excelcy 0.3.3

卓越是强大的

简单风格的培训 ，来自Spacy文档，演示如何使用Spacy来培训NER：

TRAIN_DATA=[("Uber blew through $1 million a week",{'entities':[(0,4,'ORG')]}),("Google rebrands its business apps",{'entities':[(0,6,"ORG")]})]nlp=spacy.blank('en')optimizer=nlp.begin_training()foriinrange(20):random.shuffle(TRAIN_DATA)fortext,annotationsinTRAIN_DATA:nlp.update([text],[annotations],sgd=optimizer)nlp.to_disk('/model')

训练数据描述要训练的句子和带注释的实体。总是数字符是很麻烦的。使用excelcy，可以省略（开始、结束）字符。

# download the en model from spacy# python -m spacy download en"fromexcelcyimportExcelCy# collect sentences, annotate Entities and train NER using spaCyexcelcy=ExcelCy.execute(file_path='https://github.com/kororo/excelcy/raw/master/tests/data/test_data_01.xlsx')# use the nlp object as per spaCy APIdoc=excelcy.nlp('Google rebrands its business apps')# or save_storage it for faster bootstrap for applicationexcelcy.nlp.to_disk('/model')