42 lines
1.0 KiB
Python
42 lines
1.0 KiB
Python
import json
|
|
import numpy as np
|
|
import pickle
|
|
|
|
from keras.models import load_model
|
|
from keras.preprocessing.sequence import pad_sequences
|
|
|
|
model = load_model("NER/ner_bilstm_model.keras")
|
|
|
|
with open("NER/word2idx.pkl", "rb") as f:
|
|
word2idx = pickle.load(f)
|
|
|
|
with open("NER/tag2idx.pkl", "rb") as f:
|
|
tag2idx = pickle.load(f)
|
|
|
|
idx2tag = {i: t for t, i in tag2idx.items()}
|
|
|
|
print(idx2tag)
|
|
|
|
maxlen = 100
|
|
|
|
|
|
def predict_sentence(sentence):
|
|
tokens = sentence.strip().split()
|
|
x = [word2idx.get(w.lower(), word2idx["UNK"]) for w in tokens]
|
|
x = pad_sequences([x], maxlen=maxlen, padding="post", value=word2idx["PAD"])
|
|
|
|
preds = model.predict(x)
|
|
pred_labels = np.argmax(preds[0], axis=-1)
|
|
|
|
print("Hasil prediksi NER:")
|
|
for token, label_idx in zip(tokens, pred_labels[: len(tokens)]):
|
|
print(f"{token}\t{idx2tag[label_idx]}")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
try:
|
|
sentence = "saat ini indonesia adalah negara yang sangat indah"
|
|
predict_sentence(sentence)
|
|
except KeyboardInterrupt:
|
|
print("\n\nSelesai.")
|