Classification is the task of choosing the correct class label for a given input.
A classifier is called supervised if it is built based on training corpora containing the correct label for each input.
這裏就以一個例子來說明怎樣用nltk來實現分類器訓練和分類
一個簡單的分類任務,給定一個名字,判斷其性別,就是在male,female兩類進行分類
好,先來訓練,訓練就要有corpus,就是分好類的名字的例子
nltk提供了names的corpus
>>> from nltk.corpus import names
>>> names.words('male.txt') #男性的name的列表
>>> names.words('female.txt') #女性的name的列表
有了訓練corpus,下面就是特徵提取
The first step in creating a classifier is deciding what features of the input are relevant, and how to encode those features.
這裏簡單的假設這個名字的性別和最後一個字母相關,那麼就把最後一個字母作爲每個test case的特徵
>>> def gender_features(word):
... return {'last_letter': word[-1]}
>>> gender_features('Shrek')
{'last_letter': 'k'}
所以就定義如上的特徵抽取函數,並用它來生成我們的訓練集和測試集
>>> from nltk.corpus import names
>>> import random
>>> names = ([(name, 'male') for name in names.words('male.txt')] +
... [(name, 'female') for name in names.words('female.txt')])
>>> random.shuffle(names) #原來的name是按字母排序的,爲了達到比較好的訓練效果,必須打亂順序,隨機化
>>> featuresets = [(gender_features(n), g) for (n,g) in names]
>>> train_set, test_set = featuresets[500:], featuresets[:500] #把特徵集一部分作爲train集,一部分用來測試
>>> classifier = nltk.NaiveBayesClassifier.train
(train_set) #用訓練集來訓練bayes分類器
>>> classifier.classify
(gender_features('Trinity')) #訓練完就可以用這個分類器來實際進行分類工作了
'female'
用測試集來測試
>>> print nltk.classify.accuracy
(classifier, test_set) #用測試集來測試這個分類器,nltk提供accuracy接口
0.758
現在只考慮了最後一個字母這個特徵,準確率是75%,顯然還有很大的提升空間。
>>> classifier.show_most_informative_features
(5) #這個接口有意思, 你可以顯示出區分度最高的幾個features
Most Informative Features
last_letter = 'a' female : male = 38.3 : 1.0
last_letter = 'k' male : female = 31.4 : 1.0
last_letter = 'f' male : female = 15.3 : 1.0
last_letter = 'p' male : female = 10.6 : 1.0
last_letter = 'w' male : female = 10.6 : 1.0
nltk接口很貼心,還考慮到你內存太小,放不下所有的feature集合,提供這個接口來當用到時,實時的計算feature
>>> from nltk.classify import apply_features
>>> train_set = apply_features
(gender_features, names[500:])
>>> test_set = apply_features(gender_features, names[:500])
分類器分類效果好壞很大取決於訓練集的特徵選取,特徵選取的比較合理,就會取得比較好的分類效果。
當然特徵也不是選取的越多越好,
if you provide too many features, then the algorithm will have a higher chance of relying on idiosyncrasies of your training data that don’t generalize well to new examples. This problem is known as overfitting , and can be especially problematic when working with small training sets.
所以特徵抽取這個在分類領域中是一個很重要的研究方向。
比如把上面那個例子的特徵增加爲,分別把最後兩個字符,作爲兩個特徵, 這樣會發現分類器測試的準確性有所提高。
>>> def gender_features(word):
... return {'suffix1': word[-1:],
... 'suffix2': word[-2:]}
但是如果把特徵增加爲,首字母,尾字母,並統計每個字符的出現次數,反而會導致overfitting,測試準確性反而不如之前只考慮尾字母的情況
def gender_features2(name):
features = {}
features["firstletter"] = name[0].lower()
features["lastletter"] = name[–1].lower()
for letter in 'abcdefghijklmnopqrstuvwxyz':
features["count(%s)" % letter] = name.lower().count(letter)
features["has(%s)" % letter] = (letter in name.lower())
return features
>>> gender_features2('John')
{'count(j)': 1, 'has(d)': False, 'count(b)': 0, ...}
>>> featuresets = [(gender_features2(n), g) for (n,g) in names]
>>> train_set, test_set = featuresets[500:], featuresets[:500]
>>> classifier = nltk.NaiveBayesClassifier.train(train_set)
>>> print nltk.classify.accuracy(classifier, test_set)
0.748
那麼上面這個簡單的方法已經講明瞭用nltk,進行分類的過程,那麼剩下的就是針對不同的分類任務,特徵的選取上會有不同,還有分類器的也不止bayes一種,可以針對不同的任務來選取。
比如對於文本分類,可以選取是否包含特徵詞彙作爲文本特徵
all_words = nltk.FreqDist(w.lower() for w in movie_reviews.words())
word_features = all_words.keys()[:2000] #找出出現頻率較高的特徵詞,雖然這個找法不太合理
def document_features(document):
document_words = set(document)
features = {}
for word in word_features:
features['contains(%s)' % word] = (word in document_words)
return features
>>> print document_features(movie_reviews.words('pos/cv957_8737.txt'))
{'contains(waste)': False, 'contains(lot)': False, ...}
對於pos tagging,我們也可以用分類的方法去解決
比如我們可以通過詞的後綴來判斷它的詞性, 這邊就以是否包含常見的詞的後綴作爲特徵
>>> def pos_features(word):
... features = {}
... for suffix in common_suffixes:
... features['endswith(%s)' % suffix] = word.lower().endswith(suffix)
... return features
當然這個特徵選取的比較簡單,那麼改進一下,根據後綴,並考慮context,即前一個詞和詞性,一起作爲特徵,這樣考慮就比較全面了。後綴之所以要考慮3種情況,是因爲一般表示詞性的後綴,最多3個字符,s,er,ing
def pos_features(sentence, i, history):
features = {"suffix(1)": sentence[i][-1:],
"suffix(2)": sentence[i][-2:],
"suffix(3)": sentence[i][-3:]}
if i == 0:
features["prev-word"] = "<START>"
features["prev-tag"] = "<START>"
else:
features["prev-word"] = sentence[i-1]
features["prev-tag"] = history[i-1] #history裏面存放了句子裏面每個詞的詞性
return features
那麼分類器,除了bayes外,nltk還有decision tree, Maximum Entropy classifier就不具體說了
還有對於大規模數據處理, pure python的分類器的效率相對是比較底下的,所以必須用高效的語言如c語言實現的分類器, NLTK也支持這樣的分類器的package,可以參考NLTK的web page。