此次我做的实验是二分类问题，输出precision，recall，accuracy，auc

# -*- coding: utf-8 -*-

#from sklearn.neighbors import

import numpy as np

from pandas import read_csv

import pandas as pd

import sys

import importlib

from sklearn.neighbors import KNeighborsClassifier

from sklearn.ensemble import GradientBoostingClassifier

from sklearn import svm

from sklearn import cross_validation

from sklearn.metrics import hamming_loss

from sklearn import metrics

importlib.reload(sys)

from sklearn.linear_model import LogisticRegression

from imblearn.combine import SMOTEENN

from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import RandomForestClassifier  #92%

from sklearn import tree

from xgboost.sklearn import XGBClassifier

from sklearn.linear_model import SGDClassifier

from sklearn import neighbors

from sklearn.naive_bayes import BernoulliNB

import matplotlib as mpl

import matplotlib.pyplot as plt

from sklearn.metrics import confusion_matrix

from numpy import mat

def metrics_result(actual, predict):

    print('准确度:{0:.3f}'.format(metrics.accuracy_score(actual, predict)))

    print('精密度:{0:.3f}'.format(metrics.precision_score(actual, predict,average='weighted')))

    print('召回:{0:0.3f}'.format(metrics.recall_score(actual, predict,average='weighted')))

    print('f1-score:{0:.3f}'.format(metrics.f1_score(actual, predict,average='weighted')))

    print('auc:{0:.3f}'.format(metrics.roc_auc_score(test_y, predict)))

输出混淆矩阵

    matr=confusion_matrix(test_y,predict)

    matr=mat(matr)

    conf=np.matrix([[0,0],[0,0]])

    conf[0,0]=matr[1,1]

    conf[1,0]=matr[1,0]

    conf[0,1]=matr[0,1]

    conf[1,1]=matr[0,0]

    print(conf)

全代码：

# -*- coding: utf-8 -*-

#from sklearn.neighbors import

import numpy as np

from pandas import read_csv

import pandas as pd

import sys

import importlib

from sklearn.neighbors import KNeighborsClassifier

from sklearn.ensemble import GradientBoostingClassifier

from sklearn import svm

from sklearn import cross_validation

from sklearn.metrics import hamming_loss

from sklearn import metrics

importlib.reload(sys)

from sklearn.linear_model import LogisticRegression

from imblearn.combine import SMOTEENN

from sklearn.tree import DecisionTreeClassifier

from sklearn.ensemble import RandomForestClassifier  #92%

from sklearn import tree

from xgboost.sklearn import XGBClassifier

from sklearn.linear_model import SGDClassifier

from sklearn import neighbors

from sklearn.naive_bayes import BernoulliNB

import matplotlib as mpl

import matplotlib.pyplot as plt

from sklearn.metrics import confusion_matrix

from numpy import mat

def metrics_result(actual, predict):

    print('准确度:{0:.3f}'.format(metrics.accuracy_score(actual, predict)))

    print('精密度:{0:.3f}'.format(metrics.precision_score(actual, predict,average='weighted')))

    print('召回:{0:0.3f}'.format(metrics.recall_score(actual, predict,average='weighted')))

    print('f1-score:{0:.3f}'.format(metrics.f1_score(actual, predict,average='weighted')))

    print('auc:{0:.3f}'.format(metrics.roc_auc_score(test_y, predict)))

'''分类0-1'''

root1="D:/ProgramData/station3/10.csv"

root2="D:/ProgramData/station3/more+average2.csv"

root3="D:/ProgramData/station3/new_10.csv"

root4="D:/ProgramData/station3/more+remove.csv"

root5="D:/ProgramData/station3/new_10 2.csv"

root6="D:/ProgramData/station3/new10.csv"

root7="D:/ProgramData/station3/no_-999.csv"

root=root4

data1 = read_csv(root) #数据转化为数组

data1=data1.values

print(root)

time=1

accuracy=[]

aucc=[]

pre=[]

recall=[]

for i in range(time):

    train, test= cross_validation.train_test_split(data1, test_size=0.2, random_state=i)

    test_x=test[:,:-1]

    test_y=test[:,-1]

    train_x=train[:,:-1]

    train_y=train[:,-1]

# =============================================================================

#     print(train_x.shape)

#     print(train_y.shape)

#     print(test_x.shape)

#     print(test_y.shape)

#     print(type(train_x))

# =============================================================================

    #X_Train=train_x

    #Y_Train=train_y

    X_Train, Y_Train = SMOTEENN().fit_sample(train_x, train_y)

    #clf = RandomForestClassifier()  #82

    #clf = LogisticRegression()  #82 

    #penalty=’l2’, dual=False, tol=0.0001, C=1.0, fit_intercept=True, intercept_scaling=1, class_weight=None, random_state=None, solver=’liblinear’, max_iter=100, multi_class=’ovr’, verbose=0, warm_start=False, n_jobs=1

    #clf=svm.SVC()

    clf= XGBClassifier()

    #from sklearn.ensemble import RandomForestClassifier  #92%

    #clf = DecisionTreeClassifier()

    #clf = GradientBoostingClassifier()

    #clf=neighbors.KNeighborsClassifier()

    #clf=BernoulliNB()

    print(clf)

    clf.fit(X_Train, Y_Train)

    predict=clf.predict(test_x)

    matr=confusion_matrix(test_y,predict)

    matr=mat(matr)

    conf=np.matrix([[0,0],[0,0]])

    conf[0,0]=matr[1,1]

    conf[1,0]=matr[1,0]

    conf[0,1]=matr[0,1]

    conf[1,1]=matr[0,0]

    print(conf)

    #a=metrics_result(test_y, predict)

    #a=metrics_result(test_y,predict)

    '''accuracy'''

    aa=metrics.accuracy_score(test_y, predict)

    #print(metrics.accuracy_score(test_y, predict))

    accuracy.append(aa)

    '''auc'''

    bb=metrics.roc_auc_score(test_y, predict, average=None)

    aucc.append(bb)

    '''precision'''

    cc=metrics.precision_score(test_y, predict, average=None)

    pre.append(cc[1])

# =============================================================================

#     print('cc')

#     print(type(cc))

#     print(cc[1])

#     print('cc')

# =============================================================================

    '''recall'''

    dd=metrics.recall_score(test_y, predict, average=None)

    #print(metrics.recall_score(test_y, predict,average='weighted'))

    recall.append(dd[1])

    f=open('D:\ProgramData\station3\predict.txt', 'w')

    for i in range(len(predict)):

        f.write(str(predict[i]))

        f.write('\n')

    f.write("写好了")

    f.close()

    f=open('D:\ProgramData\station3\y_.txt', 'w')

    for i in range(len(predict)):

        f.write(str(test_y[i]))

        f.write('\n')

    f.write("写好了")

    f.close()

# =============================================================================

#     f=open('D:/ProgramData/station3/predict.txt', 'w')

#     for i in range(len(predict)):

#        f.write(str(predict[i]))

#        f.write('\n')

#     f.write("写好了")

#     f.close()

#

#     f=open('D:/ProgramData/station3/y.txt', 'w')

#     for i in range(len(test_y)):

#        f.write(str(test_y[i]))

#        f.write('\n')

#     f.write("写好了")

#     f.close()

#

# =============================================================================

# =============================================================================

#     print('调用函数auc：', metrics.roc_auc_score(test_y, predict, average='micro'))

#

#     fpr, tpr, thresholds = metrics.roc_curve(test_y.ravel(),predict.ravel())

#     auc = metrics.auc(fpr, tpr)

#     print('手动计算auc：', auc)

#     #绘图

#     mpl.rcParams['font.sans-serif'] = u'SimHei'

#     mpl.rcParams['axes.unicode_minus'] = False

#     #FPR就是横坐标,TPR就是纵坐标

#     plt.plot(fpr, tpr, c = 'r', lw = 2, alpha = 0.7, label = u'AUC=%.3f' % auc)

#     plt.plot((0, 1), (0, 1), c = '#808080', lw = 1, ls = '--', alpha = 0.7)

#     plt.xlim((-0.01, 1.02))

#     plt.ylim((-0.01, 1.02))

#     plt.xticks(np.arange(0, 1.1, 0.1))

#     plt.yticks(np.arange(0, 1.1, 0.1))

#     plt.xlabel('False Positive Rate', fontsize=13)

#     plt.ylabel('True Positive Rate', fontsize=13)

#     plt.grid(b=True, ls=':')

#     plt.legend(loc='lower right', fancybox=True, framealpha=0.8, fontsize=12)

#     plt.title(u'大类问题一分类后的ROC和AUC', fontsize=17)

#     plt.show()

# =============================================================================

sum_acc=0

sum_auc=0

sum_pre=0

sum_recall=0

for i in range(time):

    sum_acc+=accuracy[i]

    sum_auc+=aucc[i]

    sum_pre+=pre[i]

    sum_recall+=recall[i]

acc1=sum_acc*1.0/time

auc1=sum_auc*1.0/time

pre1=sum_pre*1.0/time

recall1=sum_recall*1.0/time

print("acc",acc1)

print("auc",auc1)

print("pre",pre1)

print("recall",recall1)

# =============================================================================

#

# data1 = read_csv(root2) #数据转化为数组

# data1=data1.values

#

#

# accuracy=[]

# auc=[]

# pre=[]

# recall=[]

# for i in range(30):

#     train, test= cross_validation.train_test_split(data1, test_size=0.2, random_state=i)

#     test_x=test[:,:-1]

#     test_y=test[:,-1]

#     train_x=train[:,:-1]

#     train_y=train[:,-1]

#     X_Train, Y_Train = SMOTEENN().fit_sample(train_x, train_y)

#

#     #clf = RandomForestClassifier()  #82

#     clf = LogisticRegression()  #82

#     #clf=svm.SVC()

#     #clf= XGBClassifier()

#     #from sklearn.ensemble import RandomForestClassifier  #92%

#     #clf = DecisionTreeClassifier()

#     #clf = GradientBoostingClassifier()

#

#     #clf=neighbors.KNeighborsClassifier()  65.25%

#     #clf=BernoulliNB()

#     clf.fit(X_Train, Y_Train)

#     predict=clf.predict(test_x)

#

#     '''accuracy'''

#     aa=metrics.accuracy_score(test_y, predict)

#     accuracy.append(aa)

#

#     '''auc'''

#     aa=metrics.roc_auc_score(test_y, predict)

#     auc.append(aa)

#

#     '''precision'''

#     aa=metrics.precision_score(test_y, predict,average='weighted')

#     pre.append(aa)

#

#     '''recall'''

#     aa=metrics.recall_score(test_y, predict,average='weighted')

#     recall.append(aa)

#

#

# sum_acc=0

# sum_auc=0

# sum_pre=0

# sum_recall=0

# for i in range(30):

#     sum_acc+=accuracy[i]

#     sum_auc+=auc[i]

#     sum_pre+=pre[i]

#     sum_recall+=recall[i]

#

# acc1=sum_acc*1.0/30

# auc1=sum_auc*1.0/30

# pre1=sum_pre*1.0/30

# recall1=sum_recall*1.0/30

# print("more 的 acc:", acc1)

# print("more 的 auc:", auc1)

# print("more 的 precision:", pre1)

# print("more 的 recall:", recall1)

#

# =============================================================================

    #X_train, X_test, y_train, y_test = cross_validation.train_test_split(X_Train,Y_Train, test_size=0.2, random_state=i)

输出结果：

分类预测输出precision，recall，accuracy，auc和tp，tn，fp，fn矩阵的更多相关文章

  1. 目标检测的评价标准mAP, Precision, Recall, Accuracy

    目录 metrics 评价方法 TP , FP , TN , FN 概念 计算流程 Accuracy , Precision ,Recall Average Precision PR曲线 AP计算 A ...

  2. 机器学习：评价分类结果（Precision - Recall 的平衡、P - R 曲线）

    一.Precision - Recall 的平衡 1)基础理论 调整阈值的大小,可以调节精准率和召回率的比重: 阈值:threshold,分类边界值,score > threshold 时分类为 ...

  3. 机器学习基础梳理—(accuracy,precision,recall浅谈)

    一.TP TN FP FN TP:标签为正例,预测为正例(P),即预测正确(T) TN:标签为负例,预测为负例(N),即预测正确(T) FP:标签为负例,预测为正例(P),即预测错误(F) FN:标签 ...

  4. Precision,Recall,F1的计算

    Precision又叫查准率,Recall又叫查全率.这两个指标共同衡量才能评价模型输出结果. TP: 预测为1(Positive),实际也为1(Truth-预测对了) TN: 预测为0(Negati ...

  5. 评价指标整理：Precision, Recall, F-score, TPR, FPR, TNR, FNR, AUC, Accuracy

    针对二分类的结果,对模型进行评估,通常有以下几种方法: Precision.Recall.F-score(F1-measure)TPR.FPR.TNR.FNR.AUCAccuracy   真实结果 1 ...

  6. 分类指标准确率(Precision)和正确率(Accuracy)的区别

    http://www.cnblogs.com/fengfenggirl/p/classification_evaluate.html 一.引言 分类算法有很多,不同分类算法又用很多不同的变种.不同的分 ...

  7. Precision/Recall、ROC/AUC、AP/MAP等概念区分

    1. Precision和Recall Precision,准确率/查准率.Recall,召回率/查全率.这两个指标分别以两个角度衡量分类系统的准确率. 例如,有一个池塘,里面共有1000条鱼,含10 ...

  8. 机器学习--如何理解Accuracy, Precision, Recall, F1 score

    当我们在谈论一个模型好坏的时候,我们常常会听到准确率(Accuracy)这个词,我们也会听到＂如何才能使模型的Accurcy更高＂．那么是不是准确率最高的模型就一定是最好的模型? 这篇博文会向大家解释 ...

  9. 通过Precision/Recall判断分类结果偏差极大时算法的性能

    当我们对某些问题进行分类时,真实结果的分布会有明显偏差. 例如对是否患癌症进行分类,testing set 中可能只有0.5%的人患了癌症. 此时如果直接数误分类数的话,那么一个每次都预测人没有癌症的 ...

随机推荐

  1. POJ 2115 C Looooops（模线性方程）

    http://poj.org/problem?id=2115 题意: 给你一个变量,变量初始值a,终止值b,每循环一遍加c,问一共循环几遍终止,结果mod2^k.如果无法终止则输出FOREVER. 思 ...

  2. shell 判断文件是否是可执行文件

    测试变量指定的文件是否存在且是可执行文件.如果存在且是可执行文件,则执行该文件,否则通过chmod命令赋予该文件可执行权限. //test.sh #!/bin/bash echo "ente ...

  3. Redis并发竞争

    Redis是一种单线程机制的nosql数据库,基于key-value,数据可持久化落盘.由于单线程所以Redis本身并没有锁的概念,多个客户端连接并不存在竞争关系,但是利用jedis等客户端对Redi ...

  4. 【测试设计】基于正交法的测试用例设计工具--PICT

    前言 我们都知道成对组合覆盖是一种非常有效的测试用例设计方法,但是实际工作过程中当成对组合量太大,我们往往很难做到有效的用例覆盖. PICT是微软公司出品的一款成对组合命令行生成工具,它很好的解决了上 ...

  5. 【安全测试】Web应用安全之XSS跨站脚本攻击漏洞

    前言 以前都只是在各类文档中见到过XSS,也进行过相关的学习,但是都是一知半解,过了一段时间就忘了. 前几天我们收到了了一份标题为<XX账号昵称参数中存在存储XSS漏洞>的报告文档,来源是 ...

  6. JPA使用指南 javax.persistence的注解配置

    @SuppressWarnings("serial") @Entity @Table(name="T_X") public class X implements ...

  7. OOP的感悟

    不要认为你关心的东西就是对象的全部或对象的核心,相对于对象的成员家族而言,它仅仅是其中的一个‘很小的成员而已’

  8. 玲珑杯 round18 A 计算几何瞎暴力

    题目链接 : http://www.ifrog.cc/acm/problem/1143 当时没看到坐标的数据范围= =看到讨论才意识到,不同的坐标最多只有1k多个,完全可以暴力做法,不过也要一些技巧. ...

  9. 进程间通信IPC

    body, table{font-family: 微软雅黑; font-size: 13.5pt} table{border-collapse: collapse; border: solid gra ...

  10. Double H3.0

    Double H3.0 团队分工 组员 王熙航 杨艺勇 刘杰 郑沐榕 李冠锐 曾磊鑫 戴俊涵 聂寒冰 任务内容 分配任务,整理内容,审核修改 规格说明书汇总排版 ,记录其他组的提问 用例图,功能描述 ...