fasttext的使用，预料格式，调用方法
数据格式：分词后的句子+\t__label__+标签
fasttext_model.py
from fasttext import FastText
import numpy as np
def get_data_path(by_word=True,train=True):
if by_word:
return "./classify/data_by_word_train.txt" if train else "./classify/data_by_word_test.txt"
else:
return "./classify/data_train.txt" if train else "./classify/data_test.txt"
def prepar_model():
data_path = get_data_path(by_word=True,train=True)
model = FastText.train_supervised(data_path,dim=100,epoch=20,wordNgrams=2)
model.save_model("./fasttext_model/classify_by_word_100_20_2.model")
def ceshi_model():
model = FastText.load_model("./fasttext_model/classify_by_word_100_20_2.model")
test_data_path = get_data_path(by_word=True, train=False)
sentences = []
labels = []
for line in open(test_data_path,encoding="utf-8").readlines():
line = line.strip()
temp_ret = line.split("\t")
if len(temp_ret)==2:
sentences.append(temp_ret[0])
labels.append(temp_ret[1])
ret = model.predict(sentences)[0]
ret = [i[0] for i in ret]
acc = np.mean([1 if labels[i] == ret[i] else 0 for i in range(len(labels))])
print(acc)
if __name__ == '__main__':
prepar_model()
ceshi_model()
作者：高颜值的杀生丸
相关文章
Serwa
2020-03-20
Serena
2020-03-06
Neysa
2020-03-14
Rae
2023-07-22
Rhoda
2023-07-22
Hester
2023-07-22
Grace
2023-07-22
Vanna
2023-07-22
Peony
2023-07-22
Dorothy
2023-07-22
Dulcea
2023-07-22
Zandra
2023-07-22
Serafina
2023-07-24
Kathy
2023-08-08
Olivia
2023-08-08
Elina
2023-08-08
Jacinthe
2023-08-08
Viridis
2023-08-08
Hana
2023-08-08
Cybill
2023-08-08