python作业_sklearn部分

最新推荐文章于 2022-01-02 02:38:27 发布

czw0723

最新推荐文章于 2022-01-02 02:38:27 发布

阅读量337

点赞数

本文链接：https://blog.csdn.net/czw0723/article/details/80715980

版权

作业题目：

In the second MLassignment you have to compare the performance of three di↵erent classification algorithms, namely Naive Bayes, SVM, and RandomForest.

For thisassignment you need to generate a random binary classification problem, andthen train and test (using 10-fold cross validation) the three algorithms. Forsome algorithms inner cross validation (5-fold) for choosing the parameters isneeded. Then, show the classification performace (per-fold and averaged) in thereport, and briefly discussing the results.

简单翻译：

在第二个ML赋值中，你必须比较三种不同的分类算法的性能，即朴素贝叶斯、SVM和随机森林。

对于这个任务，你需要生成一个随机二进制分类问题，然后训练和测试（使用10倍交叉验证）这三个算法。对于一些算法，需要内部交叉验证（5倍）来选择参数。然后，在报告中显示分类性能（每倍和平均），并简要讨论结果。

作业前简要分析：首先通过pip下载sklearn，课件里面的代码十分关键，有助于开始入门（相当于搭个框架），其他自己上网找相关的函数，教程应该也可以了。

代码如下：

from sklearn import datasets
from sklearn import cross_validation#这个cross_validation好像过时了？
from sklearn.naive_bayes import GaussianNB
import matplotlib.pyplot as plt 
from sklearn import metrics 
from sklearn.svm import SVC
import numpy as np
from sklearn.ensemble import RandomForestClassifier
def NB(X_train,y_train,X_test):
	clf = GaussianNB()
	clf.fit(X_train,y_train)
	return clf.predict(X_test)
	
#输入训练数据列表X,y，再给出一个测试的数据列表，以及C参数，返回相关的SVM预测
def rbf_svm(X_train,y_train,X_test,C):
	clf = SVC(C = C,kernel = 'rbf')
	clf.fit(X_train,y_train)
	return clf.predict(X_test)

#输入训练数据列表X,y，再给出一个测试的数据列表，以及n_estimator参数，返回相关的RFC预测
def RFC(X_train,y_train,X_test,n_estimator):
	clf = RandomForestClassifier(n_estimators=n_estimator)
	clf.fit(X_train, y_train)
	return clf.predict(X_test)

acc_for_NB = []             #使用accuracy评估三个算法  
acc_for_SVC = []  
acc_for_RFC = []  
  
f1_for_NB = []              # 使用F1-score评估三个算法  
f1_for_SVC = []  
f1_for_RFC = []  
  
auc_for_NB = []             # 使用AUC ROC评估三个算法  
auc_for_SVC = []  
auc_for_RFC = [] 

#创建虚拟数据X,y，后面指明了相关的参数，包括例子个数，属性个数，关联度，之后的就不知道了，
#直接照着老师的课件上面的写即可
X,y = datasets.make_classification(n_samples = 1000,n_features = 10
									,n_informative = 2,n_redundant = 2
									,n_repeated = 0,n_classes = 2)

#下面的大部分其实参照课本就可以得到很好的效果了
kf = cross_validation.KFold(len(X), n_folds=10, shuffle=True
								,random_state = 1234)
for train_index, test_index in kf:
	X_train, y_train = X[train_index], y[train_index]
	X_test, y_test = X[test_index], y[test_index]
	
	ipred = NB(X_train,y_train,X_test)
	
	#分别用三种方法评估NB算法结果评估朴素贝叶斯算法
	acc_for_NB.append(metrics.accuracy_score(y_test, ipred))  
	f1_for_NB.append(metrics.f1_score(y_test, ipred))  
	auc_for_NB.append(metrics.roc_auc_score(y_test, ipred))
	
	#然后是SVM算法，先找出最好的C值
	nn = len(X_train)
	bestC = None
	Cvalues = [1e-2,1e-1,1e0,1e1,1e2]
	innerscore = []
	for C in Cvalues:
		ikf = cross_validation.KFold(nn,n_folds = 5,shuffle = True
										,random_state = 5678)
		innerf1 = []
		for t_index,v_index in ikf:
			X_t,X_v = X_train[t_index],X_train[v_index]
			y_t,y_v = y_train[t_index],y_train[v_index]
			
			ipred = rbf_svm(X_t,y_t,X_v,C)
			
			innerf1.append(metrics.f1_score(y_v,ipred))
		innerscore.append(sum(innerf1)/len(innerf1))
	bestC = Cvalues[np.argmax(innerscore)]
	
	SVCpred = rbf_svm(X_train,y_train,X_test,bestC)
	print("The bestC is:", bestC)  
	acc_for_SVC.append(metrics.accuracy_score(y_test,SVCpred))
	f1_for_SVC.append(metrics.f1_score(y_test,SVCpred))
	auc_for_SVC.append(metrics.roc_auc_score(y_test,SVCpred))
	
	#下面是随机森林random forest了，主要是对n_estimator做出评估
	nn = len(X_train)
	best_n_estimators_values = None
	n_estimators_values=[1,10,100,1000]
	innerscore = []
	
	for estimators_value in n_estimators_values:
		ikf = cross_validation.KFold(nn,n_folds = 5,shuffle = True
										,random_state = 5678)
		innerf1 = []
		for t_index,v_index in ikf:
			X_t,X_v = X_train[t_index],X_train[v_index]
			y_t,y_v = y_train[t_index],y_train[v_index]
			
			ipred = RFC(X_t,y_t,X_v,estimators_value)
			
			innerf1.append(metrics.f1_score(y_v,ipred))
		innerscore.append(sum(innerf1)/len(innerf1))
	best_n_estimators_values = n_estimators_values[np.argmax(innerscore)]
	print("The best_n_estimators_values is:", best_n_estimators_values)  
	RFCpred = RFC(X_train,y_train,X_test,best_n_estimators_values)
	acc_for_RFC.append(metrics.accuracy_score(y_test,RFCpred))
	f1_for_RFC.append(metrics.f1_score(y_test,RFCpred))
	auc_for_RFC.append(metrics.roc_auc_score(y_test,RFCpred))
	
print("Naive Bayes:")  
  
print("Evaluated by accuracy score:")  
print(acc_for_NB)  
print("Average:", sum(acc_for_NB) / len(acc_for_NB))  
print()  
  
print("Evaluated by f1 score:")  
print(f1_for_NB)  
print("Average:", sum(f1_for_NB) / len(f1_for_NB))  
print()  
  
print("Evaluated by roc auc score:")  
print(auc_for_NB)  
print("Average:", sum(auc_for_NB) / len(auc_for_NB))  
print()  
  
print("SVC:")  
  
print("Evaluated by accuracy score:")  
print(acc_for_SVC)  
print("Average:", sum(acc_for_SVC) / len(acc_for_SVC))  
print()  
  
print("Evaluated by f1 score:")  
print(f1_for_SVC)  
print("Average:", sum(f1_for_SVC) / len(f1_for_SVC))  
print()  
  
print("Evaluated by roc auc score:")  
print(auc_for_SVC)  
print("Average:", sum(auc_for_SVC) / len(auc_for_SVC))  
print()  
  
print("Random Forest:")  
  
print("Evaluated by accuracy score:")  
print(acc_for_RFC)  
print("Average:", sum(acc_for_RFC) / len(acc_for_RFC))  
print()  
  
print("Evaluated by f1 score:")  
print(f1_for_RFC)  
print("Average:", sum(f1_for_RFC) / len(f1_for_RFC))  
print()  
  
print("Evaluated by roc auc score:")  
print(auc_for_RFC)  
print("Average:", sum(auc_for_RFC) / len(auc_for_RFC))  
print()

简要分析：

从kf = cross_validation.KFold(len(X), n_folds=10, shuffle=True,random_state= 1234)谈起：

我们将数据分成10组，这个可以从KFold =10看出来，从

官方文档中看出来，将10-1=9份作为训练用的部分，剩下一部分作为检测用的（validation set）至于后面的ikf = cross_validation.KFold(nn,n_folds = 5,shuffle = True,random_state= 5678)同上面，就不详细谈了。

实验结果：

The bestC is: 1.0