Docstring patches

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, ", ")

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.**
 

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())
 ```

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]

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

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
@@ -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
@@ -318,7 +317,12 @@ 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))
 
@@ -329,7 +333,7 @@ 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)

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...) =

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.
@@ -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)`.
 
@@ -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
 
@@ -1073,8 +1074,7 @@ 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).
 

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
 
@@ -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 +772,8 @@ 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[]
@@ -790,14 +790,15 @@ 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)
 
 X, y = make_moons()
 model = ConstantClassifier()
 evaluate(model, X, y, measures=[log_loss, accuracy)])
+```
 
 """
 function default_logger(logger)
@@ -1073,8 +1074,8 @@ 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.