fasttext 使用笔记

安装

!pip install fasttext

train_unsupervised 用于学习词向量

# Skipgram model :
model = fasttext.train_unsupervised('data.txt', model='skipgram')

# or, cbow model :
model = fasttext.train_unsupervised('data.txt', model='cbow')

其中 data.txt 是 utf-8 编码的文本文件。

train_supervised 用于文本分类

model = fasttext.train_supervised('data.txt')

其中 data.txt 是多行文本，默认标签的格式为 __label__<真实标签>

Signature

fasttext.train_unsupervised(
	input,             # training file path (required)
	model,             # unsupervised fasttext model {cbow, skipgram} [skipgram]
	lr,                # learning rate [0.05]
	dim,               # size of word vectors [100]
	ws,                # size of the context window [5]
	epoch,             # number of epochs [5]
	minCount