predict.grafzahl

Make prediction from a fine-tuned grafzahl object.

Duct tape the 'quanteda' ecosystem (Benoit et al., 2018) <doi:10.21105/joss.00774> to modern Transformer-based text classification models (Wolf et al., 2020) <doi:10.18653/v1/2020.emnlp-demos.6>, in order to facilitate supervised machine learning for textual data. This package mimics the behaviors of 'quanteda.textmodels' and provides a function to setup the 'Python' environment to use the pretrained models from 'Hugging Face' <https://huggingface.co/>. More information: <doi:10.5117/CCR2023.1.003.CHAN>.

Chung-hong Chan

grafzahl

Supervised Machine Learning for Textual Data Using Transformers
and 'Quanteda'

predict.grafzahl function

<dl><dt>object</dt>
<dd>an S3 object trained with <code>grafzahl()</code></dd>
<dt>newdata</dt>
<dd>a quanteda::corpus or a character vector of texts on which prediction should be made.</dd>
<dt>cuda</dt>
<dd>logical, whether to use CUDA, default to <code>detect_cuda()</code>.</dd>
<dt>return_raw</dt>
<dd>logical, if <code>TRUE</code>, return a matrix of logits; a vector of class prediction otherwise</dd>
<dt>...</dt>
<dd>not used</dd></dl>

Arguments

Prediction from a fine-tuned grafzahl object — predict.grafzahl

<dl>

<dt>object</dt>
<dd>an S3 object trained with <code>grafzahl()</code></dd>


<dt>newdata</dt>
<dd>a quanteda::corpus or a character vector of texts on which prediction should be made.</dd>


<dt>cuda</dt>
<dd>logical, whether to use CUDA, default to <code>detect_cuda()</code>.</dd>


<dt>return_raw</dt>
<dd>logical, if <code>TRUE</code>, return a matrix of logits; a vector of class prediction otherwise</dd>


<dt>...</dt>
<dd>not used</dd>

</dl>

predict.grafzahl: Prediction from a fine-tuned grafzahl object

Description

Usage

Value

Arguments