def test_delimiter_valid(self): self.assertEqual(whitespace('data science'), ['data', 'science']) self.assertEqual(whitespace('data science'), ['data', 'science']) self.assertEqual(whitespace('data science'), ['data', 'science']) self.assertEqual(whitespace('data\tscience'), ['data', 'science']) self.assertEqual(whitespace('data\nscience'), ['data', 'science'])
def overlap_coefficient(pair, feature): if feature in products[pair[0]] and feature in products[pair[1]]: val = [products[pair[0]].get(feature, [''])[0].lower(), products[pair[1]].get(feature, [''])[0].lower()] val[0] = ' '.join([word for word in val[0].split() if word not in stop_words]) val[1] = ' '.join([word for word in val[1].split() if word not in stop_words]) return simfunctions.overlap_coefficient(tokenizers.whitespace(val[0]), tokenizers.whitespace(val[1])) else: return noneValue
def monge_elkan(pair, feature): if feature in products[pair[0]] and feature in products[pair[1]]: return simfunctions.monge_elkan( tokenizers.whitespace(products[pair[0]].get(feature, [''])[0].lower()), tokenizers.whitespace(products[pair[1]].get(feature, [''])[0].lower())) else: return noneValue
def find_model_str(name, min_len=5): model_strs = [] for string in tokenizers.whitespace(name): if len(string) < min_len: continue contains_symbol = False for char in string: if not char.isalpha(): contains_symbol = True if contains_symbol: model_strs.append(string) return model_strs
def generate_feature(file_name): lines = stage3_helper.read_file(file_name) features = [] labels = [] all_names = [] for line in lines: json1, json2, label = stage3_helper.read_jsons_label_from_line(line) string1, string2 = stage3_helper.get_attribute_from_jsons( json1, json2, product_name) all_names.append(tokenizers.whitespace(string1)) all_names.append(tokenizers.whitespace(string2)) for line in lines: json1, json2, label = stage3_helper.read_jsons_label_from_line(line) feature = [] # TODO: Add more features and optimize features. # product_type string1, string2 = stage3_helper.get_attribute_from_jsons( json1, json2, product_type) string1 = string1.lower() string2 = string2.lower() feature.append( simfunctions.jaccard(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.jaro_winkler(string1, string2, prefix_weight=0.1)) feature.append( simfunctions.jaro( tokenizers.whitespace(string1)[0], tokenizers.whitespace(string2)[0])) # if len(string1) == len(string2): # feature.append(simfunctions.hamming_distance(string1, string2)) # else: # feature.append(5) feature.append( simfunctions.cosine(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.overlap_coefficient(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.monge_elkan(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.tfidf(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append(len(string1)) feature.append(len(string2)) feature.append(len(string1) - len(string2)) feature.append(len(tokenizers.whitespace(string1))) feature.append(len(tokenizers.whitespace(string2))) # product_name string1, string2 = stage3_helper.get_attribute_from_jsons( json1, json2, product_name) string1 = string1.lower() string2 = string2.lower() feature.append( simfunctions.jaccard(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.jaro_winkler(string1, string2, prefix_weight=0.1)) if len(string1) == len(string2): feature.append(simfunctions.hamming_distance(string1, string2)) else: feature.append(5) feature.append( simfunctions.cosine(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.overlap_coefficient(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.monge_elkan(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.tfidf(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append(len(string1)) feature.append(len(string2)) feature.append(len(string1) - len(string2)) feature.append( simfunctions.jaro( tokenizers.whitespace(string1)[0], tokenizers.whitespace(string2)[0])) feature.append(len(tokenizers.whitespace(string1))) feature.append(len(tokenizers.whitespace(string2))) # product_segment string1, string2 = stage3_helper.get_attribute_from_jsons( json1, json2, product_segment) string1 = string1.lower() string2 = string2.lower() feature.append( simfunctions.jaccard(tokenizers.qgram(string1, 3), tokenizers.qgram(string2, 3))) feature.append( simfunctions.jaro_winkler(string1, string2, prefix_weight=0.1)) # if len(string1) == len(string2): # feature.append(simfunctions.hamming_distance(string1, string2)) # else: # feature.append(5) feature.append( simfunctions.cosine(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.overlap_coefficient(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.monge_elkan(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.tfidf(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.jaro( tokenizers.whitespace(string1)[0], tokenizers.whitespace(string2)[0])) feature.append(len(string1)) feature.append(len(string2)) feature.append(len(string1) - len(string2)) feature.append(len(tokenizers.whitespace(string1))) feature.append(len(tokenizers.whitespace(string2))) # product_long_description string1, string2 = stage3_helper.get_attribute_from_jsons( json1, json2, product_long_description) if string1 is None or string2 is None: feature.append(0.5) feature.append(0) feature.append(0) feature.append(0) feature.append(0) # feature.append(0) # feature.append(0) # feature.append(0) # feature.append(0) else: string1 = string1.lower() string2 = string2.lower() string1 = stage3_helper.cleanhtml(string1) string2 = stage3_helper.cleanhtml(string2) string1 = stage3_helper.clean_stop_word(string1) string2 = stage3_helper.clean_stop_word(string2) feature.append( simfunctions.jaccard(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) # feature.append(simfunctions.jaro_winkler(string1, string2, prefix_weight=0.1)) feature.append( simfunctions.overlap_coefficient( tokenizers.whitespace(string1), tokenizers.whitespace(string2))) # feature.append(simfunctions.monge_elkan(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) # feature.append(simfunctions.tfidf(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append(len(string1)) feature.append(len(string2)) feature.append(len(string1) - len(string2)) # product_brand string1, string2 = stage3_helper.get_attribute_from_jsons( json1, json2, product_brand) string1_name, string2_name = stage3_helper.get_attribute_from_jsons( json1, json2, product_name) if string1 is None or string1 == '': string1 = get_predict_brand(string1_name) if string2 is None or string2 == '': string2 = get_predict_brand(string2_name) if string1 is None or string2 is None: feature.append(0) feature.append(0) feature.append(0) feature.append(0) feature.append(0) feature.append(0) feature.append(0) feature.append(0) else: feature.append( simfunctions.jaccard(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.jaro_winkler(string1, string2, prefix_weight=0.1)) feature.append( simfunctions.overlap_coefficient( tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.monge_elkan(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append( simfunctions.tfidf(tokenizers.whitespace(string1), tokenizers.whitespace(string2))) feature.append(len(string1)) feature.append(len(string2)) feature.append(len(string1) - len(string2)) #feature.append(simfunctions.jaro(tokenizers.whitespace(string1)[0], tokenizers.whitespace(string2)[0])) # Contains similar model names. string1, string2 = stage3_helper.get_attribute_from_jsons( json1, json2, product_name) string1 = string1.lower() string2 = string2.lower() model_strs1 = stage3_helper.find_model_str(string1) model_strs2 = stage3_helper.find_model_str(string2) # share_model_str = False # for model in model_strs1: # if model.lower() in string2.lower(): # share_model_str = True # for model in model_strs2: # if model.lower() in string1.lower(): # share_model_str = True # if share_model_str: # feature.append(1) # else: # feature.append(0) if len(model_strs1) > 0 and len(model_strs2) > 0: feature.append(simfunctions.jaccard(model_strs1, model_strs2)) else: feature.append(0.5) feature.append(len(model_strs1)) feature.append(len(model_strs2)) feature.append(len(model_strs1) - len(string2)) # Other features. common = 0 common_score = 0.0 for item in json1: if item in json2: common += 1 common_score += simfunctions.jaccard( tokenizers.whitespace(json1[item][0]), tokenizers.whitespace(json2[item][0])) common_score = common_score / common feature.append(len(json1)) feature.append(len(json2)) feature.append(len(json1) - len(json2)) feature.append(common) feature.append(common_score) feature.append(len(json.dumps(json1))) feature.append(len(json.dumps(json2))) feature.append(len(json.dumps(json1)) - len(json.dumps(json2))) feature.append( simfunctions.jaccard(tokenizers.whitespace(json.dumps(json1)), tokenizers.whitespace(json.dumps(json2)))) # Add one feature and label. features.append(feature) labels.append(stage3_helper.get_01_from_label(label)) return features, labels, lines
matched2 = CaSe_re.search(item[1]).group(0) except: matched2 = None for idx, brand in enumerate(brands_re): if (item[1] == None): match = None else: match = brand.search(item[1]) if match is not None: if matched2 == None: matched2 = match.group(0) else: matchIndex = refurbished_re.sub('', item[1]).index(match.group(0)) matchedIndex = refurbished_re.sub('', item[1]).index(matched2) if matchIndex <= matchedIndex: matched2 = match.group(0) if matched2 is None: try: matched2 = CASE_re.search(item[0]).group(0) except: matched2 = ' ' brandList[i].append(matched2) i = i + 1 monge_elkan_measure = [] for pair in brandList: measure = simfunctions.monge_elkan(tokenizers.whitespace(pair[0]), tokenizers.whitespace(pair[1])) monge_elkan_measure.append(measure) print monge_elkan_measure
from py_stringmatching import simfunctions, tokenizers prodNames = [] cosineMeasure = [] with open('set_X.txt', 'r') as f: for line in f: line = unicode(line, errors='ignore') # For character which are not utf-8 data = line.strip().split('?') pairId = data[0] prod1_id = data[1] if (data[2]): prod1_json = json.loads(data[2]) else: prod1_json = dict() prod2_id = data[3] if (data[4]): prod2_json = json.loads(data[4]) else: prod2_json = dict() label = data[5] prodNames.append( (prod1_json['Product Name'][0], prod2_json['Product Name'][0])) f.close() for pair in prodNames: measure = simfunctions.cosine(tokenizers.whitespace(pair[0]), tokenizers.whitespace(pair[1])) cosineMeasure.append(measure) print cosineMeasure
def test_delimiter_invalid(self): self.assertEqual(whitespace(None))