Scaling Models and Classifiers for Textual Data
Prediction from a textmodel_wordfish method
Influence plot for text scaling models
Coerce various objects to coefficients_textmodel
Coerce various objects to statistics_textmodel
Assign the summary.textmodel class to a list
Internal function to match a dfm features to a target set
Wordscores text model
quanteda.textmodels: Scaling Models and Classifiers for Textual Data
Extract model coefficients from a fitted textmodel_ca object
Internal function to fit the likelihood scaling mixture model.
Compute feature influence from a predicted textmodel_affinity object
Prediction for a fitted affinity textmodel
Prediction from a fitted textmodel_lr object
Prediction from a fitted textmodel_nb object
Prediction from a fitted textmodel_svmlin object
Predict textmodel_wordscores
Print methods for textmodel features estimates
Implements print methods for textmodel_statistics
print method for summary.textmodel
print method for a wordfish model
summary method for textmodel_lr objects
summary method for textmodel_nb objects
summary method for textmodel_svmlin objects
summary method for textmodel_wordfish
Internal methods for textmodel_affinity
Class affinity maximum likelihood text scaling model
Correspondence analysis of a document-feature matrix
Logistic regression classifier for texts
Post-estimations methods for textmodel_lsa
Latent Semantic Analysis
Naive Bayes classifier for texts
[experimental] Linear SVM classifier for texts
Wordfish text model
Scaling models and classifiers for sparse matrix objects representing textual data in the form of a document-feature matrix. Includes original implementations of 'Laver', 'Benoit', and Garry's (2003) <doi:10.1017/S0003055403000698>, 'Wordscores' model, the Perry and 'Benoit' (2017) <doi:10.48550/arXiv.1710.08963> class affinity scaling model, and the 'Slapin' and 'Proksch' (2008) <doi:10.1111/j.1540-5907.2008.00338.x> 'wordfish' model, as well as methods for correspondence analysis, latent semantic analysis, and fast Naive Bayes and linear 'SVMs' specially designed for sparse textual data.