文本挖掘的paper没找到统一的benchmark,只好自己跑程序,走过路过的前辈如果知道20newsgroups或者其它好用的公共数据集的分类(最好要所有类分类结果,全部或取部分特征无所谓)麻烦留言告知下现在的benchmark,万谢!
嗯,说正文。20newsgroups官网上给出了3个数据集,这里我们用最原始的20news-19997.tar.gz。
分为以下几个过程:
#first extract the 20 news_group dataset to /scikit_learn_data
from sklearn.datasets import fetch_20newsgroups
#all categories
#newsgroup_train = fetch_20newsgroups(subset='train')
#part categories
categories = ['comp.graphics',
'comp.os.ms-windows.misc',
'comp.sys.ibm.pc.hardware',
'comp.sys.mac.hardware',
'comp.windows.x'];
newsgroup_train = fetch_20newsgroups(subset = 'train',categories = categories);
#print category names
from pprint import pprint
pprint(list(newsgroup_train.target_names))
#newsgroup_train.data is the original documents, but we need to extract the
#feature vectors inorder to model the text data
from sklearn.feature_extraction.text import HashingVectorizer
vectorizer = HashingVectorizer(stop_words = 'english',non_negative = True,
n_features = 10000)
fea_train = vectorizer.fit_transform(newsgroup_train.data)
fea_test = vectorizer.fit_transform(newsgroups_test.data);
#return feature vector 'fea_train' [n_samples,n_features]
print 'Size of fea_train:' + repr(fea_train.shape)
print 'Size of fea_train:' + repr(fea_test.shape)
#11314 documents, 130107 vectors for all categories
print 'The average feature sparsity is {0:.3f}%'.format(
fea_train.nnz/float(fea_train.shape[0]*fea_train.shape[1])*100);
上面代码注释说TF-IDF在train和test上提取的feature维度不同,那么怎么让它们相同呢?有两种方法:
#----------------------------------------------------
#method 1:CountVectorizer+TfidfTransformer
print '*************************\nCountVectorizer+TfidfTransformer\n*************************'
from sklearn.feature_extraction.text import CountVectorizer,TfidfTransformer
count_v1= CountVectorizer(stop_words = 'english', max_df = 0.5);
counts_train = count_v1.fit_transform(newsgroup_train.data);
print "the shape of train is "+repr(counts_train.shape)
count_v2 = CountVectorizer(vocabulary=count_v1.vocabulary_);
counts_test = count_v2.fit_transform(newsgroups_test.data);
print "the shape of test is "+repr(counts_test.shape)
tfidftransformer = TfidfTransformer();
tfidf_train = tfidftransformer.fit(counts_train).transform(counts_train);
tfidf_test = tfidftransformer.fit(counts_test).transform(counts_test);
#method 2:TfidfVectorizer
print '*************************\nTfidfVectorizer\n*************************'
from sklearn.feature_extraction.text import TfidfVectorizer
tv = TfidfVectorizer(sublinear_tf = True,
max_df = 0.5,
stop_words = 'english');
tfidf_train_2 = tv.fit_transform(newsgroup_train.data);
tv2 = TfidfVectorizer(vocabulary = tv.vocabulary_);
tfidf_test_2 = tv2.fit_transform(newsgroups_test.data);
print "the shape of train is "+repr(tfidf_train_2.shape)
print "the shape of test is "+repr(tfidf_test_2.shape)
analyze = tv.build_analyzer()
tv.get_feature_names()#statistical features/terms
print '*************************\nfetch_20newsgroups_vectorized\n*************************'
from sklearn.datasets import fetch_20newsgroups_vectorized
tfidf_train_3 = fetch_20newsgroups_vectorized(subset = 'train');
tfidf_test_3 = fetch_20newsgroups_vectorized(subset = 'test');
print "the shape of train is "+repr(tfidf_train_3.data.shape)
print "the shape of test is "+repr(tfidf_test_3.data.shape)
######################################################
#Multinomial Naive Bayes Classifier
print '*************************\nNaive Bayes\n*************************'
from sklearn.naive_bayes import MultinomialNB
from sklearn import metrics
newsgroups_test = fetch_20newsgroups(subset = 'test',
categories = categories);
fea_test = vectorizer.fit_transform(newsgroups_test.data);
#create the Multinomial Naive Bayesian Classifier
clf = MultinomialNB(alpha = 0.01)
clf.fit(fea_train,newsgroup_train.target);
pred = clf.predict(fea_test);
calculate_result(newsgroups_test.target,pred);
#notice here we can see that f1_score is not equal to 2*precision*recall/(precision+recall)
#because the m_precision and m_recall we get is averaged, however, metrics.f1_score() calculates
#weithed average, i.e., takes into the number of each class into consideration.
其中,函数calculate_result计算f1:
def calculate_result(actual,pred):
m_precision = metrics.precision_score(actual,pred);
m_recall = metrics.recall_score(actual,pred);
print 'predict info:'
print 'precision:{0:.3f}'.format(m_precision)
print 'recall:{0:0.3f}'.format(m_recall);
print 'f1-score:{0:.3f}'.format(metrics.f1_score(actual,pred));
3.2 KNN:
######################################################
#KNN Classifier
from sklearn.neighbors import KNeighborsClassifier
print '*************************\nKNN\n*************************'
knnclf = KNeighborsClassifier()#default with k=5
knnclf.fit(fea_train,newsgroup_train.target)
pred = knnclf.predict(fea_test);
calculate_result(newsgroups_test.target,pred);
3.3 SVM:
######################################################
#SVM Classifier
from sklearn.svm import SVC
print '*************************\nSVM\n*************************'
svclf = SVC(kernel = 'linear')#default with 'rbf'
svclf.fit(fea_train,newsgroup_train.target)
pred = svclf.predict(fea_test);
calculate_result(newsgroups_test.target,pred);
*************************
Naive Bayes
*************************
predict info:
precision:0.764
recall:0.759
f1-score:0.760
*************************
KNN
*************************
predict info:
precision:0.642
recall:0.635
f1-score:0.636
*************************
SVM
*************************
predict info:
precision:0.777
recall:0.774
f1-score:0.774
4. 聚类
######################################################
#KMeans Cluster
from sklearn.cluster import KMeans
print '*************************\nKMeans\n*************************'
pred = KMeans(n_clusters=5)
pred.fit(fea_test)
calculate_result(newsgroups_test.target,pred.labels_);
结果:
*************************
KMeans
*************************
predict info:
precision:0.264
recall:0.226
f1-score:0.213
本文全部代码下载:在此
貌似准确率好低……那我们用全部特征吧……结果如下:
*************************
Naive Bayes
*************************
predict info:
precision:0.771
recall:0.770
f1-score:0.769
*************************
KNN
*************************
predict info:
precision:0.652
recall:0.645
f1-score:0.645
*************************
SVM
*************************
predict info:
precision:0.819
recall:0.816
f1-score:0.816
*************************
KMeans
*************************
predict info:
precision:0.289
recall:0.313
f1-score:0.266
关于Python更多的学习资料将继续更新,敬请关注本博客和新浪微博Rachel Zhang。