1、生成回归模型的数据
X, y, coef = datasets.make_regression(n_samples=100,
n_features=1,
n_targets=1,
noise=10,
coef=True)
print("X的数据为:\n", X)
print("y的数据为:\n", y)
print("coef的数据为:\n", coef)
plt.scatter(X, y, color='black')
plt.plot(X, X*coef, color='blue', linewidth=3)
plt.show()

2、分类模型随机数据
from sklearn.datasets import make_classification
X1, Y1 = make_classification(n_samples=400, n_features=2, n_redundant=0,
n_clusters_per_class=1, n_classes=3, n_informative=2)
print(X1)
plt.scatter(X1[:, 0], X1[:, 1], marker='o', c=Y1)
plt.show()

3、聚类模型随机数据
from sklearn.datasets import make_blobs
X, y = make_blobs(n_samples=1000, n_features=2, centers=[[-1, -1], [1, 1], [2, 2]], cluster_std=[0.4, 0.5, 0.2])
plt.scatter(X[:, 0], X[:, 1], marker='o', c=y)
plt.show()

4、分组正态分布混合数据
from sklearn.datasets import make_gaussian_quantiles
X1, Y1 = make_gaussian_quantiles(n_samples=1000, n_features=2, n_classes=3, mean=[1, 2], cov=2)
plt.scatter(X1[:, 0], X1[:, 1], marker='o', c=Y1)
plt.show()

引用:随机数据生成