宵论文最终结果

SVM

mean_precision:0.94,mean_recall:0.82,mean_f:0.88,mean_accuracy:0.85,mean_auc:0.88

Gaussian Naive Bayes¶

mean_precision:0.95,mean_recall:0.78,mean_f:0.86,mean_accuracy:0.83,mean_auc:0.91

 logisClassifier

mean_precision:0.90,mean_recall:0.84,mean_f:0.87,mean_accuracy:0.83,mean_auc:0.90

SGD

mean_precision:0.94,mean_recall:0.84,mean_f:0.89,mean_accuracy:0.86,mean_auc:0.93

去除一类属性之后：

mean_precision:0.89,mean_recall:0.64,mean_f:0.75,mean_accuracy:0.71,mean_auc:0.76

mean_precision:0.90,mean_recall:0.76,mean_f:0.82,mean_accuracy:0.79,mean_auc:0.84

mean_precision:0.90,mean_recall:0.82,mean_f:0.86,mean_accuracy:0.82,mean_auc:0.88

mean_precision:0.88,mean_recall:0.72,mean_f:0.79,mean_accuracy:0.75,mean_auc:0.79

mean_precision:0.88,mean_recall:0.70,mean_f:0.78,mean_accuracy:0.74,mean_auc:0.76

mean_precision:0.89,mean_recall:0.81,mean_f:0.85,mean_accuracy:0.81,mean_auc:0.86

mean_precision:0.88,mean_recall:0.77,mean_f:0.82,mean_accuracy:0.78,mean_auc:0.80

最后一次实验的脚本是：

#!/usr/python
#!-*-coding=utf8-*-
#本周主要工作是对比几种分类算法的差别
import numpy as np
import random
import myUtil

from sklearn import metrics
from sklearn import cross_validation
from sklearn import svm
from sklearn import naive_bayes
from sklearn import metrics
from sklearn import linear_model
from sklearn import ensemble
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
import pylab as pl

root_dir="/media/新加卷/小论文实验/data/liweibo"

def loadAllFileWithSuffix(suffix):
    file_list=list()
#myUtil.traverseFile(root_dir,suffix,file_list)
#    file_list.append(root_dir+"/团圆饭/团圆饭.result")
#    file_list.append(root_dir+"/时间都去哪儿/时间都去哪儿.result")
    file_list.append(root_dir+"/bobo.pincou")
    return file_list

def loadData():
    print "start to preDataByMyOwn..."
    all_file_list=loadAllFileWithSuffix(['result'])
    for file_name in all_file_list:
        print file_name
        label_list=list()
        data_list=list()
        with open(file_name) as in_file:
            for line in in_file:
                line_list=list()
                label_list.append(int(line.strip().split('\t')[0]))
                all_features=line.strip().split('\t')[1:]
                for  feature in all_features:
                    line_list.append(float(feature))
                data_list.append(line_list)
        data_list=np.array(data_list)
        label_list=np.array(label_list)
        return (data_list,label_list)
    
    
def trainModel(data,classifier,n_folds=5):
    print "start to trainModel..."
    x=data[0]
    y=data[1]

    #shupple samples
    n_samples,n_features=x.shape
    print "n_samples:"+str(n_samples)+"n_features:"+str(n_features)
    p=range(n_samples)
    random.seed(0)
    random.shuffle(p)
    x,y=x[p],y[p]

    #cross_validation
    cv=cross_validation.KFold(len(y),n_folds=5)
    mean_tpr=0.0
    mean_fpr=np.linspace(0,1,100)

    mean_recall=0.0
    mean_accuracy=0.0
    mean_f=0.0
    mean_precision=0.0

    for i,(train,test) in enumerate(cv):
        print "the "+str(i)+"times validation..."
        classifier.fit(x[train],y[train])
        y_true,y_pred=y[test],classifier.predict(x[test])
        mean_precision+=metrics.precision_score(y_true,y_pred)
        mean_recall+=metrics.recall_score(y_true,y_pred)
#        mean_accuracy+=metrics.accuracy_score(y_true,y_pred)
        mean_accuracy+=classifier.score(x[test],y_true)
        mean_f+=metrics.fbeta_score(y_true,y_pred,beta=1)
        
        probas_=classifier.predict_proba(x[test])
        fpr,tpr,thresholds=metrics.roc_curve(y[test],probas_[:,1])
        mean_tpr+=np.interp(mean_fpr,fpr,tpr)
        mean_tpr[0]=0.0
        roc_auc=metrics.auc(fpr,tpr)
        pl.plot(fpr,tpr,lw=1,label='ROC fold %d (area=%0.2f)'%(i,roc_auc))
    pl.plot([0,1],[0,1],'--',color=(0.6,0.6,0.6),label='luck')

    mean_precision/=len(cv)
    mean_recall/=len(cv)
    mean_f/=len(cv)
    mean_accuracy/=len(cv)

    mean_tpr/=len(cv)
    mean_tpr[-1]=1.0
    mean_auc=metrics.auc(mean_fpr,mean_tpr)
    print("mean_precision:%0.2f,mean_recall:%0.2f,mean_f:%0.2f,mean_accuracy:%0.2f,mean_auc:%0.2f " % (mean_precision,mean_recall,mean_f,mean_accuracy,mean_auc))
    pl.plot(mean_fpr,mean_tpr,'k--',label='Mean ROC (area=%0.2f)'% mean_auc,lw=2)

    pl.xlim([-0.05,1.05])
    pl.ylim([-0.05,1.05])
    pl.xlabel('False Positive Rate')
    pl.ylabel('True Positive Rate')
    pl.title('ROC')
    pl.legend(loc="lower right")
    #pl.show()


def chooseSomeFeaturesThenTrain(data,clf,choose_index):
    x=data[0]
    y=data[1]
    (n_samples,n_features)=x.shape
    result_data=np.zeros(n_samples).reshape(n_samples,1)
    for i in choose_index:
            if i<1 or i > n_features:
            print "error feture comination..."
                return
        choose_column=x[:,(i-1)].reshape(n_samples,1)
            result_data=np.column_stack((result_data,choose_column))
    result_data=(result_data[:,1:],y)        
    trainModel(result_data,clf)

def main():
#尝试四种分类方法
    data=loadData()
    #print "classify by svm:"
#    clf_svm=svm.SVC(kernel='linear',C=1,probability=True,random_state=0)
#    trainModel(data,clf_svm)
#    #采用朴素贝页斯作为分类器
#    print "classify by naive_bayes_multinomialNB:"
#    clf_mnb=naive_bayes.GaussianNB()
#    trainModel(data,clf_mnb)
#    #采用逻辑回归作为分类器
#    print "classify by logisClassifier"
#    clf_sgd=linear_model.SGDClassifier(loss='log',penalty='l1')
#    trainModel(data,clf_sgd)
#    #利用梯度增强树作为分类器
    print "classify by gradientBoostingClassifier"
    clf_gbc=ensemble.GradientBoostingClassifier(n_estimators=100, learning_rate=1.0, max_depth=1, random_state=0)
    #trainModel(data,clf_gbc)
    #尝试不同的属性组合
    chooseSomeFeaturesThenTrain(data,clf_gbc,[5,6])

    
if __name__=='__main__':
    main()