sample_polem.py

import time
from poldeepner2.models import PolDeepNer2, ModelFactory

resources_path = "../poldeepner2_models"
t0 = time.time()
model = ModelFactory.get_resource("pdn2_cen_n82_roberta_large_sq_krnnt_cuda"
                                  ".pdn2", resources_path)
ner = PolDeepNer2.load(model)
time_model = time.time() - t0

sentences = ["Spotkałem Marka Nowaka na Politechnice Wrocławskiej, który "
             "pracuje w Intelu.",
             "Wczoraj mieliśmy kontrolę Naczelnej Izby Skarbowej.",
             open("tests/resources/text_krakow.txt", "r",
                  encoding="utf-8").read()]

token_count = 0

t0 = time.time()
for sentence in sentences:
    print("-" * 20)
    print(sentence.strip())
    doc = ner.process_document(sentence)
    token_count += len(doc.tokens)

    for name in doc.annotations:
        name_range = "%d:%d" % (name.start, name.end)
        char_range = "%d:%d" % (doc.tokens[name.start].start,
                                doc.tokens[name.end - 1].end)
        print(f"{name_range:<8} {char_range:<12} {name.label:<25} "
              f"{name.get_text():<25}  {name.lemma}")
    print()

print()
print(f"Model loaded in   : {time_model} seconds")
print(f"Texts processed in: {time.time()-t0} seconds")
print(f"Number of tokens  : {token_count}")