20201112-学习用决策树算法分类鸢尾花

最新推荐文章于 2023-05-25 16:39:12 发布

WhenEyesOpen

最新推荐文章于 2023-05-25 16:39:12 发布

阅读量228

点赞数

文章标签：决策树算法 python 机器学习

本文链接：https://blog.csdn.net/WhenEyesOpen/article/details/109660915

版权

本文通过Python的sklearn库，详细介绍了如何利用CART决策树算法对鸢尾花数据集进行分类。首先，对数据进行预处理，然后通过train_test_split进行数据划分，构建并训练决策树模型，并对训练集和测试集的表现进行评估。最后，用可视化手段展示了训练数据的分布及预测结果。

摘要由CSDN通过智能技术生成

https://dpaste.com/3BCX6MP5J

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm # 直接用sklearn中的包
from sklearn import datasets

%matplotlib inline

读iris数据

data,target = datasets.load_iris(return_X_y=True)
data_tmp1=data[:,0:2]
x=data_tmp1[:,0]
y=data_tmp1[:,1]

a1=0
x1=x[targeta1]
y1=y[targeta1]
plt.plot(x1,y1,‘r.’)

a1=1
x1=x[targeta1]
y1=y[targeta1]
plt.plot(x1,y1,‘b*’)
print(data.size())
print(data.size
print(data.size)
print(data.size())
print(np.size(data))
print(np.size(data))
print(np.size(data,1))
print(np.size(data,2))
print(np.size(data))
print(np.size(data,1))
print(np.size(data,0))
target<=1
data01=data(target<=1）
data01=data(target<=1)
data01=data[target<=1]
print(data01)
data01=data[target<=1]
target01=target[target<=1]
print(target01)
print(np.size(data01))
print(np.size(data01,1))
print(np.size(data01,0))
print(np.size(data01,0))
print(np.size(data01,1))
data01=data[target<=1][0:2]
target01=target[target<=1]
print(np.size(data01,0))
print(np.size(data01,1))
data01=data[target<=1,0:2]
target01=target[target<=1]
print(np.size(data01,0))
print(np.size(data01,1))
x=data01[:,0]
y=data01[:,1]

a1=0
x1=x[target01a1]
y1=y[target01a1]
plt.plot(x1,y1,‘r.’)

a1=1
x1=x[target01a1]
y1=y[target01a1]
plt.plot(x1,y1,‘b*’)
random.sample(data01, 4)

输入相应的包、数据源、画图线

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm # 直接用sklearn中的包
from sklearn import datasets
import random

%matplotlib inline
random.sample(data01, 4)
print(np.size(data01,0))
print(np.size(data01,1))
data000=pd.DataFrame({‘x1’:data01[0],
‘x2’:data01[1],
‘y’:target01,
})
print(data000)

输入相应的包、数据源、画图线

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm # 直接用sklearn中的包
from sklearn import datasets
import random
import panda as pd

%matplotlib inline

输入相应的包、数据源、画图线

import numpy as np
import matplotlib.pyplot as plt
from sklearn import svm # 直接用sklearn中的包
from sklearn import datasets
import random
import pandas as pd

%matplotlib inline
print(np.size(data01,0))
print(np.size(data01,1))
data000=pd.DataFrame({‘x1’:data01[0],
‘x2’:data01[1],
‘y’:target01,
})
print(data000)
print(np.size(data01,0))
print(np.size(data01,1))
data000=pd.DataFrame({‘x1’:data01[:,0],
‘x2’:data01[:,1],
‘y’:target01,
})
print(data000)

random.sample(data000, 4)
print(np.size(data000,1))
print(np.size(data000,0))
a_tmp=range(np.size(data000,0))
print(a_tmp)
a_tmp=range(np.size(data000,0))
print(a_tmp[0])
a_tmp=range(np.size(data000,0))
print(a_tmp[7])
a_tmp=range(np.size(data000,0))
a_tmp2=random.sample(a_tmp,50)
print(a_tmp2)
a_tmp=range(np.size(data000,0))
a_tmp2=random.sample(a_tmp,50)
print(a_tmp2)
a_tmp=range(np.size(data000,0))
a_tmp2=random.sample(a_tmp,50) #随机选择50个数据
a_tmp3=a_tmp(^a_tmp3)
print(a_tmp2)
a_tmp=range(np.size(data000,0))
a_tmp2=random.sample(a_tmp,50) #随机选择50个数据
a_tmp3=a_tmp(a_tmp2)
print(a_tmp2)
print(a_tmp3)
a_tmp=range(np.size(data000,0))
a_tmp2=random.sample(a_tmp,50) #随机选择50个数据
a_tmp3=a_tmp[a_tmp2]
print(a_tmp2)
print(a_tmp3)
random.shuffle(data000)
random.shuffle(a_tmp)
random.shuffle(data000)
random.shuffle(x)
print(random.shuffle(x))
print(ra