From 5c41370a1f90ffafe25d654d3b290941a579faa6 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:51:23 -0400
Subject: [PATCH 01/17] Fix links

---
 src/composition/learning_networks/nodes.jl |  2 +-
 src/data/datasets.jl                       |  9 +++++----
 src/data/datasets_synthetic.jl             | 12 ++++++------
 src/machines.jl                            |  3 +--
 src/resampling.jl                          |  4 ++--
 src/show.jl                                |  6 +++---
 6 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/src/composition/learning_networks/nodes.jl b/src/composition/learning_networks/nodes.jl
index c4508448..bbcd0351 100644
--- a/src/composition/learning_networks/nodes.jl
+++ b/src/composition/learning_networks/nodes.jl
@@ -277,7 +277,7 @@ function _formula(stream, X::Node, depth, indent)
     if X.machine !== nothing
         print(stream, crind(indent + length(operation_name) - anti))
         printstyled(IOContext(stream, :color=>SHOW_COLOR[]),
-#                        handle(X.machine),
+                        #handle(X.machine),
                         X.machine,
                         bold=SHOW_COLOR[])
         n_args == 0 || print(stream, ", ")
diff --git a/src/data/datasets.jl b/src/data/datasets.jl
index ba4d88db..929a41f9 100644
--- a/src/data/datasets.jl
+++ b/src/data/datasets.jl
@@ -199,7 +199,7 @@ function load_smarket()
 end
 
 """Load a well-known sunspot time series (table with one column).
-[https://www.sws.bom.gov.au/Educational/2/3/6]](https://www.sws.bom.gov.au/Educational/2/3/6)
+<https://www.sws.bom.gov.au/Educational/2/3/6>
 """
 load_sunspots() = load_dataset("sunspots.csv", COERCE_SUNSPOTS)
 
@@ -250,9 +250,10 @@ macro load_crabs()
     end
 end
 
-""" Load S&P Stock Market dataset, as used in (An Introduction to
-Statistical Learning with applications in
-R)[https://rdrr.io/cran/ISLR/man/Smarket.html](https://rdrr.io/cran/ISLR/man/Smarket.html),
+"""
+Load S&P Stock Market dataset, as used in
+[An Introduction to Statistical Learning with applications in
+R](https://rdrr.io/cran/ISLR/man/Smarket.html),
 by Witten et al (2013), Springer-Verlag, New York."""
 macro load_smarket()
     quote
diff --git a/src/data/datasets_synthetic.jl b/src/data/datasets_synthetic.jl
index d1a8830e..fcee4603 100644
--- a/src/data/datasets_synthetic.jl
+++ b/src/data/datasets_synthetic.jl
@@ -21,12 +21,12 @@ Internal function to  finalize the `make_*` functions.
 function finalize_Xy(X, y, shuffle, as_table, eltype, rng; clf::Bool=true)
     # Shuffle the rows if required
     if shuffle
-                X, y = shuffle_rows(X, y; rng=rng)
-        end
-        if eltype != Float64
-                X = convert.(eltype, X)
-        end
-        # return as matrix if as_table=false
+        X, y = shuffle_rows(X, y; rng=rng)
+    end
+    if eltype != Float64
+        X = convert.(eltype, X)
+    end
+    # return as matrix if as_table=false
     as_table || return X, y
     clf && return MLJBase.table(X), categorical(y)
     if length(size(y)) > 1
diff --git a/src/machines.jl b/src/machines.jl
index 8f5aa438..fbca305e 100644
--- a/src/machines.jl
+++ b/src/machines.jl
@@ -1073,8 +1073,7 @@ predict(predict_only_mach, X)
     general purpose serialization formats, can allow for arbitrary code
     execution during loading. This means it is possible for someone
     to use a JLS file that looks like a serialized MLJ machine as a
-    [Trojan
-    horse](https://en.wikipedia.org/wiki/Trojan_horse_(computing)).
+    [Trojan horse](https://en.wikipedia.org/wiki/Trojan_horse_(computing)).
 
 See also [`serializable`](@ref), [`machine`](@ref).
 
diff --git a/src/resampling.jl b/src/resampling.jl
index dd317092..00b7e775 100644
--- a/src/resampling.jl
+++ b/src/resampling.jl
@@ -536,8 +536,8 @@ and the corresponding estimates, aggregated over all train/test pairs, are recor
 When displayed, a `PerformanceEvaluation` object includes a value under the heading
 `1.96*SE`, derived from the standard error of the `per_fold` entries. This value is
 suitable for constructing a formal 95% confidence interval for the given
-`measurement`. Such intervals should be interpreted with caution. See, for example, Bates
-et al.  [(2021)](https://arxiv.org/abs/2104.00673).
+`measurement`. Such intervals should be interpreted with caution. See, for example, [Bates
+et al.  (2021)](https://arxiv.org/abs/2104.00673).
 
 ### Fields
 
diff --git a/src/show.jl b/src/show.jl
index 9a9616af..8206fdcc 100644
--- a/src/show.jl
+++ b/src/show.jl
@@ -347,7 +347,7 @@ function _recursive_show(stream::IO, object::MLJType, current_depth, depth)
         print(stream, "#"^current_depth, " ")
         show(stream, object)
         println(stream, ": ")
-#        println(stream)
+        # println(stream)
         if isempty(fields)
             println(stream)
             return
@@ -358,10 +358,10 @@ function _recursive_show(stream::IO, object::MLJType, current_depth, depth)
             print(stream, fld_string)
             if isdefined(object, fld)
                 _show(stream, getproperty(object, fld))
-                #           println(stream)
+                # println(stream)
             else
                 println(stream, "(undefined)")
-                #           println(stream)
+                # println(stream)
             end
         end
         println(stream)

From d12c399760637c14b173ced284e353b8288059d1 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:54:15 -0400
Subject: [PATCH 02/17] Fix/add headers in method docstrings

---
 src/composition/learning_networks/signatures.jl |  3 ++-
 src/data/datasets_synthetic.jl                  |  7 ++++++-
 src/machines.jl                                 |  2 +-
 src/show.jl                                     | 14 +++++++++++---
 4 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/src/composition/learning_networks/signatures.jl b/src/composition/learning_networks/signatures.jl
index 7ffadb7c..84c88b27 100644
--- a/src/composition/learning_networks/signatures.jl
+++ b/src/composition/learning_networks/signatures.jl
@@ -307,7 +307,8 @@ See also [`MLJBase.Signature`](@ref).
 """
 fitted_params_supplement(signature::Signature) = call_and_copy(fitted_params_nodes(signature))
 
-""" report(signature; supplement=true)
+"""
+    report(signature; supplement=true)
 
 **Private method.**
 
diff --git a/src/data/datasets_synthetic.jl b/src/data/datasets_synthetic.jl
index fcee4603..36eb4c4b 100644
--- a/src/data/datasets_synthetic.jl
+++ b/src/data/datasets_synthetic.jl
@@ -318,7 +318,12 @@ Make portion `s` of vector `θ` exactly 0.
 """
 sparsify!(rng, θ, s) = (θ .*= (rand(rng, length(θ)) .< s))
 
-"""Add outliers to portion s of vector."""
+"""
+    outlify!(rng, y, s)
+
+Add outliers to portion `s` of vector.
+
+"""
 outlify!(rng, y, s) =
         (n = length(y); y .+= 20 * randn(rng, n) .* (rand(rng, n) .< s))
 
diff --git a/src/machines.jl b/src/machines.jl
index fbca305e..e246005d 100644
--- a/src/machines.jl
+++ b/src/machines.jl
@@ -529,7 +529,7 @@ err_missing_model(model) = ErrorException(
 )
 
 """
-   last_model(mach::Machine)
+    last_model(mach::Machine)
 
 Return the last model used to train the machine `mach`. This is a bona fide model, even if
 `mach.model` is a symbol.
diff --git a/src/show.jl b/src/show.jl
index 8206fdcc..48cc13d6 100644
--- a/src/show.jl
+++ b/src/show.jl
@@ -50,14 +50,22 @@ macro constant(ex)
     end
 end
 
-"""to display abbreviated versions of integers"""
+"""
+    abbreviated(n)
+
+Display abbreviated versions of integers.
+"""
 function abbreviated(n)
     as_string = string(n)
     return "@"*as_string[end-2:end]
 end
 
-"""return abbreviated object id (as string) or it's registered handle
-(as string) if this exists"""
+"""
+    handle(X)
+
+return abbreviated object id (as string) or it's registered handle
+(as string) if this exists
+"""
 function handle(X)
     id = objectid(X)
     if id in keys(HANDLE_GIVEN_ID)

From 2a023f1f4dad9a73be37bdcdc63b0214c7507982 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:55:15 -0400
Subject: [PATCH 03/17] Fix/add admonition blocks in docstrings

---
 src/machines.jl   |  7 ++++---
 src/resampling.jl | 12 ++++++------
 src/show.jl       |  6 ++++--
 3 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/src/machines.jl b/src/machines.jl
index e246005d..f6c61fb1 100644
--- a/src/machines.jl
+++ b/src/machines.jl
@@ -1044,9 +1044,10 @@ To serialise using a different format, see [`serializable`](@ref).
 Machines are deserialized using the `machine` constructor as shown in
 the example below.
 
-> The implementation of `save` for machines changed in MLJ 0.18
->  (MLJBase 0.20). You can only restore a machine saved using older
->  versions of MLJ using an older version.
+!!! note
+    The implementation of `save` for machines changed in MLJ 0.18
+    (MLJBase 0.20). You can only restore a machine saved using older
+    versions of MLJ using an older version.
 
 ### Example
 
diff --git a/src/resampling.jl b/src/resampling.jl
index 00b7e775..ff65d33d 100644
--- a/src/resampling.jl
+++ b/src/resampling.jl
@@ -752,15 +752,15 @@ Base.show(io::IO, e::CompactPerformanceEvaluation) =
 ## USER CONTROL OF DEFAULT LOGGING
 
 const DOC_DEFAULT_LOGGER =
-    """
+"""
 
-   The default logger is used in calls to [`evaluate!`](@ref) and [`evaluate`](@ref), and
-   in the constructors `TunedModel` and `IteratedModel`, unless the `logger` keyword is
-   explicitly specified.
+The default logger is used in calls to [`evaluate!`](@ref) and [`evaluate`](@ref), and
+in the constructors `TunedModel` and `IteratedModel`, unless the `logger` keyword is
+explicitly specified.
 
-   !!! note
+!!! note
 
-   Prior to MLJ v0.20.7 (and MLJBase 1.5) the default logger was always `nothing`.
+    Prior to MLJ v0.20.7 (and MLJBase 1.5) the default logger was always `nothing`.
 
 """
 
diff --git a/src/show.jl b/src/show.jl
index 48cc13d6..7a5d0310 100644
--- a/src/show.jl
+++ b/src/show.jl
@@ -34,8 +34,10 @@ MLJBase.HANDLE_GIVEN_ID[objectid(value)] = :x
 Registered objects get displayed using the variable name to which it
 was bound in calls to `show(x)`, etc.
 
-WARNING: As with any `const` declaration, binding `x` to new value of
-the same type is not prevented and the registration will not be updated.
+!!! warning
+
+    As with any `const` declaration, binding `x` to new value of
+    the same type is not prevented and the registration will not be updated.
 
 """
 macro constant(ex)

From a135165441b78277bc16ee7f419f475e56f54193 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:55:52 -0400
Subject: [PATCH 04/17] Fix typo and remove redundant parens

---
 src/resampling.jl | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/src/resampling.jl b/src/resampling.jl
index ff65d33d..0874a4dc 100644
--- a/src/resampling.jl
+++ b/src/resampling.jl
@@ -772,8 +772,8 @@ tracking platforms, such as [MLflow](https://mlflow.org/docs/latest/index.html).
 
 $DOC_DEFAULT_LOGGER
 
- When MLJBase is first loaded, the default logger is `nothing`. To reset the logger, see
- beow.
+When MLJBase is first loaded, the default logger is `nothing`. To reset the logger, see
+below.
 
 """
 default_logger() = DEFAULT_LOGGER[]
@@ -1073,8 +1073,8 @@ instance of one of these, then a vector of tuples of the form `(train_rows, test
 is expected. For example, setting
 
 ```julia
-resampling = [((1:100), (101:200)),
-              ((101:200), (1:100))]
+resampling = [(1:100, 101:200),
+              (101:200, 1:100)]
 ```
 
 gives two-fold cross-validation using the first 200 rows of data.

From 40f6dd8b59572e7a1772c70a890945cf5cc13e45 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:56:29 -0400
Subject: [PATCH 05/17] Fix fenced code examples

---
 src/composition/models/pipelines.jl | 2 +-
 src/resampling.jl                   | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/src/composition/models/pipelines.jl b/src/composition/models/pipelines.jl
index 0ea85297..5caf54d6 100644
--- a/src/composition/models/pipelines.jl
+++ b/src/composition/models/pipelines.jl
@@ -182,7 +182,7 @@ or what `transform` returns if it is `Unsupervised`.
 Names for the component fields are automatically generated unless
 explicitly specified, as in
 
-```
+```julia
 Pipeline(encoder=ContinuousEncoder(drop_last=false),
          stand=Standardizer())
 ```
diff --git a/src/resampling.jl b/src/resampling.jl
index 0874a4dc..0cf6f929 100644
--- a/src/resampling.jl
+++ b/src/resampling.jl
@@ -790,7 +790,7 @@ on a local server at `http://127.0.0.1:500`. Then every in every `evaluate` call
 `logger` is not specified, as in the example below, the peformance evaluation is
 automatically logged to the service.
 
-```julia-repl
+```julia
 using MLJ
 logger = MLJFlow.Logger("http://127.0.0.1:5000/api")
 default_logger(logger)
@@ -798,6 +798,7 @@ default_logger(logger)
 X, y = make_moons()
 model = ConstantClassifier()
 evaluate(model, X, y, measures=[log_loss, accuracy)])
+```
 
 """
 function default_logger(logger)

From c2c6ce84a837bb4a28643a6a51685fbb3b99f7bc Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:56:44 -0400
Subject: [PATCH 06/17] Update array print look

---
 src/utilities.jl | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/utilities.jl b/src/utilities.jl
index 3dcf31a6..ccb50208 100644
--- a/src/utilities.jl
+++ b/src/utilities.jl
@@ -301,7 +301,7 @@ column cycle fastest, those in the last clolumn slowest.
 ```julia-repl
 julia> iterators = ([1, 2], ["a","b"], ["x", "y", "z"]);
 julia> MLJTuning.unwind(iterators...)
-12×3 Array{Any,2}:
+12×3 Matrix{Any}:
  1  "a"  "x"
  2  "a"  "x"
  1  "b"  "x"
@@ -347,7 +347,7 @@ Split an `AbstractRange`  into `n` subranges of approximately equal length.
 ### Example
 ```julia-repl
 julia> collect(chunks(1:5, 2))
-2-element Array{UnitRange{Int64},1}:
+2-element Vector{UnitRange{Int64}}:
  1:3
  4:5
 ```

From 6b91946ed367f047cd7e01bf3e92a4937bbe52b1 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:57:11 -0400
Subject: [PATCH 07/17] Use latex builtin exp

---
 src/data/datasets_synthetic.jl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/data/datasets_synthetic.jl b/src/data/datasets_synthetic.jl
index 36eb4c4b..b1db573c 100644
--- a/src/data/datasets_synthetic.jl
+++ b/src/data/datasets_synthetic.jl
@@ -334,7 +334,7 @@ const SIGMOID_32 = log(Float32(1)/eps(Float32) - Float32(1))
     sigmoid(x)
 
 Return the sigmoid computed in a numerically stable way:
-``σ(x) = 1/(1+exp(-x))``
+``σ(x) = 1/(1+\\exp(-x))``
 
 """
 function sigmoid(x::Float64)

From d3d9383bfe62a6a51869e2776e9fa7700769fb46 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:57:29 -0400
Subject: [PATCH 08/17] Fix argument list

Extra newline causes markdown to interpret them as two different lists.
Remove newline to keep it all as one list.
---
 src/data/datasets_synthetic.jl | 1 -
 1 file changed, 1 deletion(-)

diff --git a/src/data/datasets_synthetic.jl b/src/data/datasets_synthetic.jl
index b1db573c..f4f3167e 100644
--- a/src/data/datasets_synthetic.jl
+++ b/src/data/datasets_synthetic.jl
@@ -172,7 +172,6 @@ membership to the smaller or larger circle, respectively.
 * `noise=0`: standard deviation of the Gaussian noise added to the data,
 
 * `factor=0.8`: ratio of the smaller radius over the larger one,
-
 $(EXTRA_KW_MAKE*EXTRA_CLASSIFICATION)
 
 ### Example

From 170e9751b3346b92ec6315c99b36126619603482 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:58:37 -0400
Subject: [PATCH 09/17] Split method docstrings

---
 src/data/data.jl | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/src/data/data.jl b/src/data/data.jl
index d3242807..af6bf859 100644
--- a/src/data/data.jl
+++ b/src/data/data.jl
@@ -401,12 +401,18 @@ _isnan(x::Number) = isnan(x)
 
 skipnan(x) = Iterators.filter(!_isnan, x)
 
+isinvalid(x) = ismissing(x) || _isnan(x)
+
 """
     skipinvalid(itr)
 
 Return an iterator over the elements in `itr` skipping `missing` and
 `NaN` values. Behaviour is similar to [`skipmissing`](@ref).
 
+"""
+skipinvalid(v) = v |> skipmissing |> skipnan
+
+"""
     skipinvalid(A, B)
 
 For vectors `A` and `B` of the same length, return a tuple of vectors
@@ -417,10 +423,6 @@ always returns a vector. Does not remove `Missing` from the element
 types if present in the original iterators.
 
 """
-skipinvalid(v) = v |> skipmissing |> skipnan
-
-isinvalid(x) = ismissing(x) || _isnan(x)
-
 function skipinvalid(yhat, y)
     mask = .!(isinvalid.(yhat) .| isinvalid.(y))
     return yhat[mask], y[mask]

From 4eaa1e4324a45df031dd51c547c148eaa9ba12f4 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Wed, 26 Jun 2024 13:58:52 -0400
Subject: [PATCH 10/17] Use proper ordered lists in docstrings

Lists were already formatted as bullet lists with
extraneous numbering or as manual plaintext lists.
---
 .../one_dimensional_range_methods.jl          | 50 +++++++++----------
 src/machines.jl                               | 34 ++++++-------
 2 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/src/hyperparam/one_dimensional_range_methods.jl b/src/hyperparam/one_dimensional_range_methods.jl
index dc82d03a..b187252e 100644
--- a/src/hyperparam/one_dimensional_range_methods.jl
+++ b/src/hyperparam/one_dimensional_range_methods.jl
@@ -66,31 +66,31 @@ In the first case iteration is over all `values` stored in the range
 iteration is over approximately `n` ordered values, generated as
 follows:
 
-(i) First, exactly `n` values are generated between `U` and `L`, with a
-spacing determined by `r.scale` (uniform if `scale=:linear`) where `U`
-and `L` are given by the following table:
-
-| `r.lower`   | `r.upper`  | `L`                 | `U`                 |
-|-------------|------------|---------------------|---------------------|
-| finite      | finite     | `r.lower`           | `r.upper`           |
-| `-Inf`      | finite     | `r.upper - 2r.unit` | `r.upper`           |
-| finite      | `Inf`      | `r.lower`           | `r.lower + 2r.unit` |
-| `-Inf`      | `Inf`      | `r.origin - r.unit` | `r.origin + r.unit` |
-
-(ii) If a callable `f` is provided as `scale`, then a uniform spacing
-is always applied in (i) but `f` is broadcast over the results. (Unlike
-ordinary scales, this alters the effective range of values generated,
-instead of just altering the spacing.)
-
-(iii) If `r` is a discrete numeric range (`r isa NumericRange{<:Integer}`)
-then the values are additionally rounded, with any duplicate values
-removed. Otherwise all the values are used (and there are exacltly `n`
-of them).
-
-(iv) Finally, if a random number generator `rng` is specified, then the values are
-returned in random order (sampling without replacement), and otherwise
-they are returned in numeric order, or in the order provided to the
-range constructor, in the case of a `NominalRange`.
+1. First, exactly `n` values are generated between `U` and `L`, with a
+   spacing determined by `r.scale` (uniform if `scale=:linear`) where `U`
+   and `L` are given by the following table:
+
+   | `r.lower`   | `r.upper`  | `L`                 | `U`                 |
+   |-------------|------------|---------------------|---------------------|
+   | finite      | finite     | `r.lower`           | `r.upper`           |
+   | `-Inf`      | finite     | `r.upper - 2r.unit` | `r.upper`           |
+   | finite      | `Inf`      | `r.lower`           | `r.lower + 2r.unit` |
+   | `-Inf`      | `Inf`      | `r.origin - r.unit` | `r.origin + r.unit` |
+
+2. If a callable `f` is provided as `scale`, then a uniform spacing
+   is always applied in (1) but `f` is broadcast over the results. (Unlike
+   ordinary scales, this alters the effective range of values generated,
+   instead of just altering the spacing.)
+
+3. If `r` is a discrete numeric range (`r isa NumericRange{<:Integer}`)
+   then the values are additionally rounded, with any duplicate values
+   removed. Otherwise all the values are used (and there are exacltly `n`
+   of them).
+
+4. Finally, if a random number generator `rng` is specified, then the values are
+   returned in random order (sampling without replacement), and otherwise
+   they are returned in numeric order, or in the order provided to the
+   range constructor, in the case of a `NominalRange`.
 
 """
 iterator(rng::AbstractRNG, r::ParamRange, args...) =
diff --git a/src/machines.jl b/src/machines.jl
index f6c61fb1..76ec904c 100644
--- a/src/machines.jl
+++ b/src/machines.jl
@@ -572,31 +572,31 @@ the true model given by `getproperty(composite, model)`. See also [`machine`](@r
 For the action to be a no-operation, either `mach.frozen == true` or
 or none of the following apply:
 
-- (i) `mach` has never been trained (`mach.state == 0`).
+1. `mach` has never been trained (`mach.state == 0`).
 
-- (ii) `force == true`.
+2. `force == true`.
 
-- (iii) The `state` of some other machine on which `mach` depends has
-  changed since the last time `mach` was trained (ie, the last time
-  `mach.state` was last incremented).
+3. The `state` of some other machine on which `mach` depends has
+   changed since the last time `mach` was trained (ie, the last time
+   `mach.state` was last incremented).
 
-- (iv) The specified `rows` have changed since the last retraining and
-  `mach.model` does not have `Static` type.
+4.  The specified `rows` have changed since the last retraining and
+   `mach.model` does not have `Static` type.
 
-- (v) `mach.model` is a model and different from the last model used for training, but has
-  the same type.
+5.  `mach.model` is a model and different from the last model used for training, but has
+   the same type.
 
-- (vi) `mach.model` is a model but has a type different from the last model used for
-  training.
+6. `mach.model` is a model but has a type different from the last model used for
+   training.
 
-- (vii) `mach.model` is a symbol and `(composite, mach.model)` is different from the last
-  model used for training, but has the same type.
+7. `mach.model` is a symbol and `(composite, mach.model)` is different from the last
+   model used for training, but has the same type.
 
-- (viii) `mach.model` is a symbol and `(composite, mach.model)` has a different type from
-  the last model used for training.
+8. `mach.model` is a symbol and `(composite, mach.model)` has a different type from
+   the last model used for training.
 
-In any of the cases (i) - (iv), (vi), or (viii), `mach` is trained ab initio. If (v) or
-(vii) is true, then a training update is applied.
+In any of the cases (1) - (4), (6), or (8), `mach` is trained ab initio.
+If (5) or (7) is true, then a training update is applied.
 
 To freeze or unfreeze `mach`, use `freeze!(mach)` or `thaw!(mach)`.
 

From aa613cba161b839bd57d35071d39c464d114d13a Mon Sep 17 00:00:00 2001
From: "Anthony D. Blaom" <anthony.blaom@gmail.com>
Date: Thu, 27 Jun 2024 13:35:50 +1200
Subject: [PATCH 11/17] bump [compat] MLJModelInterface = "1.11",
 StatisticalTraits = "3.4"

---
 Project.toml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Project.toml b/Project.toml
index 792ffb6a..d39569e1 100644
--- a/Project.toml
+++ b/Project.toml
@@ -47,7 +47,7 @@ DelimitedFiles = "1"
 Distributions = "0.25.3"
 InvertedIndices = "1"
 LearnAPI = "0.1"
-MLJModelInterface = "1.10"
+MLJModelInterface = "1.11"
 Missings = "0.4, 1"
 OrderedCollections = "1.1"
 Parameters = "0.12"
@@ -58,7 +58,7 @@ Reexport = "1.2"
 ScientificTypes = "3"
 StatisticalMeasures = "0.1.1"
 StatisticalMeasuresBase = "0.1.1"
-StatisticalTraits = "3.3"
+StatisticalTraits = "3.4"
 Statistics = "1"
 StatsBase = "0.32, 0.33, 0.34"
 Tables = "0.2, 1.0"

From cb152085d66fbd8847130af091657254e9dff2c1 Mon Sep 17 00:00:00 2001
From: "Anthony D. Blaom" <anthony.blaom@gmail.com>
Date: Thu, 27 Jun 2024 13:37:07 +1200
Subject: [PATCH 12/17] bump 1.6

---
 Project.toml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Project.toml b/Project.toml
index d39569e1..80203bc0 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,7 +1,7 @@
 name = "MLJBase"
 uuid = "a7f614a8-145f-11e9-1d2a-a57a1082229d"
 authors = ["Anthony D. Blaom <anthony.blaom@gmail.com>"]
-version = "1.5.0"
+version = "1.6"
 
 [deps]
 CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"

From 4d37eedd5dce1d3f43409880181ae25b2394eb4e Mon Sep 17 00:00:00 2001
From: "Anthony D. Blaom" <anthony.blaom@gmail.com>
Date: Thu, 27 Jun 2024 15:15:25 +1200
Subject: [PATCH 13/17] make pipelines support `Unsupervised` with target in
 fit

---
 src/composition/models/pipelines.jl  | 18 ++++++++++++--
 test/composition/models/pipelines.jl | 35 ++++++++++++++++++++++++++++
 2 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/src/composition/models/pipelines.jl b/src/composition/models/pipelines.jl
index 0ea85297..fb7682a9 100644
--- a/src/composition/models/pipelines.jl
+++ b/src/composition/models/pipelines.jl
@@ -225,6 +225,15 @@ implements it (some clustering models). Similarly, calling `transform`
 on a supervised pipeline calls `transform` on the supervised
 component.
 
+### Transformers that need a target in training
+
+Some transformers that have type `Unsupervised` (so that the output of `transform` is
+propagated in pipelines) also see a target variable in training. An example are so-called
+target encoders (which transform categorical input features, based on some target
+observations). Provided they appear before any `Supervised` component in the pipelines,
+such models are supported. Of course a target must be provided whenever training such a
+pipeline, whether or not it contains a `Supervised` component.
+
 ### Optional key-word arguments
 
 - `prediction_type`  -
@@ -444,9 +453,13 @@ function extend(front::Front{Pred}, ::Static, name, cache, args...)
     Front(transform(mach, active(front)), front.transform, Pred())
 end
 
-function extend(front::Front{Trans}, component::Unsupervised, name, cache, args...)
+function extend(front::Front{Trans}, component::Unsupervised, name, cache, ::Any, sources...)
     a = active(front)
-    mach = machine(name, a; cache=cache)
+    if target_in_fit(component)
+        mach = machine(name, a, first(sources); cache=cache)
+    else
+        mach = machine(name, a; cache=cache)
+    end
     Front(predict(mach, a), transform(mach, a), Trans())
 end
 
@@ -598,6 +611,7 @@ function MMI.iteration_parameter(pipe::SupervisedPipeline)
 end
 
 MMI.target_scitype(p::SupervisedPipeline) = target_scitype(supervised_component(p))
+MMI.target_in_fit(p::SomePipeline) = any(target_in_fit, components(p))
 
 MMI.package_name(::Type{<:SomePipeline}) = "MLJBase"
 MMI.load_path(::Type{<:SomePipeline}) = "MLJBase.Pipeline"
diff --git a/test/composition/models/pipelines.jl b/test/composition/models/pipelines.jl
index e213cdc2..c90143a7 100644
--- a/test/composition/models/pipelines.jl
+++ b/test/composition/models/pipelines.jl
@@ -544,6 +544,7 @@ end
     # inverse transform:
     p = Pipeline(UnivariateBoxCoxTransformer,
                  UnivariateStandardizer)
+    @test !target_in_fit(p)
     xtrain = rand(rng, 10)
     mach = machine(p, xtrain)
     fit!(mach, verbosity=0)
@@ -702,6 +703,40 @@ end
     @test Set(features) == Set(keys(X))
 end
 
+struct SupervisedTransformer <: Unsupervised end
+
+MLJBase.fit(::SupervisedTransformer, verbosity, X, y) = (mean(y), nothing, nothing)
+MLJBase.transform(::SupervisedTransformer, fitresult, X) =
+   fitresult*MLJBase.matrix(X) |> MLJBase.table
+MLJBase.target_in_fit(::Type{<:SupervisedTransformer}) = true
+
+struct DummyTransformer <: Unsupervised end
+MLJBase.fit(::DummyTransformer, verbosity, X) = (nothing, nothing, nothing)
+MLJBase.transform(::DummyTransformer, fitresult, X) = X
+
+@testset "supervised transformers in a pipeline" begin
+    X = MLJBase.table((a=fill(10.0, 3),))
+    y = fill(2, 3)
+    pipe = SupervisedTransformer() |> DeterministicConstantRegressor()
+    @test target_in_fit(pipe)
+    mach = machine(pipe, X, y)
+    fit!(mach, verbosity=0)
+    @test predict(mach, X) == fill(2.0, 3)
+
+    pipe2 = DummyTransformer |> pipe
+    @test target_in_fit(pipe2)
+    mach = machine(pipe2, X, y)
+    fit!(mach, verbosity=0)
+    @test predict(mach, X) == fill(2.0, 3)
+
+    pipe3 = DummyTransformer |> SupervisedTransformer |> DummyTransformer
+    @test target_in_fit(pipe3)
+    mach = machine(pipe3, X, y)
+    fit!(mach, verbosity=0)
+    @test transform(mach, X).x1 == fill(20.0, 3)
+end
+
+
 end # module
 
 true

From a9442fa3f0a53784b4d66105ddaa59aed06912ff Mon Sep 17 00:00:00 2001
From: abhro <5664668+abhro@users.noreply.github.com>
Date: Thu, 27 Jun 2024 17:58:06 -0400
Subject: [PATCH 14/17] Add argument name in docstring description

Co-authored-by: Anthony Blaom, PhD <anthony.blaom@gmail.com>
---
 src/data/datasets_synthetic.jl | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/src/data/datasets_synthetic.jl b/src/data/datasets_synthetic.jl
index f4f3167e..eb442a9f 100644
--- a/src/data/datasets_synthetic.jl
+++ b/src/data/datasets_synthetic.jl
@@ -320,7 +320,7 @@ sparsify!(rng, θ, s) = (θ .*= (rand(rng, length(θ)) .< s))
 """
     outlify!(rng, y, s)
 
-Add outliers to portion `s` of vector.
+Add outliers to portion `s` of vector `y`.
 
 """
 outlify!(rng, y, s) =

From 08a014ef2c2817932adcec08a2164bdc6a622b14 Mon Sep 17 00:00:00 2001
From: Abhro R <5664668+abhro@users.noreply.github.com>
Date: Thu, 27 Jun 2024 23:46:54 -0400
Subject: [PATCH 15/17] Match variable names to docs

Update variable name style (and comments) to match docs
---
 src/machines.jl | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/src/machines.jl b/src/machines.jl
index 76ec904c..a7473642 100644
--- a/src/machines.jl
+++ b/src/machines.jl
@@ -580,10 +580,10 @@ or none of the following apply:
    changed since the last time `mach` was trained (ie, the last time
    `mach.state` was last incremented).
 
-4.  The specified `rows` have changed since the last retraining and
+4. The specified `rows` have changed since the last retraining and
    `mach.model` does not have `Static` type.
 
-5.  `mach.model` is a model and different from the last model used for training, but has
+5. `mach.model` is a model and different from the last model used for training, but has
    the same type.
 
 6. `mach.model` is a model but has a type different from the last model used for
@@ -658,7 +658,7 @@ function fit_only!(
     rows === nothing && (rows = (:))
     rows_is_new = !isdefined(mach, :old_rows) || rows != mach.old_rows
 
-    condition_iv = rows_is_new && !(mach.model isa Static)
+    condition_4 = rows_is_new && !(mach.model isa Static)
 
     upstream_has_changed = mach.old_upstream_state != upstream_state
 
@@ -672,16 +672,16 @@ function fit_only!(
 
     # build or update cached `resampled_data` if necessary (`mach.data` is already defined
     # above if needed here):
-    if cache_data && (!data_is_valid || condition_iv)
+    if cache_data && (!data_is_valid || condition_4)
         mach.resampled_data = selectrows(model, rows, mach.data...)
     end
 
     # `fit`, `update`, or return untouched:
-    if mach.state == 0 ||       # condition (i)
-        force == true ||        # condition (ii)
-        upstream_has_changed || # condition (iii)
-        condition_iv ||         # condition (iv)
-        modeltype_changed       # conditions (vi) or (vii)
+    if mach.state == 0 ||       # condition (1)
+        force == true ||        # condition (2)
+        upstream_has_changed || # condition (3)
+        condition_4 ||          # condition (4)
+        modeltype_changed       # conditions (6) or (7)
 
         isdefined(mach, :report) || (mach.report = LittleDict{Symbol,Any}())
 
@@ -709,7 +709,7 @@ function fit_only!(
                 rethrow()
             end
 
-    elseif model != mach.old_model # condition (v)
+    elseif model != mach.old_model # condition (5)
 
         # update the model:
         fitlog(mach, :update, verbosity)

From 63344b7471a640b3ea8b64126fd616670bbf9e21 Mon Sep 17 00:00:00 2001
From: "Anthony D. Blaom" <anthony.blaom@gmail.com>
Date: Wed, 3 Jul 2024 08:01:59 +1200
Subject: [PATCH 16/17] tweak docstring

---
 src/composition/models/pipelines.jl | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/src/composition/models/pipelines.jl b/src/composition/models/pipelines.jl
index fb7682a9..0d3c4c6f 100644
--- a/src/composition/models/pipelines.jl
+++ b/src/composition/models/pipelines.jl
@@ -228,11 +228,11 @@ component.
 ### Transformers that need a target in training
 
 Some transformers that have type `Unsupervised` (so that the output of `transform` is
-propagated in pipelines) also see a target variable in training. An example are so-called
-target encoders (which transform categorical input features, based on some target
-observations). Provided they appear before any `Supervised` component in the pipelines,
-such models are supported. Of course a target must be provided whenever training such a
-pipeline, whether or not it contains a `Supervised` component.
+propagated in pipelines) may require a target variable for training. An example are
+so-called target encoders (which transform categorical input features, based on some
+target observations). Provided they appear before any `Supervised` component in the
+pipelines, such models are supported. Of course a target must be provided whenever
+training such a pipeline, whether or not it contains a `Supervised` component.
 
 ### Optional key-word arguments
 

From ecb4322949dd96bac5e13b1ad1f19e2bc952aabb Mon Sep 17 00:00:00 2001
From: "Anthony D. Blaom" <anthony.blaom@gmail.com>
Date: Wed, 3 Jul 2024 08:16:49 +1200
Subject: [PATCH 17/17] fix docstring

fix some more
---
 src/resampling.jl | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/src/resampling.jl b/src/resampling.jl
index dd317092..692a467d 100644
--- a/src/resampling.jl
+++ b/src/resampling.jl
@@ -752,15 +752,15 @@ Base.show(io::IO, e::CompactPerformanceEvaluation) =
 ## USER CONTROL OF DEFAULT LOGGING
 
 const DOC_DEFAULT_LOGGER =
-    """
+"""
 
-   The default logger is used in calls to [`evaluate!`](@ref) and [`evaluate`](@ref), and
-   in the constructors `TunedModel` and `IteratedModel`, unless the `logger` keyword is
-   explicitly specified.
+The default logger is used in calls to [`evaluate!`](@ref) and [`evaluate`](@ref), and
+in the constructors `TunedModel` and `IteratedModel`, unless the `logger` keyword is
+explicitly specified.
 
-   !!! note
+!!! note
 
-   Prior to MLJ v0.20.7 (and MLJBase 1.5) the default logger was always `nothing`.
+    Prior to MLJ v0.20.7 (and MLJBase 1.5) the default logger was always `nothing`.
 
 """
 
@@ -772,8 +772,7 @@ tracking platforms, such as [MLflow](https://mlflow.org/docs/latest/index.html).
 
 $DOC_DEFAULT_LOGGER
 
- When MLJBase is first loaded, the default logger is `nothing`. To reset the logger, see
- beow.
+When MLJBase is first loaded, the default logger is `nothing`.
 
 """
 default_logger() = DEFAULT_LOGGER[]
@@ -786,9 +785,9 @@ Reset the default logger.
 # Example
 
 Suppose an [MLflow](https://mlflow.org/docs/latest/index.html) tracking service is running
-on a local server at `http://127.0.0.1:500`. Then every in every `evaluate` call in which
-`logger` is not specified, as in the example below, the peformance evaluation is
-automatically logged to the service.
+on a local server at `http://127.0.0.1:500`. Then in every `evaluate` call in which
+`logger` is not specified, the peformance evaluation is
+automatically logged to the service, as here:
 
 ```julia-repl
 using MLJ
@@ -798,6 +797,7 @@ default_logger(logger)
 X, y = make_moons()
 model = ConstantClassifier()
 evaluate(model, X, y, measures=[log_loss, accuracy)])
+```
 
 """
 function default_logger(logger)