Add pre-commit hook to check that the data dict is up to date with pa…

…rams

.pre-commit-config.yaml

@@ -27,3 +27,8 @@ repos:
         entry: Cannot commit .Rhistory, .RData, .Rds or .rds.
         language: fail
         files: '\.(Rhistory|RData|Rds|rds)$'
+      - id: check-data-dict
+        name: Data dictionary must be up to date
+        entry: Rscript R/hooks/check-data-dict.R
+        files: (^|/)((params\.yaml)|(data-dict\.csv))$
+        language: system

R/hooks/check-data-dict.R

@@ -0,0 +1,9 @@
+#!/usr/bin/env Rscript
+# Script to check that the data dictionary file is up to date with the
+# latest feature set
+library(readr)
+library(yaml)
+
+params <- read_yaml("params.yaml")
+data_dict <- read_csv("docs/data-dict.csv", show_col_types = FALSE)
+stopifnot(setequal(data_dict$variable_name, params$model$predictor$all))