fastNLP.api

fastNLP.api.api

class fastNLP.api.api.POS(model_path=None, device='cpu')

FastNLP API for Part-Of-Speech tagging.

Parameters:

• model_path (str) – the path to the model.
• device (str) – device name such as “cpu” or “cuda:0”. Use the same notation as PyTorch.

predict(content)

Parameters:content – list of list of str. Each string is a token(word). Return answer:list of list of str. Each string is a tag.

test(file_path)

Test performance over the given data set.

Parameters:file_path (str) – Returns:a dictionary of metric values

fastNLP.api.converter

fastNLP.api.model_zoo

fastNLP.api.pipeline

class fastNLP.api.pipeline.Pipeline(processors=None)

Pipeline takes a DataSet object as input, runs multiple processors sequentially, and outputs a DataSet object.

fastNLP.api.processor

class fastNLP.api.processor.FullSpaceToHalfSpaceProcessor(field_name, change_alpha=True, change_digit=True, change_punctuation=True, change_space=True)

全角转半角，以字符为处理单元

class fastNLP.api.processor.Index2WordProcessor(vocab, field_name, new_added_field_name)

将DataSet中某个为index的field根据vocab转换为str

class fastNLP.api.processor.IndexerProcessor(vocab, field_name, new_added_field_name, delete_old_field=False, is_input=True)

给定一个vocabulary , 将指定field转换为index形式。指定field应该是一维的list，比如

[‘我’, ‘是’, xxx]

class fastNLP.api.processor.Num2TagProcessor(tag, field_name, new_added_field_name=None)

将一句话中的数字转换为某个tag。

class fastNLP.api.processor.PreAppendProcessor(data, field_name, new_added_field_name=None)

向某个field的起始增加data(应该为str类型)。该field需要为list类型。即新增的field为

[data] + instance[field_name]

class fastNLP.api.processor.SeqLenProcessor(field_name, new_added_field_name='seq_lens', is_input=True)

根据某个field新增一个sequence length的field。取该field的第一维

class fastNLP.api.processor.SliceProcessor(start, end, step, field_name, new_added_field_name=None)

从某个field中只取部分内容。等价于instance[field_name][start:end:step]

class fastNLP.api.processor.VocabIndexerProcessor(field_name, new_added_filed_name=None, min_freq=1, max_size=None, verbose=0, is_input=True)

根据DataSet创建Vocabulary，并将其用数字index。新生成的index的field会被放在new_added_filed_name, 如果没有提供

new_added_field_name, 则覆盖原有的field_name.

construct_vocab(*datasets)

使用传入的DataSet创建vocabulary

Parameters:datasets – DataSet类型的数据，用于构建vocabulary Returns:

process(*datasets, only_index_dataset=None)

若还未建立Vocabulary，则使用dataset中的DataSet建立vocabulary；若已经有了vocabulary则使用已有的vocabulary。得到vocabulary

后，则会index datasets与only_index_dataset。

Parameters:

• datasets – DataSet类型的数据
• only_index_dataset – DataSet, or list of DataSet. 该参数中的内容只会被用于index，不会被用于生成vocabulary。

Returns:

set_verbose(verbose)

设置processor verbose状态。

Parameters:verbose – int, 0，不输出任何信息；1，输出vocab 信息。 Returns:

class fastNLP.api.processor.VocabProcessor(field_name, min_freq=1, max_size=None)

传入若干个DataSet以建立vocabulary。