def analyze(self,
text,
window=2,
lower=False,
vertex_source='all_filters',
edge_source='no_stop_words',
pagerank_config={
'alpha': 0.85,
}):
"""分析文本
Keyword arguments:
text -- 文本内容，字符串。
window -- 窗口大小，int，用来构造单词之间的边。默认值为2。
lower -- 是否将文本转换为小写。默认为False。
vertex_source -- 选择使用words_no_filter, words_no_stop_words, words_all_filters中的哪一个来构造pagerank对应的图中的节点。
默认值为`'all_filters'`，可选值为`'no_filter', 'no_stop_words', 'all_filters'`。关键词也来自`vertex_source`。
edge_source -- 选择使用words_no_filter, words_no_stop_words, words_all_filters中的哪一个来构造pagerank对应的图中的节点之间的边。
默认值为`'no_stop_words'`，可选值为`'no_filter', 'no_stop_words', 'all_filters'`。边的构造要结合`window`参数。
"""
# self.text = util.as_text(text)
self.text = text
self.word_index = {}
self.index_word = {}
self.keywords = []
self.graph = None
result = self.seg.segment(text=text, lower=lower)
self.sentences = result.sentences
self.words_no_filter = result.words_no_filter
self.words_no_stop_words = result.words_no_stop_words
self.words_all_filters = result.words_all_filters
util.debug(20 * '*')
util.debug('self.sentences in TextRank4Keyword:\n',
' || '.join(self.sentences))
util.debug('self.words_no_filter in TextRank4Keyword:\n',
self.words_no_filter)
util.debug('self.words_no_stop_words in TextRank4Keyword:\n',
self.words_no_stop_words)
util.debug('self.words_all_filters in TextRank4Keyword:\n',
self.words_all_filters)
options = ['no_filter', 'no_stop_words', 'all_filters']
if vertex_source in options:
_vertex_source = result['words_' + vertex_source]
else:
_vertex_source = result['words_all_filters']
if edge_source in options:
_edge_source = result['words_' + edge_source]
else:
_edge_source = result['words_no_stop_words']
self.keywords = util.sort_words(_vertex_source,
_edge_source,
window=window,
pagerank_config=pagerank_config)
def analyze(self, text,#对关键词进行网络计算
window=2,
lower=False,
vertex_source='all_filters',
edge_source='no_stop_words',
pagerank_config={'alpha': 0.85, }):
#text - - 文本内容，字符串。
#window - - 窗口大小，int，用来构造单词之间的边。默认值为2。
#lower - - 是否将文本转换为小写。默认为False。
# self.text = util.as_text(text)
self.text = text
self.word_index = {}
self.index_word = {}
self.keywords = []
self.graph = None
result = self.seg.segment(text=text, lower=lower)
self.sentences = result.sentences
self.words_no_filter = result.words_no_filter
self.words_no_stop_words = result.words_no_stop_words
self.words_all_filters = result.words_all_filters
options = ['no_filter', 'no_stop_words', 'all_filters']
if vertex_source in options:
_vertex_source = result['words_' + vertex_source]
else:
_vertex_source = result['words_all_filters']
if edge_source in options:
_edge_source = result['words_' + edge_source]
else:
_edge_source = result['words_no_stop_words']
self.keywords = util.sort_words(_vertex_source, _edge_source, window=window, pagerank_config=pagerank_config)