机器学习-支撑向量机SVM

小旺不正经2024-10-09 11:27

Support Vector Machine

离分类样本尽可能远

Soft Margin SVM

scikit-learn中的SVM

和kNN一样，要做数据标准化处理！

涉及距离！

加载数据集

python 复制代码 
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

iris = datasets.load_iris()

X = iris.data
y = iris.target

X = X[y<2,:2]
y = y[y<2]
plt.scatter(X[y==0,0], X[y==0,1], color='red')
plt.scatter(X[y==1,0], X[y==1,1], color='blue')
plt.show()

数据标准化

python 复制代码 
from sklearn.preprocessing import StandardScaler

standardScaler = StandardScaler()
standardScaler.fit(X)
X_standard = standardScaler.transform(X)

svm

python 复制代码 
from sklearn.svm import LinearSVC

svc = LinearSVC(C=1e9)
svc.fit(X_standard, y)

可视化

python 复制代码 
def plot_decision_boundary(model, axis):
    
    x0, x1 = np.meshgrid(
        np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),
        np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),
    )
    X_new = np.c_[x0.ravel(), x1.ravel()]

    y_predict = model.predict(X_new)
    zz = y_predict.reshape(x0.shape)

    from matplotlib.colors import ListedColormap
    custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
    
    plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)
python 复制代码 
plot_decision_boundary(svc, axis=[-3, 3, -3, 3])
plt.scatter(X_standard[y==0,0], X_standard[y==0,1])
plt.scatter(X_standard[y==1,0], X_standard[y==1,1])
plt.show()
python 复制代码 
svc2 = LinearSVC(C=0.01)
svc2.fit(X_standard, y)
python 复制代码 
plot_decision_boundary(svc2, axis=[-3, 3, -3, 3])
plt.scatter(X_standard[y==0,0], X_standard[y==0,1])
plt.scatter(X_standard[y==1,0], X_standard[y==1,1])
plt.show()

绘制上下对应的两条线

python 复制代码 
def plot_svc_decision_boundary(model, axis):
    
    x0, x1 = np.meshgrid(
        np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),
        np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),
    )
    X_new = np.c_[x0.ravel(), x1.ravel()]

    y_predict = model.predict(X_new)
    zz = y_predict.reshape(x0.shape)

    from matplotlib.colors import ListedColormap
    custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
    
    plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)
    
    w = model.coef_[0]
    b = model.intercept_[0]
    
    # w0*x0 + w1*x1 + b = 0
    # => x1 = -w0/w1 * x0 - b/w1
    plot_x = np.linspace(axis[0], axis[1], 200)
    up_y = -w[0]/w[1] * plot_x - b/w[1] + 1/w[1]
    down_y = -w[0]/w[1] * plot_x - b/w[1] - 1/w[1]
    
    up_index = (up_y >= axis[2]) & (up_y <= axis[3])
    down_index = (down_y >= axis[2]) & (down_y <= axis[3])
    plt.plot(plot_x[up_index], up_y[up_index], color='black')
    plt.plot(plot_x[down_index], down_y[down_index], color='black')
python 复制代码 
plot_svc_decision_boundary(svc, axis=[-3, 3, -3, 3])
plt.scatter(X_standard[y==0,0], X_standard[y==0,1])
plt.scatter(X_standard[y==1,0], X_standard[y==1,1])
plt.show()

SVM中使用多项式特征

生成数据集

python 复制代码 
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

X, y = datasets.make_moons()
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()
python 复制代码 
X, y = datasets.make_moons(noise=0.15, random_state=666)

plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

使用多项式特征的SVM

python 复制代码 
from sklearn.preprocessing import PolynomialFeatures, StandardScaler
from sklearn.svm import LinearSVC
from sklearn.pipeline import Pipeline

def PolynomialSVC(degree, C=1.0):
    return Pipeline([
        ("poly", PolynomialFeatures(degree=degree)),
        ("std_scaler", StandardScaler()),
        ("linearSVC", LinearSVC(C=C))
    ])
python 复制代码 
poly_svc = PolynomialSVC(degree=3)
poly_svc.fit(X, y)
python 复制代码 
def plot_decision_boundary(model, axis):
    
    x0, x1 = np.meshgrid(
        np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),
        np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),
    )
    X_new = np.c_[x0.ravel(), x1.ravel()]

    y_predict = model.predict(X_new)
    zz = y_predict.reshape(x0.shape)

    from matplotlib.colors import ListedColormap
    custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
    
    plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)
python 复制代码 
plot_decision_boundary(poly_svc, axis=[-1.5, 2.5, -1.0, 1.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

使用多项式核函数的SVM

python 复制代码 
from sklearn.svm import SVC

def PolynomialKernelSVC(degree, C=1.0):
    return Pipeline([
        ("std_scaler", StandardScaler()),
        ("kernelSVC", SVC(kernel="poly", degree=degree, C=C))
    ])
python 复制代码 
poly_kernel_svc = PolynomialKernelSVC(degree=3)
poly_kernel_svc.fit(X, y)
python 复制代码 
plot_decision_boundary(poly_kernel_svc, axis=[-1.5, 2.5, -1.0, 1.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

什么是核函数

多项式核函数

高斯核函数

RBF核 Radial Basis Function Kernel

将每一个样本点映射到一个无穷维的特征空间

多项式特征

高斯核

python 复制代码 
import numpy as np
import matplotlib.pyplot as plt
x = np.arange(-4, 5, 1)
y = np.array((x >= -2) & (x <= 2), dtype='int')
plt.scatter(x[y==0], [0]*len(x[y==0]))
plt.scatter(x[y==1], [0]*len(x[y==1]))
plt.show()

高斯核

python 复制代码 
def gaussian(x, l):
    gamma = 1.0
    return np.exp(-gamma * (x-l)**2)
l1, l2 = -1, 1

X_new = np.empty((len(x), 2))
for i, data in enumerate(x):
    X_new[i, 0] = gaussian(data, l1)
    X_new[i, 1] = gaussian(data, l2)
plt.scatter(X_new[y==0,0], X_new[y==0,1])
plt.scatter(X_new[y==1,0], X_new[y==1,1])
plt.show()

scikit-learn中的高斯核函数

python 复制代码 
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

X, y = datasets.make_moons(noise=0.15, random_state=666)

plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

预处理

python 复制代码 
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline
from sklearn.svm import SVC

def RBFKernelSVC(gamma):
    return Pipeline([
        ("std_scaler", StandardScaler()),
        ("svc", SVC(kernel="rbf", gamma=gamma))
    ])
python 复制代码 
svc = RBFKernelSVC(gamma=1)
svc.fit(X, y)

可视化

python 复制代码 
def plot_decision_boundary(model, axis):
    
    x0, x1 = np.meshgrid(
        np.linspace(axis[0], axis[1], int((axis[1]-axis[0])*100)).reshape(-1, 1),
        np.linspace(axis[2], axis[3], int((axis[3]-axis[2])*100)).reshape(-1, 1),
    )
    X_new = np.c_[x0.ravel(), x1.ravel()]

    y_predict = model.predict(X_new)
    zz = y_predict.reshape(x0.shape)

    from matplotlib.colors import ListedColormap
    custom_cmap = ListedColormap(['#EF9A9A','#FFF59D','#90CAF9'])
    
    plt.contourf(x0, x1, zz, linewidth=5, cmap=custom_cmap)
python 复制代码 
plot_decision_boundary(svc, axis=[-1.5, 2.5, -1.0, 1.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()
python 复制代码 
svc_gamma100 = RBFKernelSVC(gamma=100)
svc_gamma100.fit(X, y)
python 复制代码 
plot_decision_boundary(svc_gamma100, axis=[-1.5, 2.5, -1.0, 1.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()
python 复制代码 
svc_gamma10 = RBFKernelSVC(gamma=10)
svc_gamma10.fit(X, y)
plot_decision_boundary(svc_gamma10, axis=[-1.5, 2.5, -1.0, 1.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()
python 复制代码 
svc_gamma05 = RBFKernelSVC(gamma=0.5)
svc_gamma05.fit(X, y)
plot_decision_boundary(svc_gamma05, axis=[-1.5, 2.5, -1.0, 1.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()
python 复制代码 
svc_gamma01 = RBFKernelSVC(gamma=0.1)
svc_gamma01.fit(X, y)
plot_decision_boundary(svc_gamma01, axis=[-1.5, 2.5, -1.0, 1.5])
plt.scatter(X[y==0,0], X[y==0,1])
plt.scatter(X[y==1,0], X[y==1,1])
plt.show()

SVM思路解决回归问题

python 复制代码 
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets

boston = datasets.load_boston()
X = boston.data
y = boston.target
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=666)
python 复制代码 
from sklearn.svm import LinearSVR
from sklearn.svm import SVR
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

def StandardLinearSVR(epsilon=0.1):
    return Pipeline([
        ('std_scaler', StandardScaler()),
        ('linearSVR', LinearSVR(epsilon=epsilon))
    ])
python 复制代码 
svr = StandardLinearSVR()
svr.fit(X_train, y_train)
python 复制代码 
svr.score(X_test, y_test)
相关推荐
陪学7 分钟前
百度遭初创企业指控抄袭，维权还是碰瓷？
人工智能·百度·面试·职场和发展·产品运营
QCN_10 分钟前
湘潭大学人工智能考试复习1（软件工程）
人工智能
Landy_Jay11 分钟前
深度学习：GPT-1的MindSpore实践
人工智能·gpt·深度学习
白光白光19 分钟前
量子神经网络
人工智能·深度学习·神经网络
全域观察24 分钟前
如何复制只读模式下的腾讯文档
人工智能·新媒体运营·媒体·内容运营·程序员创富
panpantt32132 分钟前
【参会邀请】第二届大数据与数据挖掘国际会议（BDDM 2024）邀您相聚江城！
大数据·人工智能·数据挖掘
lindsayshuo40 分钟前
jetson orin系列开发版安装cuda的gpu版本的opencv
人工智能·opencv
向阳逐梦40 分钟前
ROS机器视觉入门：从基础到人脸识别与目标检测
人工智能·目标检测·计算机视觉
陈鋆1 小时前
智慧城市初探与解决方案
人工智能·智慧城市
qdprobot1 小时前
ESP32桌面天气摆件加文心一言AI大模型对话Mixly图形化编程STEAM创客教育
网络·人工智能·百度·文心一言·arduino
热门推荐
01(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明02PyTorch机器学习实现液态神经网络03【HarmonyOS】HUAWEI DevEco Studio 下载地址汇总04玄机平台应急响应—webshell查杀05Coze扣子平台完整体验和实践（附国内和国际版对比）06Ubuntu 20.04使用Livox mid 360 测试 FAST_LIO07【目标跟踪】相机运动补偿08Unity中PICO实现 隔空取物 和 接触抓取物体09RAG 实践- Ollama+RagFlow 部署本地知识库10怎样让音频速度变慢？请跟随以下方法进行操作