Python 3.x 未通过spacy debug data CLI正确加载文本分类器训练数据 背景
我试图在Google Colab笔记本中的Spacy中训练一个Python 3.x 未通过spacy debug data CLI正确加载文本分类器训练数据 背景,python-3.x,command-line-interface,spacy,Python 3.x,Command Line Interface,Spacy,我试图在Google Colab笔记本中的Spacy中训练一个多类(标签是互斥的)文本分类模型。 课程是 肯定的 否定的 中立的 我将训练数据格式化为指定的注释格式 下面是我做的注释示例 [. . ["Happy #MothersDay to all ... ", {'cats': {'NEUTRAL': 1.0}}], ["Happy mothers day ..", {"cats": {"POSITIVE": 1.0}}], . .] 问题 当我尝试使用spacy CLI中的选项和以下
多类
(标签是互斥的)文本分类模型。
课程是
- 肯定的
- 否定的
- 中立的
[.
.
["Happy #MothersDay to all ... ", {'cats': {'NEUTRAL': 1.0}}],
["Happy mothers day ..", {"cats": {"POSITIVE": 1.0}}],
.
.]
问题
当我尝试使用spacy CLI中的选项和以下命令调试数据时(在Jupyter笔记本中完成)
我得到以下输出
=========================== Data format validation ===========================
✔ Corpus is loadable
=============================== Training stats ===============================
Training pipeline: textcat
Starting with blank model 'en'
0 training docs
0 evaluation docs
✘ No evaluation docs
✔ No overlap between training and evaluation data
✘ Low number of examples to train from a blank model (0)
============================== Vocab & Vectors ==============================
ℹ 0 total words in the data (0 unique)
ℹ No word vectors present in the model
============================ Text Classification ============================
ℹ Text Classification: 0 new label(s), 0 existing label(s)
ℹ The train data contains only instances with mutually-exclusive
classes.
================================== Summary ==================================
✔ 2 checks passed
✘ 2 errors
它无法正确读取数据,但我已经检查了文件,我至少有1000多个样本,如上面所述
链接到和JSON
我在我的数据中找不到任何错误,有人能指出错误吗?提前谢谢 spacy debug data命令需要spacy内部JSON训练格式的数据,如下所述:
这里有一些例子:。同一目录中的转换脚本显示如何从JSONL格式转换,该格式与示例脚本中使用的
TRAIN\u DATA
-类型格式非常相似。spacy debug DATA命令需要spacy内部JSON训练格式的数据,如下所述:
这里有一些例子:。同一目录中的转换脚本显示了如何从与示例脚本中使用的TRAIN\u DATA
-类型格式非常相似的JSONL格式转换
=========================== Data format validation ===========================
✔ Corpus is loadable
=============================== Training stats ===============================
Training pipeline: textcat
Starting with blank model 'en'
0 training docs
0 evaluation docs
✘ No evaluation docs
✔ No overlap between training and evaluation data
✘ Low number of examples to train from a blank model (0)
============================== Vocab & Vectors ==============================
ℹ 0 total words in the data (0 unique)
ℹ No word vectors present in the model
============================ Text Classification ============================
ℹ Text Classification: 0 new label(s), 0 existing label(s)
ℹ The train data contains only instances with mutually-exclusive
classes.
================================== Summary ==================================
✔ 2 checks passed
✘ 2 errors