'''linnerud数据集，多元回归使用。样本数据集的特征默认是一个(20, 3)大小的矩阵，样本值也是(20, 3)大小的矩阵。也就是3种特征，有3个输出结果，所以系数矩阵w为(3, 3)'''from sklearn.datasets import load_linnerudfrom sklearn import linear_modellinnered = load_linnerud()data = linnered.dataprint(data)target = linnered.targetprint(target)print(data.shape)print(target.shape)print('系数矩阵:n',linear_model.LinearRegression().fit(data,target).coef_) '''图像样本数据集'''from sklearn.datasets import load_sample_imageimport matplotlib.pyplot as pltimg = load_sample_image('china.jpg')plt.imshow(img)plt.show()
'''sklearn.datasets.make_classification(n_samples=100, n_features=20, n_informative=2, n_redundant=2, n_repeated=0, n_classes=2, n_clusters_per_class=2, weights=None, flip_y=0.01, class_sep=1.0, hypercube=True,shift=0.0, scale=1.0, shuffle=True, random_state=None) 通常用于分类算法。 n_features :特征个数= n_informative + n_redundant + n_repeated n_informative：多信息特征的个数 n_redundant：冗余信息，informative特征的随机线性组合 n_repeated ：重复信息，随机提取n_informative和n_redundant 特征 n_classes：分类类别 n_clusters_per_class ：某一个类别是由几个cluster构成的'''from sklearn import datasetsimport matplotlib.pyplot as plt data,target = datasets.make_classification(n_samples=100,n_features=2, n_informative=2,n_redundant=0,n_repeated=0, n_classes=2,n_clusters_per_class=1)print(data.shape)print(target.shape)plt.scatter(data[:,0],data[:,1],c=target)plt.show()
''' 其它生成分类样本的函数 make_blobs函数会根据用户指定的特征数量、中心点数量、 范围等来生成几类数据，这些数据可用于测试聚类算法的效果。 其中： n_samples是待生成的样本的总数。 n_features是每个样本的特征数。 centers表示类别数。 cluster_std表示每个类别的方差，例如我们希望生成2类数据， 其中一类比另一类具有更大的方差，可以将cluster_std设置为[1.0,3.0]。'''import matplotlib.pyplot as pltfrom sklearn.datasets import make_classificationfrom sklearn.datasets import make_blobsfrom sklearn.datasets import make_gaussian_quantilesfrom sklearn.datasets import make_hastie_10_2plt.figure(figsize=(10,10)) # 创建一个10 * 10 英寸的图像plt.subplots_adjust(bottom=.05,top=.9,left=.05,right=.95)plt.subplot(421)plt.title("One informative feature, one cluster per class",fontsize='small')X1,Y1= make_classification(n_samples=1000,n_features=2,n_redundant=0,n_informative=1,n_clusters_per_class=1)plt.scatter(X1[:,0],X1[:,1],marker='o',c=Y1)plt.subplot(422)plt.title("Two informative features, one cluster per class", fontsize='small')X2,Y2 = make_classification(n_samples=1000,n_features=2,n_redundant=0,n_informative=2)plt.scatter(X2[:,0],X2[:,1],marker='o',c=Y2)plt.subplot(423)plt.title("Two informative features, two clusters per class", fontsize='small')X2,Y2 = make_classification(n_samples=1000,n_features=2,n_redundant=0,n_informative=2)plt.scatter(X2[:,0],X2[:,1],marker='o',c=Y2)plt.subplot(424)plt.title("Multi-class, two informative features, one cluster",fontsize='small')X1,Y1= make_classification(n_samples=1000,n_features=2,n_redundant=0,n_informative=2,n_clusters_per_class=1,n_classes=3)plt.scatter(X1[:,0],X1[:,1],marker='o',c=Y1)plt.subplot(425)plt.title("Three blobs", fontsize='small')# 1000个样本，2个属性，3种类别，方差分别为1.0,3.0,2.0X1,Y1 = make_blobs(n_samples=1000,n_features=2,centers=3,cluster_std=[1.0,3.0,2.0])plt.scatter(X1[:,0],X1[:,1],marker='o',c=Y1)plt.subplot(426)plt.title("Gaussian divided into four quantiles", fontsize='small')# make_gaussian_quantiles函数利用稳重的裙子分位点区分不同数据X1,Y1 = make_gaussian_quantiles(n_samples=1000,n_features=2,n_classes=4)plt.scatter(X1[:,0],X1[:,1],marker='o',c=Y1)# make_hastie_10_2函数利用Hastie算法，生成2分类数据plt.subplot(427)plt.title("hastie data ", fontsize='small')X1,Y1 = make_hastie_10_2(n_samples=1000) # plt.scatter(X1[:,0],X1[:,1],marker='o',c=Y1)plt.show() ''' 自定义生成圆形和月牙形分类数据 sklearn.datasets.make_circles(n_samples=100, shuffle=True, noise=None, random_state=None, factor=0.8) 生成环形 factor ：外圈与内圈的尺度因子<1 sklearn.datasets.make_moons(n_samples=100, shuffle=True, noise=None, random_state=None) 生成半环形'''from sklearn.datasets import make_circlesfrom sklearn.datasets import make_moonsimport matplotlib.pyplot as pltfig = plt.figure(1)x1,y1 = make_circles(n_samples=1000,factor=0.5,noise=0.1)plt.subplot(121)plt.title('make_circles function example')plt.scatter(x1[:,0],x1[:,1],marker='o',c=y1)plt.subplot(122)x1,y1 = make_moons(n_samples=1000,noise=0.1)plt.title('make_moons function example')plt.scatter(x1[:,0],x1[:,1],marker='o',c=y1)plt.show()