一:月亮数据集-make_moons
sklearn.datasets.make_moons(n_samples=100, shuffle=True, noise=None, random_state=None)
重要参数:n_samples:设置样本数量、noise:设置噪声、random_state:设置随机参数(嘿嘿,无所谓,随便设),我们主要讲参数noise
#导入必要库
from sklearn.datasets import make_moons
import numpy as np
from numpy import where
import matplotlib.pyplot as plt
X, yy = make_moons(n_samples=200, random_state=123,noise=0.02) #噪声为0.02
#绘图
# 为每个类的样本创建散点图
for class_value in range(2):
# 获取此类的示例的行索引
row_ix = where(yy == class_value)
# 创建这些样本的散布
plt.scatter(X[row_ix, 0], X[row_ix, 1]) #什么意思?
# 绘制散点图
plt.show()
1:比较不同噪声的影响
# 月亮数据集
plt.figure(figsize=(7,7))
plt.subplot(211)
X, y = make_moons(n_samples=200, random_state=123,noise=0.02)
plt.title("noise=0.02")
plt.scatter(X[:, 0], X[:, 1], c=y)
plt.subplot(212)
X1, y1 = make_moons(n_samples=200, random_state=123,noise=0.1)
plt.title("noise=0.1")
plt.scatter(X1[:, 0], X1[:, 1], c=y1)
<matplotlib.collections.PathCollection at 0x23da1626670>
二:圆环数据–make_circles()
sklearn.datasets.make_circles(n_samples=100, shuffle=True, noise=None, random_state=None, factor=0.8)
重要参数:n_samples:设置样本数量、noise:设置噪声、factor:0 < double < 1 默认值0.8,内外圆之间的比例因子、random_state:设置随机参数(嘿嘿,无所谓,随便设),我们主要讲参数noise、factor
#导入必要库
from sklearn.datasets import make_circles
import numpy as np
from numpy import where
import matplotlib.pyplot as plt
X, yy = make_circles(n_samples=200, random_state=123,