9种常用的机器学习算法实现

import matplotlib.pyplot as pltimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.datasets import make_classification
# SVMfrom sklearn import svm# 1. 准备数据svm_X_train, svm_y_train = make_classification(n_features=2, n_redundant=0, n_informative=2,                           random_state=1, n_clusters_per_class=1, n_classes=4)# 2. 构造训练与测试集l, r = svm_X_train[:, 0].min() - 1, svm_X_train[:, 0].max() + 1b, t = svm_X_train[:, 1].min() - 1,svm_X_train[:, 1].max() + 1n = 1000grid_x, grid_y = np.meshgrid(np.linspace(l, r, n), np.linspace(b, t, n))svm_X_test = np.column_stack((grid_x.ravel(), grid_y.ravel()))# 3. 训练模型# svm_model = RandomForestClassifier(max_depth=4)svm_model = svm.SVC(kernel='rbf', gamma=1, C=0.0001).fit(svm_X_train, svm_y_train)svm_model.fit(svm_X_train, svm_y_train)# 4. 预测数据svm_y_pred = svm_model.predict(svm_X_test)# 5. 可视化grid_z = svm_y_pred.reshape(grid_x.shape)plt.figure('SVM')plt.title('SVM')plt.pcolormesh(grid_x, grid_y, grid_z, cmap='Blues')plt.scatter(svm_X_train[:, 0], svm_X_train[:, 1], s=30, c=svm_y_train, cmap='pink')plt.show()

import matplotlib.pyplot as pltimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.datasets.samples_generator import make_blobs
# K-means 任务为聚类 n_classes=5from sklearn.cluster import KMeans
# 1. 准备数据kmeans_X_data, kmeans_y_data = make_blobs(n_samples=500, centers=5, cluster_std=0.60, random_state=0)# 2. 训练模型kmeans_model = KMeans(n_clusters=5)kmeans_model.fit(kmeans_X_data)# 3. 预测模型kmeans_y_pred = kmeans_model.predict(kmeans_X_data)# 4. 可视化plt.figure('K-Means')plt.title('K-Means')plt.scatter(kmeans_X_data[:,0], kmeans_X_data[:, 1], s=50)plt.scatter(kmeans_X_data[:, 0], kmeans_X_data[:, 1], c=kmeans_y_pred, s=50, cmap='viridis')centers = kmeans_model.cluster_centers_plt.scatter(centers[:,0], centers[:, 1], c='red', s=80, marker='x')plt.show()

import matplotlib.pyplot as pltimport numpy as npfrom sklearn.model_selection import train_test_splitfrom sklearn.datasets import make_classification
# PCAfrom sklearn.decomposition import PCAfrom sklearn.datasets import load_iris
# 1. 准备数据pca_data=load_iris()pca_X_data=pca_data.datapca_y_data=pca_data.target# 2. 训练模型, 维度为2pca_model=PCA(n_components=2)  # 3. 降维reduced_X=pca_model.fit_transform(pca_X_data)# 4. 可视化red_x,red_y=[],[]blue_x,blue_y=[],[]green_x,green_y=[],[]
for i in range(len(reduced_X)): if pca_y_data[i] ==0:  red_x.append(reduced_X[i][0])  red_y.append(reduced_X[i][1]) elif pca_y_data[i]==1:  blue_x.append(reduced_X[i][0])  blue_y.append(reduced_X[i][1]) else:  green_x.append(reduced_X[i][0])  green_y.append(reduced_X[i][1])
plt.figure('PCA')plt.title('PCA')plt.scatter(red_x,red_y,c='r')plt.scatter(blue_x,blue_y,c='b')plt.scatter(green_x,green_y,c='g')plt.show()