Natural feeling domain-specific language for building structural equation models in R for estimation by covariance-based methods (like LISREL/Lavaan) or partial least squares (like SmartPLS)
58
stars
19
forks
source link
fix #333: Cross-Validation fails when using a tibble #349
predict_pls uses a matrix with variable names to subset the data set. This works with data.frames, but not with tibbles, which results in the error reported in issue #333. This fix addresses the issue by first casting the matrix to a vector when subsetting the data.
Example:
library(seminr)
library(tibble)
mobi_mm <- constructs(
composite("Image", multi_items("IMAG", 1:5)),
composite("Expectation", multi_items("CUEX", 1:3)),
composite("Value", multi_items("PERV", 1:2)),
composite("Satisfaction", multi_items("CUSA", 1:3))
)
mobi_sm <- relationships(
paths(to = "Satisfaction",
from = c("Image", "Expectation", "Value"))
)
mobi_pls <- estimate_pls(mobi, mobi_mm, mobi_sm)
cross_validated_predictions <- predict_pls(model = mobi_pls,
technique = predict_DA,
noFolds = 10,
cores = NULL)
# The following fails in the current version of seminr:
mobi_pls <- estimate_pls(tibble::as_tibble(mobi), mobi_mm, mobi_sm)
cross_validated_predictions_tibble <- predict_pls(model = mobi_pls,
technique = predict_DA,
noFolds = 10,
cores = NULL)
predict_pls uses a matrix with variable names to subset the data set. This works with data.frames, but not with tibbles, which results in the error reported in issue #333. This fix addresses the issue by first casting the matrix to a vector when subsetting the data.
Example: