Python：如何将编码后的one-hot向量与字符串POS标签关联

嘿，这事儿其实很简单，LabelBinarizer本身就自带了能帮你建立映射的属性，不用额外费劲！我给你一步步拆解：

1. 先明确标签与编码的对应关系基础 #

你用fit_transform传入的POS标签列表，LabelBinarizer会把这些标签按传入顺序存到encoder.classes_属性里。而transfomed_label矩阵的每一行，正好对应encoder.classes_中对应索引位置标签的独热编码。

2. 创建标签到独热向量的映射字典 #

直接用字典推导式就能快速生成这个映射：

import numpy as np
from sklearn.preprocessing import LabelBinarizer

# 你的原始代码
encoder = LabelBinarizer()
pos_tags = ["CC","CD","DT","EX","FW","IN","JJ","JJR","JJS","LS","MD","NN","NNS","NNP","NNPS","PDT","POS","PRP","PRP$","RB","RBR","RBS","RP","SYM","TO","UH","VB","VBD","VBG","VBN","VBP","VBZ","WDT","WP","WP$","WRB"]
transfomed_label = encoder.fit_transform(pos_tags)

# 生成标签→独热向量的映射
label_to_onehot = {tag: transfomed_label[i] for i, tag in enumerate(encoder.classes_)}

# 举个例子：查看"CC"对应的独热向量
print(label_to_onehot["CC"])

3. 从独热向量反向查找对应的POS标签 #

如果手里有一个独热向量，想找到它对应的标签，可以先通过np.argmax()找到向量中1的索引，再从encoder.classes_里取对应位置的标签：

# 假设我们有一个独热向量（比如对应"NN"的向量）
sample_vec = transfomed_label[11]  # 因为"NN"在原始列表的第12个位置，索引是11
# 找到对应的标签
tag_index = np.argmax(sample_vec)
corresponding_tag = encoder.classes_[tag_index]
print(corresponding_tag)  # 输出: NN

这样你就能轻松双向关联POS标签和它的独热编码向量啦！

内容的提问来源于stack exchange，提问作者Timothy Rajan