similarities 實(shí)現(xiàn)了多種相似度計(jì)算、匹配搜索算法，支持文本、圖像，python3開發(fā)。

安裝

pip3 install torch # conda install pytorch
pip3 install -U similarities

或

git clone https://github.com/shibing624/similarities.git
cd similarities
python3 setup.py install

報(bào)錯(cuò)

ChineseCLIPProcessor

Traceback (most recent call last): File “xx\similarity_test1.py”,
line 9, in
from similarities import BertSimilarity File “xx\lib\site-packages\similarities_init_.py”, line 28, in
from similarities.clip_similarity import ClipSimilarity File “xx\lib\site-packages\similarities\clip_similarity.py”, line 16, in

from similarities.clip_module import ClipModule File “xx\lib\site-packages\similarities\clip_module.py”, line 18, in

from transformers import ChineseCLIPProcessor, ChineseCLIPModel, CLIPProcessor, CLIPModel ImportError: cannot import name
‘ChineseCLIPProcessor’ from ‘transformers’
(xx\lib\site-packages\transformers_init_.py)

報(bào)這個(gè)錯(cuò)的原因是transformers版本太低，升級下版本就可以了。

pip install --upgrade transformers

pydantic

另外還缺少pydantic：

pip install pydantic

樣例

# -*- coding: utf-8 -*-
"""
@author:XuMing(xuming624@qq.com)
@description: 文本語義相似度計(jì)算和文本匹配搜索
"""
import sys

sys.path.append('..')
from similarities import BertSimilarity

# 1.Compute cosine similarity between two sentences.
sentences = ['如何更換花唄綁定銀行卡',
             '花唄更改綁定銀行卡']
corpus = [
    '花唄更改綁定銀行卡',
    '我什么時(shí)候開通了花唄',
    '俄羅斯警告烏克蘭反對歐盟協(xié)議',
    '暴風(fēng)雨掩埋了東北部；新澤西16英寸的降雪',
    '中央情報(bào)局局長訪問以色列敘利亞會談',
    '人在巴基斯坦基地的炸彈襲擊中喪生',
]
model = BertSimilarity(model_name_or_path="shibing624/text2vec-base-chinese")
print(model)
similarity_score = model.similarity(sentences[0], sentences[1])
print(f"{sentences[0]} vs {sentences[1]}, score: {float(similarity_score):.4f}")

print('-' * 50 + '\n')
# 2.Compute similarity between two list
similarity_scores = model.similarity(sentences, corpus)
print(similarity_scores.numpy())
for i in range(len(sentences)):
    for j in range(len(corpus)):
        print(f"{sentences[i]} vs {corpus[j]}, score: {similarity_scores.numpy()[i][j]:.4f}")

print('-' * 50 + '\n')
# 3.Semantic Search
model.add_corpus(corpus)
res = model.most_similar(queries=sentences, topn=3)
print(res)
for q_id, id_score_dict in res.items():
    print('query:', sentences[q_id])
    print("search top 3:")
    for corpus_id, s in id_score_dict.items():
        print(f'\t{model.corpus[corpus_id]}: {s:.4f}')

print('-' * 50 + '\n')
print(model.search(sentences[0], topn=3))

結(jié)果：

Similarity: BertSimilarity, matching_model: <SentenceModel: shibing624/text2vec-base-chinese, encoder_type: MEAN, max_seq_length: 256, emb_dim: 768>
2024-03-07 20:12:46.481 | DEBUG    | text2vec.sentence_model:__init__:80 - Use device: cpu
如何更換花唄綁定銀行卡 vs 花唄更改綁定銀行卡, score: 0.8551
--------------------------------------------------

[[0.8551465  0.72119546 0.14502521 0.21666759 0.25171342 0.08089039]
 [0.9999997  0.6807433  0.17136583 0.21621695 0.27282682 0.12791349]]
如何更換花唄綁定銀行卡 vs 花唄更改綁定銀行卡, score: 0.8551
如何更換花唄綁定銀行卡 vs 我什么時(shí)候開通了花唄, score: 0.7212
如何更換花唄綁定銀行卡 vs 俄羅斯警告烏克蘭反對歐盟協(xié)議, score: 0.1450
如何更換花唄綁定銀行卡 vs 暴風(fēng)雨掩埋了東北部；新澤西16英寸的降雪, score: 0.2167
如何更換花唄綁定銀行卡 vs 中央情報(bào)局局長訪問以色列敘利亞會談, score: 0.2517
如何更換花唄綁定銀行卡 vs 人在巴基斯坦基地的炸彈襲擊中喪生, score: 0.0809
花唄更改綁定銀行卡 vs 花唄更改綁定銀行卡, score: 1.0000
花唄更改綁定銀行卡 vs 我什么時(shí)候開通了花唄, score: 0.6807
花唄更改綁定銀行卡 vs 俄羅斯警告烏克蘭反對歐盟協(xié)議, score: 0.1714
花唄更改綁定銀行卡 vs 暴風(fēng)雨掩埋了東北部；新澤西16英寸的降雪, score: 0.2162
花唄更改綁定銀行卡 vs 中央情報(bào)局局長訪問以色列敘利亞會談, score: 0.2728
花唄更改綁定銀行卡 vs 人在巴基斯坦基地的炸彈襲擊中喪生, score: 0.1279
--------------------------------------------------

2024-03-07 20:13:03.429 | INFO     | similarities.bert_similarity:add_corpus:108 - Start computing corpus embeddings, new docs: 6
Batches: 100%|██████████| 1/1 [00:10<00:00, 10.45s/it]
2024-03-07 20:13:13.889 | INFO     | similarities.bert_similarity:add_corpus:120 - Add 6 docs, total: 6, emb len: 6
{0: {0: 0.8551465272903442, 1: 0.7211954593658447, 4: 0.25171342492103577}, 1: {0: 0.9999997019767761, 1: 0.6807432770729065, 4: 0.27282682061195374}}
query: 如何更換花唄綁定銀行卡
search top 3:
    花唄更改綁定銀行卡: 0.8551
    我什么時(shí)候開通了花唄: 0.7212
    中央情報(bào)局局長訪問以色列敘利亞會談: 0.2517
query: 花唄更改綁定銀行卡
search top 3:
    花唄更改綁定銀行卡: 1.0000
    我什么時(shí)候開通了花唄: 0.6807
    中央情報(bào)局局長訪問以色列敘利亞會談: 0.2728
--------------------------------------------------

{0: {0: 0.8551465272903442, 1: 0.7211954593658447, 4: 0.25171342492103577}}

以上就是Python基于similarities實(shí)現(xiàn)文本語義相似度計(jì)算和文本匹配搜索的詳細(xì)內(nèi)容，更多關(guān)于Python文本相似度計(jì)算的資料請關(guān)注腳本之家其它相關(guān)文章！

最新評論