1.LDA+鳶尾花

import numpy as np import matplotlib.pyplot as plt from sklearn import datasetsdef LDA(X, y):#根據y等于0或1分類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])len1 = len(X1)len2 = len(X2) mju1 = np.mean(X1, axis=0)#求中心點mju2 = np.mean(X2, axis=0)cov1 = np.dot((X1 - mju1).T, (X1 - mju1))cov2=np.dot((X2 - mju2).T, (X2 - mju2))Sw = cov1 + cov2a=mju1-mju2a=(np.array([a])).T#計算ww=(np.dot(np.linalg.inv(Sw),a))#計算投影直線#k=w[1]/w[0]#b=0;#x=np.arange(0,5)#yy=k*x+b#plt.plot(x,yy)X1_new =func(X1, w)X2_new = func(X2, w)y1_new = [1 for i in range(len1)]y2_new = [2 for i in range(len2)]return X1_new,X2_new,y1_new,y2_new def func(x, w):return np.dot((x), w)iris = datasets.load_iris() X = iris["data"][:, (2, 3)] # 花瓣長度與花瓣寬度 petal length, petal width y = iris["target"] #print(y) setosa_or_versicolor = (y == 0) | (y == 1) X = X[setosa_or_versicolor] y = y[setosa_or_versicolor] #print(Sw) x1_new, X2_new, y1_new, y2_new = LDA(X, y) plt.xlabel('花瓣長度') plt.ylabel('花瓣寬度') plt.rcParams['font.sans-serif']=['SimHei'] #顯示中文標簽 plt.rcParams['axes.unicode_minus']=False plt.scatter(X[:, 0], X[:, 1], marker='o', c=y) plt.show()

2.LDA+月亮

import numpy as np import matplotlib.pyplot as plt from sklearn import datasetsdef LDA(X, y):#根據y等于0或1分類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])len1 = len(X1)len2 = len(X2) mju1 = np.mean(X1, axis=0)#求中心點mju2 = np.mean(X2, axis=0)cov1 = np.dot((X1 - mju1).T, (X1 - mju1))cov2=np.dot((X2 - mju2).T, (X2 - mju2))Sw = cov1 + cov2a=mju1-mju2a=(np.array([a])).Tw=(np.dot(np.linalg.inv(Sw),a))X1_new =func(X1, w)X2_new = func(X2, w)y1_new = [1 for i in range(len1)]y2_new = [2 for i in range(len2)]def func(x, w):return np.dot((x), w)X, y = datasets.make_moons(n_samples=100, noise=0.15, random_state=42)#print(Sw) #x1_new, X2_new, y1_new, y2_new = LDA(X, y) plt.scatter(X[:, 0], X[:, 1], marker='o', c=y) plt.show()

3.K-means+鳶尾花

from sklearn import datasets import matplotlib.pyplot as plt from sklearn.cluster import KMeans #加載數據集 lris_df = datasets.load_iris() #print(lris_df) #挑選第2列，花瓣的長度 x_axis = lris_df.data[:,2] #print(x_axis) #挑選第三列，花瓣的寬度 y_axis = lris_df.data[:,3] #print(y_axis) #這里已經知道了分2類，其他分類這里的參數需要調試 model = KMeans(n_clusters=2) #訓練模型 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('花瓣的長度') plt.ylabel('花瓣的寬度') plt.rcParams['font.sans-serif']=['SimHei'] #顯示中文標簽 plt.rcParams['axes.unicode_minus']=False #打印出來對150條數據的聚類散點圖 plt.scatter(x_axis, y_axis, c=all_predictions) plt.show()

4.K-means+月亮

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是一個100X2維度的，分別選取兩列的數據 X1=X[:,0] X2=X[:,1] #這里已經知道了分2類，其他分類這里的參數需要調試 model = KMeans(n_clusters=2) #訓練模型 model.fit(X) #print(z[50]) #選取行標為50的那條數據，進行預測 prddicted_label= model.predict([[-0.22452786,1.01733299]]) #預測全部100條數據 all_predictions = model.predict(X) #plt.plot(a, b, "bs") #打印聚類散點圖 plt.scatter(X1, X2, c=all_predictions) plt.show()

5.SVM+鳶尾花

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)] # 花瓣長度與花瓣寬度 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):# 獲取決策邊界的w和bw = svm_clf.coef_[0]b = svm_clf.intercept_[0]# At the decision boundary, w0*x0 + w1*x1 + b = 0# => x1 = -w0/w1 * x0 - b/w1x0 = np.linspace(xmin, xmax, 200)# 畫中間的粗線decision_boundary = -w[0]/w[1] * x0 - b/w[1]# 計算間隔margin = 1/w[1]gutter_up = decision_boundary + margingutter_down = decision_boundary - margin# 獲取支持向量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("大間隔分類", fontsize=16) plt.rcParams['font.sans-serif']=['SimHei'] #顯示中文標簽 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()

6.SVM+月亮

from sklearn.svm import SVC from sklearn import datasets import matplotlib.pyplot as plt import numpy as np X, y = datasets.make_moons(n_samples=100, noise=0.15, random_state=42) svm_clf = SVC(kernel="linear") svm_clf.fit(X, y) def plot_svc_decision_boundary(svm_clf, xmin, xmax):# 獲取決策邊界的w和bw = svm_clf.coef_[0]b = svm_clf.intercept_[0]x0 = np.linspace(xmin, xmax, 200)# 畫中間的粗線decision_boundary = -w[0]/w[1] * x0 - b/w[1]# 計算間隔margin = 1/w[1]gutter_up = decision_boundary + margingutter_down = decision_boundary - margin# 獲取支持向量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) plot_svc_decision_boundary(svm_clf, -2, 3) plt.plot(X[:, 0][y==1], X[:, 1][y==1], "bs") plt.plot(X[:, 0][y==0], X[:, 1][y==0], "yo") plt.axis([-1, 2.5, -0.75, 1.25]) plt.show()

總結

以上是生活随笔為你收集整理的【机器学习11】LAD,K-means,SVM分析鸢尾花和月亮数据集的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。