Spaces:
Runtime error
Runtime error
| from transformers import AlbertTokenizer, AlbertModel | |
| from sklearn.metrics.pairwise import cosine_similarity | |
| from sentence_transformers import SentenceTransformer | |
| #This is a quick evaluation on a few cases | |
| # base | |
| # large | |
| tokenizer = AlbertTokenizer.from_pretrained('albert-base-v2') | |
| #model = AlbertModel.from_pretrained("albert-base-v2") | |
| #'sentence-transformers/paraphrase-albert-base-v2' | |
| model_name = 'output/training_OnlineConstrativeLoss-2023-03-10_11-17-15' | |
| model_name = 'output/training_OnlineConstrativeLoss-2023-03-11_00-24-35' | |
| model_name = 'output/training_OnlineConstrativeLoss-2023-03-11_01-00-19' | |
| model_name='output/training_OnlineConstrativeLoss-2023-03-17_16-10-39' | |
| model_name='output/training_OnlineConstrativeLoss-2023-03-17_23-15-52' | |
| #model_name='output/training_OnlineConstrativeLoss-2023-03-14_00-40-03' | |
| model_sbert = SentenceTransformer(model_name) | |
| def get_sbert_embedding(input_text): | |
| embedding = model_sbert.encode(input_text) | |
| return embedding.tolist() | |
| a1 = "65 MOUNTAIN BLVD EXT, WARREN, NJ 07059" | |
| a2 = "112 MOUNTAIN BLVD EXT, WARREN, NJ 07059" | |
| a3 = "1677 NJ-27 #2, EDISON, NJ 08817" | |
| a4 = "5078 S MARYLAND PKWY, LAS VEGAS, NV 89119" | |
| a5 = "65 MOUNTAIN BOULEVARD EXT, WARREN, NJ 07059" | |
| a6 = "123 BROAD ST, NEW YORK, NY, 10304-2345" | |
| a7 = "440 TECHNOLOGY CENTER DRIVE, BOSTON, MA 10034" | |
| a8 = "200 TECHNOLOGY CENTER DRIVE, BOSTON, MA 10034" | |
| a8x= "87 TECHNOLOGY CENTER DRIVE, BOSTON, MA 10034" | |
| #a9 = "440 TECHNOLOGY CENTER DR., BOSTON, MA 10034" | |
| a10= "440 TECHNOLOGY CENTER DR., BOSTON, MA 10034" | |
| a11="87-22 ROUTE 13, CORTLANDVILLE, NY 13045" | |
| a12="87 22 ROUTE 13, CORTLANDVILLE, NY 13045" | |
| a13="87-55 ROUTE 13, CORTLANDVILLE, NY 13045" | |
| a14="257 37 US ROUTE 11, EVANS MILLS, NY 13637" | |
| a15="257-37 US ROUTE 11, EVANS MILLS, NY 13637" | |
| a16="15645 S MAIN ST SUITE D, PENNINGTON, NJ 08534" | |
| a17="156-45 S MAIN ST SUITE D, PENNINGTON, NJ 08534" | |
| a18="156-46 S MAIN ST SUITE D, PENNINGTON, NJ 08534" | |
| a19 = "THE PAVILION AT QUEENS FOR REHABILITAION AND NURSING 36-17 PARSONS BOULEVARD, FLUSHING, NY 11354" | |
| a20 = "136-17 39TH AVENUE, 4TH FLOOR, SUITE CF-E, FLUSHING, NY 11354" | |
| a21="WISDOM MEDICAL P.C., 136-20 38 TH AVE 6E, FLUSHING, NY 11354" | |
| encoded_input = tokenizer(a21, return_tensors='pt') | |
| input_ids = encoded_input.input_ids | |
| input_num_tokens = input_ids.shape[1] | |
| print(input_num_tokens) | |
| list_of_tokens = tokenizer.convert_ids_to_tokens(input_ids.view(-1).tolist()) | |
| # | |
| print( "Tokens : " + ' '.join(list_of_tokens)) | |
| #def get_embedding(input_text): | |
| # encoded_input = tokenizer(input_text, return_tensors='pt') | |
| # input_ids = encoded_input.input_ids | |
| # input_num_tokens = input_ids.shape[1] | |
| # | |
| # print( "Number of input tokens: " + str(input_num_tokens)) | |
| # print("Length of input: " + str(len(input_text))) | |
| # | |
| # list_of_tokens = tokenizer.convert_ids_to_tokens(input_ids.view(-1).tolist()) | |
| # | |
| # print( "Tokens : " + ' '.join(list_of_tokens)) | |
| # with torch.no_grad(): | |
| # | |
| # outputs = model(**encoded_input) | |
| # last_hidden_states = outputs[0] | |
| # sentence_embedding = torch.mean(last_hidden_states[0], dim=0) | |
| # #sentence_embedding = output.last_hidden_state[0][0] | |
| # return sentence_embedding.tolist() | |
| e1 = get_sbert_embedding(a1) | |
| e2 = get_sbert_embedding(a2) | |
| #e3 = get_sbert_embedding(a3) | |
| e4 = get_sbert_embedding(a4) | |
| e5 = get_sbert_embedding(a5) | |
| e6 = get_sbert_embedding(a6) | |
| e7 = get_sbert_embedding(a7) | |
| e8 = get_sbert_embedding(a8) | |
| e8x = get_sbert_embedding(a8x) | |
| #e9 = get_sbert_embedding(a9) | |
| e10 = get_sbert_embedding(a10) | |
| e11 = get_sbert_embedding(a11) | |
| e12 = get_sbert_embedding(a12) | |
| e13 = get_sbert_embedding(a13) | |
| e14 = get_sbert_embedding(a14) | |
| e15 = get_sbert_embedding(a15) | |
| e16 = get_sbert_embedding(a16) | |
| e17 = get_sbert_embedding(a17) | |
| e18 = get_sbert_embedding(a18) | |
| print(f"a1 \"{a1}\" to \"{a2}\" a2 - expected Different") | |
| print(cosine_similarity([e1], [e2])) | |
| print(f"a1 \"{a1}\" to \"{a4}\" a4 - expected Different") | |
| print(cosine_similarity([e1], [e4])) | |
| print(f"a1 \"{a1}\" to \"{a5}\" a5 - expected Same") | |
| print(cosine_similarity([e1], [e5])) | |
| print(f"a7 \"{a7}\" to \"{a8}\" a8 - expected Different") | |
| print(cosine_similarity([e7], [e8])) | |
| print(f"a7 \"{a7}\" to \"{a8x}\" a8x - expected Different") | |
| print(cosine_similarity([e7], [e8x])) | |
| #print(f"a7 \"{a7}\" to \"{a9}\" a9 - expected Same") | |
| #print(cosine_similarity([e7], [e9])) | |
| print(f"a7 \"{a7}\" to \"{a10}\" a10 - expected Same") | |
| print(cosine_similarity([e7], [e10])) | |
| print(f"a11 \"{a11}\" to \"{a12}\" a12 - expected Same") | |
| print(cosine_similarity([e11], [e12])) | |
| print(f"a11 \"{a11}\" to \"{a13}\" a13 - expected Different") | |
| print(cosine_similarity([e11], [e13])) | |
| print(f"a14 \"{a14}\" to \"{a15}\" a15 - expected Same") | |
| print(cosine_similarity([e14], [e15])) | |
| print(f"a16 \"{a16}\" to \"{a17}\" a17 - expected Same") | |
| print(cosine_similarity([e16], [e17])) | |
| print(f"a16 \"{a16}\" to \"{a18}\" a18 - expected Different") | |
| print(cosine_similarity([e16], [e18])) | |
| # with base | |
| #a1 to a2 | |
| #[[0.99512167]] | |
| #a1 to a4 | |
| #[[0.94850088]] | |
| #a1 to a5 | |
| #[[0.99636901]] | |
| # with large | |
| #a1 to a2 | |
| #[[0.99682108]] | |
| #a1 to a4 | |
| #[[0.94006972]] | |
| #a1 to a5 | |
| #[[0.99503919]] |