diff --git a/Project.toml b/Project.toml
index 7d338db..e6486ad 100644
--- a/Project.toml
+++ b/Project.toml
@@ -14,11 +14,11 @@ Requires = "ae029012-a4dd-5104-9daa-d747884805df"
 [compat]
 ADNLPModels = "^0.3, 0.4, 0.7"
 Distributions = "0.25"
+MLDatasets = "^0.7.4"
 NLPModels = "0.16, 0.17, 0.18, 0.19, 0.20"
 Noise = "0.2"
 Requires = "1"
 julia = "^1.3.0"
-MLDatasets = "^0.7.4"
 
 [extras]
 ADNLPModels = "54578032-b7ea-4c30-94aa-7cbd1cce6c9a"
@@ -28,4 +28,3 @@ Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
 test = ["ADNLPModels", "DifferentialEquations", "MLDatasets", "Test"]
-
diff --git a/docs/Project.toml b/docs/Project.toml
index 5977598..1a69045 100644
--- a/docs/Project.toml
+++ b/docs/Project.toml
@@ -2,6 +2,7 @@
 ADNLPModels = "54578032-b7ea-4c30-94aa-7cbd1cce6c9a"
 DifferentialEquations = "0c46a032-eb83-5123-abaf-570d42b7fbaa"
 Documenter = "e30172f5-a6a5-5a46-863b-614d45cd2de4"
+MLDatasets = "eb30cadb-4394-5ae3-aed4-317e484a6458"
 RegularizedProblems = "ea076b23-609f-44d2-bb12-a4ae45328278"
 
 [compat]
diff --git a/docs/make.jl b/docs/make.jl
index 2275125..331cab7 100644
--- a/docs/make.jl
+++ b/docs/make.jl
@@ -1,5 +1,5 @@
 using Documenter
-using ADNLPModels, DifferentialEquations
+using ADNLPModels, DifferentialEquations, MLDatasets
 using RegularizedProblems
 
 makedocs(
diff --git a/src/nnmf.jl b/src/nnmf.jl
index ca85762..a2f163f 100644
--- a/src/nnmf.jl
+++ b/src/nnmf.jl
@@ -15,14 +15,31 @@ function nnmf_data(m::Int, n::Int, k::Int, T::DataType = Float64)
       parameters[i][2][j, j] = parameters[i][1][j] > 0.0 ? 0.3 : ϵ # to avoid problems in Cholesky factorization when calling MixtureModel
     end
   end
-  # generate a mixture of gaussians 
+  # generate a mixture of gaussians
   dist = MixtureModel(MvNormal, parameters)
-  # sample data 
+  # sample data
   A = rand(dist, m)'
   A[A .< 0] .= 0
   return A
 end
 
+
+"""
+    model, Av, selected = nnmf_model(m = 100, n = 50, k = 10, T = Float64)
+
+Return an instance of an `NLPModel` representing the non-negative matrix factorization
+objective
+
+    f(W, H) = ½ ‖A - WH‖₂²,
+
+where A ∈ Rᵐˣⁿ has non-negative entries and can be separeted into k clusters, `Av = A[:]`.
+The vector of indices `selected = k*m+1: k*(m+n)` is used to indicate the components of W ∈ Rᵐˣᵏ and H ∈ Rᵏˣⁿ to apply  the regularizer to (so that the regularizer only applies to entries of H).
+
+## Arguments
+* `m :: Int`: the number of rows of A
+* `n :: Int`: the number of columns of A (with `n` ≥ `m`)
+* `k :: Int`: the number of clusters
+"""
 function nnmf_model(m::Int = 100, n::Int = 50, k::Int = 10, T::DataType = Float64)
   A = nnmf_data(m, n, k, T)
   r = similar(A, m * n)