Merge pull request #171 from tidymodels/RC-0.2.0

Author: EmilHvitfeldt

.Rbuildignore

@@ -12,3 +12,4 @@
 ^vignettes/articles$
 ^cran-comments\.md$
 ^CRAN-SUBMISSION$
+^revdep$

.gitignore

@@ -5,3 +5,8 @@
 .DS_Store
 docs
 hex sticker/
+revdep/checks.noindex
+revdep/library.noindex
+revdep/data.sqlite
+.httr-oauth
+revdep/cloud.noindex/*

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: tidyclust
 Title: A Common API to Clustering
-Version: 0.1.2.9000
+Version: 0.2.0.9000
 Authors@R: c(
     person("Emil", "Hvitfeldt", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-0679-1945")),
@@ -13,6 +13,8 @@ Description: A common interface to specifying clustering models, in the
 License: MIT + file LICENSE
 URL: https://github.com/tidymodels/tidyclust, https://tidyclust.tidymodels.org/
 BugReports: https://github.com/tidymodels/tidyclust/issues
+Depends: 
+    R (>= 3.6)
 Imports: 
     cli (>= 3.0.0),
     dials (>= 1.1.0),

NEWS.md

@@ -1,5 +1,19 @@
 # tidyclust (development version)
 
+# tidyclust 0.2.0
+
+## New Engines
+
+* The clustMixType engine as been added to `k_means()`. This engine allows fitting of k-prototype models. (#63)
+
+* The klaR engine as been added to `k_means()`. This engine allows fitting of k-modes models. (#63)
+
+## Improvements
+
+* Engine specific documentation has been added for all models and engines. (#159)
+
+## Bug Fixes
+
 * Fixed bug where engine specific arguments were passed along for `k_means()` when the engine ClusterR. (#142)
 
 * Fixed bug where `prefix` argument wouldn't be correctly passed through `extract_cluster_assignment()`, `extract_centroids()`, and `predict()` (#145)
@@ -12,19 +26,15 @@
 
 * `k_means()` now errors informatively if `fit()` without `num_clust` specified. (#134)
 
-* Exported internal functions `ClusterR_kmeans_fit()`, `stats_kmeans_fit()`, and `hclust_fit()` have been renamed to `.k_means_fit_ClusterR()`, `.k_means_fit_stats()`, and `.hier_clust_fit_stats()` to reduce visibility for users. 
-
-* The clustMixType engine as been added to `k_means()`. This engine allows fitting of k-prototype models. (#63)
+* Fixed bug where levels didn't match number of clusters if prediction on fewer number of observations. (#158)
 
-* The klaR engine as been added to `k_means()`. This engine allows fitting of k-modes models. (#63)
+* Fixed bug where `tune_cluster()` would error if used with an recipe that contained non-predictor variables such as id variables. (#124)
 
-* Cluster reordering is now done at the fitting time, not the extraction and prediction time. (#154)
+## Breaking Changes
 
-* Engine specific documentation has been added for all models and engines. (#159)
-
-* Fixed bug where levels didn't match number of clusters if prediction on fewer number of observations. (#158)
+* Exported internal functions `ClusterR_kmeans_fit()`, `stats_kmeans_fit()`, and `hclust_fit()` have been renamed to `.k_means_fit_ClusterR()`, `.k_means_fit_stats()`, and `.hier_clust_fit_stats()` to reduce visibility for users. 
 
-* Fixed bug where `tune_cluster()` would error if used with an recipe that contained non-predictor variables such as id variables. (#124)
+* Cluster reordering is now done at the fitting time, not the extraction and prediction time. (#154)
 
 # tidyclust 0.1.2
 

R/engine_docs.R

@@ -3,7 +3,6 @@
 #' Knit engine-specific documentation
 #' @param pattern A regular expression to specify which files to knit. The
 #' default knits all engine documentation files.
-#' @param ... Options passed to [knitr::knit()].
 #' @return A tibble with column `file` for the file name and `result` (a
 #' character vector that echos the output file name or, when there is
 #' a failure, the error message).

R/hier_clust.R

@@ -171,7 +171,7 @@ translate_tidyclust.hier_clust <- function(x, engine = x$engine, ...) {
 #'
 #' @param x matrix or data frame
 #' @param num_clusters the number of clusters
-#' @param h the height to cut the dendrogram
+#' @param cut_height the height to cut the dendrogram
 #' @param linkage_method the agglomeration method to be used. This should be (an
 #'   unambiguous abbreviation of) one of `"ward.D"`, `"ward.D2"`, `"single"`,
 #'   `"complete"`, `"average"` (= UPGMA), `"mcquitty"` (= WPGMA), `"median"` (=

README.md

@@ -41,7 +41,7 @@ library(tidyclust)
 set.seed(1234)
 
 kmeans_spec <- k_means(num_clusters = 3) %>%
-  set_engine("stats") 
+  set_engine("stats")
 
 kmeans_spec
 #> K Means Cluster Specification (partition)
@@ -60,38 +60,38 @@ kmeans_spec_fit <- kmeans_spec %>%
 kmeans_spec_fit
 #> tidyclust cluster object
 #> 
-#> K-means clustering with 3 clusters of sizes 7, 14, 11
+#> K-means clustering with 3 clusters of sizes 7, 11, 14
 #> 
 #> Cluster means:
 #>        mpg cyl     disp        hp     drat       wt     qsec        vs
 #> 1 19.74286   6 183.3143 122.28571 3.585714 3.117143 17.97714 0.5714286
-#> 2 15.10000   8 353.1000 209.21429 3.229286 3.999214 16.77214 0.0000000
 #> 3 26.66364   4 105.1364  82.63636 4.070909 2.285727 19.13727 0.9090909
+#> 2 15.10000   8 353.1000 209.21429 3.229286 3.999214 16.77214 0.0000000
 #>          am     gear     carb
 #> 1 0.4285714 3.857143 3.428571
-#> 2 0.1428571 3.285714 3.500000
 #> 3 0.7272727 4.090909 1.545455
+#> 2 0.1428571 3.285714 3.500000
 #> 
 #> Clustering vector:
 #>           Mazda RX4       Mazda RX4 Wag          Datsun 710      Hornet 4 Drive 
-#>                   1                   1                   3                   1 
+#>                   1                   1                   2                   1 
 #>   Hornet Sportabout             Valiant          Duster 360           Merc 240D 
-#>                   2                   1                   2                   3 
+#>                   3                   1                   3                   2 
 #>            Merc 230            Merc 280           Merc 280C          Merc 450SE 
-#>                   3                   1                   1                   2 
+#>                   2                   1                   1                   3 
 #>          Merc 450SL         Merc 450SLC  Cadillac Fleetwood Lincoln Continental 
-#>                   2                   2                   2                   2 
+#>                   3                   3                   3                   3 
 #>   Chrysler Imperial            Fiat 128         Honda Civic      Toyota Corolla 
-#>                   2                   3                   3                   3 
-#>       Toyota Corona    Dodge Challenger         AMC Javelin          Camaro Z28 
 #>                   3                   2                   2                   2 
-#>    Pontiac Firebird           Fiat X1-9       Porsche 914-2        Lotus Europa 
+#>       Toyota Corona    Dodge Challenger         AMC Javelin          Camaro Z28 
 #>                   2                   3                   3                   3 
+#>    Pontiac Firebird           Fiat X1-9       Porsche 914-2        Lotus Europa 
+#>                   3                   2                   2                   2 
 #>      Ford Pantera L        Ferrari Dino       Maserati Bora          Volvo 142E 
-#>                   2                   1                   2                   3 
+#>                   3                   1                   3                   2 
 #> 
 #> Within cluster sum of squares by cluster:
-#> [1] 13954.34 93643.90 11848.37
+#> [1] 13954.34 11848.37 93643.90
 #>  (between_SS / total_SS =  80.8 %)
 #> 
 #> Available components:
@@ -132,7 +132,7 @@ extract_cluster_assignment(kmeans_spec_fit)
 #>  8 Cluster_2
 #>  9 Cluster_2
 #> 10 Cluster_1
-#> # … with 22 more rows
+#> # ℹ 22 more rows
 ```
 
 and `extract_centroids()` returns the locations of the clusters

cran-comments.md

@@ -1,6 +1,6 @@
 ## Comments
 
-Patch release to make sure `utils::packageVersion()` doesn't cause issues when package isn't available.
+Release including fix for all known bugs, new engines and better document and error messages.
 
 ## R CMD check results