讓 jieba 可以切換 idf 語料庫

1. 新增繁體中文 idf 語料庫
2. 為了讓 jieba 可以切換 iff 語料庫，新增 get_idf, set_idf_path 方法，並改寫 extract_tags
3. test 增加 extract_tags_idfpath

jieba/__init__.py

@@ -39,7 +39,7 @@ def gen_trie(f_name):
     trie = {}
     ltotal = 0.0
     with open(f_name, 'rb') as f:
-        lineno = 0 
+        lineno = 0
         for line in f.read().rstrip().decode('utf-8').split('\n'):
             lineno += 1
             try:
@@ -134,7 +134,7 @@ def __cut_all(sentence):
     for k,L in dag.iteritems():
         if len(L)==1 and k>old_j:
             yield sentence[k:L[0]+1]
-            old_j = L[0] 
+            old_j = L[0]
         else:
             for j in L:
                 if j>k:
@@ -195,7 +195,7 @@ def __cut_DAG_NO_HMM(sentence):
             if len(buf)>0:
                 yield buf
                 buf = u''
-            yield l_word        
+            yield l_word
             x =y
     if len(buf)>0:
         yield buf
@@ -227,7 +227,7 @@ def __cut_DAG(sentence):
                         for elem in buf:
                             yield elem
                     buf=u''
-            yield l_word        
+            yield l_word
         x =y
 
     if len(buf)>0:
@@ -243,8 +243,8 @@ def __cut_DAG(sentence):
                     yield elem
 
 def cut(sentence,cut_all=False,HMM=True):
-    '''The main function that segments an entire sentence that contains 
+    '''The main function that segments an entire sentence that contains
-    Chinese characters into seperated words. 
+    Chinese characters into seperated words.
     Parameter:
         - sentence: The String to be segmented
         - cut_all: Model. True means full pattern, false means accurate pattern.
@@ -257,8 +257,8 @@ def cut(sentence,cut_all=False,HMM=True):
             sentence = sentence.decode('gbk','ignore')
     '''
         \u4E00-\u9FA5a-zA-Z0-9+#&\._ : All non-space characters. Will be handled with re_han
-        \r\n|\s : whitespace characters. Will not be Handled. 
+        \r\n|\s : whitespace characters. Will not be Handled.
-    ''' 
+    '''
     re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5a-zA-Z0-9+#&\._]+)", re.U), re.compile(ur"(\r\n|\s)", re.U)
     if cut_all:
         re_han, re_skip = re.compile(ur"([\u4E00-\u9FA5]+)", re.U), re.compile(ur"[^a-zA-Z0-9+#\n]", re.U)
@@ -306,7 +306,7 @@ def load_userdict(f):
     ''' Load personalized dict to improve detect rate.
     Parameter:
         - f : A plain text file contains words and their ocurrences.
-    Structure of dict file: 
+    Structure of dict file:
     word1 freq1 word_type1
     word2 freq2 word_type2
     ...
@@ -372,7 +372,7 @@ def enable_parallel(processnum=None):
     def pcut(sentence,cut_all=False,HMM=True):
         parts = re.compile('([\r\n]+)').split(sentence)
         if cut_all:
-            result = pool.map(__lcut_all,parts) 
+            result = pool.map(__lcut_all,parts)
         else:
             if HMM:
                 result = pool.map(__lcut,parts)
@@ -418,7 +418,7 @@ def tokenize(unicode_sentence,mode="default",HMM=True):
     #mode ("default" or "search")
     if not isinstance(unicode_sentence, unicode):
         raise Exception("jieba: the input parameter should  unicode.")
-    start = 0 
+    start = 0
     if mode=='default':
         for w in cut(unicode_sentence,HMM=HMM):
             width = len(w)

jieba/analyse/__init__.py

@@ -1,3 +1,4 @@
+#encoding=utf-8
 import jieba
 import os
 try:
@@ -5,22 +6,34 @@ try:
 except ImportError:
     pass
 
-_curpath=os.path.normpath( os.path.join( os.getcwd(), os.path.dirname(__file__) )  )
+_curpath = os.path.normpath( os.path.join( os.getcwd(), os.path.dirname(__file__) )  )
-f_name = os.path.join(_curpath,"idf.txt")
+abs_path = os.path.join(_curpath, "idf.txt")
-content = open(f_name,'rb').read().decode('utf-8')
+IDF_DICTIONARY = abs_path
 
-idf_freq = {}
+def set_idf_path(idf_path):
-lines = content.split('\n')
+    global IDF_DICTIONARY
-for line in lines:
+    abs_path = os.path.normpath( os.path.join( os.getcwd(), idf_path )  )
-    word,freq = line.split(' ')
+    if not os.path.exists(abs_path):
-    idf_freq[word] = float(freq)
+        raise Exception("jieba: path does not exist:" + abs_path)
+    IDF_DICTIONARY = abs_path
+    return
 
-median_idf = sorted(idf_freq.values())[len(idf_freq)/2]
+def get_idf(abs_path):
-stop_words= set([
+    content = open(abs_path,'rb').read().decode('utf-8')
-"the","of","is","and","to","in","that","we","for","an","are","by","be","as","on","with","can","if","from","which","you","it","this","then","at","have","all","not","one","has","or","that"
+    idf_freq = {}
-])
+    lines = content.split('\n')
+    for line in lines:
+        word,freq = line.split(' ')
+        idf_freq[word] = float(freq)
+    median_idf = sorted(idf_freq.values())[len(idf_freq)/2]
+    return idf_freq, median_idf
 
 def extract_tags(sentence,topK=20):
+    global IDF_DICTIONARY
+    idf_freq, median_idf = get_idf(IDF_DICTIONARY)
+    stop_words= set([
+        "the","of","is","and","to","in","that","we","for","an","are","by","be","as","on","with","can","if","from","which","you","it","this","then","at","have","all","not","one","has","or","that"
+    ])
     words = jieba.cut(sentence)
     freq = {}
     for w in words:

test/extract_tags_idfpath.py

@@ -0,0 +1,32 @@
+import sys
+sys.path.append('../')
+
+import jieba
+import jieba.analyse
+from optparse import OptionParser
+
+USAGE = "usage:    python extract_tags_idfpath.py [file name] -k [top k]"
+
+parser = OptionParser(USAGE)
+parser.add_option("-k", dest="topK")
+opt, args = parser.parse_args()
+
+
+if len(args) < 1:
+    print USAGE
+    sys.exit(1)
+
+file_name = args[0]
+
+if opt.topK is None:
+    topK = 10
+else:
+    topK = int(opt.topK)
+
+content = open(file_name, 'rb').read()
+
+jieba.analyse.set_idf_path("../extra_dict/idf.txt.big");
+
+tags = jieba.analyse.extract_tags(content, topK=topK)
+
+print ",".join(tags)