PecanProject · ANAMASGARD · Jul 17, 2026 · Sep 15, 2026 · Sep 15, 2026
diff --git a/.github/workflows/quarto-publish.yml b/.github/workflows/quarto-publish.yml
@@ -29,6 +29,7 @@ jobs:
         with:
           extra-packages: |
             local::.
+            any::DT
             any::dplyr
             any::ggplot2
             any::knitr

diff --git a/CITATION.cff b/CITATION.cff
@@ -33,6 +33,9 @@ authors:
     family-names: BV
     email: www.divinehome12@gmail.com
     affiliation: CMR Institute of Technology, Bengaluru
+  - given-names: Gaurav
+    family-names: Chaudhary
+    email: chaudharygaurav2004@gmail.com
 preferred-citation:
   type: article
   title: >-

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -4,7 +4,13 @@ Title: Public Data from the BETYdb Database
 Version: 0.1.0
 Authors@R: c(
     person("David", "LeBauer", email = "dlebauer@arizona.edu", role = c("aut", "cre")),
-    person("Akash B V", email = "www.divinehome12@gmail.com", role = "aut")
+    person("Akash B V", email = "www.divinehome12@gmail.com", role = "aut"),
+    person(
+        "Gaurav",
+        "Chaudhary",
+        email = "chaudharygaurav2004@gmail.com",
+        role = "ctb"
+    )
     )
 Description: An R data package providing offline access to public data from 
     the BETYdb database (betydb.org). Includes plant traits, crop yields, 
@@ -17,14 +23,16 @@ BugReports: https://github.com/PecanProject/betydata/issues
 Depends:
     R (>= 4.1.0)
 Suggests:
+    DT,
     dplyr (>= 1.1.0),
     ggplot2,
     jsonlite,
     knitr,
     maps,
     quarto,
     rmarkdown,
-    testthat (>= 3.0.0)
+    testthat (>= 3.0.0),
+    tibble
 VignetteBuilder: quarto
 SystemRequirements: Quarto command line tool (https://github.com/quarto-dev/quarto-cli)
 Encoding: UTF-8

diff --git a/NEWS.md b/NEWS.md
@@ -1,7 +1,10 @@
 # betydata (development version)
 
+* Improved the website homepage with observation-backed summary metrics, a searchable observation preview, and summaries of the most represented
+  variables and species (#26).
 * Replaced `Infinity` and `-Infinity` variable-bound placeholders with `NA`.
 
+
 # betydata 0.1.0
 
 ## Initial Release

diff --git a/R/homepage-data.R b/R/homepage-data.R
@@ -0,0 +1,101 @@
+# Homepage summary helpers used by the Quarto site.
+
+homepage_non_blank <- function(x) {
+  !is.na(x) & (!is.character(x) | nzchar(trimws(x)))
+}
+
+homepage_labels <- function(x) {
+  values <- trimws(as.character(x))
+  sort(unique(values[homepage_non_blank(values)]))
+}
+
+homepage_collapse_labels <- function(x) {
+  values <- homepage_labels(x)
+
+  if (length(values) == 0L) {
+    return(NA_character_)
+  }
+
+  paste(values, collapse = "; ")
+}
+
+homepage_metrics <- function(data) {
+  tibble::tibble(
+    metric = c(
+      "Observations",
+      "Measured variables",
+      "Represented species",
+      "Contributing sites",
+      "Data sources"
+    ),
+    value = c(
+      nrow(data),
+      length(unique(data$trait[homepage_non_blank(data$trait)])),
+      length(unique(data$species_id[!is.na(data$species_id)])),
+      length(unique(data$site_id[!is.na(data$site_id)])),
+      length(unique(data$citation_id[!is.na(data$citation_id)]))
+    ),
+    definition = c(
+      "Trait and yield records in the primary dataset",
+      "Distinct variables with recorded observations",
+      "Distinct species linked to observation records",
+      "Distinct research sites linked to observation records",
+      "Distinct cited sources linked to observation records"
+    )
+  )
+}
+
+homepage_top_traits <- function(data, n = 10L) {
+  data <- dplyr::filter(data, homepage_non_blank(data[["trait"]]))
+
+  summary <- dplyr::summarise(
+    data,
+    description = homepage_collapse_labels(
+      dplyr::pick("trait_description")[[1L]]
+    ),
+    observations = dplyr::n(),
+    .by = "trait"
+  )
+
+  summary <- dplyr::arrange(
+    summary,
+    dplyr::desc(summary[["observations"]]),
+    summary[["trait"]]
+  )
+
+  dplyr::slice_head(summary, n = n)
+}
+
+homepage_top_species <- function(data, n = 10L) {
+  data <- dplyr::filter(data, !is.na(data[["species_id"]]))
+
+  summary <- dplyr::summarise(
+    data,
+    scientific_name = {
+      names <- homepage_labels(dplyr::pick("scientificname")[[1L]])
+
+      if (length(names) > 1L) {
+        stop(
+          "Each species_id must have at most one non-blank scientific name.",
+          call. = FALSE
+        )
+      }
+
+      if (length(names) == 0L) NA_character_ else names
+    },
+    common_name = homepage_collapse_labels(
+      dplyr::pick("commonname")[[1L]]
+    ),
+    observations = dplyr::n(),
+    .by = "species_id"
+  )
+
+  summary <- dplyr::arrange(
+    summary,
+    dplyr::desc(summary[["observations"]]),
+    summary[["scientific_name"]],
+    summary[["species_id"]]
+  )
+
+  dplyr::slice_head(summary, n = n)
+}
diff --git a/_quarto.yml b/_quarto.yml
@@ -35,6 +35,7 @@ website:
 format:
   html:
     theme: cosmo
+    css: inst/styles/homepage.css
     toc: true
     self-contained: false
     df-print: paged

diff --git a/index.qmd b/index.qmd
@@ -6,31 +6,36 @@ subtitle: "Public Data from the BETYdb Database"
 ```{r}
 #| echo: false
 library(betydata)
-library(dplyr)
+source("R/homepage-data.R", local = TRUE)
 ```
 
 **betydata** is an R data package providing offline access to public data from [BETYdb](https://betydb.org) (Biofuel Ecophysiological Traits and Yields database). It enables reproducible analyses of plant traits, crop yields, and supporting metadata without requiring database connectivity.
 
+## Guides
+
+| Guide | Description |
+|-------|-------------|
+| [Getting Started](vignettes/getting_started.qmd) | Package overview, data model, and key concepts |
+| [Common Analyses](vignettes/common_analyses.qmd) | Practical analysis patterns with dplyr |
+| [PFTs & Priors](vignettes/pfts-priors.qmd) | Plant Functional Types and Bayesian prior distributions |
+| [Manuscript Reproduction](vignettes/manuscript.qmd) | Reproduce key analyses from LeBauer et al. (2018) |
+
 ## At a Glance
 
 ```{r}
 #| echo: false
-#| label: tbl-overview
-#| tbl-cap: "Dataset summary"
-tibble::tibble(
-  Metric = c(
-    "Total observations", "Unique traits", "Plant species",
-    "Research sites", "Literature citations", "Tables"
-  ),
-  Value = c(
-    format(nrow(traitsview), big.mark = ","),
-    n_distinct(traitsview$trait),
-    format(nrow(species), big.mark = ","),
-    nrow(sites),
-    nrow(citations),
-    16
-  )
-) |> knitr::kable()
+#| results: asis
+metrics <- homepage_metrics(traitsview)
+
+cat("::: {.homepage-metrics}\n")
+for (i in seq_len(nrow(metrics))) {
+  cat("::: {.homepage-metric-card}\n")
+  cat(sprintf("### %s\n\n", metrics$metric[[i]]))
+  cat(sprintf("<span class=\"homepage-metric-value\">%s</span>\n\n", format(metrics$value[[i]], big.mark = ",")))
+  cat(sprintf("%s\n", metrics$definition[[i]]))
+  cat(":::\n")
+}
+cat(":::\n")
 ```
 
 ## Installation
@@ -43,27 +48,58 @@ remotes::install_github("PecanProject/betydata")
 ## Quick Start
 
 ```{r}
-library(betydata)
-library(dplyr)
+#| echo: false
+if (!requireNamespace("DT", quietly = TRUE)) {
+  stop("Package 'DT' is required to render the searchable homepage preview.", call. = FALSE)
+}
+
+preview <- traitsview[, c(
+  "trait", "mean", "units", "scientificname", "sitename",
+  "author", "citation_year", "year"
+)]
+names(preview) <- c(
+  "Trait", "Value", "Units", "Species", "Site",
+  "Data-source author", "Citation year", "Observation year"
+)
+
+DT::datatable(
+  preview,
+  caption = "Searchable preview of trait and yield observations",
+  rownames = FALSE,
+  options = list(
+    deferRender = TRUE,
+    pageLength = 25,
+    lengthMenu = c(10, 25, 50, 100),
+    scrollX = TRUE
+  )
+)
+```
 
-# The primary table -- key columns first, IDs last
-traitsview
+## Most Represented Variables and Species
 
-# Bioenergy crop observations
-bioenergy_genera <- c("Miscanthus", "Panicum", "Populus", "Salix", "Saccharum")
-traitsview |>
-  filter(genus %in% bioenergy_genera) |>
-  count(genus, sort = TRUE)
+```{r}
+#| echo: false
+#| label: tbl-top-traits
+#| tbl-cap: "Variables with the most observation records"
+homepage_top_traits(traitsview) |>
+  knitr::kable(
+    col.names = c("Variable", "Description", "Observations"),
+    row.names = FALSE
+  )
 ```
 
-## Guides
-
-| Guide | Description |
-|-------|-------------|
-| [Getting Started](vignettes/getting_started.qmd) | Package overview, data model, and key concepts |
-| [Common Analyses](vignettes/common_analyses.qmd) | Practical analysis patterns with dplyr |
-| [PFTs & Priors](vignettes/pfts-priors.qmd) | Plant Functional Types and Bayesian prior distributions |
-| [Manuscript Reproduction](vignettes/manuscript.qmd) | Reproduce key analyses from LeBauer et al. (2018) |
+```{r}
+#| echo: false
+#| label: tbl-top-species
+#| tbl-cap: "Species with the most observation records"
+homepage_top_species(traitsview)[
+  , c("scientific_name", "common_name", "observations")
+] |>
+  knitr::kable(
+    col.names = c("Scientific name", "Common name", "Observations"),
+    row.names = FALSE
+  )
+```
 
 ## Data License
 

diff --git a/inst/styles/homepage.css b/inst/styles/homepage.css
@@ -0,0 +1,29 @@
+.homepage-metrics {
+  display: grid;
+  gap: 1rem;
+  grid-template-columns: repeat(auto-fit, minmax(12rem, 1fr));
+  margin: 1.5rem 0 2rem;
+}
+
+.homepage-metric-card {
+  border: 1px solid var(--bs-border-color, #dee2e6);
+  border-radius: 0.375rem;
+  padding: 1rem;
+}
+
+.homepage-metric-card h3 {
+  font-size: 1rem;
+  margin: 0;
+}
+
+.homepage-metric-value {
+  display: block;
+  font-size: 2rem;
+  font-weight: 700;
+  line-height: 1.2;
+  margin: 0.5rem 0;
+}
+
+.homepage-metric-card p {
+  margin: 0;
+}