`gclda.decode`.encode¶

gclda.decode.encode(model, text, out_file=None, topic_priors=None, prior_weight=1.0)[source]¶

Perform text-to-image encoding.

Parameters:

model : gclda.model.Model: Model object needed for decoding.
text : str or list: Text to encode into an image.
out_file : str, optional: If not None, writes the encoded image to a file.
topic_priors : numpy.ndarray of float, optional: A 1d array of size (n_topics) with values for topic weighting. If None, no weighting is done. Default is None.
prior_weight : float, optional: The weight by which the prior will affect the encoding. Default is 1.

Returns:

img : nibabel.Nifti1Image: The encoded image.
topic_weights : numpy.ndarray of float: The weights of the topics used in encoding.

Notes

Notation	Meaning
$v$	Voxel
$t$	Topic
$w$	Word type
$h$	Input text
$p(v\|t)$	Probability of topic given voxel (`p_topic_g_voxel`)
$\tau_{t}$	Topic weight vector (`topic_weights`)
$p(w\|t)$	Probability of word type given topic (`p_word_g_topic`)
$\omega$	1d array from input image (`input_values`)

Compute $p(v|t)$ (p_voxel_g_topic).
- From gclda.model.Model.get_spatial_probs()
Compute $p(t|w)$ (p_topic_g_word).
Vectorize input text according to model vocabulary.
Reduce $p(t|w)$ to only include word types in input text.
Compute $p(t|h)$ (p_topic_g_text) by multiplying $p(t|w)$ by word counts for input text.
Sum topic weights ( $\tau_{t}$ ) across words.
- $\tau_{t} = \sum_{i}{p(t|h_{i})}$
Compute voxel weights.
- $p(v|h) \propto p(v|t) \cdot \tau_{t}$
The resulting array (voxel_weights) reflects arbitrarily scaled voxel weights for the input text.
Unmask and reshape voxel_weights into brain image.

gclda.decode.encode¶