- Implement the
multiview
function for multiview embedding forecast (MVE) method (#221).
-
Eliminate redundant computations at the source C++ code level (#233).
-
Apply parallel-level computations for each libsize when executing
gccm
on spatial grid data (#203). -
Introduce
trend.rm
option in the R API forembedded
,simplex
, andsmap
methods to align withgccm
behavior (#191). -
Refactor indexing of lag values and embedding vector generation for spatial lattice (#186,#184) and grid data (#183,#181).
-
Centered around example cases in the
gccm
vignette (#170).
- Fix bug in R functions
embedded
,simplex
,smap
when input data contains only one attribute column (#246).
- Improve default spatial neighbors list generation for spatial lattice data with support from the
sdsfun
package (#159).
- Adjust the behavior of the
tau
parameter in the C++ source code and update the R side API (#154).
-
Implement the
smap
function to enable the selection of the optimal theta parameter (#128). -
Add
simplex
function to support selecting the optimal embedding dimension for variables (#98). -
Provide an R-level API for generating embeddings (#97).
-
Now bidirectional mapping in the
gccm
result uses afull join
structure when organized on the R side (#118). -
Support for calculating unidirectional mappings in the
gccm
function (#117). -
Relax
gccm
C++ source codelibsizes
minimum value constraint ofE+2
(#109). -
Include an option in
gccm
to determine whether to include the current state when generating embedding vectors (#103). -
Provide a complete
GCCM
workflow for spatial lattice and grid data in thegccm
vignette (#100). -
Support testing causal links in GCCM with different
E
andk
for cause and effect variables (#96). -
Add thread settings for
gccm
(#94). -
Add
S-maps
cross-prediction support togccm
(#81).
-
Resolve r crash caused by invalid
E
#90 andk
#89 parameter settings ingccm
. -
Fix incorrect Pearson correlation calculation in
C++
code when input contains NA (#83).
-
Encapsulate the
gccm
function using the S4 class (#72). -
Add options for
tau
,k
, andprogressbar
ingccm
(#69). -
Add
print
andplot
s3 methods forgccm
result (#64).
- Fix the bug where the
gccm
function returns empty results when input grid data contains NA values (#61).
- Resolve CRAN auto check issues, no significant API changes.
- Implementing the
GCCM
method for spatial lattice and grid data using pureC++11
.