Paper #217
Open
Paper #217
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* First push to begin bringing SEMinR partially in-line with Primer for PLS * Added corporate reputation data and documents. Added a demo file for Chap 4 of the PLS Primer in R. * Removed changes to seminr-demo. Corrected bug in plot_results. * Resolved Issue #161 with processing very complicated HOC models. * # Addresses Issue #149. Added test-only-sm-composites-evaluated * This commit addresses issue #147 to include missing values mean replacement method in estimate_pls(). Added test: test_clean_data.R. Also groups validity metrics in report_summary() together as summary_model$validity and updated tests in test_validity.R * Added a S3 method for plotting reliability of mode_A constructs plot.reliability_table. Also added method for outputting fl_criteria_table with a comment. Class "table_output" will print an associated comment() with the matrix. * House keeping. All tests pass. But some documentation issues. R CMD Check: 0 Errors, 3 Warnings, 0 Notes * Housekeeping. R CMD Check has 0 errors, 0 Warnings, 0 Notes. * Attedns to issue #162. This is just a patch. A more conclusive bug fix will include correctly reporting the metrics for the first AND second order models. * New feature to bootstrapp total paths and report the output differently * Fix Arturo's name in README (#166) * # Feature added: PLSpredict, format output for class table_output. Update primer demos. * Plot reliablity metrics relative differences (#165) * Plot reliablity metrics relative differences * Added a grid to the plot. Co-authored-by: NicholasDanks <[email protected]> * Updated feature PLSpredict and included simple model comparison. demo file seminr-primer-chap6.R for use case. * Added feature for multiple mediator testing and for total effects and total indirect effects. Addresses issue #164. New feature. Not tested or checked yet. * Updated demo Chap 3 and 8. Cleaned some plot code and corrected some bugs * Committing the pre-R CMD CHECK changes to SEMinR, next step is to R CMD CHECK and test on Travis CI. * All tests pass * R CMd Check no errors, warnings or notes * Make SEMinR compatible with R Version 4.0.3 * Removed fixtures, updated changelog, updated vignette * fixed bug in plot * Addresses Issue #169 - Bugs in the README.Rmd. Corrected these bugs. * # Updated the name of the textbook in demonstration files * Runs Github Actions - added GH workflow config file - removed travis config file * Updated HOC feature to output both first and second stage outer loadings and weights. Modified estimate_bootstrap to bre more robust and take more complex matrix shapes * Refactored slightly and added comments. All test pass. now for R CMD Check * R CMD Check passes * Convert lavaan/csem syntax to seminr model objects (#192) * lavaan2seminr() converts lavaan/csem syntax to seminr model objects * estimate_pls() takes specified model or model components; tests fail * Importing lavaan models for CBSEM/CFA * Specified CBSEM/CFA models * Fix bug due to R v4 changes to lapply() * Updated documentation for estimate_* and specify_model * Model viz (#181) Model Graph Visualization * added DiagrammeR to package suggestions. * added first version of model viz * added basic plotting function * added new theme-based plotting mechanism * removed "old" plotting function. Added some safety checks. Added tests for these checks. * some documentation fixes. * added second plot model functionality * added automatic sizing * migrated most of the things * removed another iteration of graphing. * added a mini-plot demo * added absolute to measurement model for inverted items. * fixed demo, added plotting for measurement-model only code. * removed accidental output file * fixed some tests * renamed test-cases for graphing * some refactoring and renaming * added structural model plots and moved dot_graph to S3 generic * added interaction capability and a function to determine how negative paths are visualized. * added bootstrapped models and matching visualization for path coefficients * updated the demo to showcase bootstrapped models * corrected a typo * Extended the demo to include the t-value * Before the removal of uneccessary (?) code. * removed the unnecessary "if(is.vector(...))" code part. * split functions into multiple files. Also provided a method plot_model that uses DiagrammeR grViz if available. This does not introduce a dependency. * added a save plot function * added test cased for save_plot * corrected degrees of freedom. * switched to HTML-based sm.edge.labels to allow for more details in graphs. * added preliminary support for lavaan models using semPlot package. * fixed some minor problems, removed magrittr dependency * removed uneccesary pdf file. * fixed an error where missing t-values removed the edge label. * test alternative run for windows * typo * re-introduced webp * added dependency to webp * testing minimal windows github action * removed windows. * removed pipe from the demo * Test windows build * removed another pipe * moved to plot_model * added two todos * added new test_cases and refactored code a little. Sprinkled in some debug todos * minor comment * renamed files * t-values were incorrevtly converted to p-values in plotting for negative paths coefficients * with Johannes updates to plotting (renamed, non-greekletters, removed single quotes, install_query for all packages) * added seminr_model as class to all model types * added test for utils functions in plotting * fixed some things in plotting and S3 and added asterisks as an option for edges * added mm.edge templates and sm.node templates * removed windows build. * with Johannes. Refactored code added style-customization for edges, style customization for sm shapes. * with Johannes. Fixed HOC plotting. Feature complete? * added a browse_plot function to open edotor web editor * minor bug fix * forgot to document a function. * repaired structure_only parameter for HOC * fixed bug, where measurement model with spaces in the name would cause the dot graph to fail. * first experiments with an RStudio addin * added some theme options for font-color, bg-color, and a width-offset for edges to prevent them from completely disappearing for small path coefficients. * added improved width offset for different shapes * minor theme tweak regarding sizes of different constructs (incl. testcases) * fixed third theme name * added the modern theme to the documentation * error in length saftey check fixed * with Johannes: Major refactoring started * with Johannes: Bootstrapped ltbl function for SM edges works * with Johannes: Added a dark theme and more documentation. * with Johannes: Added (basic) plotting to the vignette. * theme addin * added a theming adding. Works fine :) * reduce to one addin * removed the unused addin (only theme edit in there now). * removed the addin. Migrated to seminr/seminrstudio * added arrow direction and usage of weights/loading on a per-construct basis to the theme. * fixed the plot function for lavaan plots and included the specified model as a plot function * fixed p-value calculation for negative t-values * updated readme Co-authored-by: Johannes Nakayama <[email protected]> * Change the output of plot(bootstrap_model) to return the lambda = the original estimate, not the bootstrap mean. * Updated plot(bootstrap_model) updated to return the original estimate for loadings/weights * R CMD Check passes no notes, errors, or warnings * Bump version and add aut/ctb info in DESCRIPTION * - added contributors, allowed themes to be used as closures, defined how the default theme should look like, previous default is now seminr_theme_old. (#201) * Update DESCRIPTION Added a missing comma * Update README (#202) * added seminrstudio as a sister project. * Updated description to reflect Susi Adler as contributor * No files in root * Final commits before submission to CRAN * Updated Jame's web address. * Removed MASS package from dependencies * Bumped version to 2.0.1 and changed date. Co-authored-by: Soumya Ray <[email protected]> Co-authored-by: André Calero Valdez <[email protected]> Co-authored-by: Johannes Nakayama <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
* NEVER MERGE *
This PR is only to review changes to the paper accompanying this package.