一个超强算法全总结，SVM ！！

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm
from sklearn.datasets import make_blobs

# 创建 2D 数据集
X, y = make_blobs(n_samples=40, centers=2, random_state=6)

# 训练 SVM 模型
clf = svm.SVC(kernel='linear', C=1000)
clf.fit(X, y)

# 绘制数据点
plt.scatter(X[:, 0], X[:, 1], c=y, s=30, cmap=plt.cm.Paired)

# 绘制决策边界
ax = plt.gca()
xlim = ax.get_xlim()
ylim = ax.get_ylim()

# 创建网格来评估模型
xx = np.linspace(xlim[0], xlim[1], 30)
yy = np.linspace(ylim[0], ylim[1], 30)
YY, XX = np.meshgrid(yy, xx)
xy = np.vstack([XX.ravel(), YY.ravel()]).T
Z = clf.decision_function(xy).reshape(XX.shape)

# 绘制决策边界和边距
ax.contour(XX, YY, Z, colors='k', levels=[-1, 0, 1], alpha=0.5, linestyles=['--', '-', '--'])

# 标记支持向量
ax.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1], s=100, linewidth=1, facecolors='none', edgecolors='k')
plt.show()

import numpy as np
from matplotlib.colors import Normalize
from sklearn.datasets import load_iris
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import GridSearchCV, StratifiedShuffleSplit
from sklearn.svm import SVC
import matplotlib.pyplot as plt

# 自定义归一化类
class MidpointNormalize(Normalize):
    def __init__(self, vmin=None, vmax=None, midpoint=None, clip=False):
        self.midpoint = midpoint
        Normalize.__init__(self, vmin, vmax, clip)
    def __call__(self, value, clip=None):
        x, y = [self.vmin, self.midpoint, self.vmax], [0, 0.5, 1]
        return np.ma.masked_array(np.interp(value, x, y))

# 数据加载和预处理
iris = load_iris()
X = iris.data
y = iris.target

# 二维化数据，只保留两个特征和两个类别
X_2d = X[:, :2]
X_2d = X_2d[y > 0]
y_2d = y[y > 0]
y_2d -= 1

# 数据标准化
scaler = StandardScaler()
X = scaler.fit_transform(X)
X_2d = scaler.fit_transform(X_2d)

# 参数网格和网格搜索
C_range = np.logspace(-2, 10, 13)
gamma_range = np.logspace(-9, 3, 13)
param_grid = dict(gamma=gamma_range, C=C_range)
cv = StratifiedShuffleSplit(n_splits=5, test_size=0.2, random_state=42)
grid = GridSearchCV(SVC(), param_grid=param_grid, cv=cv)
grid.fit(X, y)
print("The best parameters are %s with a score of %0.2f" % (grid.best_params_, grid.best_score_))

# 训练用于可视化的分类器
C_2d_range = [1e-2, 1, 1e2]
gamma_2d_range = [1e-1, 1, 1e1]
classifiers = []
for C in C_2d_range:
    for gamma in gamma_2d_range:
        clf = SVC(C=C, gamma=gamma)
        clf.fit(X_2d, y_2d)
        classifiers.append((C, gamma, clf))

# 决策边界可视化
plt.figure(figsize=(8, 6))
xx, yy = np.meshgrid(np.linspace(-3, 3, 200), np.linspace(-3, 3, 200))
for k, (C, gamma, clf) in enumerate(classifiers):
    Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
    Z = Z.reshape(xx.shape)
    plt.subplot(len(C_2d_range), len(gamma_2d_range), k + 1)
    plt.title("gamma=10^%d, C=10^%d" % (np.log10(gamma), np.log10(C)), size="medium")
    plt.pcolormesh(xx, yy, -Z, cmap=plt.cm.RdBu)
    plt.scatter(X_2d[:, 0], X_2d[:, 1], c=y_2d, cmap=plt.cm.RdBu_r, edgecolors="k")
    plt.xticks(())
    plt.yticks(())
    plt.axis("tight")

# 热图绘制
scores = grid.cv_results_["mean_test_score"].reshape(len(C_range), len(gamma_range))
plt.figure(figsize=(8, 6))
plt.subplots_adjust(left=0.2, right=0.95, bottom=0.15, top=0.95)
plt.imshow(
    scores,
    interpolation="nearest",
    cmap=plt.cm.hot,
    norm=MidpointNormalize(vmin=0.2, midpoint=0.92),
)
plt.xlabel("gamma")
plt.ylabel("C")
plt.colorbar()
plt.xticks(np.arange(len(gamma_range)), gamma_range, rotation=45)
plt.yticks(np.arange(len(C_range)), C_range)
plt.title("Validation accuracy")
plt.show()