对鸢尾花数据集和月亮数据集，分别采用线性LDA、k-means和SVM算法进行二分类可视化分析

线性判别分析LDA

鸢尾花数据集

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets.samples_generator import make_classification

class LDA():
    def Train(self, X, y):
        # X为训练数据集，y为训练label
        X1 = np.array([X[i] for i in range(len(X)) if y[i] == 0])
        X2 = np.array([X[i] for i in range(len(X)) if y[i] == 1])
        # 求中心点
        mju1 = np.mean(X1, axis=0)  # mju1是ndrray类型
        mju2 = np.mean(X2, axis=0)
        # dot(a, b, out=None) 计算矩阵乘法
        cov1 = np.dot((X1 - mju1).T, (X1 - mju1))
        cov2 = np.dot((X2 - mju2).T, (X2 - mju2))
        Sw = cov1 + cov2
        # 计算w
        w = np.dot(np.mat(Sw).I, (mju1 - mju2).reshape((len(mju1), 1)))
        # 记录训练结果
        self.mju1 = mju1  # 第1类的分类中心
        self.cov1 = cov1
        self.mju2 = mju2  # 第2类的分类中心
        self.cov2 = cov2
        self.Sw = Sw  # 类内散度矩阵
        self.w = w  # 判别权重矩阵
    def Test(self, X, y):
        """X为测试数据集，y为测试label"""
        # 分类结果
        y_new = np.dot((X), self.w)
        # 计算fisher线性判别式
        nums = len(y)
        c1 = np.dot((self.mju1 - self.mju2).reshape(1, (len(self.mju1))), np.mat(self.Sw).I)
        c2 = np.dot(c1, (self.mju1 + self.mju2).reshape((len(self.mju1), 1)))
        c = 1/2 * c2  # 2个分类的中心
        h = y_new - c
        # 判别
        y_hat = []
        for i in range(nums):
            if h[i] >= 0:
                y_hat.append(0)
            else:
                y_hat.append(1)
        # 计算分类精度
        count = 0
        for i in range(nums):
            if y_hat[i] == y[i]:
                count += 1
        precise = count / nums
        # 显示信息
        print("测试样本数量:", nums)
        print("预测正确样本的数量:", count)
        print("测试准确度:", precise)
        return precise
    
if '__main__' == __name__:
    # 产生分类数据
    n_samples = 500
    X, y = make_classification(n_samples=n_samples, n_features=2, n_redundant=0, n_classes=2,n_informative=1, n_clusters_per_class=1, class_sep=0.5, random_state=10)
    # LDA线性判别分析(二分类)
    lda = LDA()
    # 60% 用作训练，40%用作测试
    Xtrain = X[:299, :]
    Ytrain = y[:299]
    Xtest = X[300:, :]
    Ytest = y[300:]
    lda.Train(Xtrain, Ytrain)
    precise = lda.Test(Xtest, Ytest)
    # 原始数据
    plt.scatter(X[:, 0], X[:, 1], marker='o', c=y)
    plt.xlabel("x1")
    plt.ylabel("x2")
    plt.title("Test precise:" + str(precise))
    plt.show()

月亮数据集

from sklearn.svm import SVC
from sklearn import datasets
import matplotlib.pyplot as plt
import numpy as np
iris = datasets.load_iris()
X = iris["data"][:, (2, 3)]  # 花瓣长度与花瓣宽度  petal length, petal width
y = iris["target"]
setosa_or_versicolor = (y == 0) | (y == 1)
X = X[setosa_or_versicolor]
y = y[setosa_or_versicolor]
# SVM Classifier model
svm_clf = SVC(kernel="linear", C=float("inf"))
svm_clf.fit(X, y)
def plot_svc_decision_boundary(svm_clf, xmin, xmax):
    # 获取决策边界的w和b
    w = svm_clf.coef_[0]
    b = svm_clf.intercept_[0]

    # At the decision boundary, w0*x0 + w1*x1 + b = 0
    # => x1 = -w0/w1 * x0 - b/w1
    x0 = np.linspace(xmin, xmax, 200)
    # 画中间的粗线
    decision_boundary = -w[0]/w[1] * x0 - b/w[1]
    # 计算间隔
    margin = 1/w[1]
    gutter_up = decision_boundary + margin
    gutter_down = decision_boundary - margin
    # 获取支持向量
    svs = svm_clf.support_vectors_
    plt.scatter(svs[:, 0], svs[:, 1], s=180, facecolors='#FFAAAA')
    plt.plot(x0, decision_boundary, "k-", linewidth=2)
    plt.plot(x0, gutter_up, "k--", linewidth=2)
    plt.plot(x0, gutter_down, "k--", linewidth=2)
plt.title("大间隔分类", fontsize=16)
plt.rcParams['font.sans-serif']=['SimHei'] #显示中文标签
plt.rcParams['axes.unicode_minus']=False
plot_svc_decision_boundary(svm_clf, 0, 5.5)
plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs")
plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo")
plt.xlabel("Petal length", fontsize=14)
plt.axis([0, 5.5, 0, 2])
plt.show()

SVM（支持向量机）算法

鸢尾花数据集

from sklearn.svm import SVC
from sklearn import datasets
import matplotlib.pyplot as plt
import numpy as np
iris = datasets.load_iris()
X = iris["data"][:, (2, 3)]  # 花瓣长度与花瓣宽度  petal length, petal width
y = iris["target"]
setosa_or_versicolor = (y == 0) | (y == 1)
X = X[setosa_or_versicolor]
y = y[setosa_or_versicolor]
# SVM Classifier model
svm_clf = SVC(kernel="linear", C=float("inf"))
svm_clf.fit(X, y)
def plot_svc_decision_boundary(svm_clf, xmin, xmax):
    # 获取决策边界的w和b
    w = svm_clf.coef_[0]
    b = svm_clf.intercept_[0]

    # At the decision boundary, w0*x0 + w1*x1 + b = 0
    # => x1 = -w0/w1 * x0 - b/w1
    x0 = np.linspace(xmin, xmax, 200)
    # 画中间的粗线
    decision_boundary = -w[0]/w[1] * x0 - b/w[1]
    # 计算间隔
    margin = 1/w[1]
    gutter_up = decision_boundary + margin
    gutter_down = decision_boundary - margin
    # 获取支持向量
    svs = svm_clf.support_vectors_
    plt.scatter(svs[:, 0], svs[:, 1], s=180, facecolors='#FFAAAA')
    plt.plot(x0, decision_boundary, "k-", linewidth=2)
    plt.plot(x0, gutter_up, "k--", linewidth=2)
    plt.plot(x0, gutter_down, "k--", linewidth=2)
plt.title("大间隔分类", fontsize=16)
plt.rcParams['font.sans-serif']=['SimHei'] #显示中文标签
plt.rcParams['axes.unicode_minus']=False
plot_svc_decision_boundary(svm_clf, 0, 5.5)
plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs")
plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo")
plt.xlabel("Petal length", fontsize=14)
plt.axis([0, 5.5, 0, 2])
plt.show()

月亮数据集

import matplotlib.pyplot as plt
from sklearn.pipeline import Pipeline
import numpy as np
import matplotlib as mpl
from sklearn.datasets import make_moons
from sklearn.preprocessing import PolynomialFeatures
from sklearn.preprocessing import StandardScaler
from sklearn.svm import LinearSVC
# 为了显示中文
mpl.rcParams['font.sans-serif'] = [u'SimHei']
mpl.rcParams['axes.unicode_minus'] = False
X, y = make_moons(n_samples=100, noise=0.15, random_state=42)
def plot_dataset(X, y, axes):
    plt.plot(X[:, 0][y==0], X[:, 1][y==0], "bs")
    plt.plot(X[:, 0][y==1], X[:, 1][y==1], "g^")
    plt.axis(axes)
    plt.grid(True, which='both')
    plt.xlabel(r"$x_1$", fontsize=20)
    plt.ylabel(r"$x_2$", fontsize=20, rotation=0)
    plt.title("月亮数据",fontsize=20)
plot_dataset(X, y, [-1.5, 2.5, -1, 1.5])
plt.show()

k-means聚类分析

鸢尾花数据集

from sklearn import datasets
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
#加载数据集
lris_df = datasets.load_iris()
#print(lris_df) 
#挑选第2列，花瓣的长度
x_axis = lris_df.data[:,2]
#print(x_axis)
#挑选第三列，花瓣的宽度
y_axis = lris_df.data[:,3]
#print(y_axis)
#这里已经知道了分2类，其他分类这里的参数需要调试
model = KMeans(n_clusters=2)
#训练模型
model.fit(lris_df.data)
prddicted_label= model.predict([[6.3, 3.3, 6, 2.5]])
all_predictions = model.predict(lris_df.data)
#plt.plot(a, b, "bs")
plt.xlabel('花瓣的长度')
plt.ylabel('花瓣的宽度')
plt.rcParams['font.sans-serif']=['SimHei'] #显示中文标签
plt.rcParams['axes.unicode_minus']=False
#打印出来对150条数据的聚类散点图
plt.scatter(x_axis, y_axis, c=all_predictions)
plt.show()

月亮数据集

from sklearn.datasets import make_moons
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
import numpy as np
X, y = make_moons(n_samples=100, noise=0.15, random_state=42)
#X是一个100X2维度的，分别选取两列的数据
X1=X[:,0]
X2=X[:,1]
#这里已经知道了分2类，其他分类这里的参数需要调试
model = KMeans(n_clusters=2)
#训练模型
model.fit(X)
#print(z[50])
#选取行标为50的那条数据，进行预测
prddicted_label= model.predict([[-0.22452786,1.01733299]])
#预测全部100条数据
all_predictions = model.predict(X)
#plt.plot(a, b, "bs")
#打印聚类散点图
plt.scatter(X1, X2, c=all_predictions)
plt.show()