alg-ml >> {usearchlite}; geo-mod >> {geocmeans}; r-tidy >> resource

Author: ercbk

qmd/algorithms-ml.qmd

@@ -283,6 +283,8 @@
             -   kNN search
             -   Fixed-radius NN search
             -   The implementations use the kd-tree data structure (from library ANN) for faster k-nearest neighbor search, and are for Euclidean distance typically faster than the native R implementations (e.g., dbscan in package `fpc`), or the implementations in [WEKA](#0), [ELKI](#0) and Python’s scikit-learn.
+        -   [{]{style="color: #990000"}[usearchlite](https://cran.r-project.org/web/packages/usearchlite/index.html){style="color: #990000"}[}]{style="color: #990000"} - Local Vector Search with 'USearch'
+            -   A lightweight local vector index for approximate nearest neighbor (ANN) search using the vendored 'USearch' library
 -   Used mostly in Similarity Search: Quickly identify items most similar to a given item or user profile.
     -   Commonly used in Recommendation algs to find similar user-item embeddings at the end. Also, any NLP task where you need to do a similarity search of one character embedding to other character embeddings.
 -   Generally uses one of two main categories of hashing methods: either data-independent methods, such as locality-sensitive hashing (LSH); or data-dependent methods, such as Locality-preserving hashing (LPH)

qmd/geospatial-modeling.qmd

@@ -11,6 +11,8 @@
         -   Passing distance matrices to a clustering algorithm
     -   The current distance matrix is an implementation of the flow distance and flow dissimilarity measures
     -   Can aggregate the flows in each cluster into a single line representing the average flow direction and magnitude
+-   [{]{style="color: #990000"}[geocmeans](https://jeremygelb.github.io/geocmeans/){style="color: #990000"}[}]{style="color: #990000"} - Apply Spatial Fuzzy c-means Algorithm, visualize and interpret results. This method is well suited when the user wants to analyze data with a fuzzy clustering algorithm and to account for the spatial dimension of the dataset.
+    -   In addition, indexes for measuring the spatial consistency and classification quality are proposed
 -   [{]{style="color: #990000"}[GWnnegPCA](https://cran.r-project.org/web/packages/GWnnegPCA/index.html){style="color: #990000"}[}]{style="color: #990000"} - Geographically Weighted Non-Negative **Principal Components Analysis**
 -   [{]{style="color: #990000"}[lagsarlmtree](https://cran.r-project.org/web/packages/lagsarlmtree/index.html){style="color: #990000"}[}]{style="color: #990000"} - Model-based linear model **trees adjusting for spatial correlation** using a simultaneous autoregressive spatial lag
     -   The linear model is a SLM econometric spatial regression model imported from spatialreg (See [Regression, Spatial \>\> Econometric](regression-spatial.qmd#sec-reg-spatial-econ){style="color: #990000"})

qmd/r-tidyverse.qmd

@@ -10,6 +10,7 @@
                 ![](_resources/R-tidyverse.resources/tidylog-leftjoin-1.jpg){.lightbox}
     -   Resources
         -   [Let’s talk about joins](https://cghlewis.com/blog/joins/)
+        -   [Suzan Baert Dplyr Tutorials](https://github.com/suzanbaert/Dplyr_Tutorials/tree/master)
 -   [Tidy Selectors]{.underline}
     -   [Docs](https://dplyr.tidyverse.org/reference/select.html#overview-of-selection-features)
     -   Operators