Support Vector Machine (SVM)

import numpy as np
import matplotlib.pyplot as plt
from sklearn.svm import SVC

X = np.array([[1, 5], [2, 4], [2, 6], [3, 3], [3, 5], [4, 2],      # failed
              [5, 7], [6, 6], [6, 8], [7, 5], [8, 7], [8, 6]])     # passed
y = np.array([0] * 6 + [1] * 6)

model = SVC(kernel="linear", C=1.0).fit(X, y)
print("support vectors:\n", model.support_vectors_)
print("prediction for 4.5 h study, 6 h sleep:", ["fail", "pass"][model.predict([[4.5, 6]])[0]])

# draw points, boundary and margins
xx, yy = np.meshgrid(np.linspace(0, 9, 200), np.linspace(1, 9, 200))
zz = model.decision_function(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)
fig, ax = plt.subplots(figsize=(7, 4.2), dpi=110)
ax.contour(xx, yy, zz, levels=[-1, 0, 1], linestyles=["--", "-", "--"], colors="#334155")
ax.scatter(X[:, 0], X[:, 1], c=np.where(y == 1, "#16a34a", "#dc2626"), s=60, edgecolor="k")
ax.scatter(*model.support_vectors_.T, s=220, facecolors="none", edgecolors="#2563eb", linewidths=2, label="support vectors")
ax.set_xlabel("hours studied"); ax.set_ylabel("hours slept"); ax.legend(loc="lower right")
ax.set_title("Linear SVM: solid = boundary, dashed = margin")
fig.tight_layout(); fig.savefig("svm_margin.png")

import matplotlib.pyplot as plt
import numpy as np
from sklearn.datasets import make_moons
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC

X, y = make_moons(n_samples=300, noise=0.2, random_state=42)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

fig, axes = plt.subplots(1, 2, figsize=(9, 3.6), dpi=110)
xx, yy = np.meshgrid(np.linspace(-1.5, 2.5, 300), np.linspace(-1, 1.5, 300))
for ax, kernel in zip(axes, ["linear", "rbf"]):
    m = SVC(kernel=kernel, C=1, gamma="scale").fit(X_train, y_train)
    print(f"{kernel:<6} test accuracy: {m.score(X_test, y_test):.2f}")
    zz = m.predict(np.c_[xx.ravel(), yy.ravel()]).reshape(xx.shape)
    ax.contourf(xx, yy, zz, alpha=0.25, cmap="RdYlGn")
    ax.scatter(X[:, 0], X[:, 1], c=y, cmap="RdYlGn", s=12, edgecolor="k", linewidths=0.3)
    ax.set_title(f"kernel = {kernel}")
fig.tight_layout(); fig.savefig("kernels.png")

from sklearn.datasets import make_moons
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC

X, y = make_moons(n_samples=300, noise=0.25, random_state=1)
X_tr, X_te, y_tr, y_te = train_test_split(X, y, test_size=0.3, random_state=1)

print(f"{'C':>6} {'gamma':>6} {'train':>6} {'test':>6} {'#SV':>5}")
for C, gamma in [(0.1, 0.5), (1, 0.5), (1, 5), (100, 50)]:
    m = SVC(kernel="rbf", C=C, gamma=gamma).fit(X_tr, y_tr)
    print(f"{C:>6} {gamma:>6} {m.score(X_tr, y_tr):>6.2f} {m.score(X_te, y_te):>6.2f} {len(m.support_):>5}")

from sklearn.datasets import load_breast_cancer
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.model_selection import GridSearchCV, train_test_split
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC

data = load_breast_cancer()
X_train, X_test, y_train, y_test = train_test_split(
    data.data, data.target, test_size=0.25, stratify=data.target, random_state=42)

unscaled = SVC().fit(X_train, y_train)
print("without scaling:", round(unscaled.score(X_test, y_test), 3))

pipe = make_pipeline(StandardScaler(), SVC())
grid = GridSearchCV(pipe, {"svc__C": [0.1, 1, 10], "svc__gamma": ["scale", 0.01, 0.1]}, cv=5)
grid.fit(X_train, y_train)
print("best params    :", grid.best_params_)
print("with scaling   :", round(grid.score(X_test, y_test), 3))

pred = grid.predict(X_test)
print(confusion_matrix(y_test, pred))
print(classification_report(y_test, pred, target_names=data.target_names, digits=3))