Hive Color

gensim関係のやってみたシリーズのリンク一覧

Python GensimでLDAを使うための前準備・パッケージのインストール

gensimを使ったwikipediaのコーパス作成

gensim0.8.6のチュートリアルをやってみた【コーパスとベクトル空間】

gensim0.8.6のチュートリアルをやってみた【Topics and Transformations】

gensim0.8.6のチュートリアルをやってみた【Similarity Queries】

# ロギングの設定。なくてもOK
import logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)

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

# 出力結果
[['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']]

dictionary = corpora.Dictionary(texts)
dictionary.save('/tmp/deerwester.dict') # store the dictionary, for future reference
# バイナリではなくテキストとして保存する場合
dictionary.save_as_text('/tmp/deerwester_text.dict')

print dictionary

# 出力結果
Dictionary(12 unique tokens)

$ less deerwester_text.dict

0	computer	2
8	eps	2
10	graph	3
1	human	2
2	interface	2
11	minors	2
3	response	2
4	survey	2
5	system	3
6	time	2
9	trees	3
7	user	3

print dictionary.token2id

# 出力結果
{'minors': 11, 'graph': 10, 'system': 5, 'trees': 9, 'eps': 8, 'computer': 0,
'survey': 4, 'user': 7, 'human': 1, 'time': 6, 'interface': 2, 'response': 3}

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)]

corpus = [dictionary.doc2bow(text) for text in texts]
corpora.MmCorpus.serialize('/tmp/deerwester.mm', corpus) # store to disk, for later use

# 後から読み込む場合
corpus = corpora.MmCorpus('/tmp/deerwester.mm')
# ファイルから読み込んだ場合はストリームになっているので単純にはprintできないことに注意。ファイルから読み込んだ場合のprintはこれ↓
# print list(corpus)

print corpus

# 出力結果
[(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)]

# 辞書内の単語とIDの対応表
{'minors': 11, 'graph': 10, 'system': 5, 'trees': 9, 'eps': 8, 'computer': 0,
'survey': 4, 'user': 7, 'human': 1, 'time': 6, 'interface': 2, 'response': 3}

# 元の文章
"Graph minors A survey"

# トークンに分割後
['graph', 'minors', 'survey']

# 辞書内のIDと出現回数のベクトル(ID順でソートされている)
[(4, 1), (10, 1), (11, 1)]