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. js模拟类的创建以及继承的四部曲

    <script> 1)创建父类 function Person(){ } Person.prototype.age = 18;//给父类添加属性 var p1 = new Person() ...

  2. MyBatis小案例完善增强

    https://blog.csdn.net/techbirds_bao/article/details/9233599 上链接为一个不错的Mybatis进阶博客 当你把握时间,时间与你为伍. 将上一个 ...

  3. adb 安装软件

    一.连接 adb connect 192.168.1.10 输出 connected to 二.查看设备 adb devices 输出 List of devices attached device ...

  4. mysql explain extended 查看 执行计划

    本文以转移至本人的个人博客,请多多关注! 本文以转移至本人的个人博客,请多多关注! 本文以转移至本人的个人博客,请多多关注! 本文以转移至本人的个人博客,请多多关注! 1. explain 可以查看 ...

  5. Docker和k8s的区别与介绍

    本文来源:鲜枣课堂 2010年,几个搞IT的年轻人,在美国旧金山成立了一家名叫“dotCloud”的公司. 这家公司主要提供基于PaaS的云计算技术服务.具体来说,是和LXC有关的容器技术. LXC, ...

  6. Deploying Qt or how to avoid “could not find or load the Qt platform plugin”

    (转自:http://www.tripleboot.org/?p=138) Once you’ve built your first Qt program, have you tried it on ...

  7. Python+Flask+MysqL的web建设技术过程

    一.前言(个人学期总结) 个人总结一下这学期对于Python+Flask+MysqL的web建设技术过程的学习体会,Flask小辣椒框架相对于其他框架而言,更加稳定,不会有莫名其妙的错误,容错性强,运 ...

  8. mmap实现大文件快速拷贝

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

  9. Jacoco的原理

    覆盖率计数器 Jacoco使用一系列的不同的计数器来做覆盖率的度量计算.所有这些计数器都是从java的class文件中获取信息,这些class文件可以(可选)包含调试的信息在里面.即使在没有源码的情况 ...

  10. Missing artifact com.sun:tools:jar:1.7解决方案

    在配置Java + Robotframework时遇到的问题“Missing artifact com.sun:tools:jar” 1. 先检查一下eclipse或STS中的JDK路径配置是否正确( ...