from gensim import corpora, models, similarities

documents = ["Human machine interface for lab abc computer applications",

              "A survey of user opinion of computer system response time",

              "The EPS user interface management system",

              "System and human system engineering testing of EPS",

              "Relation of user perceived response time to error measurement",

              "The generation of random binary unordered trees",

              "The intersection graph of paths in trees",

              "Graph minors IV Widths of trees and well quasi ordering",

              "Graph minors A survey"]  





# remove common words and tokenize

stoplist = set('for a of the and to in'.split())

texts = [[word for word in document.lower().split() if word not in stoplist]

          for document in documents]

 

# remove words that appear only once

all_tokens = sum(texts, [])

tokens_once = set(word for word in set(all_tokens) if all_tokens.count(word) == 1)

texts = [[word for word in text if word not in tokens_once]

          for text in texts]

 

print texts

 

[['human', 'interface', 'computer'],

 ['survey', 'user', 'computer', 'system', 'response', 'time'],

 ['eps', 'user', 'interface', 'system'],

 ['system', 'human', 'system', 'eps'],

 ['user', 'response', 'time'],

 ['trees'],

 ['graph', 'trees'],

 ['graph', 'minors', 'trees'],

 ['graph', 'minors', 'survey']] 
 

去停止詞之後 ，文字變成了這個格式，下面我們看一下如何實現了向量化

dictionary = corpora.Dictionary(texts)

##這裡實現了單詞的--對映

print dictionary.token2id

{'minors': 11, 'graph': 10, 'system': 5, 'trees': 9, 'eps': 8, 'computer': 0,

'survey': 4, 'user': 7, 'human': 1, 'time': 6, 'interface': 2, 'response': 3}

如何用這種方法去表示一片文件呢

new_doc = "Human computer interaction"

new_vec = dictionary.doc2bow(new_doc.lower().split())

print new_vec # the word "interaction" does not appear in the dictionary and is ignored

 

[(0, 1), (1, 1)] 
 

這是什麼意思，首先前面建立的dict沒有interaction，自動過濾 

字典0：computer出現了一次所以[0,1]

字典1：human出現了一次所以[1,1]

其他字典詞出現0詞

corpus = [dictionary.doc2bow(text) for text in texts]

corpora.MmCorpus.serialize('/tmp/deerwester.mm', corpus) # store to disk, for later use

print corpus

 

[(0, 1), (1, 1), (2, 1)]

[(0, 1), (3, 1), (4, 1), (5, 1), (6, 1), (7, 1)]

[(2, 1), (5, 1), (7, 1), (8, 1)]

[(1, 1), (5, 2), (8, 1)]

[(3, 1), (6, 1), (7, 1)]

[(9, 1)]

[(9, 1), (10, 1)]

[(9, 1), (10, 1), (11, 1)]

[(4, 1), (10, 1), (11, 1)]
 

同理對應到文字上