Merge pull request #1125 from e-sensing/dev

Pre-realease 1.5.0

Author: OldLipe

DESCRIPTION

@@ -27,7 +27,7 @@ Description: An end-to-end toolkit for land use and land cover classification
     random forests, extreme gradient boosting, multi-layer perceptrons,
     temporal convolutional neural networks proposed by Pelletier et al (2019) <doi:10.3390/rs11050523>, 
     residual networks by Fawaz et al (2019) <doi:10.1007/s10618-019-00619-1>, and temporal attention encoders
-    by Garnot and Landrieu (2020) <arXiv:2007.00586>.
+    by Garnot and Landrieu (2020) <doi:10.48550/arXiv.2007.00586>.
     Performs efficient classification of big Earth observation data cubes and includes 
     functions for post-classification smoothing based on Bayesian inference, and 
     methods for uncertainty assessment. Enables best
@@ -138,6 +138,7 @@ Collate:
     'api_gdal.R'
     'api_gdalcubes.R'
     'api_jobs.R'
+    'api_kohonen.R'
     'api_label_class.R'
     'api_merge.R'
     'api_mixture_model.R'

NAMESPACE

@@ -93,6 +93,10 @@ S3method(.data_get_ts,raster_cube)
 S3method(.gc_arrange_images,raster_cube)
 S3method(.mosaic_split_band_date,derived_cube)
 S3method(.mosaic_split_band_date,raster_cube)
+S3method(.opensearch_cdse_extract_tile,RTC)
+S3method(.opensearch_cdse_extract_tile,S2MSI2A)
+S3method(.opensearch_cdse_search,RTC)
+S3method(.opensearch_cdse_search,S2MSI2A)
 S3method(.raster_check_package,terra)
 S3method(.raster_col,terra)
 S3method(.raster_crop,terra)
@@ -414,7 +418,6 @@ S3method(summary,sits_accuracy)
 S3method(summary,sits_area_accuracy)
 export("sits_bands<-")
 export("sits_labels<-")
-export(.mpc_clean_token_cache)
 export(impute_linear)
 export(sits_accuracy)
 export(sits_accuracy_summary)

R/RcppExports.R

@@ -37,8 +37,32 @@ C_kernel_modal <- function(x, ncols, nrows, band, window_size) {
     .Call(`_sits_C_kernel_modal`, x, ncols, nrows, band, window_size)
 }
 
-dtw <- function() {
-    .Call(`_sits_dtw`)
+kohonen_dtw <- function() {
+    .Call(`_sits_kohonen_dtw`)
+}
+
+kohonen_euclidean <- function() {
+    .Call(`_sits_kohonen_euclidean`)
+}
+
+kohonen_object_distances <- function(data, numVars, numNAs, distanceFunction, weights) {
+    .Call(`_sits_kohonen_object_distances`, data, numVars, numNAs, distanceFunction, weights)
+}
+
+RcppMap <- function(data, numVars, numNAs, codes, weights, distanceFunction) {
+    .Call(`_sits_RcppMap`, data, numVars, numNAs, codes, weights, distanceFunction)
+}
+
+RcppSupersom <- function(data, codes, numVars, weights, distanceFunction, numNAs, neighbourhoodDistances, alphas, radii, numEpochs) {
+    .Call(`_sits_RcppSupersom`, data, codes, numVars, weights, distanceFunction, numNAs, neighbourhoodDistances, alphas, radii, numEpochs)
+}
+
+RcppBatchSupersom <- function(data, codes, numVars, weights, distanceFunction, numNAs, neighbourhoodDistances, radii, numEpochs) {
+    .Call(`_sits_RcppBatchSupersom`, data, codes, numVars, weights, distanceFunction, numNAs, neighbourhoodDistances, radii, numEpochs)
+}
+
+RcppParallelBatchSupersom <- function(data, codes, numVars, weights, distanceFunction, numNAs, neighbourhoodDistances, radii, numEpochs, numCores) {
+    .Call(`_sits_RcppParallelBatchSupersom`, data, codes, numVars, weights, distanceFunction, numNAs, neighbourhoodDistances, radii, numEpochs, numCores)
 }
 
 C_label_max_prob <- function(x) {
@@ -141,14 +165,6 @@ C_temp_iqr <- function(mtx) {
     .Call(`_sits_C_temp_iqr`, mtx)
 }
 
-rlang_env_unlock <- function(env) {
-    invisible(.Call(`_sits_rlang_env_unlock`, env))
-}
-
-rlang_env_lock <- function(env) {
-    invisible(.Call(`_sits_rlang_env_lock`, env))
-}
-
 C_max_sampling <- function(x, nrows, ncols, window_size) {
     .Call(`_sits_C_max_sampling`, x, nrows, ncols, window_size)
 }