Improve printing CoefTable (#481)

Rely on printing code from Base to align numbers on the decimal separator.
Unfortunately, we cannot treat column names as a normal row since names would
be left-aligned with the decimal separator, which wastes space and is less clean.
Instead, adjust the alignment manually so that columns are wide enough to contain
names.

Only convert values to PValue before printing, so that users can still access the contents
of columns as normal numbers. This is convenient in particular for testing in packages.

Print test statistics with 2 decimals.

Add horizontal lines.

Author: nalimilan

src/statmodels.jl

@@ -358,36 +358,41 @@ function params! end
 
 ## coefficient tables with specialized show method
 
-## Nms are the coefficient names, corresponding to rows in the table
 mutable struct CoefTable
     cols::Vector
     colnms::Vector
     rownms::Vector
-    function CoefTable(cols::Vector,colnms::Vector,rownms::Vector)
+    pvalcol::Int
+    teststatcol::Int
+    function CoefTable(cols::Vector,colnms::Vector,rownms::Vector,
+                       pvalcol::Int=0,teststatcol::Int=0)
         nc = length(cols)
         nrs = map(length,cols)
         nr = nrs[1]
-        length(colnms) in [0,nc] || error("colnms should have length 0 or $nc")
-        length(rownms) in [0,nr] || error("rownms should have length 0 or $nr")
-        all(nrs .== nr) || error("Elements of cols should have equal lengths, but got $nrs")
-        new(cols,colnms,rownms)
+        length(colnms) in [0,nc] || throw(ArgumentError("colnms should have length 0 or $nc"))
+        length(rownms) in [0,nr] || throw(ArgumentError("rownms should have length 0 or $nr"))
+        all(nrs .== nr) || throw(ArgumentError("Elements of cols should have equal lengths, but got $nrs"))
+        pvalcol in 0:nc || throw(ArgumentError("pvalcol should be between 0 and $nc"))
+        teststatcol in 0:nc || throw(ArgumentError("teststatcol should be between 0 and $nc"))
+        new(cols,colnms,rownms,pvalcol,teststatcol)
     end
 
-    function CoefTable(mat::Matrix,colnms::Vector,rownms::Vector,pvalcol::Int=0)
+    function CoefTable(mat::Matrix,colnms::Vector,rownms::Vector,
+                       pvalcol::Int=0,teststatcol::Int=0)
         nc = size(mat,2)
         cols = Any[mat[:, i] for i in 1:nc]
-        if pvalcol != 0                         # format the p-values column
-            cols[pvalcol] = [PValue(cols[pvalcol][j])
-                            for j in eachindex(cols[pvalcol])]
-        end
-        CoefTable(cols,colnms,rownms)
+        CoefTable(cols,colnms,rownms,pvalcol,teststatcol)
     end
 end
 
-mutable struct PValue
-    v::Number
-    function PValue(v::Number)
-        0. <= v <= 1. || isnan(v) || error("p-values must be in [0.,1.]")
+"""
+Show a p-value using 6 characters, either using the standard 0.XXXX
+representation or as <Xe-YY.
+"""
+struct PValue
+    v::Real
+    function PValue(v::Real)
+        0 <= v <= 1 || isnan(v) || error("p-values must be in [0; 1]")
         new(v)
     end
 end
@@ -403,36 +408,52 @@ function show(io::IO, pv::PValue)
     end
 end
 
+"""Show a test statistic using 2 decimal digits"""
+struct TestStat <: Real
+    v::Real
+end
+
+show(io::IO, x::TestStat) = @printf(io, "%.2f", x.v)
+
+"""Wrap a string so that show omits quotes"""
+struct NoQuote
+    s::String
+end
+
+show(io::IO, n::NoQuote) = print(io, n.s)
+
 function show(io::IO, ct::CoefTable)
     cols = ct.cols; rownms = ct.rownms; colnms = ct.colnms;
     nc = length(cols)
     nr = length(cols[1])
     if length(rownms) == 0
         rownms = [lpad("[$i]",floor(Integer, log10(nr))+3) for i in 1:nr]
     end
-    rnwidth = max(4,maximum([length(nm) for nm in rownms]) + 1)
-    rownms = [rpad(nm,rnwidth) for nm in rownms]
-    widths = [length(cn)::Int for cn in colnms]
-    str = String[isa(cols[j][i], AbstractString) ? cols[j][i] :
-        sprint(show, cols[j][i], context=:compact=>true) for i in 1:nr, j in 1:nc]
-    for j in 1:nc
-        for i in 1:nr
-            lij = length(str[i,j])
-            if lij > widths[j]
-                widths[j] = lij
-            end
-        end
+    mat = [j == 1 ? NoQuote(rownms[i]) :
+           j-1 == ct.pvalcol ? PValue(cols[j-1][i]) :
+           j-1 in ct.teststatcol ? TestStat(cols[j-1][i]) :
+           cols[j-1][i] isa AbstractString ? NoQuote(cols[j-1][i]) : cols[j-1][i]
+           for i in 1:nr, j in 1:nc+1]
+    # Code inspired by print_matrix in Base
+    io = IOContext(io, :compact=>true, :limit=>false)
+    A = Base.alignment(io, mat, 1:size(mat, 1), 1:size(mat, 2),
+                       typemax(Int), typemax(Int), 3)
+    nmswidths = pushfirst!(length.(colnms), 0)
+    A = [nmswidths[i] > sum(A[i]) ? (A[i][1]+nmswidths[i]-sum(A[i]), A[i][2]) : A[i]
+         for i in 1:length(A)]
+    totwidth = sum(sum.(A)) + 2 * (length(A) - 1)
+    println(io, repeat('─', totwidth))
+    print(io, repeat(' ', sum(A[1])))
+    for j in 1:length(colnms)
+        print(io, "  ", lpad(colnms[j], sum(A[j+1])))
     end
-    widths .+= 1
-    println(io," " ^ rnwidth *
-            join([lpad(string(colnms[i]), widths[i]) for i = 1:nc], ""))
-    for i = 1:nr
-        print(io, rownms[i])
-        for j in 1:nc
-            print(io, lpad(str[i,j],widths[j]))
-        end
-        println(io)
+    println(io, '\n', repeat('─', totwidth))
+    for i in 1:size(mat, 1)
+        Base.print_matrix_row(io, mat, A, i, 1:size(mat, 2), "  ")
+        i != size(mat, 1) && println(io)
     end
+    print(io, '\n', repeat('─', totwidth))
+    nothing
 end
 
 """

test/statmodels.jl

@@ -1,28 +1,32 @@
 using StatsBase
 using Test, Random
 
-Random.seed!(10)
-v1 = rand(3)
+v1 = [1.45666, -23.14, 1.56734e-13]
 v2 = ["Good", "Great", "Bad"]
-v3 = rand(Int8, 3)
-v4 = [StatsBase.PValue(rand()./10000) for i in 1:3]
-m = rand(3,4)
-@test sprint(show, CoefTable(Any[v1, v2, v3, v4],
-    ["Estimate", "Comments", "df", "p"],
-    ["x1", "x2", "x3"])) == """
-     Estimate Comments  df     p
-x1   0.112582     Good  88 <1e-4
-x2   0.368314    Great -90 <1e-4
-x3   0.344454      Bad -80 <1e-4
-"""
+v3 = [1, 56, 2]
+v4 = [-12.56, 0.1326, 2.68e-16]
+v5 = [0.12, 0.3467, 1.345e-16]
+@test sprint(show, CoefTable(Any[v1, v2, v3, v4, v5],
+    ["Estimate", "Comments", "df", "t", "p"],
+    ["x1", "x2", "x3"], 5, 4)) == """
+───────────────────────────────────────────────
+         Estimate  Comments  df       t       p
+───────────────────────────────────────────────
+x1    1.45666         Good    1  -12.56  0.1200
+x2  -23.14            Great  56    0.13  0.3467
+x3    1.56734e-13     Bad     2    0.00  <1e-15
+───────────────────────────────────────────────"""
 
-@test sprint(show, CoefTable(m, ["Estimate", "Stderror", "df", "p"],
-    ["x1", "x2", "x3"], 4)) == """
-     Estimate Stderror       df      p
-x1   0.819778 0.844007 0.923676 0.1717
-x2   0.669931  0.67919 0.066098 0.4204
-x3   0.453058  0.72525 0.999172 0.5567
-"""
+Random.seed!(10)
+m = rand(3,4)
+@test sprint(show, CoefTable(m, ["Estimate", "Stderror", "df", "p"], [], 4)) == """
+──────────────────────────────────────────
+     Estimate   Stderror        df       p
+──────────────────────────────────────────
+[1]  0.112582  0.0566454  0.381813  0.8198
+[2]  0.368314  0.120781   0.815104  0.6699
+[3]  0.344454  0.179574   0.242208  0.4531
+──────────────────────────────────────────"""
 
 @test sprint(show, StatsBase.PValue(1.0)) == "1.0000"
 @test sprint(show, StatsBase.PValue(1e-1)) == "0.1000"