y_te, m.predict(X_te))
    print(f"{name}: {acc:.4f}")

Explanation

scikit-learn exposes a uniform fit/predict API across classifiers, so swapping models requires only changing the class. Random forests and gradient boosting are strong tabular-data baselines, while logistic regression and SVMs work well on linearly separable data. Comparing accuracy across several models is a fast first pass.

More Machine Learning Snippets