Python 英文分词
来源:互联网 发布:win10磁盘优化 编辑:程序博客网 时间:2024/04/20 03:29
Python 英文分词,词倒排索引
【一.一般多次查询】
'''Created on 2015-11-18'''#encoding=utf-8# List Of English Stop Words# http://armandbrahaj.blog.al/2009/04/14/list-of-english-stop-words/_WORD_MIN_LENGTH = 3_STOP_WORDS = frozenset(['a', 'about', 'above', 'above', 'across', 'after', 'afterwards', 'again', 'against', 'all', 'almost', 'alone', 'along', 'already', 'also','although','always','am','among', 'amongst', 'amoungst', 'amount', 'an', 'and', 'another','any','anyhow','anyone','anything','anyway', 'anywhere', 'are', 'around', 'as','at', 'back','be','became', 'because','become','becomes', 'becoming', 'been', 'before', 'beforehand', 'behind', 'being', 'below', 'beside', 'besides', 'between', 'beyond', 'bill', 'both', 'bottom','but', 'by', 'call', 'can', 'cannot', 'cant', 'co', 'con', 'could', 'couldnt', 'cry', 'de', 'describe', 'detail', 'do', 'done', 'down', 'due', 'during', 'each', 'eg', 'eight', 'either', 'eleven','else', 'elsewhere', 'empty', 'enough', 'etc', 'even', 'ever', 'every', 'everyone', 'everything', 'everywhere', 'except', 'few', 'fifteen', 'fify', 'fill', 'find', 'fire', 'first', 'five', 'for', 'former', 'formerly', 'forty', 'found', 'four', 'from', 'front', 'full', 'further', 'get','give', 'go', 'had', 'has', 'hasnt', 'have', 'he', 'hence', 'her', 'here', 'hereafter', 'hereby', 'herein', 'hereupon', 'hers', 'herself', 'him', 'himself', 'his', 'how', 'however', 'hundred', 'ie', 'if', 'in', 'inc', 'indeed', 'interest', 'into', 'is', 'it', 'its', 'itself', 'keep', 'last', 'latter', 'latterly', 'least', 'less', 'ltd', 'made', 'many', 'may', 'me', 'meanwhile', 'might', 'mill', 'mine', 'more', 'moreover', 'most', 'mostly', 'move', 'much', 'must', 'my', 'myself', 'name', 'namely', 'neither', 'never', 'nevertheless', 'next', 'nine', 'no', 'nobody', 'none', 'noone', 'nor', 'not', 'nothing', 'now', 'nowhere', 'of', 'off', 'often', 'on', 'once', 'one', 'only','onto', 'or', 'other', 'others', 'otherwise', 'our', 'ours', 'ourselves', 'out','over', 'own','part', 'per', 'perhaps', 'please', 'put', 'rather', 're', 'same','see', 'seem', 'seemed', 'seeming', 'seems', 'serious', 'several', 'she', 'should', 'show', 'side', 'since', 'sincere', 'six', 'sixty', 'so', 'some', 'somehow', 'someone', 'something', 'sometime', 'sometimes', 'somewhere', 'still', 'such', 'system', 'take', 'ten', 'than', 'that', 'the', 'their', 'them', 'themselves', 'then', 'thence', 'there', 'thereafter', 'thereby', 'therefore', 'therein', 'thereupon', 'these', 'they', 'thickv', 'thin', 'third','this', 'those', 'though', 'three', 'through', 'throughout', 'thru', 'thus', 'to', 'together', 'too', 'top', 'toward', 'towards', 'twelve', 'twenty', 'two', 'un', 'under', 'until', 'up', 'upon', 'us', 'very', 'via', 'was', 'we', 'well', 'were', 'what', 'whatever', 'when', 'whence', 'whenever', 'where', 'whereafter','whereas', 'whereby', 'wherein', 'whereupon', 'wherever', 'whether', 'which', 'while', 'whither', 'who', 'whoever', 'whole', 'whom', 'whose', 'why', 'will', 'with', 'within', 'without', 'would', 'yet', 'you', 'your', 'yours', 'yourself','yourselves', 'the'])def word_split_out(text): word_list = [] wcurrent = [] for i, c in enumerate(text): if c.isalnum(): wcurrent.append(c) elif wcurrent: word = u''.join(wcurrent) word_list.append(word) wcurrent = [] if wcurrent: word = u''.join(wcurrent) word_list.append(word) return word_listdef word_split(text): """ Split a text in words. Returns a list of tuple that contains (word, location) location is the starting byte position of the word. """ word_list = [] wcurrent = [] windex = 0 for i, c in enumerate(text): if c.isalnum(): wcurrent.append(c) elif wcurrent: word = u''.join(wcurrent) word_list.append((windex, word)) windex += 1 wcurrent = [] if wcurrent: word = u''.join(wcurrent) word_list.append((windex, word)) windex += 1 return word_listdef words_cleanup(words): """ Remove words with length less then a minimum and stopwords. """ cleaned_words = [] for index, word in words: if len(word) < _WORD_MIN_LENGTH or word in _STOP_WORDS: continue cleaned_words.append((index, word)) return cleaned_wordsdef words_normalize(words): """ Do a normalization precess on words. In this case is just a tolower(), but you can add accents stripping, convert to singular and so on... """ normalized_words = [] for index, word in words: wnormalized = word.lower() normalized_words.append((index, wnormalized)) return normalized_wordsdef word_index(text): """ Just a helper method to process a text. It calls word split, normalize and cleanup. """ words = word_split(text) words = words_normalize(words) words = words_cleanup(words) return wordsdef inverted_index(text): """ Create an Inverted-Index of the specified text document. {word:[locations]} """ inverted = {} for index, word in word_index(text): locations = inverted.setdefault(word, []) locations.append(index) return inverteddef inverted_index_add(inverted, doc_id, doc_index): """ Add Invertd-Index doc_index of the document doc_id to the Multi-Document Inverted-Index (inverted), using doc_id as document identifier. {word:{doc_id:[locations]}} """ for word, locations in doc_index.iteritems(): indices = inverted.setdefault(word, {}) indices[doc_id] = locations return inverteddef search(inverted, query): """ Returns a set of documents id that contains all the words in your query. """ words = [word for _, word in word_index(query) if word in inverted] results = [set(inverted[word].keys()) for word in words] return reduce(lambda x, y: x & y, results) if results else []if __name__ == '__main__': doc1 = """Niners head coach Mike Singletary will let Alex Smith remain his starting quarterback, but his vote of confidence is anything but a long-term mandate.Smith now will work on a week-to-week basis, because Singletary has voided his year-long lease on the job."I think from this point on, you have to do what's best for the football team,"Singletary said Monday, one day after threatening to bench Smith during a 27-24 loss to the visiting Eagles.""" doc2 = """The fifth edition of West Coast Green, a conference focusing on "green" home innovations and products, rolled into San Francisco's Fort Mason last week intent, per usual, on making our living spaces more environmentally friendly - one used-tire house at a time.To that end, there were presentations on topics such as water efficiency and the burgeoning future of Net Zero-rated buildings that consume no energy and produce no carbon emissions.""" # Build Inverted-Index for documents inverted = {} documents = {'doc1':doc1, 'doc2':doc2} for doc_id, text in documents.iteritems(): doc_index = inverted_index(text) inverted_index_add(inverted, doc_id, doc_index) # Print Inverted-Index for word, doc_locations in inverted.iteritems(): print word, doc_locations # Search something and print results queries = ['Week', 'Niners week', 'West-coast Week'] for query in queries: result_docs = search(inverted, query) print "Search for '%s': %r" % (query, result_docs) for _, word in word_index(query): def extract_text(doc, index): word_list = word_split_out(documents[doc]) word_string = "" for i in range(index, index +4): word_string += word_list[i] + " " word_string = word_string.replace("\n", "") return word_string for doc in result_docs: for index in inverted[word][doc]: print ' - %s...' % extract_text(doc, index) print
【二. 短语查询】
'''Created on 2015-11-18'''#encoding=utf-8# List Of English Stop Words# http://armandbrahaj.blog.al/2009/04/14/list-of-english-stop-words/_WORD_MIN_LENGTH = 3_STOP_WORDS = frozenset(['a', 'about', 'above', 'above', 'across', 'after', 'afterwards', 'again', 'against', 'all', 'almost', 'alone', 'along', 'already', 'also','although','always','am','among', 'amongst', 'amoungst', 'amount', 'an', 'and', 'another','any','anyhow','anyone','anything','anyway', 'anywhere', 'are', 'around', 'as','at', 'back','be','became', 'because','become','becomes', 'becoming', 'been', 'before', 'beforehand', 'behind', 'being', 'below', 'beside', 'besides', 'between', 'beyond', 'bill', 'both', 'bottom','but', 'by', 'call', 'can', 'cannot', 'cant', 'co', 'con', 'could', 'couldnt', 'cry', 'de', 'describe', 'detail', 'do', 'done', 'down', 'due', 'during', 'each', 'eg', 'eight', 'either', 'eleven','else', 'elsewhere', 'empty', 'enough', 'etc', 'even', 'ever', 'every', 'everyone', 'everything', 'everywhere', 'except', 'few', 'fifteen', 'fify', 'fill', 'find', 'fire', 'first', 'five', 'for', 'former', 'formerly', 'forty', 'found', 'four', 'from', 'front', 'full', 'further', 'get','give', 'go', 'had', 'has', 'hasnt', 'have', 'he', 'hence', 'her', 'here', 'hereafter', 'hereby', 'herein', 'hereupon', 'hers', 'herself', 'him', 'himself', 'his', 'how', 'however', 'hundred', 'ie', 'if', 'in', 'inc', 'indeed', 'interest', 'into', 'is', 'it', 'its', 'itself', 'keep', 'last', 'latter', 'latterly', 'least', 'less', 'ltd', 'made', 'many', 'may', 'me', 'meanwhile', 'might', 'mill', 'mine', 'more', 'moreover', 'most', 'mostly', 'move', 'much', 'must', 'my', 'myself', 'name', 'namely', 'neither', 'never', 'nevertheless', 'next', 'nine', 'no', 'nobody', 'none', 'noone', 'nor', 'not', 'nothing', 'now', 'nowhere', 'of', 'off', 'often', 'on', 'once', 'one', 'only','onto', 'or', 'other', 'others', 'otherwise', 'our', 'ours', 'ourselves', 'out','over', 'own','part', 'per', 'perhaps', 'please', 'put', 'rather', 're', 'same','see', 'seem', 'seemed', 'seeming', 'seems', 'serious', 'several', 'she', 'should', 'show', 'side', 'since', 'sincere', 'six', 'sixty', 'so', 'some', 'somehow', 'someone', 'something', 'sometime', 'sometimes', 'somewhere', 'still', 'such', 'system', 'take', 'ten', 'than', 'that', 'the', 'their', 'them', 'themselves', 'then', 'thence', 'there', 'thereafter', 'thereby', 'therefore', 'therein', 'thereupon', 'these', 'they', 'thickv', 'thin', 'third','this', 'those', 'though', 'three', 'through', 'throughout', 'thru', 'thus', 'to', 'together', 'too', 'top', 'toward', 'towards', 'twelve', 'twenty', 'two', 'un', 'under', 'until', 'up', 'upon', 'us', 'very', 'via', 'was', 'we', 'well', 'were', 'what', 'whatever', 'when', 'whence', 'whenever', 'where', 'whereafter','whereas', 'whereby', 'wherein', 'whereupon', 'wherever', 'whether', 'which', 'while', 'whither', 'who', 'whoever', 'whole', 'whom', 'whose', 'why', 'will', 'with', 'within', 'without', 'would', 'yet', 'you', 'your', 'yours', 'yourself','yourselves', 'the'])def word_split_out(text): word_list = [] wcurrent = [] for i, c in enumerate(text): if c.isalnum(): wcurrent.append(c) elif wcurrent: word = u''.join(wcurrent) word_list.append(word) wcurrent = [] if wcurrent: word = u''.join(wcurrent) word_list.append(word) return word_listdef word_split(text): """ Split a text in words. Returns a list of tuple that contains (word, location) location is the starting byte position of the word. """ word_list = [] wcurrent = [] windex = 0 for i, c in enumerate(text): if c.isalnum(): wcurrent.append(c) elif wcurrent: word = u''.join(wcurrent) word_list.append((windex, word)) windex += 1 wcurrent = [] if wcurrent: word = u''.join(wcurrent) word_list.append((windex, word)) windex += 1 return word_listdef words_cleanup(words): """ Remove words with length less then a minimum and stopwords. """ cleaned_words = [] for index, word in words: if len(word) < _WORD_MIN_LENGTH or word in _STOP_WORDS: continue cleaned_words.append((index, word)) return cleaned_wordsdef words_normalize(words): """ Do a normalization precess on words. In this case is just a tolower(), but you can add accents stripping, convert to singular and so on... """ normalized_words = [] for index, word in words: wnormalized = word.lower() normalized_words.append((index, wnormalized)) return normalized_wordsdef word_index(text): """ Just a helper method to process a text. It calls word split, normalize and cleanup. """ words = word_split(text) words = words_normalize(words) words = words_cleanup(words) return wordsdef inverted_index(text): """ Create an Inverted-Index of the specified text document. {word:[locations]} """ inverted = {} for index, word in word_index(text): locations = inverted.setdefault(word, []) locations.append(index) return inverteddef inverted_index_add(inverted, doc_id, doc_index): """ Add Invertd-Index doc_index of the document doc_id to the Multi-Document Inverted-Index (inverted), using doc_id as document identifier. {word:{doc_id:[locations]}} """ for word, locations in doc_index.iteritems(): indices = inverted.setdefault(word, {}) indices[doc_id] = locations return inverteddef search(inverted, query): """ Returns a set of documents id that contains all the words in your query. """ words = [word for _, word in word_index(query) if word in inverted] results = [set(inverted[word].keys()) for word in words] return reduce(lambda x, y: x & y, results) if results else []def distance_between_word(word_index_1, word_index_2, distance): """ To judge whether the distance between the two words is equal distance """ distance_list = [] for index_1 in word_index_1: for index_2 in word_index_2: if (index_1 < index_2): if(index_2 - index_1 == distance): distance_list.append(index_1) else: continue return distance_listdef extract_text(doc, index): """ Output search results """ word_list = word_split_out(documents[doc]) word_string = "" for i in range(index, index +4): word_string += word_list[i] + " " word_string = word_string.replace("\n", "") return word_stringif __name__ == '__main__': doc1 = """Niners head coach Mike Singletary will let Alex Smith remain his starting quarterback, but his vote of confidence is anything but a long-term mandate.Smith now will work on a week-to-week basis, because Singletary has voided his year-long lease on the job."I think from this point on, you have to do what's best for the football team,"Singletary said Monday, one day after threatening to bench Smith during a 27-24 loss to the visiting Eagles.""" doc2 = """The fifth edition of West Coast Green, a conference focusing on "green" home innovations and products, rolled into San Francisco's Fort Mason last week intent, per usual, on making our living spaces more environmentally friendly - one used-tire house at a time.To that end, there were presentations on topics such as water efficiency and the burgeoning future of Net Zero-rated buildings that consume no energy and produce no carbon emissions.""" # Build Inverted-Index for documents inverted = {} documents = {'doc1':doc1, 'doc2':doc2} for doc_id, text in documents.iteritems(): doc_index = inverted_index(text) inverted_index_add(inverted, doc_id, doc_index) # Print Inverted-Index for word, doc_locations in inverted.iteritems(): print word, doc_locations # Search something and print results queries = ['Week', 'water efficiency', 'Singletary said Monday'] for query in queries: result_docs = search(inverted, query) print "Search for '%s': %r" % (query, result_docs) query_word_list = word_index(query) for doc in result_docs: index_first = [] distance = 1 for _, word in query_word_list: index_second = inverted[word][doc] index_new = [] if(index_first != []): index_first = distance_between_word(index_first, index_second, distance) distance += 1 else: index_first = index_second for index in index_first: print ' - %s...' % extract_text(doc, index) print【三. 临近词查询】
'''Created on 2015-11-18'''#encoding=utf-8# List Of English Stop Words# http://armandbrahaj.blog.al/2009/04/14/list-of-english-stop-words/_WORD_MIN_LENGTH = 3_STOP_WORDS = frozenset(['a', 'about', 'above', 'above', 'across', 'after', 'afterwards', 'again', 'against', 'all', 'almost', 'alone', 'along', 'already', 'also','although','always','am','among', 'amongst', 'amoungst', 'amount', 'an', 'and', 'another','any','anyhow','anyone','anything','anyway', 'anywhere', 'are', 'around', 'as','at', 'back','be','became', 'because','become','becomes', 'becoming', 'been', 'before', 'beforehand', 'behind', 'being', 'below', 'beside', 'besides', 'between', 'beyond', 'bill', 'both', 'bottom','but', 'by', 'call', 'can', 'cannot', 'cant', 'co', 'con', 'could', 'couldnt', 'cry', 'de', 'describe', 'detail', 'do', 'done', 'down', 'due', 'during', 'each', 'eg', 'eight', 'either', 'eleven','else', 'elsewhere', 'empty', 'enough', 'etc', 'even', 'ever', 'every', 'everyone', 'everything', 'everywhere', 'except', 'few', 'fifteen', 'fify', 'fill', 'find', 'fire', 'first', 'five', 'for', 'former', 'formerly', 'forty', 'found', 'four', 'from', 'front', 'full', 'further', 'get','give', 'go', 'had', 'has', 'hasnt', 'have', 'he', 'hence', 'her', 'here', 'hereafter', 'hereby', 'herein', 'hereupon', 'hers', 'herself', 'him', 'himself', 'his', 'how', 'however', 'hundred', 'ie', 'if', 'in', 'inc', 'indeed', 'interest', 'into', 'is', 'it', 'its', 'itself', 'keep', 'last', 'latter', 'latterly', 'least', 'less', 'ltd', 'made', 'many', 'may', 'me', 'meanwhile', 'might', 'mill', 'mine', 'more', 'moreover', 'most', 'mostly', 'move', 'much', 'must', 'my', 'myself', 'name', 'namely', 'neither', 'never', 'nevertheless', 'next', 'nine', 'no', 'nobody', 'none', 'noone', 'nor', 'not', 'nothing', 'now', 'nowhere', 'of', 'off', 'often', 'on', 'once', 'one', 'only','onto', 'or', 'other', 'others', 'otherwise', 'our', 'ours', 'ourselves', 'out','over', 'own','part', 'per', 'perhaps', 'please', 'put', 'rather', 're', 'same','see', 'seem', 'seemed', 'seeming', 'seems', 'serious', 'several', 'she', 'should', 'show', 'side', 'since', 'sincere', 'six', 'sixty', 'so', 'some', 'somehow', 'someone', 'something', 'sometime', 'sometimes', 'somewhere', 'still', 'such', 'system', 'take', 'ten', 'than', 'that', 'the', 'their', 'them', 'themselves', 'then', 'thence', 'there', 'thereafter', 'thereby', 'therefore', 'therein', 'thereupon', 'these', 'they', 'thickv', 'thin', 'third','this', 'those', 'though', 'three', 'through', 'throughout', 'thru', 'thus', 'to', 'together', 'too', 'top', 'toward', 'towards', 'twelve', 'twenty', 'two', 'un', 'under', 'until', 'up', 'upon', 'us', 'very', 'via', 'was', 'we', 'well', 'were', 'what', 'whatever', 'when', 'whence', 'whenever', 'where', 'whereafter','whereas', 'whereby', 'wherein', 'whereupon', 'wherever', 'whether', 'which', 'while', 'whither', 'who', 'whoever', 'whole', 'whom', 'whose', 'why', 'will', 'with', 'within', 'without', 'would', 'yet', 'you', 'your', 'yours', 'yourself','yourselves', 'the'])def word_split_out(text): word_list = [] wcurrent = [] for i, c in enumerate(text): if c.isalnum(): wcurrent.append(c) elif wcurrent: word = u''.join(wcurrent) word_list.append(word) wcurrent = [] if wcurrent: word = u''.join(wcurrent) word_list.append(word) return word_listdef word_split(text): """ Split a text in words. Returns a list of tuple that contains (word, location) location is the starting byte position of the word. """ word_list = [] wcurrent = [] windex = 0 for i, c in enumerate(text): if c.isalnum(): wcurrent.append(c) elif wcurrent: word = u''.join(wcurrent) word_list.append((windex, word)) windex += 1 wcurrent = [] if wcurrent: word = u''.join(wcurrent) word_list.append((windex, word)) windex += 1 return word_listdef words_cleanup(words): """ Remove words with length less then a minimum and stopwords. """ cleaned_words = [] for index, word in words: if len(word) < _WORD_MIN_LENGTH or word in _STOP_WORDS: continue cleaned_words.append((index, word)) return cleaned_wordsdef words_normalize(words): """ Do a normalization precess on words. In this case is just a tolower(), but you can add accents stripping, convert to singular and so on... """ normalized_words = [] for index, word in words: wnormalized = word.lower() normalized_words.append((index, wnormalized)) return normalized_wordsdef word_index(text): """ Just a helper method to process a text. It calls word split, normalize and cleanup. """ words = word_split(text) words = words_normalize(words) words = words_cleanup(words) return wordsdef inverted_index(text): """ Create an Inverted-Index of the specified text document. {word:[locations]} """ inverted = {} for index, word in word_index(text): locations = inverted.setdefault(word, []) locations.append(index) return inverteddef inverted_index_add(inverted, doc_id, doc_index): """ Add Invertd-Index doc_index of the document doc_id to the Multi-Document Inverted-Index (inverted), using doc_id as document identifier. {word:{doc_id:[locations]}} """ for word, locations in doc_index.iteritems(): indices = inverted.setdefault(word, {}) indices[doc_id] = locations return inverteddef search(inverted, query): """ Returns a set of documents id that contains all the words in your query. """ words = [word for _, word in word_index(query) if word in inverted] results = [set(inverted[word].keys()) for word in words] return reduce(lambda x, y: x & y, results) if results else []def distance_between_word(word_index_1, word_index_2, distance): """ To judge whether the distance between the two words is smaller than distance """ distance_list = [] for index_1 in word_index_1: for index_2 in word_index_2: if (index_1 < index_2): if(index_2 - index_1 <= distance): distance_list.append(index_1) else: continue return distance_listdef extract_text(doc, index): """ Output search results """ word_list = word_split_out(documents[doc]) word_string = "" for i in range(index, index + 7): word_string += word_list[i] + " " word_string = word_string.replace("\n", "") return word_stringif __name__ == '__main__': doc1 = """Niners head coach Mike Singletary will let Alex Smith remain his starting quarterback, but his vote of confidence is anything but a long-term mandate.Smith now will work on a week-to-week basis, because Singletary has voided his year-long lease on the job."I think from this point on, you have to do what's best for the football team,"Singletary said Monday, one day after threatening to bench Smith during a 27-24 loss to the visiting Eagles.""" doc2 = """The fifth edition of West Coast Green, a conference focusing on "green" home innovations and products, rolled into San Francisco's Fort Mason last week intent, per usual, on making our living spaces more environmentally friendly - one used-tire house at a time.To that end, there were presentations on topics such as water efficiency and the burgeoning future of Net Zero-rated buildings that consume no energy and produce no carbon emissions.""" # Build Inverted-Index for documents inverted = {} documents = {'doc1':doc1, 'doc2':doc2} for doc_id, text in documents.iteritems(): doc_index = inverted_index(text) inverted_index_add(inverted, doc_id, doc_index) # Print Inverted-Index for word, doc_locations in inverted.iteritems(): print word, doc_locations # Search something and print results queries = ['Week', 'buildings consume', 'Alex remain quarterback'] for query in queries: result_docs = search(inverted, query) print "Search for '%s': %r" % (query, result_docs) query_word_list = word_index(query) for doc in result_docs: index_first = [] step = 3 distance = 3 for _, word in query_word_list: index_second = inverted[word][doc] index_new = [] if(index_first != []): index_first = distance_between_word(index_first, index_second, distance) distance += step else: index_first = index_second for index in index_first: print ' - %s...' % extract_text(doc, index) print
0 0
- Python 英文分词
- Python 英文分词
- 简易英文分词算法(python)
- 利用python对一段英文文本进行分词,分句
- 英文分词+提取词干
- JavaScript英文分词
- 【英文分词】Stemming Segmentation,基于词干分词
- python 分词
- 用python进行数据预处理,过滤特殊符号,英文和数字。(适用于中文分词)
- 英文分词算法(Porter stemmer)
- 英文分词算法(Porter stemmer)
- 英文分词算法(Porter stemmer)
- python中文分词:结巴分词
- 一个简单的英文分词程序
- 关于英文文章分词排序的问题
- 利用 tweet 工具进行英文分词
- elasticsearch 1.1.0 mmseg 英文数字分词
- 英文分词的算法和原理
- SFTP使用资料整理及例子
- 正则表达式
- 苹果开源
- 1029. 旧键盘(20)
- 简述quartz应用到servlet
- Python 英文分词
- HDU - 2444 The Accomodation of Students
- MySQL数据导出导入
- STM32基础学习
- 利用指针对字符串排序
- ArrayList<Integer> 中remove 方法调用的区分
- groovy
- 拓扑排序 详解
- 机器学习实战python版 朴素贝叶斯示例 垃圾邮件分类 从个人广告中获取趋于趋向