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

# -*- coding: utf-8 -*-
"""
Created on Tue Mar 27 22:59:44 2018

@author: Toby，项目合作QQ：231469242
radius半径
texture结构，灰度值标准差
symmetry对称

决策树找出强因子
worst radius
worst symmetry
worst texture
texture error

"""
import csv,pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import pydotplus
from IPython.display import Image
import graphviz
from sklearn.tree import export_graphviz
from sklearn.datasets import load_breast_cancer
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

cancer=load_breast_cancer()

featureNames=cancer.feature_names
#random_state 相当于随机数种子
X_train,x_test,y_train,y_test=train_test_split(cancer.data,cancer.target,stratify=cancer.target,random_state=42)

list_average_accuracy=[]
depth=range(1,30)
for i in depth:
#max_depth=4限制决策树深度可以降低算法复杂度，获取更精确值
tree= DecisionTreeClassifier(max_depth=i,random_state=0)
tree.fit(X_train,y_train)
accuracy_training=tree.score(X_train,y_train)
accuracy_test=tree.score(x_test,y_test)
average_accuracy=(accuracy_training+accuracy_test)/2.0
#print("average_accuracy:",average_accuracy)
list_average_accuracy.append(average_accuracy)

max_value=max(list_average_accuracy)
#索引是0开头，结果要加1
best_depth=list_average_accuracy.index(max_value)+1
print("best_depth:",best_depth)

best_tree= DecisionTreeClassifier(max_depth=best_depth,random_state=0)
best_tree.fit(X_train,y_train)
accuracy_training=best_tree.score(X_train,y_train)
accuracy_test=best_tree.score(x_test,y_test)

print("decision tree:")
print("accuracy on the training subset:{:.3f}".format(best_tree.score(X_train,y_train)))
print("accuracy on the test subset:{:.3f}".format(best_tree.score(x_test,y_test)))
#print('Feature importances:{}'.format(best_tree.feature_importances_))
#绘图，显示因子重要性
n_features=cancer.data.shape[1]
plt.barh(range(n_features),best_tree.feature_importances_,align='center')
plt.yticks(np.arange(n_features),cancer.feature_names)
plt.title("Decision Tree:")
plt.xlabel('Feature Importance')
plt.ylabel('Feature')
plt.show()

#生成一个dot文件，以后用cmd形式生成图片
export_graphviz(tree,out_file="cancertree.dot",class_names=['malignant','benign'],feature_names=cancer.feature_names,impurity=False,filled=True)

import csv,pandas as pd

import matplotlib.pyplot as plt

import numpy as np

import pydotplus

from IPython.display import Image

import graphviz

from sklearn.tree import export_graphviz

from sklearn.datasets import load_breast_cancer

from sklearn.tree import DecisionTreeClassifier

from sklearn import tree

from sklearn.model_selection import train_test_split

#交叉验证样本平均测试，评分更加

from sklearn.cross_validation import cross_val_score

#交叉验证得分，返回数组

#score_decisionTree=cross_val_score(decisionTree,x,y,cv=5,scoring='accuracy')

#print("cross value decisionTree= score:",score_decisionTree.mean())

cancer=load_breast_cancer()

#数据

data=cancer.data

#分类

target=cancer.target

x=data

y=target

featureNames=cancer.feature_names

#5.决策树

#建立决策树分类器

decisionTree= tree.DecisionTreeClassifier(max_depth=5)

#交叉验证得分，返回数组

score_decisionTree=cross_val_score(decisionTree,x,y,cv=10,scoring='accuracy')

print("cross value decisionTree= score:",score_decisionTree.mean())

python风控评分卡建模和风控常识(博客主亲自录制视频教程)

微信扫二维码，免费学习更多python资源