ditch negative zero in ftest output (#501)

* ditch negative zero in ftest output * move it to the show method * oops * one more try
JuliaStats · Sep 29, 2022 · 9bec51e · 9bec51e
1 parent 7299d18
commit 9bec51e
Show file tree

Hide file tree

Showing 5 changed files with 80 additions and 74 deletions.
diff --git a/docs/src/api.md b/docs/src/api.md
@@ -25,7 +25,7 @@ The most general approach to fitting a model is with the `fit` function, as in
 julia> using Random
 
 julia> fit(LinearModel, hcat(ones(10), 1:10), randn(MersenneTwister(12321), 10))
-LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}}}}:
+LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}, Vector{Int64}}}}:
 
 Coefficients:
 ────────────────────────────────────────────────────────────────
@@ -41,7 +41,7 @@ This model can also be fit as
 julia> using Random
 
 julia> lm(hcat(ones(10), 1:10), randn(MersenneTwister(12321), 10))
-LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}}}}:
+LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}, Vector{Int64}}}}:
 
 Coefficients:
 ────────────────────────────────────────────────────────────────

diff --git a/docs/src/examples.md b/docs/src/examples.md
@@ -20,7 +20,7 @@ julia> data = DataFrame(X=[1,2,3], Y=[2,4,7])
    3 │     3      7
 
 julia> ols = lm(@formula(Y ~ X), data)
-StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}}}}, Matrix{Float64}}
+StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}, Vector{Int64}}}}, Matrix{Float64}}
 
 Y ~ 1 + X
 
@@ -207,7 +207,7 @@ julia> form = dataset("datasets", "Formaldehyde")
    6 │     0.9    0.782
 
 julia> lm1 = fit(LinearModel, @formula(OptDen ~ Carb), form)
-StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}}}}, Matrix{Float64}}
+StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}, Vector{Int64}}}}, Matrix{Float64}}
 
 OptDen ~ 1 + Carb
 
@@ -256,7 +256,7 @@ julia> LifeCycleSavings = dataset("datasets", "LifeCycleSavings")
                                                     35 rows omitted
 
 julia> fm2 = fit(LinearModel, @formula(SR ~ Pop15 + Pop75 + DPI + DDPI), LifeCycleSavings)
-StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}}}}, Matrix{Float64}}
+StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}, Vector{Int64}}}}, Matrix{Float64}}
 
 SR ~ 1 + Pop15 + Pop75 + DPI + DDPI
 

diff --git a/docs/src/index.md b/docs/src/index.md
@@ -85,7 +85,7 @@ julia> data = DataFrame(y = rand(rng, 100), x = categorical(repeat([1, 2, 3, 4],
 
 
 julia> lm(@formula(y ~ x), data)
-StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}}}}, Matrix{Float64}}
+StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}, Vector{Int64}}}}, Matrix{Float64}}
 
 y ~ 1 + x
 
@@ -108,7 +108,7 @@ julia> using StableRNGs
 julia> data = DataFrame(y = rand(StableRNG(1), 100), x = repeat([1, 2, 3, 4], 25));
 
 julia> lm(@formula(y ~ x), data, contrasts = Dict(:x => DummyCoding()))
-StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}}}}, Matrix{Float64}}
+StatsModels.TableRegressionModel{LinearModel{GLM.LmResp{Vector{Float64}}, GLM.DensePredChol{Float64, LinearAlgebra.CholeskyPivoted{Float64, Matrix{Float64}, Vector{Int64}}}}, Matrix{Float64}}
 
 y ~ 1 + x
 

diff --git a/src/ftest.jl b/src/ftest.jl
@@ -111,22 +111,22 @@ julia> bigmodel = lm(@formula(Result ~ 1 + Treatment + Other), dat);
 
 julia> ftest(nullmodel.model, model.model)
 F-test: 2 models fitted on 12 observations
-──────────────────────────────────────────────────────────────────
-     DOF  ΔDOF     SSR     ΔSSR       R²     ΔR²        F*   p(>F)
-──────────────────────────────────────────────────────────────────
-[1]    2        3.2292           -0.0000
-[2]    3     1  0.1283  -3.1008   0.9603  0.9603  241.6234  <1e-07
-──────────────────────────────────────────────────────────────────
+─────────────────────────────────────────────────────────────────
+     DOF  ΔDOF     SSR     ΔSSR      R²     ΔR²        F*   p(>F)
+─────────────────────────────────────────────────────────────────
+[1]    2        3.2292           0.0000
+[2]    3     1  0.1283  -3.1008  0.9603  0.9603  241.6234  <1e-07
+─────────────────────────────────────────────────────────────────
 
 julia> ftest(nullmodel.model, model.model, bigmodel.model)
 F-test: 3 models fitted on 12 observations
-──────────────────────────────────────────────────────────────────
-     DOF  ΔDOF     SSR     ΔSSR       R²     ΔR²        F*   p(>F)
-──────────────────────────────────────────────────────────────────
-[1]    2        3.2292           -0.0000
-[2]    3     1  0.1283  -3.1008   0.9603  0.9603  241.6234  <1e-07
-[3]    5     2  0.1017  -0.0266   0.9685  0.0082    1.0456  0.3950
-──────────────────────────────────────────────────────────────────
+─────────────────────────────────────────────────────────────────
+     DOF  ΔDOF     SSR     ΔSSR      R²     ΔR²        F*   p(>F)
+─────────────────────────────────────────────────────────────────
+[1]    2        3.2292           0.0000
+[2]    3     1  0.1283  -3.1008  0.9603  0.9603  241.6234  <1e-07
+[3]    5     2  0.1017  -0.0266  0.9685  0.0082    1.0456  0.3950
+─────────────────────────────────────────────────────────────────
 ```
 """
 function ftest(mods::LinearModel...; atol::Real=0.0)
@@ -166,6 +166,7 @@ function ftest(mods::LinearModel...; atol::Real=0.0)
 
     fstat = (NaN, (MSR1 ./ MSR2)...)
     pval = (NaN, ccdf.(FDist.(abs.(Δdf), dfr_big), abs.(fstat[2:end]))...)
+
     return FTestResult(Int(nobs(mods[1])), SSR, df, r2.(mods), fstat, pval)
 end
 
@@ -187,15 +188,20 @@ function show(io::IO, ftr::FTestResult{N}) where N
     outrows[1, :] = ["", "DOF", "ΔDOF", "SSR", "ΔSSR",
                      "R²", "ΔR²", "F*", "p(>F)"]
 
+    # get rid of negative zero -- doesn't matter mathematically,
+    # but messes up doctests and various other things
+    # cf. Issue #461 
+    r2vals = [replace(@sprintf("%.4f", val), "-0.0000" => "0.0000") for val in ftr.r2]
+
     outrows[2, :] = ["[1]", @sprintf("%.0d", ftr.dof[1]), " ",
                      @sprintf("%.4f", ftr.ssr[1]), " ",
-                     @sprintf("%.4f", ftr.r2[1]), " ", " ", " "]
+                     r2vals[1], " ", " ", " "]
 
     for i in 2:nr
         outrows[i+1, :] = ["[$i]",
                            @sprintf("%.0d", ftr.dof[i]), @sprintf("%.0d", Δdof[i-1]),
                            @sprintf("%.4f", ftr.ssr[i]), @sprintf("%.4f", Δssr[i-1]),
-                           @sprintf("%.4f", ftr.r2[i]), @sprintf("%.4f", ΔR²[i-1]),
+                           r2vals[i], @sprintf("%.4f", ΔR²[i-1]),
                            @sprintf("%.4f", ftr.fstat[i]), string(PValue(ftr.pval[i])) ]
     end
     colwidths = length.(outrows)