Merge pull request #121 from Wander03/create-find-table-clustering

Author: EmilHvitfeldt

_freeze/find/tidyclust/index/execute-results/html.json

@@ -0,0 +1,19 @@
+{
+  "hash": "0e8f13f1432971d2a7e8cd1950864393",
+  "result": {
+    "engine": "knitr",
+    "markdown": "---\ntitle: Search tidyclust models\nweight: 2\ndescription: | \n  Find model types and engines to fit and predict clustering methods in the tidymodels framework.\ntoc: true\ntoc-depth: 0\ninclude-after-body: ../../resources.html\ncss: ../styles-find.css\n---\n\n\n\n\nTo learn about the tidyclust package, click on the link in the topic column. Use the tables below to find [model types and engines](#models).\n\n\n\n\n\n\n::: {.cell}\n::: {.cell-output-display}\n\n```{=html}\n<div class=\"datatables html-widget html-fill-item\" id=\"htmlwidget-1b4ff99564eb6e8884a5\" style=\"width:100%;height:auto;\"></div>\n<script type=\"application/json\" data-for=\"htmlwidget-1b4ff99564eb6e8884a5\">{\"x\":{\"filter\":\"top\",\"vertical\":false,\"filterHTML\":\"<tr>\\n  <td data-type=\\\"character\\\" style=\\\"vertical-align: top;\\\">\\n    <div class=\\\"form-group has-feedback\\\" style=\\\"margin-bottom: auto;\\\">\\n      <input type=\\\"search\\\" placeholder=\\\"All\\\" class=\\\"form-control\\\" style=\\\"width: 100%;\\\"/>\\n      <span class=\\\"glyphicon glyphicon-remove-circle form-control-feedback\\\"><\\/span>\\n    <\\/div>\\n  <\\/td>\\n  <td data-type=\\\"character\\\" style=\\\"vertical-align: top;\\\">\\n    <div class=\\\"form-group has-feedback\\\" style=\\\"margin-bottom: auto;\\\">\\n      <input type=\\\"search\\\" placeholder=\\\"All\\\" class=\\\"form-control\\\" style=\\\"width: 100%;\\\"/>\\n      <span class=\\\"glyphicon glyphicon-remove-circle form-control-feedback\\\"><\\/span>\\n    <\\/div>\\n  <\\/td>\\n  <td data-type=\\\"character\\\" style=\\\"vertical-align: top;\\\">\\n    <div class=\\\"form-group has-feedback\\\" style=\\\"margin-bottom: auto;\\\">\\n      <input type=\\\"search\\\" placeholder=\\\"All\\\" class=\\\"form-control\\\" style=\\\"width: 100%;\\\"/>\\n      <span class=\\\"glyphicon glyphicon-remove-circle form-control-feedback\\\"><\\/span>\\n    <\\/div>\\n  <\\/td>\\n  <td data-type=\\\"character\\\" style=\\\"vertical-align: top;\\\">\\n    <div class=\\\"form-group has-feedback\\\" style=\\\"margin-bottom: auto;\\\">\\n      <input type=\\\"search\\\" placeholder=\\\"All\\\" class=\\\"form-control\\\" style=\\\"width: 100%;\\\"/>\\n      <span class=\\\"glyphicon glyphicon-remove-circle form-control-feedback\\\"><\\/span>\\n    <\\/div>\\n  <\\/td>\\n  <td data-type=\\\"factor\\\" style=\\\"vertical-align: top;\\\">\\n    <div class=\\\"form-group has-feedback\\\" style=\\\"margin-bottom: auto;\\\">\\n      <input type=\\\"search\\\" placeholder=\\\"All\\\" class=\\\"form-control\\\" style=\\\"width: 100%;\\\" disabled=\\\"\\\"/>\\n      <span class=\\\"glyphicon glyphicon-remove-circle form-control-feedback\\\"><\\/span>\\n    <\\/div>\\n    <div style=\\\"width: 100%; display: none;\\\">\\n      <select multiple=\\\"multiple\\\" style=\\\"width: 100%;\\\" data-options=\\\"[&quot;partition&quot;]\\\"><\\/select>\\n    <\\/div>\\n  <\\/td>\\n  <td data-type=\\\"factor\\\" style=\\\"vertical-align: top;\\\">\\n    <div class=\\\"form-group has-feedback\\\" style=\\\"margin-bottom: auto;\\\">\\n      <input type=\\\"search\\\" placeholder=\\\"All\\\" class=\\\"form-control\\\" style=\\\"width: 100%;\\\" disabled=\\\"\\\"/>\\n      <span class=\\\"glyphicon glyphicon-remove-circle form-control-feedback\\\"><\\/span>\\n    <\\/div>\\n    <div style=\\\"width: 100%; display: none;\\\">\\n      <select multiple=\\\"multiple\\\" style=\\\"width: 100%;\\\" data-options=\\\"[&quot;tidyclust&quot;]\\\"><\\/select>\\n    <\\/div>\\n  <\\/td>\\n<\\/tr>\",\"data\":[[\"Hierarchical (Agglomerative) Clustering via stats\",\"K-means via ClusterR\",\"K-means via clustMixType\",\"K-means via klaR\",\"K-means via stats\"],[\"<code>hier_clust<\\/code>\",\"<code>k_means<\\/code>\",\"<code>k_means<\\/code>\",\"<code>k_means<\\/code>\",\"<code>k_means<\\/code>\"],[\"<code>stats<\\/code>\",\"<code>ClusterR<\\/code>\",\"<code>clustMixType<\\/code>\",\"<code>klaR<\\/code>\",\"<code>stats<\\/code>\"],[\"<a href='https://tidyclust.tidymodels.org//reference/details_hier_clust_stats.html' target='_blank'><tt>details_hier_clust_stats<\\/tt><\\/a>\",\"<a href='https://tidyclust.tidymodels.org//reference/details_k_means_ClusterR.html' target='_blank'><tt>details_k_means_ClusterR<\\/tt><\\/a>\",\"<a href='https://tidyclust.tidymodels.org//reference/details_k_means_clustMixType.html' target='_blank'><tt>details_k_means_clustMixType<\\/tt><\\/a>\",\"<a href='https://tidyclust.tidymodels.org//reference/details_k_means_klaR.html' target='_blank'><tt>details_k_means_klaR<\\/tt><\\/a>\",\"<a href='https://tidyclust.tidymodels.org//reference/details_k_means_stats.html' target='_blank'><tt>details_k_means_stats<\\/tt><\\/a>\"],[\"partition\",\"partition\",\"partition\",\"partition\",\"partition\"],[\"tidyclust\",\"tidyclust\",\"tidyclust\",\"tidyclust\",\"tidyclust\"]],\"container\":\"<table class=\\\"cell-border stripe\\\">\\n  <thead>\\n    <tr>\\n      <th>title<\\/th>\\n      <th>model<\\/th>\\n      <th>engine<\\/th>\\n      <th>topic<\\/th>\\n      <th>mode<\\/th>\\n      <th>package<\\/th>\\n    <\\/tr>\\n  <\\/thead>\\n<\\/table>\",\"options\":{\"pageLength\":25,\"columnDefs\":[{\"name\":\"title\",\"targets\":0},{\"name\":\"model\",\"targets\":1},{\"name\":\"engine\",\"targets\":2},{\"name\":\"topic\",\"targets\":3},{\"name\":\"mode\",\"targets\":4},{\"name\":\"package\",\"targets\":5}],\"order\":[],\"autoWidth\":false,\"orderClasses\":false,\"orderCellsTop\":true}},\"evals\":[],\"jsHooks\":[]}</script>\n```\n\n:::\n:::\n",
+    "supporting": [],
+    "filters": [
+      "rmarkdown/pagebreak.lua"
+    ],
+    "includes": {
+      "include-in-header": [
+        "<link href=\"../../site_libs/htmltools-fill-0.5.8.1/fill.css\" rel=\"stylesheet\" />\n<script src=\"../../site_libs/htmlwidgets-1.6.4/htmlwidgets.js\"></script>\n<link href=\"../../site_libs/datatables-css-0.0.0/datatables-crosstalk.css\" rel=\"stylesheet\" />\n<script src=\"../../site_libs/datatables-binding-0.33/datatables.js\"></script>\n<script src=\"../../site_libs/jquery-3.6.0/jquery-3.6.0.min.js\"></script>\n<link href=\"../../site_libs/dt-core-1.13.6/css/jquery.dataTables.min.css\" rel=\"stylesheet\" />\n<link href=\"../../site_libs/dt-core-1.13.6/css/jquery.dataTables.extra.css\" rel=\"stylesheet\" />\n<script src=\"../../site_libs/dt-core-1.13.6/js/jquery.dataTables.min.js\"></script>\n<link href=\"../../site_libs/nouislider-7.0.10/jquery.nouislider.min.css\" rel=\"stylesheet\" />\n<script src=\"../../site_libs/nouislider-7.0.10/jquery.nouislider.min.js\"></script>\n<link href=\"../../site_libs/selectize-0.12.0/selectize.bootstrap3.css\" rel=\"stylesheet\" />\n<script src=\"../../site_libs/selectize-0.12.0/selectize.min.js\"></script>\n<link href=\"../../site_libs/crosstalk-1.2.1/css/crosstalk.min.css\" rel=\"stylesheet\" />\n<script src=\"../../site_libs/crosstalk-1.2.1/js/crosstalk.min.js\"></script>\n"
+      ]
+    },
+    "engineDependencies": {},
+    "preserve": {},
+    "postProcess": true
+  }
+}

find/index.html.md

@@ -20,6 +20,8 @@ Below you'll find searchable tables to help you explore the tidymodels packages
 
 * [Search sparse data compatible methods](sparse/index.qmd)
 
+* [Search tidyclust models](tidyclust/index.qmd)
+
 # Books
 
 If you want to read more long form there are a number of books written about and using tidymodels

find/index.qmd

@@ -20,6 +20,8 @@ Below you'll find searchable tables to help you explore the tidymodels packages
 
 * [Search sparse data compatible methods](sparse/index.qmd)
 
+* [Search tidyclust models](tidyclust/index.qmd)
+
 # Books
 
 If you want to read more long form there are a number of books written about and using tidymodels

find/tidyclust/index.html.md

@@ -0,0 +1,23 @@
+---
+title: Search tidyclust models
+weight: 2
+description: | 
+  Find model types and engines to fit and predict clustering methods in the tidymodels framework.
+toc: true
+toc-depth: 0
+include-after-body: ../../resources.html
+css: ../styles-find.css
+---
+
+To learn about the tidyclust package, click on the link in the topic column. Use the tables below to find [model types and engines](#models).
+
+::: {.cell}
+::: {.cell-output-display}
+
+```{=html}
+<div class="datatables html-widget html-fill-item" id="htmlwidget-1b4ff99564eb6e8884a5" style="width:100%;height:auto;"></div>
+<script type="application/json" data-for="htmlwidget-1b4ff99564eb6e8884a5">{"x":{"filter":"top","vertical":false,"filterHTML":"<tr>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"character\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n  <\/td>\n  <td data-type=\"factor\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\" disabled=\"\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"width: 100%; display: none;\">\n      <select multiple=\"multiple\" style=\"width: 100%;\" data-options=\"[&quot;partition&quot;]\"><\/select>\n    <\/div>\n  <\/td>\n  <td data-type=\"factor\" style=\"vertical-align: top;\">\n    <div class=\"form-group has-feedback\" style=\"margin-bottom: auto;\">\n      <input type=\"search\" placeholder=\"All\" class=\"form-control\" style=\"width: 100%;\" disabled=\"\"/>\n      <span class=\"glyphicon glyphicon-remove-circle form-control-feedback\"><\/span>\n    <\/div>\n    <div style=\"width: 100%; display: none;\">\n      <select multiple=\"multiple\" style=\"width: 100%;\" data-options=\"[&quot;tidyclust&quot;]\"><\/select>\n    <\/div>\n  <\/td>\n<\/tr>","data":[["Hierarchical (Agglomerative) Clustering via stats","K-means via ClusterR","K-means via clustMixType","K-means via klaR","K-means via stats"],["<code>hier_clust<\/code>","<code>k_means<\/code>","<code>k_means<\/code>","<code>k_means<\/code>","<code>k_means<\/code>"],["<code>stats<\/code>","<code>ClusterR<\/code>","<code>clustMixType<\/code>","<code>klaR<\/code>","<code>stats<\/code>"],["<a href='https://tidyclust.tidymodels.org//reference/details_hier_clust_stats.html' target='_blank'><tt>details_hier_clust_stats<\/tt><\/a>","<a href='https://tidyclust.tidymodels.org//reference/details_k_means_ClusterR.html' target='_blank'><tt>details_k_means_ClusterR<\/tt><\/a>","<a href='https://tidyclust.tidymodels.org//reference/details_k_means_clustMixType.html' target='_blank'><tt>details_k_means_clustMixType<\/tt><\/a>","<a href='https://tidyclust.tidymodels.org//reference/details_k_means_klaR.html' target='_blank'><tt>details_k_means_klaR<\/tt><\/a>","<a href='https://tidyclust.tidymodels.org//reference/details_k_means_stats.html' target='_blank'><tt>details_k_means_stats<\/tt><\/a>"],["partition","partition","partition","partition","partition"],["tidyclust","tidyclust","tidyclust","tidyclust","tidyclust"]],"container":"<table class=\"cell-border stripe\">\n  <thead>\n    <tr>\n      <th>title<\/th>\n      <th>model<\/th>\n      <th>engine<\/th>\n      <th>topic<\/th>\n      <th>mode<\/th>\n      <th>package<\/th>\n    <\/tr>\n  <\/thead>\n<\/table>","options":{"pageLength":25,"columnDefs":[{"name":"title","targets":0},{"name":"model","targets":1},{"name":"engine","targets":2},{"name":"topic","targets":3},{"name":"mode","targets":4},{"name":"package","targets":5}],"order":[],"autoWidth":false,"orderClasses":false,"orderCellsTop":true}},"evals":[],"jsHooks":[]}</script>
+```
+
+:::
+:::

find/tidyclust/index.qmd

@@ -0,0 +1,37 @@
+---
+title: Search tidyclust models
+weight: 2
+description: | 
+  Find model types and engines to fit and predict clustering methods in the tidymodels framework.
+toc: true
+toc-depth: 0
+include-after-body: ../../resources.html
+css: ../styles-find.css
+---
+
+To learn about the tidyclust package, click on the link in the topic column. Use the tables below to find [model types and engines](#models).
+
+```{r}
+#| include: false
+
+library(tidymodels)
+library(readr)
+library(DT)
+library(htmlwidgets)
+setWidgetIdSeed(1234)
+tidymodels_prefer()
+tidyclust_models <- read_csv("tidyclust_models.csv")
+```
+
+```{r}
+#| label: table-display
+#| echo: false
+tidyclust_models %>% 
+  mutate(package = factor(package)) %>%
+  mutate(mode = factor(mode)) %>%
+  datatable(rownames = FALSE,
+            class = 'cell-border stripe',
+            filter = 'top',
+            escape = FALSE,
+            options = list(pageLength = 25))
+```

find/tidyclust/tidyclust_models.csv

@@ -0,0 +1,6 @@
+title,model,engine,topic,mode,package
+Hierarchical (Agglomerative) Clustering via stats,<code>hier_clust</code>,<code>stats</code>,<a href='https://tidyclust.tidymodels.org//reference/details_hier_clust_stats.html' target='_blank'><tt>details_hier_clust_stats</tt></a>,partition,tidyclust
+K-means via ClusterR,<code>k_means</code>,<code>ClusterR</code>,<a href='https://tidyclust.tidymodels.org//reference/details_k_means_ClusterR.html' target='_blank'><tt>details_k_means_ClusterR</tt></a>,partition,tidyclust
+K-means via clustMixType,<code>k_means</code>,<code>clustMixType</code>,<a href='https://tidyclust.tidymodels.org//reference/details_k_means_clustMixType.html' target='_blank'><tt>details_k_means_clustMixType</tt></a>,partition,tidyclust
+K-means via klaR,<code>k_means</code>,<code>klaR</code>,<a href='https://tidyclust.tidymodels.org//reference/details_k_means_klaR.html' target='_blank'><tt>details_k_means_klaR</tt></a>,partition,tidyclust
+K-means via stats,<code>k_means</code>,<code>stats</code>,<a href='https://tidyclust.tidymodels.org//reference/details_k_means_stats.html' target='_blank'><tt>details_k_means_stats</tt></a>,partition,tidyclust

make_function_lists.R

@@ -368,3 +368,78 @@ write_csv(
   sparse_steps_preserve,
   file = "find/sparse/steps_preserve.csv"
 )
+
+# ------------------------------------------------------------------------------
+
+# currently does not rely on any packages, leaving in if added in future
+tidyclust_pkgs <- revdepcheck::cran_revdeps(
+  "tidyclust",
+  dependencies = c("Depends", "Imports")
+)
+
+tidyclust_pkgs <- c(tidyclust_pkgs, "tidyclust")
+
+# Load them then get the model data base
+loaded <- purrr::map_lgl(
+  tidyclust_pkgs,
+  ~ suppressPackageStartupMessages(require(.x, character.only = TRUE))
+)
+table(loaded)
+
+# h2o overwrites soooo many functions; this may take a few minutes
+conflicted::conflict_prefer_all("base", loser = "h2o", quiet = TRUE)
+
+origin_pkg <- rlang::env_get_list(
+  env = modelenv::get_model_env(),
+  nms = ls(modelenv::get_model_env(), pattern = "_pkg")
+) %>%
+  purrr::list_rbind(names_to = "model") %>%
+  dplyr::mutate(
+    pkg = purrr::map_chr(
+      pkg,
+      ~ {
+        pkg <- intersect(.x, tidyclust_pkgs)
+        if (length(pkg) == 0) {
+          pkg <- "tidyclust"
+        }
+        pkg
+      }
+    )
+  ) %>%
+  dplyr::mutate(
+    model = stringr::str_remove(model, "_pkgs$"),
+    functions = paste("details", model, engine, sep = "_")
+    )
+
+# Add more clustering methods as they become available
+cluster_types <- c(
+  "Hierarchical \\(Agglomerative\\) Clustering",
+  "K-[M|m]eans"
+)
+
+tidyclust_model_info <-
+  purrr::map_dfr(
+    tidyclust_pkgs,
+    get_pkg_info,
+    keep_internal = TRUE,
+    .progress = TRUE
+  ) %>%
+  sort_out_urls() %>%
+  filter(str_detect(title, paste(cluster_types, collapse = "|")))
+
+tidyclust_models <-
+  tidyclust_model_info %>%
+  dplyr::filter(grepl("^details_", functions)) %>%
+  dplyr::inner_join(origin_pkg, by = "functions") %>%
+  dplyr::mutate(
+    model = paste0("<code>", model, "</code>"),
+    engine = paste0("<code>", engine, "</code>"),
+    title = gsub("General Interface for ", "", title)
+  ) %>%
+  dplyr::arrange(model, engine) %>%
+  dplyr::select(title, model, engine, topic, mode, package)
+
+write_csv(
+  tidyclust_models,
+  file = "find/tidyclust/tidyclust_models.csv"
+)