-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #28 from ismaelgutier/work_dog
updating README and vignettes
- Loading branch information
Showing
14 changed files
with
312 additions
and
502 deletions.
There are no files selected for viewing
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
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
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
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
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
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,172 @@ | ||
| --- | ||
| title: "Data Analysis Workflow using the Sunflower Package" | ||
| author: "Ismael Gutiérrez-Cordero" | ||
| date: "`r Sys.Date()`" | ||
| output: | ||
| html_document: | ||
| toc: true | ||
| toc_float: true | ||
| number_sections: true | ||
| theme: cerulean | ||
| --- | ||
|
|
||
| ```{r setup, include=FALSE} | ||
| knitr::opts_chunk$set(echo = TRUE) | ||
| ``` | ||
|
|
||
| In this vignette, we present a practical example of using the sunflower package to work with datasets that include a column of responses containing multiple answers. We demonstrate how to convert the dataset into a long format to obtain formal similarity metrics. Additionally, we illustrate how to perform error classification based on classical criteria found in the literature (e.g., [Dell et al., 1997](https://doi.org/10.1037/0033-295x.104.4.801); [Gold & Kertesz, 2001](https://doi.org/10.1006/brln.2000.2441); see also, [García-Orza et al., 2020](https://doi.org/10.1016/j.cortex.2020.03.020)). | ||
|
|
||
| # Environment Setup | ||
|
|
||
| ```{r} | ||
| # Clear the workspace and unload all packages | ||
| #rm(list = ls()) | ||
| #invisible(lapply(paste("package:", names(sessionInfo()$otherPkgs), sep = ""), | ||
| # detach, character.only = TRUE, unload = TRUE)) | ||
| # Install and load `devtools` package | ||
| if (!requireNamespace("devtools", quietly = TRUE)) { | ||
| install.packages("devtools") | ||
| } | ||
| library(devtools) | ||
| # Install RTools on Windows (if applicable) | ||
| # Visit: https://cran.rstudio.com/bin/windows/Rtools/ for installation. | ||
| # Not needed on macOS or Linux (I am not an user, so I am guessing) | ||
| ``` | ||
|
|
||
| # Install and Load Required Packages | ||
|
|
||
| ```{r} | ||
| # Install additional packages if needed | ||
| possible_dependencies <- c("tidyverse", "htmlTable", "knitr") | ||
| for (pkg in possible_dependencies) { | ||
| if (!requireNamespace(pkg, quietly = TRUE)) { | ||
| install.packages(pkg) | ||
| } | ||
| } | ||
| # Install the `xfun` package (if necessary) | ||
| if (!requireNamespace("xfun", quietly = TRUE)) { | ||
| install.packages("xfun", type = "source") | ||
| } | ||
| # Install the `sunflower` package from GitHub | ||
| if (!requireNamespace("sunflower", quietly = TRUE)) { | ||
| devtools::install_github("ismaelgutier/sunflower") | ||
| } | ||
| # Load required libraries | ||
| library(sunflower) | ||
| ``` | ||
|
|
||
| # Step 1 | ||
| ## Load and Wrangle Data | ||
|
|
||
| ```{r} | ||
| # Load dataset | ||
| dataframe0 <- sunflower::IGC_sample | ||
| # Separate responses | ||
| dataframe1 <- dataframe0 %>% | ||
| sunflower::separate_responses(col_name = "response", | ||
| separate_with = ", ") | ||
| # Extract attempts and clean blank spaces | ||
| dataframe2 <- dataframe1 %>% | ||
| sunflower::get_attempts(first_production = attempt_1, | ||
| drop_blank_spaces = TRUE) | ||
| ``` | ||
|
|
||
| # Step 2 | ||
| ## Formal Similarity Analysis | ||
|
|
||
| ```{r} | ||
| # Calculate formal similarity | ||
| dataframe3 <- dataframe2 %>% | ||
| sunflower::get_formal_similarity(item_col = "item", | ||
| response_col = "response", | ||
| attempt_col = "attempt", | ||
| group_cols = c("task_item_ID")) | ||
| ``` | ||
|
|
||
| # Step 2.1 | ||
| ## Positional Accuracy | ||
|
|
||
| ```{r} | ||
| # Calculate positional accuracy | ||
| dataframe3.1 <- dataframe3 %>% | ||
| sunflower::positional_accuracy(item_col = "item", | ||
| response_col = "response", | ||
| match_col = "adj_strict_match_pos") | ||
| ``` | ||
|
|
||
| # Step 3 | ||
| ## Lexicality Check | ||
|
|
||
| ```{r} | ||
| # Check lexicality | ||
| dataframe4 <- dataframe3 %>% | ||
| sunflower::check_lexicality(item_col = "item", | ||
| response_col = "response", | ||
| criterion = "dictionary") | ||
| ``` | ||
|
|
||
| ## Semantic Similarity Analysis | ||
|
|
||
| ```{r} | ||
| # Load a pre-trained word2vec model | ||
| model <- word2vec::read.word2vec(file = file.choose(), normalize = FALSE) | ||
| # Calculate semantic similarity | ||
| dataframe5 <- dataframe4 %>% | ||
| sunflower::get_semantic_similarity(item_col = "item", | ||
| response_col = "response", | ||
| model = model) | ||
| ``` | ||
|
|
||
| ## Error Classification | ||
|
|
||
| ### Classify Errors Considering Retrieval Attempts (RAs) | ||
|
|
||
| ```{r} | ||
| dataframe6a <- dataframe5 %>% | ||
| dplyr::select(-correct) %>% # remove old correct_column (the user might also rename if want to keep it) | ||
| dplyr::mutate(accessed = ifelse(item == response, 1, 0)) %>% | ||
| sunflower::classify_errors(access_col = "accessed", | ||
| RA_col = "RA", | ||
| response_col = "response", | ||
| item_col = "item", | ||
| also_classify_RAs = TRUE, | ||
| cosine_limit_value = 0.46) | ||
| knitr::kable(dataframe6a) %>% | ||
| kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed")) %>% | ||
| kableExtra::scroll_box(width = "120%", height = "500px") | ||
| ``` | ||
|
|
||
| ### Classify Errors Without Considering RAs | ||
|
|
||
| ```{r} | ||
| dataframe6b <- dataframe5 %>% | ||
| dplyr::select(-correct) %>% # remove old correct_column (the user might also rename if want to keep it) | ||
| dplyr::mutate(accessed = ifelse(item == response, 1, 0)) %>% | ||
| sunflower::classify_errors_regular(access_col = "accessed", | ||
| response_col = "response", | ||
| item_col = "item", | ||
| cosine_limit_value = 0.46) | ||
| knitr::kable(dataframe6b) %>% | ||
| kableExtra::kable_styling(bootstrap_options = c("striped", "hover", "condensed")) %>% | ||
| kableExtra::scroll_box(width = "120%", height = "500px") | ||
| ``` | ||
|
|
||
| # Conclusion | ||
|
|
||
| This R Markdown document provides a complete workflow for analyzing data using the sunflower package, incorporating data wrangling, similarity metrics, and error classification. | ||
|
|
||
| # R Session Info. | ||
| ```{r} | ||
| sessionInfo() | ||
| ``` |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Oops, something went wrong.