#coding=utf-8import xlrdimport distancefrom sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizerimport numpy as npfrom scipy.linalg import normworkbook = xlrd.open_workbook(u'工程师问答.xls')sheet_names= workbook.sheet_names()ls = []for sheet_name in sheet_names:    sheet1 = workbook.sheet_by_name(sheet_name)    for i in range(1, 3858):        row = sheet1.row_values(i)        ls.append(row[0])# print len(ls)target = u'D90的发动机热效率是多少？'print u'目标语句：' + target# 编辑距离计算def edit_distance(s1, s2):    return distance.levenshtein(s1, s2)results = list(filter(lambda x: edit_distance(x, target) <= 5, ls))print u'1)编辑距离计算，阈值为5'for i in results:    print i# 杰卡德系数计算def jaccard_similarity(s1, s2):    def add_space(s):        return ' '.join(list(s))        # 将字中间加入空格    s1, s2 = add_space(s1), add_space(s2)    # 转化为TF矩阵    cv = CountVectorizer(tokenizer=lambda s: s.split())    corpus = [s1, s2]    vectors = cv.fit_transform(corpus).toarray()    # 求交集    numerator = np.sum(np.min(vectors, axis=0))    # 求并集    denominator = np.sum(np.max(vectors, axis=0))    # 计算杰卡德系数    return 1.0 * numerator / denominatorresults = list(filter(lambda x: jaccard_similarity(x, target) > 0.6, ls))print u'2)杰卡德系数计算，阈值为0.6'for i in results:    print i# TF 计算def tf_similarity(s1, s2):    def add_space(s):        return ' '.join(list(s))        # 将字中间加入空格    s1, s2 = add_space(s1), add_space(s2)    # 转化为TF矩阵    cv = CountVectorizer(tokenizer=lambda s: s.split())    corpus = [s1, s2]    vectors = cv.fit_transform(corpus).toarray()    # 计算TF系数    return np.dot(vectors[0], vectors[1]) / (norm(vectors[0]) * norm(vectors[1]))results = list(filter(lambda x: tf_similarity(x, target) > 0.7, ls))print u'3)TF 计算，阈值为0.7'for i in results:    print i# TFIDF 系数def tfidf_similarity(s1, s2):    def add_space(s):        return ' '.join(list(s))        # 将字中间加入空格    s1, s2 = add_space(s1), add_space(s2)    # 转化为TF矩阵    cv = TfidfVectorizer(tokenizer=lambda s: s.split())    corpus = [s1, s2]    vectors = cv.fit_transform(corpus).toarray()    # 计算TF系数    return np.dot(vectors[0], vectors[1]) / (norm(vectors[0]) * norm(vectors[1]))results = list(filter(lambda x: tfidf_similarity(x, target) > 0.6, ls))print u'4)TFIDF 系数，阈值为0.6'for i in results:    print i