solving notes

r-spatial · Apr 23, 2021 · c0b6e40 · c0b6e40
1 parent e1809d9
commit c0b6e40
Show file tree

Hide file tree

Showing 4 changed files with 4 additions and 4 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -90,7 +90,7 @@ Description: Earth Engine <https://earthengine.google.com/> client library for R
   and metadata display. See <https://r-spatial.github.io/rgee/> for further details.
 License: Apache License (>= 2.0)
 Encoding: UTF-8
-LazyData: true
+LazyData: false
 Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.1.1
 Depends:

diff --git a/R/sf_as_ee.R b/R/sf_as_ee.R
@@ -57,7 +57,7 @@
 #' file in the /temp directory. Secondly, using the function \code{local_to_gcs}
 #' will move the shapefile from local to Google Cloud Storage. Finally, using
 #' the function \code{gcs_to_ee_table} the ESRI shapefile will be loaded
-#' to their EE Assets. See \href{https://developers.google.com/earth-engine/guides/importing/}{Importing
+#' to their EE Assets. See \href{https://developers.google.com/earth-engine/guides/table_upload/}{Importing
 #' table data} documentation for more details.
 #'
 #' @examples

diff --git a/man/sf_as_ee.Rd b/man/sf_as_ee.Rd
diff --git a/vignettes/rgee03.Rmd b/vignettes/rgee03.Rmd
@@ -572,7 +572,7 @@ Map$addLayer(optimizedConvolution, viz, "optimizedConvolution")
 
 ## **Don't sample more data than you need**
 
-Resist the urge to increase your training dataset size unnecessarily. Although increasing the amount of training data is an effective machine learning strategy in some circumstances, it can also increase computational cost with no corresponding increase in accuracy. (For an understanding of when to increase training dataset size, see [this reference](https://www.deeplearning.ai/machine-learning-yearning/)). The following example demonstrates how requesting too much training data can result in the dreaded "Computed value is too large" error:
+Resist the urge to increase your training dataset size unnecessarily. Although increasing the amount of training data is an effective machine learning strategy in some circumstances, it can also increase computational cost with no corresponding increase in accuracy. (For an understanding of when to increase training dataset size, see [this reference](https://www.deeplearning.ai/programs/)). The following example demonstrates how requesting too much training data can result in the dreaded "Computed value is too large" error:
 
 <img src="thumb_down.png" width=25px>
 &nbsp; **Bad** — Don't sample too much data!