sklearn6_生成分类数据

 python机器学习-乳腺癌细胞挖掘（博主亲自录制视频）

https://study.163.com/course/introduction.htm?courseId=1005269003&utm_campaign=commission&utm_source=cp-400000000398149&utm_medium=share

生成2类数据

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 preprocessing
import numpy as np
#生成分类数据的分类器
from sklearn.datasets.samples_generator import make_classification
#自动生成训练数据和测试数据
from sklearn.cross_validation import train_test_split
#导入支持向量模型
from sklearn.svm import SVC
import matplotlib.pyplot as plt

x,y=make_classification(n_samples=300,n_features=2,n_redundant=0,n_informative=2,random_state=22,n_clusters_per_class=1,scale=100)

#c=y表示color为黄色
plt.scatter(x[:,0],x[:,1],c=y)
plt.show()

　　

生成4类数据

# -*- coding: utf-8 -*-
"""
Created on Sun Jan  7 15:54:56 2018

@author: Administrator
"""

from sklearn import preprocessing
import numpy as np
#生成分类数据的分类器
from sklearn.datasets.samples_generator import make_classification
#自动生成训练数据和测试数据
from sklearn.cross_validation import train_test_split
#导入支持向量模型
from sklearn.svm import SVC
import matplotlib.pyplot as plt

#n_classes=4生成4类数据
x,y=make_classification(n_classes=4,n_samples=300,n_features=2,n_redundant=0,n_informative=2,random_state=22,n_clusters_per_class=1,scale=100)

#c=y表示color为黄色
plt.scatter(x[:,0],x[:,1],c=y)
plt.show()

　　

# -*- coding: utf-8 -*-
"""
Created on Sun Jan  7 16:51:38 2018

@author: Administrator
"""

import matplotlib.pyplot as plt  
  
from sklearn.datasets import make_classification  
from sklearn.datasets import make_blobs  
from sklearn.datasets import make_gaussian_quantiles  
from sklearn.datasets import make_hastie_10_2  
  
plt.figure(figsize=(8, 8))  
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')  
X1, Y1 = make_classification(n_samples=1000,n_features=2, n_redundant=0, n_informative=2,  
                             n_clusters_per_class=1)  
plt.scatter(X1[:, 0], X1[:, 1], marker='o', c=Y1)  
  
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')  
X1, Y1 = make_blobs(n_samples=1000,n_features=2, centers=3)  
plt.scatter(X1[:, 0], X1[:, 1], marker='o', c=Y1)  
  
plt.subplot(426)  
plt.title("Gaussian divided into four quantiles", fontsize='small')  
X1, Y1 = make_gaussian_quantiles(n_samples=1000,n_features=2, n_classes=4)  
plt.scatter(X1[:, 0], X1[:, 1], marker='o', c=Y1)  
  
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()  

# -*- coding: utf-8 -*-
"""
Created on Sun Jan  7 16:29:35 2018

@author: Administrator
"""

import matplotlib.pyplot as plt  
  
from sklearn.datasets import make_classification  
from sklearn.datasets import make_blobs  
from sklearn.datasets import make_gaussian_quantiles  
from sklearn.datasets import make_hastie_10_2  

#画布的大小为长20cm高20cm
plt.figure(figsize=(15,10))

#标题，fontsize为标题字体大小
plt.title("Gaussian divided into six quantiles", fontsize='large')  
X1, Y1 = make_gaussian_quantiles(n_samples=1000,n_features=2, n_classes=6)  

#绘制点，X1[:, 0]为点的x列表值， X1[:, 1]为点的y列表值， c=Y1表示颜色，c为color缩写
plt.scatter(X1[:, 0], X1[:, 1], marker='o', c=Y1)  

　　

# -*- coding: utf-8 -*-
"""
Created on Sun Jan  7 16:51:38 2018

@author: Administrator
"""

  
from sklearn.datasets import make_circles  
from sklearn.datasets import make_moons  
import matplotlib.pyplot as plt  
import numpy as np  
  
#画布的大小为长20cm高20cm
plt.figure(figsize=(15,10))

fig=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()  

　　

 https://study.163.com/provider/400000000398149/index.htm?share=2&shareId=400000000398149（ 欢迎关注博主主页，学习python视频资源，还有大量免费python经典文章）