机器学习实验5——肿瘤预测（AdaBoost）

实验5 AdaBoost 实操项目：肿瘤预测（AdaBoost）

【实验内容】

 基于威斯康星乳腺癌数据集，使用AdaBoost算法实现肿瘤预测。

【实验要求】

 1.加载sklearn自带的数据集，使用DataFrame形式探索数据。
 
 2.划分训练集和测试集，检查训练集和测试集的平均癌症发生率。
 
 3.配置模型，训练模型，模型预测，模型评估。
 
  （1）构建一棵最大深度为2的决策树弱学习器，训练、预测、评估。
  
  （2）再构建一个包含50棵树的AdaBoost集成分类器（步长为3），训练、预测、评估。   
  
      参考：将决策树的数量从1增加到50，步长为3。输出集成后的准确度。
      
  （3）将（2）的性能与弱学习者进行比较。
  
 4.绘制准确度的折线图，x轴为决策树的数量，y轴为准确度。

AdaBoostClassifier参数解释:

base_estimator：弱分类器，默认是CART分类树：DecisionTressClassifier
algorithm：在scikit-learn实现了两种AdaBoost分类算法，即SAMME和SAMME.R， SAMME就是AdaBoost算法，指Discrete。AdaBoost.SAMME.R指Real AdaBoost，返回值不再是离散的类型，而是一个表示概率的实数值。SAMME.R的迭代一般比SAMME快，默认算法是SAMME.R。因此，base_estimator必须使用支持概率预测的分类器。
n_estimator：最大迭代次数，默认50。在实际调参过程中，常常将n_estimator和学习率learning_rate一起考虑。
learning_rate：每个弱分类器的权重缩减系数v。fk(x)=fk−1∗ak∗Gk(x)f_k(x)=f_{k-1}a_kG_k(x)f k(x)=f k−1∗a k∗G k(x)。较小的v意味着更多的迭代次数，默认是1，也就是v不发挥作用。

In [1]

#1.加载sklearn自带的数据集，使用DataFrame形式探索数据。
from sklearn.datasets import load_breast_cancer
import pandas as pd
load_cancer=load_breast_cancer()
cancer_data=pd.DataFrame(load_cancer.data)
cancer_target=pd.DataFrame(load_cancer.target)
print(cancer_data[:3],'\n',cancer_target[:3])
#2.划分训练集和测试集，检查训练集和测试集的平均癌症发生率。
from sklearn.model_selection import train_test_split
data_train,data_test,target_train,target_test=train_test_split(cancer_data,cancer_target,test_size=0.2)
#检查癌症发生率,即求平均值
test_mean=target_test[0].mean()
train_mean=target_train[0].mean()
print('训练集癌症发生率为:',train_mean)
print('测试集癌症发生率为:',test_mean)

      0      1      2       3        4        5       6        7       8   \
0  17.99  10.38  122.8  1001.0  0.11840  0.27760  0.3001  0.14710  0.2419   
1  20.57  17.77  132.9  1326.0  0.08474  0.07864  0.0869  0.07017  0.1812   
2  19.69  21.25  130.0  1203.0  0.10960  0.15990  0.1974  0.12790  0.2069   

        9   ...     20     21     22      23      24      25      26      27  \
0  0.07871  ...  25.38  17.33  184.6  2019.0  0.1622  0.6656  0.7119  0.2654   
1  0.05667  ...  24.99  23.41  158.8  1956.0  0.1238  0.1866  0.2416  0.1860   
2  0.05999  ...  23.57  25.53  152.5  1709.0  0.1444  0.4245  0.4504  0.2430   

       28       29  
0  0.4601  0.11890  
1  0.2750  0.08902  
2  0.3613  0.08758  

[3 rows x 30 columns] 
    0
0  0
1  0
2  0
训练集癌症发生率为: 0.6307692307692307
测试集癌症发生率为: 0.6140350877192983

In [2]

#3.配置模型，训练模型，模型预测，模型评估。
 
#（1）构建一棵最大深度为2的决策树弱学习器，训练、预测、评估。
from sklearn import tree # 导入决策树包
clf_low = tree.DecisionTreeClassifier(max_depth=2) #加载决策树模型
clf_low.fit(data_train,target_train)#训练
pred_low=clf_low.predict(data_test)#预测
from sklearn.metrics import accuracy_score
print('tree_Accuracy:%s'%accuracy_score(target_test,pred_low))#评估
print('*********************')
#（2）再构建一个包含50棵树的AdaBoost集成分类器（步长为3），训练、预测、评估。   
from sklearn.model_selection import cross_val_score
from sklearn.ensemble import AdaBoostClassifier
scores=[]
for i in range(1,51,3):
    clf=AdaBoostClassifier(n_estimators=i)
    clf.fit(data_train,target_train)
    pred=clf.predict(data_test)
    scores.append(accuracy_score(target_test,pred))
    print('n_estimators=',i,'\nAccuracy=',accuracy_score(target_test,pred))

    #  参考：将决策树的数量从1增加到50，步长为3。输出集成后的准确度。
      
#（3）将（2）的性能与弱学习者进行比较。
import matplotlib.pyplot as plt
import numpy as np
plt.figure()
plt.xlabel('accuracy_score')
plt.ylabel('n_estimators')
plt.axhline(y=accuracy_score(target_test,pred_low),c='red')
plt.plot(range(1,51,3),scores)
plt.show()

tree_Accuracy:0.9298245614035088
*********************
n_estimators= 1 
Accuracy= 0.9035087719298246
n_estimators= 4 
Accuracy= 0.9385964912280702
n_estimators= 7 
Accuracy= 0.9385964912280702
n_estimators= 10 
Accuracy= 0.956140350877193
n_estimators= 13 
Accuracy= 0.956140350877193
n_estimators= 16 
Accuracy= 0.956140350877193

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

n_estimators= 19 
Accuracy= 0.956140350877193
n_estimators= 22 
Accuracy= 0.9649122807017544
n_estimators= 25 
Accuracy= 0.956140350877193

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

n_estimators= 28 
Accuracy= 0.956140350877193
n_estimators= 31 
Accuracy= 0.9649122807017544
n_estimators= 34 
Accuracy= 0.956140350877193

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

n_estimators= 37 
Accuracy= 0.956140350877193
n_estimators= 40 
Accuracy= 0.9649122807017544

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

n_estimators= 43 
Accuracy= 0.9649122807017544
n_estimators= 46 
Accuracy= 0.9824561403508771
n_estimators= 49 
Accuracy= 0.9824561403508771

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)
/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  y = column_or_1d(y, warn=True)

<Figure size 432x288 with 1 Axes>

posted @ 2022-03-28 15:19 XDawned 阅读(301) 评论(0) 收藏举报

刷新页面返回顶部

xdawned

机器学习实验5——肿瘤预测（AdaBoost）

实验5 AdaBoost 实操项目：肿瘤预测（AdaBoost）

【实验内容】

【实验要求】

AdaBoostClassifier参数解释:

公告