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. noip 2018 D1T3 赛道修建

    noip 2018 D1T3 赛道修建 首先考虑二分答案,这时需要的就是对于一个长度求出能在树中选出来的最多的路径条数.考虑到一条路径是由一条向上的路径与一条向下的路径构成,或者仅仅是向上或向下的路径 ...

  2. hiho一下 第二周 trie树

    Trie树 时间限制:10000ms 单点时限:1000ms 内存限制:256MB 描述 小Hi和小Ho是一对好朋友,出生在信息化社会的他们对编程产生了莫大的兴趣,他们约定好互相帮助,在编程的学习道路 ...

  3. Java IO流-标准输入输出流

    2017-11-05 19:13:21 标准输入输出流:System类中的两个成员变量. 标准输入流(public static final InputStream in):“标准”输入流.此流已打开 ...

  4. CPU上下文切换详解

    CPU上下文切换详解 原文地址,译文地址,译者: 董明鑫,校对:郑旭东 上下文切换(有时也称做进程切换或任务切换)是指CPU 从一个进程或线程切换到另一个进程或线程.进程(有时候也称做任务)是指一个程 ...

  5. rails安装使用版本控制器的原因。

    使用版本控制器的原因: 你没有系统根权限,所以你没有别的选择 你想要分开运行几个rails 系统 ,并且这几个rails有不同的Ruby版本.使用RVM就可以轻松做到. 没有什么新鲜的先安装xcode ...

  6. js预解析相关知识总结以及一些好玩的面试题

    js预解析的题像在做智力题一样有意思~ 预解析 预解析:在解释这行代码之前发生的事情——变量的声明提前了,函数的声明提前 console.log(num) ——未定义Num,结果是报错 var num ...

  7. @pathVariable的作用（二十二）

    spring mvc中的@PathVariable是用来获得请求url中的动态参数的,十分方便,复习下: @Controller public class TestController { @Requ ...

  8. Cache应用/任务Mutex，用于高并发任务处理经过多个项目使用

    <?php /** * Class Cache redis 用于报表的缓存基本存储和读写 2.0 * <pre> * Cache::read("diamond.accoun ...

  9. New Concept English Two 6 13

    $课文11 礼尚往来 105. I was having dinner at a restaurant when Tony Steele came in. 我正在一家饭馆吃饭,托尼.斯蒂尔走了进来. ...

  10. 严重: Dispatcher initialization failed java.lang.RuntimeException: java.lang.reflect.InvocationT

    严重: Dispatcher initialization failed java.lang.RuntimeException: java.lang.reflect.InvocationT (2012 ...