napsternxg

human	gender	genderLabel	ethnic_group	ethnic_groupLabel	given_name	date_of_birth	date_of_birthLabel	given_nameLabel	family_name	family_nameLabel
http://www.wikidata.org/entity/Q946	http://www.wikidata.org/entity/Q6581097	male	http://www.wikidata.org/entity/Q1026	Poles	http://www.wikidata.org/entity/Q13422248	1957-04-22T00:00:00Z	1957-04-22T00:00:00Z	Donald	http://www.wikidata.org/entity/Q62102784	Tusk
http://www.wikidata.org/entity/Q946	http://www.wikidata.org/entity/Q6581097	male	http://www.wikidata.org/entity/Q1026	Poles	http://www.wikidata.org/entity/Q15207702	1957-04-22T00:00:00Z	1957-04-22T00:00:00Z	Franciszek	http://www.wikidata.org/entity/Q62102784	Tusk
http://www.wikidata.org/entity/Q989	http://www.wikidata.org/entity/Q6581097	male	http://www.wikidata.org/entity/Q1026	Poles	http://www.wikidata.org/entity/Q69242302	1920-05-18T00:00:00Z	1920-05-18T00:00:00Z	Iohannes Paulus	http://www.wikidata.org/entity/Q56541347	Wojtyła
http://www.wikidata.org/entity/Q18978	http://www.wikidata.org/entity/Q6581072	femal

napsternxg

napsternxg

import onnx

model_path = "./model.onnx"
fixed_model_path = model_path.replace(".onnx", ".fixed.onnx")

# # Load the ONNX model which should have last layer as Sigmoid. 
# LGBM Models may sometime not add the Sigmoid op during export when using regression loss
onnx_model = onnx.load(model_path)
print(onnx_model)
onnx.checker.check_model(onnx_model)

napsternxg

diff --git a/sentence_transformers/SentenceTransformer.py b/sentence_transformers/SentenceTransformer.py
index e44e573..ae4dea4 100644
--- a/sentence_transformers/SentenceTransformer.py
+++ b/sentence_transformers/SentenceTransformer.py
@@ -16,6 +16,7 @@ from torch.optim import Optimizer
 from torch.utils.data import DataLoader
 import torch.multiprocessing as mp
 from tqdm.autonotebook import trange
+from tqdm.autonotebook import tqdm
 import math

napsternxg

napsternxg

from IPython.display import display, HTML

class DisplayEntities:
    @classmethod
    def display(cls, texts, grouped_entities):
        html = []
        html.append(cls.get_style())
        for text, entities in zip(texts, grouped_entities):
            html.append(cls.show_entities(text, entities))
        display(HTML("".join(html)))

napsternxg

"""Faster Implementation of Unsupervised Query Segmentation.

Uses vectorized operations

- author: @napsternxg

Unsupervised Query Segmentation Using only Query Logs [Mishra et. al. 2011]

https://www.microsoft.com/en-us/research/wp-content/uploads/2011/01/pp0295-mishra.pdf

napsternxg

SELECT ?subClass ?subClassLabel ?desc WHERE {
  ?subClass wdt:P279* wd:Q5. # Here we are getting all subClasses of Human and its subclasses
  OPTIONAL {
    ?subClass rdfs:label ?desc.
    FILTER((LANG(?desc)) = "en")
  }
  SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
}

napsternxg

from datasets import load_dataset, Dataset, DatasetDict
from sentence_transformers.losses import CosineSimilarityLoss
from sentence_transformers import SentenceTransformer

from setfit import SetFitModel, SetFitTrainer, sample_dataset
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
import json

napsternxg

import asyncio
import logging
import random
import time
from dataclasses import dataclass
from typing import Any

from tqdm.auto import tqdm

logger = logging.getLogger(__name__)