机器学习实验之肿瘤预测（决策树）

肿瘤预测（决策树）

【实验内容】

 基于威斯康辛乳腺癌数据集，采用决策树的方法进行肿瘤预测。

【实验要求】

1.加载sklearn自带的威斯康星乳腺癌数据集，探索数据。

2.进行数据集分割。

3.配置决策树模型。

4.训练决策树模型。

5.模型预测。

6.模型评估。

7.参数调优。可以根据评估结果，对模型设置或调整为更优的参数，使评估结果更准确。

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import numpy as np
from sklearn import tree # 导入决策树包

## 加载sklearn自带的威斯康星乳腺癌数据集，探索数据

cancers = load_breast_cancer()
cancers

## 进行数据集分割

x_train, x_test, y_train, y_test = train_test_split(
    cancers.data, cancers.target, test_size=0.30)
print("x_train.shape:", x_train.shape)
print("y_train.shape:", y_train.shape)
print("x_test.shape:", x_test.shape)
print("y_test.shape:", y_test.shape)

## 配置决策树模型

clf = tree.DecisionTreeClassifier() #加载决策树模型

## 训练决策树模型

clf.fit(x_train, y_train)

## 模型预测

predictions = clf.predict(x_test)

## 模型评估

from sklearn.metrics import accuracy_score # 导入准确率评价指标
print('Accuracy:%s'% accuracy_score(y_test, predictions))

## 参数调优

### criterion

clf = tree.DecisionTreeClassifier(criterion = 'entropy') #更换criterion参数
clf.fit(x_train, y_train)
predictions = clf.predict(x_test)
print('Accuracy:%s'% accuracy_score(y_test, predictions))

### max_depth

clf = tree.DecisionTreeClassifier(criterion = 'entropy',max_depth=2) 
clf.fit(x_train, y_train)
predictions = clf.predict(x_test)
print('Accuracy:%s'% accuracy_score(y_test, predictions))
x_train.shape: (398, 30)
y_train.shape: (398,)
x_test.shape: (171, 30)
y_test.shape: (171,)
Accuracy:0.9181286549707602
Accuracy:0.9005847953216374
Accuracy:0.9239766081871345

from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
import numpy as np
from sklearn import tree # 导入决策树包
from jupyterthemes import jtplot
jtplot.style(theme='monokai')  # 选择一个绘图主题

加载sklearn自带的威斯康星乳腺癌数据集，探索数据

cancers = load_breast_cancer()
cancers

{'data': array([[1.799e+01, 1.038e+01, 1.228e+02, ..., 2.654e-01, 4.601e-01,
         1.189e-01],
        [2.057e+01, 1.777e+01, 1.329e+02, ..., 1.860e-01, 2.750e-01,
         8.902e-02],
        [1.969e+01, 2.125e+01, 1.300e+02, ..., 2.430e-01, 3.613e-01,
         8.758e-02],
        ...,
        [1.660e+01, 2.808e+01, 1.083e+02, ..., 1.418e-01, 2.218e-01,
         7.820e-02],
        [2.060e+01, 2.933e+01, 1.401e+02, ..., 2.650e-01, 4.087e-01,
         1.240e-01],
        [7.760e+00, 2.454e+01, 4.792e+01, ..., 0.000e+00, 2.871e-01,
         7.039e-02]]),
 'target': array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1,
        0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0,
        0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 0, 0,
        1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 0, 0,
        1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1,
        1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0,
        0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1,
        1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1, 1,
        1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0,
        0, 0, 1, 0, 0, 0, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0,
        1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,
        1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
        0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0,
        0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0,
        0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 0, 0, 1, 0, 0,
        1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1,
        1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 0, 1, 1, 1, 1,
        1, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0,
        1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1,
        1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1,
        1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1,
        1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
        1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1]),
 'frame': None,
 'target_names': array(['malignant', 'benign'], dtype='

进行数据集分割

x_train, x_test, y_train, y_test = train_test_split(
    cancers.data, cancers.target, test_size=0.30)
print("x_train.shape:", x_train.shape)
print("y_train.shape:", y_train.shape)
print("x_test.shape:", x_test.shape)
print("y_test.shape:", y_test.shape)

x_train.shape: (398, 30)
y_train.shape: (398,)
x_test.shape: (171, 30)
y_test.shape: (171,)

配置决策树模型

clf = tree.DecisionTreeClassifier() #加载决策树模型

训练决策树模型

clf.fit(x_train, y_train)

DecisionTreeClassifier()

模型预测

predictions = clf.predict(x_test)

模型评估

from sklearn.metrics import accuracy_score # 导入准确率评价指标
print('Accuracy:%s'% accuracy_score(y_test, predictions))

Accuracy:0.9122807017543859

参数调优

criterion

clf = tree.DecisionTreeClassifier(criterion = 'entropy') #更换criterion参数
clf.fit(x_train, y_train)
predictions = clf.predict(x_test)
print('Accuracy:%s'% accuracy_score(y_test, predictions))

Accuracy:0.9239766081871345

max_depth

clf = tree.DecisionTreeClassifier(criterion = 'entropy',max_depth=2) 
clf.fit(x_train, y_train)
predictions = clf.predict(x_test)
print('Accuracy:%s'% accuracy_score(y_test, predictions))

Accuracy:0.9415204678362573