Catch typos in gear_params and species_params column names (#442)

NEWS.md

@@ -1,5 +1,12 @@
 # mizer 3.1.0.9000 (development version)
 
+- Mis-spelled column names in the `gear_params` and `species_params` data frames
+  are now detected by fuzzy matching against the recognised parameter names. A
+  near miss such as `sel_fun` (instead of `sel_func`) triggers a warning that
+  suggests the intended name, rather than being silently ignored (#442). Columns
+  are only flagged, never renamed, so legitimate custom columns are left
+  untouched.
+
 - `compareParams()` now checks that the number of size bins, species and gears
   agree before comparing the array-valued slots. When they differ it reports the
   mismatch instead of erroring while trying to compare arrays of incompatible

R/helpers.R

@@ -302,3 +302,57 @@ get_steady_state_n <- function(params, g, mu, D, N0,
 
     return(zero_above_support(n, w_top))
 }
+
+#' Warn about column names that look like mis-spelled parameter names
+#'
+#' Compares the actual column names of a parameter data frame against the set of
+#' recognised names and issues a single warning about any names that are a near
+#' match (a likely typo) but not an exact match. Names are not corrected, only
+#' flagged, so that legitimate custom columns are left untouched.
+#'
+#' @param actual Character vector of the column names present in the data frame.
+#' @param known Character vector of recognised parameter names.
+#' @param df_type A short description of the data frame used in the warning
+#'   message, e.g. `"gear parameter"` or `"species parameter"`.
+#' @param curated Character vector of known problematic names that should always
+#'   be flagged even when they are further than the fuzzy-match threshold from
+#'   any recognised name (e.g. familiar abbreviations).
+#'
+#' @return Called for its side effect (a warning). Returns `NULL` invisibly.
+#' @concept helper
+#' @noRd
+check_for_misspellings <- function(actual, known, df_type,
+                                   curated = character(0)) {
+    unknown <- setdiff(actual, known)
+    if (length(unknown) == 0) {
+        return(invisible(NULL))
+    }
+    # Only fuzzy-match against names long enough that a near miss is meaningful.
+    known_fuzzy <- known[nchar(known) >= 3]
+    hits <- character(0)
+    guess <- character(0)
+    for (nm in unknown) {
+        if (length(known_fuzzy) == 0) {
+            j <- integer(0)
+            near <- FALSE
+        } else {
+            d <- as.vector(adist(nm, known_fuzzy, ignore.case = TRUE))
+            j <- which.min(d)
+            near <- nchar(nm) >= 3 &&
+                (d[j] == 1 || (d[j] <= 2 && nchar(known_fuzzy[j]) >= 6))
+        }
+        if (nm %in% curated || near) {
+            hits <- c(hits, nm)
+            guess <- c(guess, if (length(j) == 1) known_fuzzy[j] else NA_character_)
+        }
+    }
+    if (length(hits) > 0) {
+        suggestions <- ifelse(is.na(guess), paste0("`", hits, "`"),
+                              paste0("`", hits, "` (did you mean `", guess, "`?)"))
+        warning("Some column names in your ", df_type, " data ",
+                "frame are very close to standard parameter names: ",
+                paste(suggestions, collapse = ", "),
+                ". Please check for mis-spellings.")
+    }
+    invisible(NULL)
+}

R/setFishing.R

@@ -324,7 +324,7 @@ setFishing.MizerParams <- function(params, selectivity = NULL, catchability = NU
 #'     gear = c("gear1", "gear2", "gear1"),
 #'     species = c("Cod", "Cod", "Haddock"),
 #'     catchability = c(0.5, 2, 1),
-#'     sel_fun = c("sigmoid_weight", "knife_edge", "sigmoid_weight"),
+#'     sel_func = c("sigmoid_weight", "knife_edge", "sigmoid_weight"),
 #'     sigmoidal_weight = c(1000, NA, 800),
 #'     sigmoidal_sigma = c(100, NA, 100),
 #'     knife_edge_size = c(NA, 1000, NA)
@@ -391,16 +391,22 @@ is.gear_params <- function(x) {
 }
 
 check_gear_params <- function(x) {
-    # Check for misspellings
-    misspellings <- c("selfunc", "selectivity_function", "catch", "catchab",
-                      "sigmoid_weight", "sigmoid_sigma", "knife_edge")
-    query <- intersect(misspellings, names(x))
-    if (length(query) > 0) {
-        warning("Some column names in your gear parameter data ",
-                "frame are very close to standard parameter names: ",
-                paste(query, collapse = ", "),
-                ". Did you perhaps mis-spell the names?")
+    # Warn about column names that look like mis-spelled parameter names.
+    # Recognised names are the core columns plus the parameters of the
+    # selectivity functions (both the built-in ones and any function actually
+    # referenced in the `sel_func` column, so custom parameters are recognised).
+    known <- c("species", "gear", "sel_func", "catchability", "yield_observed",
+               "l25", "l50", "l50_right", "l25_right", "knife_edge_size",
+               "sigmoidal_weight", "sigmoidal_sigma")
+    if ("sel_func" %in% names(x)) {
+        for (sf in unique(x$sel_func[!is.na(x$sel_func)])) {
+            args <- tryCatch(names(formals(sf)), error = function(e) NULL)
+            known <- union(known, setdiff(args, c("w", "species_params", "...")))
+        }
     }
+    curated <- c("selfunc", "selectivity_function", "catch", "catchab",
+                 "sigmoid_weight", "sigmoid_sigma", "knife_edge")
+    check_for_misspellings(names(x), known, "gear parameter", curated)
 
     # Auto-populate missing argument columns for selectivity functions
     if ("sel_func" %in% names(x)) {

R/species_params.R

@@ -243,19 +243,51 @@ is.species_params <- function(x) {
     inherits(x, "species_params")
 }
 
+# Recognised species_params column names, used by check_for_misspellings() to
+# flag likely typos. This is not an exhaustive list of every possible column
+# (users may add custom columns), but covers the standard parameters so that a
+# near miss can be detected. Grouped roughly by purpose.
+known_species_params_columns <- function() {
+    c(# identity and sizes
+      "species", "w_max", "w_mat", "w_mat25", "w_min", "w_inf",
+      "w_repro_max", "w_min_idx",
+      # length-based equivalents and length-weight parameters
+      "l_max", "l_mat", "l_mat25", "l_min", "l_inf", "l_repro_max", "a", "b",
+      # von Bertalanffy growth
+      "k_vb", "t0", "age_mat",
+      # physiology
+      "h", "k", "ks", "gamma", "alpha", "beta", "sigma",
+      "n", "p", "q", "m", "z0", "fc", "f0", "erepro",
+      "d", "z_ext", "D_ext", "E_ext",
+      # reproduction
+      "R_max", "r_max", "constant_recruitment", "constant_reproduction",
+      "ricker_b", "sheperd_b", "sheperd_c",
+      # predation kernel
+      "pred_kernel_type", "kernel_exp", "kernel_l_l", "kernel_u_l",
+      "kernel_l_r", "kernel_u_r", "ppmr_min", "ppmr_max",
+      # fishing
+      "gear", "sel_func", "catchability", "knife_edge_size",
+      "yield_observed", "catch_observed",
+      # interactions
+      "interaction_resource", "interaction_p",
+      # observations
+      "biomass_observed", "biomass_cutoff", "number_observed", "number_cutoff",
+      # flags and plotting
+      "is_background", "linecolour", "linetype", "legend_name")
+}
+
+# Familiar abbreviations / capitalisation mistakes that should always be flagged
+# even when further than the fuzzy-match threshold from a recognised name.
+curated_species_params_misspellings <- function() {
+    c("wmin", "wmax", "wmat", "wmat25", "w_mat_25", "Rmax",
+      "Species", "Gamma", "Beta", "Sigma", "Alpha",
+      "W_min", "W_max", "W_mat", "e_repro", "Age_mat", "w_max_mat")
+}
+
 check_and_convert_species_params <- function(x) {
-    # Check for misspellings
-    misspellings <- c("wmin", "wmax", "wmat", "wmat25", "w_mat_25", "Rmax",
-                      "Species", "Gamma", "Beta", "Sigma", "Alpha",
-                      "W_min", "W_max", "W_mat", "e_repro", "Age_mat",
-                      "w_max_mat")
-    query <- intersect(misspellings, names(x))
-    if (length(query) > 0) {
-        warning("Some column names in your species parameter data ",
-                "frame are very close to standard parameter names: ",
-                paste(query, collapse = ", "),
-                ". Did you perhaps mis-spell the names?")
-    }
+    check_for_misspellings(names(x), known_species_params_columns(),
+                           "species parameter",
+                           curated_species_params_misspellings())
 
     # Auto convert length to weight if allometric parameters exist
     if (all(c("a", "b") %in% names(x))) {
@@ -413,19 +445,10 @@ given_species_params.data.frame <- function(object, strict = FALSE, ...) {
     # Convert a tibble back to an ordinary data frame
     sp <- as.data.frame(object, stringsAsFactors = FALSE)
 
-    # Check for misspellings
-    misspellings <- c("wmin", "wmax", "wmat", "wmat25", "w_mat_25", "Rmax",
-                      "Species", "Gamma", "Beta", "Sigma", "Alpha",
-                      "W_min", "W_max", "W_mat", "e_repro", "Age_mat",
-                      "w_max_mat")
-    query <- intersect(misspellings, names(sp))
-    if (length(query) > 0) {
-        warning("Some column names in your species parameter data ",
-                "frame are very close to standard parameter names: ",
-                paste(query, collapse = ", "),
-                ". Did you perhaps mis-spell the names?")
-    }
-
+    check_for_misspellings(names(sp), known_species_params_columns(),
+                           "species parameter",
+                           curated_species_params_misspellings())
+
     # check species
     if (!("species" %in% colnames(sp))) {
         stop("The species params dataframe needs a column 'species' with the species names")

tests/testthat/test-setFishing.R

@@ -408,6 +408,15 @@ test_that("gear_params reactive validation works", {
     df <- data.frame(species = "Sprat", gear = "g", selfunc = "knife_edge")
     expect_warning(gp <- gear_params(df), "very close to standard parameter names")
 
+    # 1b. Fuzzy typo (issue #442): `sel_fun` should be flagged as `sel_func`
+    df_typo <- data.frame(species = "Sprat", gear = "g", sel_fun = "knife_edge")
+    expect_warning(gear_params(df_typo), "did you mean `sel_func`")
+    # A legitimate custom column must not be flagged
+    df_custom <- data.frame(species = "Sprat", gear = "g",
+                            sel_func = "knife_edge", knife_edge_size = 10,
+                            my_custom_note = "abc")
+    expect_no_warning(gear_params(df_custom))
+
     # 2. Parameter checks for sigmoid_length (l25 >= l50)
     df2 <- data.frame(species = "Sprat", gear = "g", sel_func = "sigmoid_length", l25 = 15, l50 = 10)
     expect_warning(gp2 <- gear_params(df2), "must be smaller than l50")

tests/testthat/test-species_params.R

@@ -298,6 +298,12 @@ test_that("Reactive validation and conversions work", {
     df <- data.frame(species = c("Sprat", "Herring"), w_inf = c(10, 100))
     sp <- species_params(df)
     expect_warning(sp$wmin <- 0.1, "very close to standard parameter names")
+    # Fuzzy typo of a recognised name is flagged with a suggestion ...
+    expect_warning(sp$w_maxx <- 100, "did you mean `w_max`")
+    # ... but a genuine custom column is not (use a fresh object without the
+    # typo'd columns added above)
+    sp_clean <- species_params(df)
+    expect_no_warning(sp_clean$my_note <- "x")
 
     # 2. Length-to-weight conversion
     df2 <- data.frame(species = "Sprat", a = 0.01, b = 3, l_mat = 10)