3

cppy/cp_util.py

@@ -0,0 +1,70 @@
+
+import site
+import os,re
+import string,operator
+
+################################################################################
+#  变量
+################################################################################
+testfilename = 'test.txt'
+testfilename = 'pride-and-prejudice.txt'
+testfilename = 'Prey.txt'
+
+site_packages = site.getsitepackages()
+for package in site_packages:
+    if 'package' in  package:
+        basePath = package
+stopwordfilepath = os.path.join(basePath, 'cppy','data','stop_words.txt')
+testfilepath = os.path.join(basePath, 'cppy','data',testfilename )
+
+
+################################################################################
+#  函数
+################################################################################
+def read_file(path_to_file):    
+    with open(path_to_file,encoding='utf-8') as f:
+        data = f.read()
+    return data
+
+def re_split( data ):
+    pattern = re.compile('[\W_]+')
+    data = pattern.sub(' ', data).lower()
+    return data.split()
+
+def get_stopwords( path_to_file = stopwordfilepath ):
+    with open(path_to_file,encoding='utf-8') as f:
+        data = f.read().split(',')        
+    data.extend(list(string.ascii_lowercase))
+    return data
+
+def extract_file_words(path_to_file):
+    word_list = re_split( read_file(path_to_file) )
+    stop_words = get_stopwords()
+    return [ w for w in word_list if ( not w in stop_words ) and len(w) >= 3 ]
+
+def extract_str_words(data_str):
+    word_list = re_split( data_str )
+    stop_words = get_stopwords()
+    return [ w for w in word_list if ( not w in stop_words ) and len(w) >= 3 ]
+
+def count_word(word, word_freqs, stopwords):
+    if word not in stopwords:
+        word_freqs[word] = word_freqs.get(word, 0) + 1
+
+def get_frequencies(word_list):    
+    word_freqs = {}  
+    for word in word_list:  
+        word_freqs[word] = word_freqs.get(word, 0) + 1    
+    return word_freqs
+
+def sort_dict (word_freq):
+    return sorted(word_freq.items(), key=operator.itemgetter(1), reverse=True)
+    # return sorted( word_freq, key=lambda x: x[1], reverse=True )
+
+def print_word_freqs( word_freqs, n = 10):
+    for (w, c) in word_freqs[ :n ]:
+        print( w, '-', c )
+
+
+def  test():
+    print( 'cppy welcome' )

cppy/data/stop_words.txt

@@ -0,0 +1 @@
+a,able,about,across,after,all,almost,also,am,among,an,and,any,are,as,at,be,because,been,but,by,can,cannot,could,dear,did,do,does,either,else,ever,every,for,from,get,got,had,has,have,he,her,hers,him,his,how,however,i,if,in,into,is,it,its,just,least,let,like,likely,may,me,might,most,must,my,neither,no,nor,not,of,off,often,on,only,or,other,our,own,rather,said,say,says,she,should,since,so,some,than,that,the,their,them,then,there,these,they,this,tis,to,too,twas,us,wants,was,we,were,what,when,where,which,while,who,whom,why,will,with,would,yet,you,your

cppy/data/test.txt

@@ -0,0 +1,2 @@
+"Some acquaintance or other, my dear, I suppose; I am sure I do not
+know."