Better error messages for totally empty columns (#248)

* nicer error message for empty columns

* tests

* bump patch

Author: kleinschmidt

Project.toml

@@ -1,6 +1,6 @@
 name = "StatsModels"
 uuid = "3eaba693-59b7-5ba5-a881-562e759f1c8d"
-version = "0.6.27"
+version = "0.6.28"
 
 [deps]
 DataAPI = "9a962f9c-6df0-11e9-0e5d-c546b8b5ee8a"

src/errormessages.jl

@@ -23,6 +23,12 @@ function checkcol(table, name::Symbol)
         nearestnames = join(fuzzymatch(names, name),", " )
         return "There isn't a variable called '$name' in your data; the nearest names appear to be: $nearestnames"
     end
+
+    nrows = length(Tables.getcolumn(table, name))
+    if nrows == 0
+        return "Column '$name' is empty."
+    end
+
     return ""
 end
 
@@ -41,4 +47,4 @@ function checknamesexist(f::FormulaTerm, t)
         end
     end    
     return ""
-end
+end

src/schema.jl

@@ -120,7 +120,7 @@ schema(ts::AbstractVector{<:AbstractTerm}, data, hints::Dict{Symbol}) =
 
 # handle hints:
 schema(ts::AbstractVector{<:AbstractTerm}, dt::ColumnTable,
-      hints::Dict{Symbol}=Dict{Symbol,Any}()) =
+       hints::Dict{Symbol}=Dict{Symbol,Any}()) =
     sch = Schema(t=>concrete_term(t, dt, hints) for t in ts)
 
 schema(f::TermOrTerms, data, hints::Dict{Symbol}) =
@@ -169,15 +169,15 @@ a(continuous)
 concrete_term(t::Term, d, hints::Dict{Symbol}) = concrete_term(t, d, get(hints, t.sym, nothing))
 
 function concrete_term(t::Term, dt::ColumnTable, hint)
-    msg::String = checkcol( dt, t.sym )
+    msg = checkcol(dt, t.sym)
     if msg != ""
         throw(ArgumentError(msg))
     end
     return concrete_term(t, getproperty(dt, t.sym), hint)
 end
 
 function concrete_term(t::Term, dt::ColumnTable, hints::Dict{Symbol})
-    msg::String = checkcol( dt, t.sym )
+    msg = checkcol(dt, t.sym)
     if msg != ""
         throw(ArgumentError(msg))
     end

test/schema.jl

@@ -70,4 +70,15 @@
 
     end
 
+    @testset "nice errors" begin
+        d = (yyy = rand(10), aaa = rand(10), bbb = repeat([:a, :b], 5))
+        @test_throws ArgumentError("There isn't a variable called 'aa' in your data; the nearest names appear to be: aaa") concrete_term(Term(:aa), d, nothing)
+        @test_throws ArgumentError("There isn't a variable called 'aab' in your data; the nearest names appear to be: aaa, bbb") concrete_term(Term(:aab), d, nothing)
+
+        @test_throws ArgumentError("Column 'a' is empty.") concrete_term(Term(:a), (; a=[]), nothing)
+        @test_throws ArgumentError("Column 'a' is empty.") schema((; b=[1,2], a=[]))
+        
+    end
+    
+
 end