From 9de452445c4e918b76199c7f7d8d37d8b296d2a3 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Fri, 5 Apr 2024 16:58:01 +0200
Subject: [PATCH 01/11] field added

---
 Project.toml                                  |  1 +
 src/ConformalPrediction.jl                    |  2 +
 .../inductive_classification.jl               |  8 ++-
 src/conformal_models/inductive_regression.jl  |  8 ++-
 .../transductive_classification.jl            |  8 ++-
 .../transductive_regression.jl                | 52 ++++++++++++++-----
 6 files changed, 60 insertions(+), 19 deletions(-)

diff --git a/Project.toml b/Project.toml
index c728ff5..277ebe0 100755
--- a/Project.toml
+++ b/Project.toml
@@ -20,6 +20,7 @@ ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
+TaijaBase = "10284c91-9f28-4c9a-abbf-ee43576dfff6"
 
 [compat]
 Aqua = "0.8"
diff --git a/src/ConformalPrediction.jl b/src/ConformalPrediction.jl
index eafc829..9164852 100755
--- a/src/ConformalPrediction.jl
+++ b/src/ConformalPrediction.jl
@@ -1,5 +1,7 @@
 module ConformalPrediction
 
+using TaijaBase
+
 # Conformal Models:
 include("conformal_models/conformal_models.jl")
 export ConformalModel
diff --git a/src/conformal_models/inductive_classification.jl b/src/conformal_models/inductive_classification.jl
index 8cdb9e4..119d84d 100755
--- a/src/conformal_models/inductive_classification.jl
+++ b/src/conformal_models/inductive_classification.jl
@@ -29,6 +29,7 @@ mutable struct SimpleInductiveClassifier{Model<:Supervised} <: ConformalProbabil
     coverage::AbstractFloat
     scores::Union{Nothing,Dict{Any,Any}}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     train_ratio::AbstractFloat
 end
 
@@ -36,9 +37,10 @@ function SimpleInductiveClassifier(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=minus_softmax,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return SimpleInductiveClassifier(model, coverage, nothing, heuristic, train_ratio)
+    return SimpleInductiveClassifier(model, coverage, nothing, heuristic, parallelizer, train_ratio)
 end
 
 """
@@ -127,6 +129,7 @@ mutable struct AdaptiveInductiveClassifier{Model<:Supervised} <: ConformalProbab
     coverage::AbstractFloat
     scores::Union{Nothing,Dict{Any,Any}}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     train_ratio::AbstractFloat
 end
 
@@ -134,9 +137,10 @@ function AdaptiveInductiveClassifier(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=minus_softmax,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return AdaptiveInductiveClassifier(model, coverage, nothing, heuristic, train_ratio)
+    return AdaptiveInductiveClassifier(model, coverage, nothing, heuristic, parallelizer, train_ratio)
 end
 
 @doc raw"""
diff --git a/src/conformal_models/inductive_regression.jl b/src/conformal_models/inductive_regression.jl
index cfeeb69..7f19fa9 100755
--- a/src/conformal_models/inductive_regression.jl
+++ b/src/conformal_models/inductive_regression.jl
@@ -6,6 +6,7 @@ mutable struct SimpleInductiveRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     train_ratio::AbstractFloat
 end
 
@@ -13,9 +14,10 @@ function SimpleInductiveRegressor(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return SimpleInductiveRegressor(model, coverage, nothing, heuristic, train_ratio)
+    return SimpleInductiveRegressor(model, coverage, nothing, heuristic, parallelizer, train_ratio)
 end
 
 @doc raw"""
@@ -84,6 +86,7 @@ mutable struct ConformalQuantileRegressor{Model<:QuantileModel} <: ConformalInte
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     train_ratio::AbstractFloat
 end
 
@@ -93,9 +96,10 @@ function ConformalQuantileRegressor(
     heuristic::Function=function f(y, ŷ_lb, ŷ_ub)
         return reduce((x, y) -> max.(x, y), [ŷ_lb - y, y - ŷ_ub])
     end,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return ConformalQuantileRegressor(model, coverage, nothing, heuristic, train_ratio)
+    return ConformalQuantileRegressor(model, coverage, nothing, heuristic, parallelizer, train_ratio)
 end
 
 @doc raw"""
diff --git a/src/conformal_models/transductive_classification.jl b/src/conformal_models/transductive_classification.jl
index d13da08..e489670 100755
--- a/src/conformal_models/transductive_classification.jl
+++ b/src/conformal_models/transductive_classification.jl
@@ -5,12 +5,16 @@ mutable struct NaiveClassifier{Model<:Supervised} <: ConformalProbabilisticSet
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
 end
 
 function NaiveClassifier(
-    model::Supervised; coverage::AbstractFloat=0.95, heuristic::Function=minus_softmax
+    model::Supervised;
+    coverage::AbstractFloat=0.95,
+    heuristic::Function=minus_softmax,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
 )
-    return NaiveClassifier(model, coverage, nothing, heuristic)
+    return NaiveClassifier(model, coverage, nothing, heuristic, parallelizer)
 end
 
 @doc raw"""
diff --git a/src/conformal_models/transductive_regression.jl b/src/conformal_models/transductive_regression.jl
index 6598531..2e3b150 100755
--- a/src/conformal_models/transductive_regression.jl
+++ b/src/conformal_models/transductive_regression.jl
@@ -10,12 +10,16 @@ mutable struct NaiveRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
 end
 
 function NaiveRegressor(
-    model::Supervised; coverage::AbstractFloat=0.95, heuristic::Function=absolute_error
+    model::Supervised;
+    coverage::AbstractFloat=0.95,
+    heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
 )
-    return NaiveRegressor(model, coverage, nothing, heuristic)
+    return NaiveRegressor(model, coverage, nothing, heuristic, parallelizer)
 end
 
 @doc raw"""
@@ -79,12 +83,16 @@ mutable struct JackknifeRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
 end
 
 function JackknifeRegressor(
-    model::Supervised; coverage::AbstractFloat=0.95, heuristic::Function=absolute_error
+    model::Supervised;
+    coverage::AbstractFloat=0.95,
+    heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
 )
-    return JackknifeRegressor(model, coverage, nothing, heuristic)
+    return JackknifeRegressor(model, coverage, nothing, heuristic, parallelizer)
 end
 
 @doc raw"""
@@ -160,12 +168,16 @@ mutable struct JackknifePlusRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
 end
 
 function JackknifePlusRegressor(
-    model::Supervised; coverage::AbstractFloat=0.95, heuristic::Function=absolute_error
+    model::Supervised;
+    coverage::AbstractFloat=0.95,
+    heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
 )
-    return JackknifePlusRegressor(model, coverage, nothing, heuristic)
+    return JackknifePlusRegressor(model, coverage, nothing, heuristic, parallelizer)
 end
 
 @doc raw"""
@@ -249,12 +261,16 @@ mutable struct JackknifeMinMaxRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
 end
 
 function JackknifeMinMaxRegressor(
-    model::Supervised; coverage::AbstractFloat=0.95, heuristic::Function=absolute_error
+    model::Supervised;
+    coverage::AbstractFloat=0.95,
+    heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
 )
-    return JackknifeMinMaxRegressor(model, coverage, nothing, heuristic)
+    return JackknifeMinMaxRegressor(model, coverage, nothing, heuristic, parallelizer)
 end
 
 @doc raw"""
@@ -337,6 +353,7 @@ mutable struct CVPlusRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     cv::MLJBase.CV
 end
 
@@ -344,9 +361,10 @@ function CVPlusRegressor(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     cv::MLJBase.CV=MLJBase.CV(),
 )
-    return CVPlusRegressor(model, coverage, nothing, heuristic, cv)
+    return CVPlusRegressor(model, coverage, nothing, heuristic, parallelizer, cv)
 end
 
 @doc raw"""
@@ -442,6 +460,7 @@ mutable struct CVMinMaxRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     cv::MLJBase.CV
 end
 
@@ -449,9 +468,10 @@ function CVMinMaxRegressor(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     cv::MLJBase.CV=MLJBase.CV(),
 )
-    return CVMinMaxRegressor(model, coverage, nothing, heuristic, cv)
+    return CVMinMaxRegressor(model, coverage, nothing, heuristic, parallelizer, cv)
 end
 
 @doc raw"""
@@ -567,6 +587,7 @@ mutable struct JackknifePlusAbRegressor{Model<:Supervised} <: ConformalInterval
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     nsampling::Int
     sample_size::AbstractFloat
     replacement::Bool
@@ -577,13 +598,14 @@ function JackknifePlusAbRegressor(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     nsampling::Int=30,
     sample_size::AbstractFloat=0.5,
     replacement::Bool=true,
     aggregate::Union{Symbol,String}="mean",
 )
     return JackknifePlusAbRegressor(
-        model, coverage, nothing, heuristic, nsampling, sample_size, replacement, aggregate
+        model, coverage, nothing, heuristic, parallelizer, nsampling, sample_size, replacement, aggregate
     )
 end
 
@@ -673,6 +695,7 @@ mutable struct JackknifePlusAbMinMaxRegressor{Model<:Supervised} <: ConformalInt
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     nsampling::Int
     sample_size::AbstractFloat
     replacement::Bool
@@ -683,13 +706,14 @@ function JackknifePlusAbMinMaxRegressor(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     nsampling::Int=30,
     sample_size::AbstractFloat=0.5,
     replacement::Bool=true,
     aggregate::Union{Symbol,String}="mean",
 )
     return JackknifePlusAbMinMaxRegressor(
-        model, coverage, nothing, heuristic, nsampling, sample_size, replacement, aggregate
+        model, coverage, nothing, heuristic, parallelizer, nsampling, sample_size, replacement, aggregate
     )
 end
 
@@ -777,6 +801,7 @@ mutable struct TimeSeriesRegressorEnsembleBatch{Model<:Supervised} <: ConformalI
     coverage::AbstractFloat
     scores::Union{Nothing,AbstractArray}
     heuristic::Function
+    parallelizer::Union{Nothing,AbstractParallelizer}
     nsampling::Int
     sample_size::AbstractFloat
     aggregate::Union{Symbol,String}
@@ -786,12 +811,13 @@ function TimeSeriesRegressorEnsembleBatch(
     model::Supervised;
     coverage::AbstractFloat=0.95,
     heuristic::Function=absolute_error,
+    parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     nsampling::Int=50,
     sample_size::AbstractFloat=0.3,
     aggregate::Union{Symbol,String}="mean",
 )
     return TimeSeriesRegressorEnsembleBatch(
-        model, coverage, nothing, heuristic, nsampling, sample_size, aggregate
+        model, coverage, nothing, heuristic, parallelizer, nsampling, sample_size, aggregate
     )
 end
 

From 8559209495302dda90b4c0d57be4e5874ccb9406 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Fri, 5 Apr 2024 17:00:24 +0200
Subject: [PATCH 02/11] format

---
 .../inductive_classification.jl               |  8 ++++++--
 src/conformal_models/inductive_regression.jl  |  8 ++++++--
 .../transductive_regression.jl                | 20 +++++++++++++++++--
 3 files changed, 30 insertions(+), 6 deletions(-)

diff --git a/src/conformal_models/inductive_classification.jl b/src/conformal_models/inductive_classification.jl
index 119d84d..39c9442 100755
--- a/src/conformal_models/inductive_classification.jl
+++ b/src/conformal_models/inductive_classification.jl
@@ -40,7 +40,9 @@ function SimpleInductiveClassifier(
     parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return SimpleInductiveClassifier(model, coverage, nothing, heuristic, parallelizer, train_ratio)
+    return SimpleInductiveClassifier(
+        model, coverage, nothing, heuristic, parallelizer, train_ratio
+    )
 end
 
 """
@@ -140,7 +142,9 @@ function AdaptiveInductiveClassifier(
     parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return AdaptiveInductiveClassifier(model, coverage, nothing, heuristic, parallelizer, train_ratio)
+    return AdaptiveInductiveClassifier(
+        model, coverage, nothing, heuristic, parallelizer, train_ratio
+    )
 end
 
 @doc raw"""
diff --git a/src/conformal_models/inductive_regression.jl b/src/conformal_models/inductive_regression.jl
index 7f19fa9..f52d6f0 100755
--- a/src/conformal_models/inductive_regression.jl
+++ b/src/conformal_models/inductive_regression.jl
@@ -17,7 +17,9 @@ function SimpleInductiveRegressor(
     parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return SimpleInductiveRegressor(model, coverage, nothing, heuristic, parallelizer, train_ratio)
+    return SimpleInductiveRegressor(
+        model, coverage, nothing, heuristic, parallelizer, train_ratio
+    )
 end
 
 @doc raw"""
@@ -99,7 +101,9 @@ function ConformalQuantileRegressor(
     parallelizer::Union{Nothing,AbstractParallelizer}=nothing,
     train_ratio::AbstractFloat=0.5,
 )
-    return ConformalQuantileRegressor(model, coverage, nothing, heuristic, parallelizer, train_ratio)
+    return ConformalQuantileRegressor(
+        model, coverage, nothing, heuristic, parallelizer, train_ratio
+    )
 end
 
 @doc raw"""
diff --git a/src/conformal_models/transductive_regression.jl b/src/conformal_models/transductive_regression.jl
index 2e3b150..a07e762 100755
--- a/src/conformal_models/transductive_regression.jl
+++ b/src/conformal_models/transductive_regression.jl
@@ -605,7 +605,15 @@ function JackknifePlusAbRegressor(
     aggregate::Union{Symbol,String}="mean",
 )
     return JackknifePlusAbRegressor(
-        model, coverage, nothing, heuristic, parallelizer, nsampling, sample_size, replacement, aggregate
+        model,
+        coverage,
+        nothing,
+        heuristic,
+        parallelizer,
+        nsampling,
+        sample_size,
+        replacement,
+        aggregate,
     )
 end
 
@@ -713,7 +721,15 @@ function JackknifePlusAbMinMaxRegressor(
     aggregate::Union{Symbol,String}="mean",
 )
     return JackknifePlusAbMinMaxRegressor(
-        model, coverage, nothing, heuristic, parallelizer, nsampling, sample_size, replacement, aggregate
+        model,
+        coverage,
+        nothing,
+        heuristic,
+        parallelizer,
+        nsampling,
+        sample_size,
+        replacement,
+        aggregate,
     )
 end
 

From aa55c6ebc794358ce43fcf55415b4fda4c47f45a Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Fri, 5 Apr 2024 17:30:10 +0200
Subject: [PATCH 03/11] added compat entry

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

diff --git a/Project.toml b/Project.toml
index 277ebe0..0446e4e 100755
--- a/Project.toml
+++ b/Project.toml
@@ -40,6 +40,7 @@ ProgressMeter = "1"
 Random = "1.7, 1.8, 1.9, 1.10"
 StatsBase = "0.33, 0.34.0"
 Tables = "1"
+TaijaBase = "1"
 Test = "1.7, 1.8, 1.9, 1.10"
 julia = "1.7, 1.8, 1.9, 1.10"
 

From bf6289abc5df632fdf14b9285cfde05b8559d87a Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Fri, 5 Apr 2024 17:56:23 +0200
Subject: [PATCH 04/11] will also use this same branch to streamline the
 codebase a bit

---
 src/conformal_models/conformal_models.jl      | 13 +---
 .../classification.jl}                        | 67 +++++++----------
 .../inductive/inductive_models.jl             | 27 +++++++
 .../regression.jl}                            | 14 +---
 src/conformal_models/inductive_bayes.jl       | 74 -------------------
 5 files changed, 58 insertions(+), 137 deletions(-)
 rename src/conformal_models/{inductive_classification.jl => inductive/classification.jl} (92%)
 create mode 100644 src/conformal_models/inductive/inductive_models.jl
 rename src/conformal_models/{inductive_regression.jl => inductive/regression.jl} (92%)
 delete mode 100755 src/conformal_models/inductive_bayes.jl

diff --git a/src/conformal_models/conformal_models.jl b/src/conformal_models/conformal_models.jl
index 4023173..d8e63f8 100755
--- a/src/conformal_models/conformal_models.jl
+++ b/src/conformal_models/conformal_models.jl
@@ -50,26 +50,19 @@ function conformal_model(
     return conf_model
 end
 
+# Inductive Models:
+include("inductive/inductive_models.jl")
+
 # Regression Models:
-include("inductive_regression.jl")
 include("transductive_regression.jl")
 
 # Classification Models
-include("inductive_classification.jl")
 include("transductive_classification.jl")
 
 # Training:
 include("ConformalTraining/ConformalTraining.jl")
 using .ConformalTraining
 
-# Type unions:
-const InductiveModel = Union{
-    SimpleInductiveRegressor,
-    SimpleInductiveClassifier,
-    AdaptiveInductiveClassifier,
-    ConformalQuantileRegressor,
-}
-
 const TransductiveModel = Union{
     NaiveRegressor,
     JackknifeRegressor,
diff --git a/src/conformal_models/inductive_classification.jl b/src/conformal_models/inductive/classification.jl
similarity index 92%
rename from src/conformal_models/inductive_classification.jl
rename to src/conformal_models/inductive/classification.jl
index 39c9442..baad252 100755
--- a/src/conformal_models/inductive_classification.jl
+++ b/src/conformal_models/inductive/classification.jl
@@ -7,19 +7,26 @@ function score(conf_model::ConformalProbabilisticSet, fitresult, X, y=nothing)
     return score(conf_model, conf_model.model, fitresult, X, y)
 end
 
-"""
-    split_data(conf_model::ConformalProbabilisticSet, indices::Base.OneTo{Int})
+@doc raw"""
+    MMI.fit(conf_model::ConformalProbabilisticSet, verbosity, X, y)
 
-Splits the data into a proper training and calibration set.
+Fits the [`ConformalProbabilisticSet`](@ref) model. 
 """
-function split_data(conf_model::ConformalProbabilisticSet, X, y)
-    train, calibration = partition(eachindex(y), conf_model.train_ratio)
-    Xtrain = selectrows(X, train)
-    ytrain = y[train]
-    Xcal = selectrows(X, calibration)
-    ycal = y[calibration]
-
-    return Xtrain, ytrain, Xcal, ycal
+function MMI.fit(conf_model::ConformalProbabilisticSet, verbosity, X, y)
+
+    # Data Splitting:
+    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
+
+    # Training:
+    fitresult, cache, report = MMI.fit(
+        conf_model.model, verbosity, MMI.reformat(conf_model.model, Xtrain, ytrain)...
+    )
+
+    # Nonconformity Scores:
+    cal_scores, scores = score(conf_model, fitresult, Xcal, ycal)
+    conf_model.scores = Dict(:calibration => cal_scores, :all => scores)
+
+    return (fitresult, cache, report)
 end
 
 # Simple
@@ -45,10 +52,16 @@ function SimpleInductiveClassifier(
     )
 end
 
-"""
+@doc raw"""
     score(conf_model::SimpleInductiveClassifier, ::Type{<:Supervised}, fitresult, X, y::Union{Nothing,AbstractArray}=nothing)
 
-Score method for the [`SimpleInductiveClassifier`](@ref) dispatched for any `<:Supervised` model.
+Score method for the [`SimpleInductiveClassifier`](@ref) dispatched for any `<:Supervised` model. For the [`SimpleInductiveClassifier`](@ref) nonconformity scores are computed as follows:
+
+``
+S_i^{\text{CAL}} = s(X_i, Y_i) = h(\hat\mu(X_i), Y_i), \ i \in \mathcal{D}_{\text{calibration}}
+``
+
+A typical choice for the heuristic function is ``h(\hat\mu(X_i), Y_i)=1-\hat\mu(X_i)_{Y_i}`` where ``\hat\mu(X_i)_{Y_i}`` denotes the softmax output of the true class and ``\hat\mu`` denotes the model fitted on training data ``\mathcal{D}_{\text{train}}``. The simple approach only takes the softmax probability of the true label into account.
 """
 function score(
     conf_model::SimpleInductiveClassifier, atomic::Supervised, fitresult, X, y=nothing
@@ -65,34 +78,6 @@ function score(
     end
 end
 
-@doc raw"""
-    MMI.fit(conf_model::SimpleInductiveClassifier, verbosity, X, y)
-
-For the [`SimpleInductiveClassifier`](@ref) nonconformity scores are computed as follows:
-
-``
-S_i^{\text{CAL}} = s(X_i, Y_i) = h(\hat\mu(X_i), Y_i), \ i \in \mathcal{D}_{\text{calibration}}
-``
-
-A typical choice for the heuristic function is ``h(\hat\mu(X_i), Y_i)=1-\hat\mu(X_i)_{Y_i}`` where ``\hat\mu(X_i)_{Y_i}`` denotes the softmax output of the true class and ``\hat\mu`` denotes the model fitted on training data ``\mathcal{D}_{\text{train}}``. The simple approach only takes the softmax probability of the true label into account.
-"""
-function MMI.fit(conf_model::SimpleInductiveClassifier, verbosity, X, y)
-
-    # Data Splitting:
-    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
-
-    # Training:
-    fitresult, cache, report = MMI.fit(
-        conf_model.model, verbosity, MMI.reformat(conf_model.model, Xtrain, ytrain)...
-    )
-
-    # Nonconformity Scores:
-    cal_scores, scores = score(conf_model, fitresult, Xcal, ycal)
-    conf_model.scores = Dict(:calibration => cal_scores, :all => scores)
-
-    return (fitresult, cache, report)
-end
-
 @doc raw"""
     MMI.predict(conf_model::SimpleInductiveClassifier, fitresult, Xnew)
 
diff --git a/src/conformal_models/inductive/inductive_models.jl b/src/conformal_models/inductive/inductive_models.jl
new file mode 100644
index 0000000..0e69bf9
--- /dev/null
+++ b/src/conformal_models/inductive/inductive_models.jl
@@ -0,0 +1,27 @@
+# Type unions:
+include("classification.jl")
+include("regression.jl")
+
+const InductiveModel = Union{
+    SimpleInductiveRegressor,
+    SimpleInductiveClassifier,
+    AdaptiveInductiveClassifier,
+    ConformalQuantileRegressor,
+}
+
+"""
+    split_data(conf_model::InductiveModel, indices::Base.OneTo{Int})
+
+Splits the data into a proper training and calibration set.
+"""
+function split_data(conf_model::InductiveModel, X, y)
+    train, calibration = partition(eachindex(y), conf_model.train_ratio)
+    Xtrain = selectrows(X, train)
+    ytrain = y[train]
+    Xtrain, ytrain = MMI.reformat(conf_model.model, Xtrain, ytrain)
+    Xcal = selectrows(X, calibration)
+    ycal = y[calibration]
+    Xcal, ycal = MMI.reformat(conf_model.model, Xcal, ycal)
+
+    return Xtrain, ytrain, Xcal, ycal
+end
diff --git a/src/conformal_models/inductive_regression.jl b/src/conformal_models/inductive/regression.jl
similarity index 92%
rename from src/conformal_models/inductive_regression.jl
rename to src/conformal_models/inductive/regression.jl
index f52d6f0..a11dcad 100755
--- a/src/conformal_models/inductive_regression.jl
+++ b/src/conformal_models/inductive/regression.jl
@@ -36,11 +36,7 @@ A typical choice for the heuristic function is ``h(\hat\mu(X_i),Y_i)=|Y_i-\hat\m
 function MMI.fit(conf_model::SimpleInductiveRegressor, verbosity, X, y)
 
     # Data Splitting:
-    train, calibration = partition(eachindex(y), conf_model.train_ratio)
-    Xtrain = selectrows(X, train)
-    ytrain = y[train]
-    Xcal = selectrows(X, calibration)
-    ycal = y[calibration]
+    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
 
     # Training:
     fitresult, cache, report = MMI.fit(
@@ -122,13 +118,7 @@ A typical choice for the heuristic function is ``h(\hat\mu_{\alpha_{lo}}(X_i), \
 function MMI.fit(conf_model::ConformalQuantileRegressor, verbosity, X, y)
 
     # Data Splitting:
-    train, calibration = partition(eachindex(y), conf_model.train_ratio)
-    Xtrain = selectrows(X, train)
-    ytrain = y[train]
-    Xtrain, ytrain = MMI.reformat(conf_model.model, Xtrain, ytrain)
-    Xcal = selectrows(X, calibration)
-    ycal = y[calibration]
-    Xcal, ycal = MMI.reformat(conf_model.model, Xcal, ycal)
+    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
 
     # Training:
     fitresult, cache, report, y_pred = ([], [], [], [])
diff --git a/src/conformal_models/inductive_bayes.jl b/src/conformal_models/inductive_bayes.jl
deleted file mode 100755
index 7c330d5..0000000
--- a/src/conformal_models/inductive_bayes.jl
+++ /dev/null
@@ -1,74 +0,0 @@
-# # Simple
-# "The `SimpleInductiveBayes` is the simplest approach to Inductive Conformalized Bayes."
-# mutable struct SimpleInductiveBayes{Model <: Supervised} <: ConformalModel
-#     model::Model
-#     coverage::AbstractFloat
-#     scores::Union{Nothing,AbstractArray}
-#     heuristic::Function
-#     train_ratio::AbstractFloat
-# end
-
-# function SimpleInductiveBayes(model::Supervised; coverage::AbstractFloat=0.95, heuristic::Function=f(y, ŷ)=-ŷ, train_ratio::AbstractFloat=0.5)
-#     return SimpleInductiveBayes(model, coverage, nothing, heuristic, train_ratio)
-# end
-
-# @doc raw"""
-#     MMI.fit(conf_model::SimpleInductiveBayes, verbosity, X, y)
-
-# For the [`SimpleInductiveBayes`](@ref) nonconformity scores are computed as follows:
-
-# ``
-# S_i^{\text{CAL}} = s(X_i, Y_i) = h(\hat\mu(X_i), Y_i), \ i \in \mathcal{D}_{\text{calibration}}
-# ``
-
-# A typical choice for the heuristic function is ``h(\hat\mu(X_i), Y_i)=1-\hat\mu(X_i)_{Y_i}`` where ``\hat\mu(X_i)_{Y_i}`` denotes the softmax output of the true class and ``\hat\mu`` denotes the model fitted on training data ``\mathcal{D}_{\text{train}}``. The simple approach only takes the softmax probability of the true label into account.
-# """
-# function MMI.fit(conf_model::SimpleInductiveBayes, verbosity, X, y)
-    
-#     # Data Splitting:
-#     train, calibration = partition(eachindex(y), conf_model.train_ratio)
-#     Xtrain = selectrows(X, train)
-#     ytrain = y[train]
-#     Xtrain, ytrain = MMI.reformat(conf_model.model, Xtrain, ytrain)
-#     Xcal = selectrows(X, calibration)
-#     ycal = y[calibration]
-#     Xcal, ycal = MMI.reformat(conf_model.model, Xcal, ycal)
-
-#     # Training: 
-#     fitresult, cache, report = MMI.fit(conf_model.model, verbosity, Xtrain, ytrain)
-
-#     # Nonconformity Scores:
-#     ŷ = pdf.(MMI.predict(conf_model.model, fitresult, Xcal), ycal)      # predict returns a vector of distributions
-#     conf_model.scores = @.(conf_model.heuristic(ycal, ŷ))
-
-#     return (fitresult, cache, report)
-# end
-
-# @doc raw"""
-#     MMI.predict(conf_model::SimpleInductiveBayes, fitresult, Xnew)
-
-# For the [`SimpleInductiveBayes`](@ref) prediction sets are computed as follows,
-
-# ``
-# \hat{C}_{n,\alpha}(X_{n+1}) = \left\{y: s(X_{n+1},y) \le \hat{q}_{n, \alpha}^{+} \{S_i^{\text{CAL}}\} \right\}, \ i \in \mathcal{D}_{\text{calibration}}
-# ``
-
-# where ``\mathcal{D}_{\text{calibration}}`` denotes the designated calibration data.
-# """
-# function MMI.predict(conf_model::SimpleInductiveBayes, fitresult, Xnew)
-#     p̂ = MMI.predict(conf_model.model, fitresult, MMI.reformat(conf_model.model, Xnew)...)
-#     v = conf_model.scores
-#     q̂ = qplus(v, conf_model.coverage)
-#     p̂ = map(p̂) do pp
-#         L = p̂.decoder.classes
-#         probas = pdf.(pp, L)
-#         is_in_set = 1.0 .- probas .<= q̂
-#         if !all(is_in_set .== false)
-#             pp = UnivariateFinite(L[is_in_set], probas[is_in_set])
-#         else
-#             pp = missing
-#         end
-#         return pp
-#     end
-#     return p̂
-# end

From c6ae2b5ef6cbc995259856299b28a94ed57cc76f Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Fri, 5 Apr 2024 18:09:07 +0200
Subject: [PATCH 05/11] lets try this again

---
 src/conformal_models/inductive/inductive_models.jl | 2 --
 1 file changed, 2 deletions(-)

diff --git a/src/conformal_models/inductive/inductive_models.jl b/src/conformal_models/inductive/inductive_models.jl
index 0e69bf9..5975f3d 100644
--- a/src/conformal_models/inductive/inductive_models.jl
+++ b/src/conformal_models/inductive/inductive_models.jl
@@ -18,10 +18,8 @@ function split_data(conf_model::InductiveModel, X, y)
     train, calibration = partition(eachindex(y), conf_model.train_ratio)
     Xtrain = selectrows(X, train)
     ytrain = y[train]
-    Xtrain, ytrain = MMI.reformat(conf_model.model, Xtrain, ytrain)
     Xcal = selectrows(X, calibration)
     ycal = y[calibration]
-    Xcal, ycal = MMI.reformat(conf_model.model, Xcal, ycal)
 
     return Xtrain, ytrain, Xcal, ycal
 end

From eeda2a10d55dccaa9b8acf132d8e333af87f6623 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Fri, 5 Apr 2024 21:32:37 +0200
Subject: [PATCH 06/11] trying to fix the erorr

---
 .../inductive/classification.jl               | 57 -------------------
 .../inductive/inductive_models.jl             | 31 ++++++++++
 src/conformal_models/inductive/regression.jl  | 29 +++++-----
 3 files changed, 44 insertions(+), 73 deletions(-)

diff --git a/src/conformal_models/inductive/classification.jl b/src/conformal_models/inductive/classification.jl
index baad252..5524bde 100755
--- a/src/conformal_models/inductive/classification.jl
+++ b/src/conformal_models/inductive/classification.jl
@@ -1,34 +1,3 @@
-"""
-    score(conf_model::ConformalProbabilisticSet, fitresult, X, y=nothing)
-
-Generic score method for the [`ConformalProbabilisticSet`](@ref). It computes nonconformity scores using the heuristic function `h` and the softmax probabilities of the true class. Method is dispatched for different Conformal Probabilistic Sets and atomic models.
-"""
-function score(conf_model::ConformalProbabilisticSet, fitresult, X, y=nothing)
-    return score(conf_model, conf_model.model, fitresult, X, y)
-end
-
-@doc raw"""
-    MMI.fit(conf_model::ConformalProbabilisticSet, verbosity, X, y)
-
-Fits the [`ConformalProbabilisticSet`](@ref) model. 
-"""
-function MMI.fit(conf_model::ConformalProbabilisticSet, verbosity, X, y)
-
-    # Data Splitting:
-    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
-
-    # Training:
-    fitresult, cache, report = MMI.fit(
-        conf_model.model, verbosity, MMI.reformat(conf_model.model, Xtrain, ytrain)...
-    )
-
-    # Nonconformity Scores:
-    cal_scores, scores = score(conf_model, fitresult, Xcal, ycal)
-    conf_model.scores = Dict(:calibration => cal_scores, :all => scores)
-
-    return (fitresult, cache, report)
-end
-
 # Simple
 "The `SimpleInductiveClassifier` is the simplest approach to Inductive Conformal Classification. Contrary to the [`NaiveClassifier`](@ref) it computes nonconformity scores using a designated calibration dataset."
 mutable struct SimpleInductiveClassifier{Model<:Supervised} <: ConformalProbabilisticSet
@@ -132,32 +101,6 @@ function AdaptiveInductiveClassifier(
     )
 end
 
-@doc raw"""
-    MMI.fit(conf_model::AdaptiveInductiveClassifier, verbosity, X, y)
-
-For the [`AdaptiveInductiveClassifier`](@ref) nonconformity scores are computed by cumulatively summing the ranked scores of each label in descending order until reaching the true label ``Y_i``:
-
-``
-S_i^{\text{CAL}} = s(X_i,Y_i) = \sum_{j=1}^k  \hat\mu(X_i)_{\pi_j} \ \text{where } \ Y_i=\pi_k,  i \in \mathcal{D}_{\text{calibration}}
-``
-"""
-function MMI.fit(conf_model::AdaptiveInductiveClassifier, verbosity, X, y)
-
-    # Data Splitting:
-    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
-
-    # Training:
-    fitresult, cache, report = MMI.fit(
-        conf_model.model, verbosity, MMI.reformat(conf_model.model, Xtrain, ytrain)...
-    )
-
-    # Nonconformity Scores:
-    cal_scores, scores = score(conf_model, fitresult, Xcal, ycal)
-    conf_model.scores = Dict(:calibration => cal_scores, :all => scores)
-
-    return (fitresult, cache, report)
-end
-
 """
     score(conf_model::AdaptiveInductiveClassifier, ::Type{<:Supervised}, fitresult, X, y::Union{Nothing,AbstractArray}=nothing)
 
diff --git a/src/conformal_models/inductive/inductive_models.jl b/src/conformal_models/inductive/inductive_models.jl
index 5975f3d..c3298be 100644
--- a/src/conformal_models/inductive/inductive_models.jl
+++ b/src/conformal_models/inductive/inductive_models.jl
@@ -23,3 +23,34 @@ function split_data(conf_model::InductiveModel, X, y)
 
     return Xtrain, ytrain, Xcal, ycal
 end
+
+"""
+    score(conf_model::InductiveModel, fitresult, X, y=nothing)
+
+Generic score method for the [`InductiveModel`](@ref). It computes nonconformity scores using the heuristic function `h` and the softmax probabilities of the true class. Method is dispatched for different Conformal Probabilistic Sets and atomic models.
+"""
+function score(conf_model::InductiveModel, fitresult, X, y=nothing)
+    return score(conf_model, conf_model.model, fitresult, X, y)
+end
+
+@doc raw"""
+    MMI.fit(conf_model::InductiveModel, verbosity, X, y)
+
+Fits the [`InductiveModel`](@ref) model. 
+"""
+function MMI.fit(conf_model::InductiveModel, verbosity, X, y)
+
+    # Data Splitting:
+    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
+
+    # Training:
+    fitresult, cache, report = MMI.fit(
+        conf_model.model, verbosity, MMI.reformat(conf_model.model, Xtrain, ytrain)...
+    )
+
+    # Nonconformity Scores:
+    cal_scores, scores = score(conf_model, fitresult, Xcal, ycal)
+    conf_model.scores = Dict(:calibration => cal_scores, :all => scores)
+
+    return (fitresult, cache, report)
+end
diff --git a/src/conformal_models/inductive/regression.jl b/src/conformal_models/inductive/regression.jl
index a11dcad..3d72226 100755
--- a/src/conformal_models/inductive/regression.jl
+++ b/src/conformal_models/inductive/regression.jl
@@ -22,8 +22,9 @@ function SimpleInductiveRegressor(
     )
 end
 
+
 @doc raw"""
-    MMI.fit(conf_model::SimpleInductiveRegressor, verbosity, X, y)
+    score(conf_model::SimpleInductiveRegressor, atomic::Supervised, fitresult, X, y=nothing)
 
 For the [`SimpleInductiveRegressor`](@ref) nonconformity scores are computed as follows:
 
@@ -33,23 +34,19 @@ S_i^{\text{CAL}} = s(X_i, Y_i) = h(\hat\mu(X_i), Y_i), \ i \in \mathcal{D}_{\tex
 
 A typical choice for the heuristic function is ``h(\hat\mu(X_i),Y_i)=|Y_i-\hat\mu(X_i)|`` where ``\hat\mu`` denotes the model fitted on training data ``\mathcal{D}_{\text{train}}``.
 """
-function MMI.fit(conf_model::SimpleInductiveRegressor, verbosity, X, y)
-
-    # Data Splitting:
-    Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
-
-    # Training:
-    fitresult, cache, report = MMI.fit(
-        conf_model.model, verbosity, MMI.reformat(conf_model.model, Xtrain, ytrain)...
-    )
-
-    # Nonconformity Scores:
+function score(
+    conf_model::SimpleInductiveRegressor, atomic::Supervised, fitresult, X, y=nothing
+)
     ŷ = reformat_mlj_prediction(
-        MMI.predict(conf_model.model, fitresult, MMI.reformat(conf_model.model, Xcal)...)
+        MMI.predict(atomic, fitresult, MMI.reformat(atomic, X)...)
     )
-    conf_model.scores = @.(conf_model.heuristic(ycal, ŷ))
-
-    return (fitresult, cache, report)
+    scores = @.(conf_model.heuristic(y, ŷ))
+    if isnothing(y)
+        return scores
+    else
+        cal_scores = getindex.(Ref(scores), 1:size(scores, 1), y)
+        return cal_scores, scores
+    end
 end
 
 # Prediction

From 624d4a736a51945d797b8e501e4d09887da0d046 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Fri, 5 Apr 2024 21:34:43 +0200
Subject: [PATCH 07/11] formatter

---
 src/conformal_models/inductive/regression.jl | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/src/conformal_models/inductive/regression.jl b/src/conformal_models/inductive/regression.jl
index 3d72226..d75215a 100755
--- a/src/conformal_models/inductive/regression.jl
+++ b/src/conformal_models/inductive/regression.jl
@@ -22,7 +22,6 @@ function SimpleInductiveRegressor(
     )
 end
 
-
 @doc raw"""
     score(conf_model::SimpleInductiveRegressor, atomic::Supervised, fitresult, X, y=nothing)
 
@@ -37,9 +36,7 @@ A typical choice for the heuristic function is ``h(\hat\mu(X_i),Y_i)=|Y_i-\hat\m
 function score(
     conf_model::SimpleInductiveRegressor, atomic::Supervised, fitresult, X, y=nothing
 )
-    ŷ = reformat_mlj_prediction(
-        MMI.predict(atomic, fitresult, MMI.reformat(atomic, X)...)
-    )
+    ŷ = reformat_mlj_prediction(MMI.predict(atomic, fitresult, MMI.reformat(atomic, X)...))
     scores = @.(conf_model.heuristic(y, ŷ))
     if isnothing(y)
         return scores

From dfe58d7a82891ed4fbafaff274b3e3675ade5451 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Sat, 6 Apr 2024 16:10:21 +0200
Subject: [PATCH 08/11] uh

---
 src/conformal_models/inductive/inductive_models.jl | 3 ++-
 src/conformal_models/inductive/regression.jl       | 7 +------
 2 files changed, 3 insertions(+), 7 deletions(-)

diff --git a/src/conformal_models/inductive/inductive_models.jl b/src/conformal_models/inductive/inductive_models.jl
index c3298be..f68f654 100644
--- a/src/conformal_models/inductive/inductive_models.jl
+++ b/src/conformal_models/inductive/inductive_models.jl
@@ -12,9 +12,10 @@ const InductiveModel = Union{
 """
     split_data(conf_model::InductiveModel, indices::Base.OneTo{Int})
 
-Splits the data into a proper training and calibration set.
+Splits the data into a proper training and calibration set for inductive models.
 """
 function split_data(conf_model::InductiveModel, X, y)
+    
     train, calibration = partition(eachindex(y), conf_model.train_ratio)
     Xtrain = selectrows(X, train)
     ytrain = y[train]
diff --git a/src/conformal_models/inductive/regression.jl b/src/conformal_models/inductive/regression.jl
index d75215a..44bc3b7 100755
--- a/src/conformal_models/inductive/regression.jl
+++ b/src/conformal_models/inductive/regression.jl
@@ -38,12 +38,7 @@ function score(
 )
     ŷ = reformat_mlj_prediction(MMI.predict(atomic, fitresult, MMI.reformat(atomic, X)...))
     scores = @.(conf_model.heuristic(y, ŷ))
-    if isnothing(y)
-        return scores
-    else
-        cal_scores = getindex.(Ref(scores), 1:size(scores, 1), y)
-        return cal_scores, scores
-    end
+    return scores, scores
 end
 
 # Prediction

From 255b7c552cf13739def3b88148001fc6b0d8ac35 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Sat, 6 Apr 2024 16:12:33 +0200
Subject: [PATCH 09/11] formatter

---
 src/conformal_models/inductive/inductive_models.jl | 1 -
 1 file changed, 1 deletion(-)

diff --git a/src/conformal_models/inductive/inductive_models.jl b/src/conformal_models/inductive/inductive_models.jl
index f68f654..9d6bffc 100644
--- a/src/conformal_models/inductive/inductive_models.jl
+++ b/src/conformal_models/inductive/inductive_models.jl
@@ -15,7 +15,6 @@ const InductiveModel = Union{
 Splits the data into a proper training and calibration set for inductive models.
 """
 function split_data(conf_model::InductiveModel, X, y)
-    
     train, calibration = partition(eachindex(y), conf_model.train_ratio)
     Xtrain = selectrows(X, train)
     ytrain = y[train]

From 81bd64f873ecb970d87e5a33efa007a34bc2d339 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Sat, 6 Apr 2024 16:34:45 +0200
Subject: [PATCH 10/11] slowly slowly

---
 src/conformal_models/inductive/inductive_models.jl | 14 +++++++++++---
 src/conformal_models/inductive/regression.jl       | 13 +++++++++++--
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/src/conformal_models/inductive/inductive_models.jl b/src/conformal_models/inductive/inductive_models.jl
index 9d6bffc..c05834f 100644
--- a/src/conformal_models/inductive/inductive_models.jl
+++ b/src/conformal_models/inductive/inductive_models.jl
@@ -33,6 +33,16 @@ function score(conf_model::InductiveModel, fitresult, X, y=nothing)
     return score(conf_model, conf_model.model, fitresult, X, y)
 end
 
+"""
+    fit_atomic(conf_model::InductiveModel, verbosity, X, y)
+
+Fits the atomic model for the [`InductiveModel`](@ref). In the case of inductive models, the atomic model is fit once on the proper training data.
+"""
+function fit_atomic(conf_model::InductiveModel, verbosity, X, y)
+    fitresult, cache, report = MMI.fit(conf_model.model, verbosity, MMI.reformat(conf_model.model, X, y)...)
+    return fitresult, cache, report
+end
+
 @doc raw"""
     MMI.fit(conf_model::InductiveModel, verbosity, X, y)
 
@@ -44,9 +54,7 @@ function MMI.fit(conf_model::InductiveModel, verbosity, X, y)
     Xtrain, ytrain, Xcal, ycal = split_data(conf_model, X, y)
 
     # Training:
-    fitresult, cache, report = MMI.fit(
-        conf_model.model, verbosity, MMI.reformat(conf_model.model, Xtrain, ytrain)...
-    )
+    fitresult, cache, report = fit_atomic(conf_model, verbosity, Xtrain, ytrain)
 
     # Nonconformity Scores:
     cal_scores, scores = score(conf_model, fitresult, Xcal, ycal)
diff --git a/src/conformal_models/inductive/regression.jl b/src/conformal_models/inductive/regression.jl
index 44bc3b7..008f3c7 100755
--- a/src/conformal_models/inductive/regression.jl
+++ b/src/conformal_models/inductive/regression.jl
@@ -4,7 +4,7 @@ using MLJLinearModels: MLJLinearModels
 mutable struct SimpleInductiveRegressor{Model<:Supervised} <: ConformalInterval
     model::Model
     coverage::AbstractFloat
-    scores::Union{Nothing,AbstractArray}
+    scores::Union{Nothing,Dict{Any,Any}}
     heuristic::Function
     parallelizer::Union{Nothing,AbstractParallelizer}
     train_ratio::AbstractFloat
@@ -38,7 +38,11 @@ function score(
 )
     ŷ = reformat_mlj_prediction(MMI.predict(atomic, fitresult, MMI.reformat(atomic, X)...))
     scores = @.(conf_model.heuristic(y, ŷ))
-    return scores, scores
+    if isnothing(y)
+        return scores
+    else
+        return scores, scores
+    end
 end
 
 # Prediction
@@ -91,6 +95,11 @@ function ConformalQuantileRegressor(
     )
 end
 
+# function fit_atomic(conf_model::ConformalQuantileRegressor, verbosity, X, y)
+#     fitresult, cache, report = MMI.fit(conf_model.model, verbosity, MMI.reformat(conf_model.model, X, y)...)
+#     return fitresult, cache, report
+# end
+
 @doc raw"""
     MMI.fit(conf_model::ConformalQuantileRegressor, verbosity, X, y)
 

From 8bc0d800d41b17ba4e337f6759013c4e9bf89f89 Mon Sep 17 00:00:00 2001
From: pat-alt <altmeyerpat@gmail.com>
Date: Sat, 6 Apr 2024 16:37:05 +0200
Subject: [PATCH 11/11] formatter

---
 src/conformal_models/inductive/inductive_models.jl | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/src/conformal_models/inductive/inductive_models.jl b/src/conformal_models/inductive/inductive_models.jl
index c05834f..a89f8ba 100644
--- a/src/conformal_models/inductive/inductive_models.jl
+++ b/src/conformal_models/inductive/inductive_models.jl
@@ -39,7 +39,9 @@ end
 Fits the atomic model for the [`InductiveModel`](@ref). In the case of inductive models, the atomic model is fit once on the proper training data.
 """
 function fit_atomic(conf_model::InductiveModel, verbosity, X, y)
-    fitresult, cache, report = MMI.fit(conf_model.model, verbosity, MMI.reformat(conf_model.model, X, y)...)
+    fitresult, cache, report = MMI.fit(
+        conf_model.model, verbosity, MMI.reformat(conf_model.model, X, y)...
+    )
     return fitresult, cache, report
 end