Package: autovi 0.4.1

autovi: Auto Visual Inference with Computer Vision Models

Provides automated visual inference of residual plots using computer vision models, facilitating diagnostic checks for classical normal linear regression models.

Authors:Weihao Li [aut, cre, cph]

autovi_0.4.1.tar.gz
autovi_0.4.1.zip(r-4.5)autovi_0.4.1.zip(r-4.4)autovi_0.4.1.zip(r-4.3)
autovi_0.4.1.tgz(r-4.4-any)autovi_0.4.1.tgz(r-4.3-any)
autovi_0.4.1.tar.gz(r-4.5-noble)autovi_0.4.1.tar.gz(r-4.4-noble)
autovi_0.4.1.tgz(r-4.4-emscripten)autovi_0.4.1.tgz(r-4.3-emscripten)
autovi.pdf |autovi.html✨
autovi/json (API)
NEWS

# Install 'autovi' in R:

install.packages('autovi', repos = c('https://tengmcing.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/tengmcing/autovi/issues

On CRAN:

4.18 score 1 stars 15 scripts 578 downloads 10 exports 66 dependencies

Last updated 4 days agofrom:06687368da. Checks:OK: 7. Indexed: yes.

Target	Result	Date
Doc / Vignettes	OK	Nov 19 2024
R-4.5-win	OK	Nov 19 2024
R-4.5-linux	OK	Nov 19 2024
R-4.4-win	OK	Nov 19 2024
R-4.4-mac	OK	Nov 19 2024
R-4.3-win	OK	Nov 19 2024
R-4.3-mac	OK	Nov 19 2024

Exports:auto_vi AUTO_VI check_python_library_available get_keras_model keras_wrapper KERAS_WRAPPER list_keras_model remove_plot residual_checker save_plot

Dependencies:alphahull bandicoot boot cassowaryr cli colorspace cpp11 crayon deldir dplyr energy fansi farver generics ggplot2 glue gsl gtable here hms igraph interp isoband jsonlite labeling lattice lifecycle magrittr MASS Matrix mgcv munsell nlme pillar pkgconfig png polyclip prettyunits progress R.methodsS3 R.oo R.utils R6 rappdirs RColorBrewer Rcpp RcppEigen RcppTOML reticulate rlang rprojroot scales sgeostat sp spatstat.data spatstat.geom spatstat.random spatstat.univar spatstat.utils splancs tibble tidyselect utf8 vctrs viridisLite withr

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
AUTO_VI class environment	AUTO_VI auto_vi residual_checker
Initialization method
String representation of the object
Compute auxiliary variables for the keras model	AUTO_VI$auxiliary
Get bootstrapped residuals from a fitted model	AUTO_VI$boot_method
Predict visual signal strength for bootstrapped residual plots	AUTO_VI$boot_vss
Conduct a auto visual inference check with a computer vision model	AUTO_VI$check
List of diagnostic results	AUTO_VI$check_result
Conduct principal component analysis for features extracted from keras model	AUTO_VI$feature_pca
Draw a summary Plot for principal component analysis conducted on extracted features	AUTO_VI$feature_pca_plot
Get data out of a model object	AUTO_VI$get_data
Get fitted values and residuals out of a model object	AUTO_VI$get_fitted_and_resid
Compute the likelihood ratio using the simulated result	AUTO_VI$likelihood_ratio
Conduct a auto visual inference lineup check with a computer vision model	AUTO_VI$lineup_check
Get null residuals from a fitted model	AUTO_VI$null_method
Simulate null plots and predict the visual signal strength	AUTO_VI$null_vss
Compute the p-value based on the check result	AUTO_VI$p_value
Draw a lineup of standard residual plots	AUTO_VI$plot_lineup
Draw a pair of standard residual plots	AUTO_VI$plot_pair
Draw a standard residual plot	AUTO_VI$plot_resid
Get rotated residuals from a fitted linear model	AUTO_VI$rotate_resid
Save plot(s)	AUTO_VI$save_plot
Summary of the object	AUTO_VI$summary
Draw a summary density plot for the result	AUTO_VI$summary_density_plot
Draw a summary plot for the result	AUTO_VI$summary_plot
Draw a summary rank plot for the result	AUTO_VI$summary_rank_plot
Predict the visual signal strength	AUTO_VI$vss
Check python library availability	check_python_library_available
Download and load the keras model	get_keras_model
KERAS_WRAPPER class environment	KERAS_WRAPPER keras_wrapper
Initialization method
String representation of the object
Get keras model input image height	KERAS_WRAPPER$get_input_height
Get keras model input image width	KERAS_WRAPPER$get_input_width
Load an image as numpy array	KERAS_WRAPPER$image_to_array
List all layer names	KERAS_WRAPPER$list_layer_name
Predict visual signal strength	KERAS_WRAPPER$predict
List all available pre-trained computer vision models	list_keras_model
Remove a plot	remove_plot
Save plot(s)	save_plot