treatment, test included

aclai-lab · Feb 24, 2025 · 8c357f7 · 8c357f7
1 parent 8267065
commit 8c357f7
Show file tree

Hide file tree

Showing 7 changed files with 1,205 additions and 296 deletions.
diff --git a/Project.toml b/Project.toml
@@ -1,39 +1,29 @@
 name = "SoleFeatures"
 uuid = "3ceb4e54-d968-4e97-8c18-2deeb0d429fb"
 authors = ["Patrik Cavina", "Federico Manzella", "Giovanni Pagliarini"]
-version = "0.2.0"
+version = "0.3.0"
 
 [deps]
 Catch22 = "acdeb78f-3d39-4310-8fdf-6d75c17c6d5a"
+CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 HypothesisTests = "09f84164-cd44-5f33-b23f-e6b0d136a0d5"
 IterTools = "c8e1da08-722c-5040-9ed9-7db0dc04731e"
-LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 MLBase = "f0e99cf1-93fa-52ec-9ecc-5026115318e0"
-MultiData = "8cc5100c-b3d1-4f82-90cb-0ea93d317aba"
 OrderedCollections = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
-PyCall = "438e738f-606a-5dbb-bf0a-cddfbfd45ab0"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-Reexport = "189a3867-3050-52da-a836-e630ba90ab69"
-Revise = "295af30f-e4ad-537b-8983-00126c2a3abe"
 SoleBase = "4475fa32-7023-44a0-aa70-4813b230e492"
-SoleData = "123f1ae1-6307-4526-ab5b-aab3a92a2b8c"
-SoleLogics = "b002da8f-3cb3-4d91-bbe3-2953433912b5"
-Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 
 [compat]
 Catch22 = "0.7"
+CategoricalArrays = "0.10"
 DataFrames = "1"
-HypothesisTests = "0.10 - 0.11"
+HypothesisTests = "0.11"
 IterTools = "1"
-MultiData = "0 - 0.1"
 OrderedCollections = "1"
-PyCall = "1"
 Random = "1"
-Reexport = "1"
-Revise = "3"
-SoleData = "0.16"
+SoleBase = "0.13"
 StatsBase = "0.30 - 0.34"
 julia = "1"
 

diff --git a/src/SoleFeatures.jl b/src/SoleFeatures.jl
@@ -1,96 +1,111 @@
-__precompile__()
+# __precompile__()
 module SoleFeatures
 
-using StatsBase
-using MultiData
-using SoleData
-using Reexport
+using SoleBase
+using StatsBase, Catch22
+using CategoricalArrays, DataFrames
 using Random
-using LinearAlgebra
-using HypothesisTests
-using IterTools
-using PyCall
-using MLBase
-# using Pkg
 
-# abstracts
-export AbstractFeaturesSelector
-export AbstractFilterBased
-export AbstractWrapperBased
-export AbstractEmbeddedBased
-export AbstractLimiter
-# structs
-export VarianceThreshold
-export VarianceRanking
-export RandomRanking
-export StatisticalAtLeastOnce
-export StatisticalMajority
-export PearsonCorRanking
-export Chi2Ranking
-export Chi2Threshold
-export MutualInformationClassifRanking
-export CompoundStatisticalAtLeastOnce
-export CompoundStatisticalMajority
-export CorrelationFilter
-# main functions
-export apply, buildbitmask, transform, transform!
-# utils
-export bm2var
+include("utils/features_set.jl")
+export mode_5, mode_10, embedding_dist, acf_timescale, acf_first_min, ami2, trev, outlier_timing_pos
+export outlier_timing_neg, whiten_timescale, forecast_error, ami_timescale, high_fluctuation, stretch_decreasing
+export stretch_high, entropy_pairs, rs_range, dfa, low_freq_power, centroid_freq, transition_variance, periodicity
+export base_set, catch9, catch22_set, complete_set
 
-@reexport using DataFrames
+include("dataset/dataset_structs.jl")
+export Feature
 
-const req_py_pkgs = ["scipy", "scikit-learn", "skfeature"]
-const fs = PyNULL()
-const construct_w = PyNULL()
-const lap_score = PyNULL()
-const fisher_score = PyNULL()
-function __init__()
+include("dataset/prepare_dataset.jl")
+export feature_selection_preprocess
 
-    pypkgs = getindex.(PyCall.Conda.parseconda(`list`, PyCall.Conda.ROOTENV), "name")
-    needinstall = !all(p -> in(p, pypkgs), req_py_pkgs)
+# using MultiData
+# using SoleData
+# using Reexport
+# using LinearAlgebra
+# using HypothesisTests
+# using IterTools
+# using PyCall
+# using MLBase
+# # using Pkg
 
-    if (needinstall)
-        PyCall.Conda.pip_interop(true, PyCall.Conda.ROOTENV)
-        PyCall.Conda.add("scipy")
-        PyCall.Conda.add("scikit-learn")
-        PyCall.Conda.pip(
-            "install",
-            "git+https://github.com/jundongl/scikit-feature.git#egg=skfeature",
-            PyCall.Conda.ROOTENV
-        )
-    end
+# # abstracts
+# export AbstractFeaturesSelector
+# export AbstractFilterBased
+# export AbstractWrapperBased
+# export AbstractEmbeddedBased
+# export AbstractLimiter
+# # structs
+# export VarianceThreshold
+# export VarianceRanking
+# export RandomRanking
+# export StatisticalAtLeastOnce
+# export StatisticalMajority
+# export PearsonCorRanking
+# export Chi2Ranking
+# export Chi2Threshold
+# export MutualInformationClassifRanking
+# export CompoundStatisticalAtLeastOnce
+# export CompoundStatisticalMajority
+# export CorrelationFilter
+# # main functions
+# export apply, buildbitmask, transform, transform!
+# # utils
+# export bm2var
 
-    copy!(fs, pyimport_conda("sklearn.feature_selection", "scikit-learn"))
-    copy!(construct_w, pyimport_conda("skfeature.utility.construct_W", "skfeature"))
-    copy!(lap_score, pyimport_conda(
-        "skfeature.function.similarity_based.lap_score",
-        "skfeature"
-    ))
-    copy!(fisher_score, pyimport_conda(
-        "skfeature.function.similarity_based.fisher_score",
-        "skfeature"
-    ))
-end
+# @reexport using DataFrames
 
-include("interface.jl")
-include("core.jl")
-# Utils
-include("utils/utils.jl")
-# Filters
-include("filters/limiter.jl")
-include("filters/interface.jl")
-include("filters/univariate/randomfilter.jl")
-include("filters/univariate/statisticalfilter.jl")
-include("filters/univariate/variancefilter.jl")
-include("filters/univariate/chi2filter.jl")
-include("filters/univariate/pearsoncorfilter.jl")
-include("filters/univariate/mutualinformationclassif.jl")
-include("filters/univariate/suplapscorefiler.jl")
-include("filters/univariate/fisherscorefilter.jl")
-include("filters/univariate/utils.jl")
-include("filters/multivariate/correlationfilter.jl")
-# Experimental
-include("experimental/Experimental.jl")
-import .Experimental
+# const req_py_pkgs = ["scipy", "scikit-learn", "skfeature"]
+# const fs = PyNULL()
+# const construct_w = PyNULL()
+# const lap_score = PyNULL()
+# const fisher_score = PyNULL()
+# function __init__()
+
+#     pypkgs = getindex.(PyCall.Conda.parseconda(`list`, PyCall.Conda.ROOTENV), "name")
+#     needinstall = !all(p -> in(p, pypkgs), req_py_pkgs)
+
+#     if (needinstall)
+#         PyCall.Conda.pip_interop(true, PyCall.Conda.ROOTENV)
+#         PyCall.Conda.add("scipy")
+#         PyCall.Conda.add("scikit-learn")
+#         PyCall.Conda.pip(
+#             "install",
+#             "git+https://github.com/jundongl/scikit-feature.git#egg=skfeature",
+#             PyCall.Conda.ROOTENV
+#         )
+#     end
+
+#     copy!(fs, pyimport_conda("sklearn.feature_selection", "scikit-learn"))
+#     copy!(construct_w, pyimport_conda("skfeature.utility.construct_W", "skfeature"))
+#     copy!(lap_score, pyimport_conda(
+#         "skfeature.function.similarity_based.lap_score",
+#         "skfeature"
+#     ))
+#     copy!(fisher_score, pyimport_conda(
+#         "skfeature.function.similarity_based.fisher_score",
+#         "skfeature"
+#     ))
+# end
+
+# include("interface.jl")
+# include("core.jl")
+# # Utils
+# include("utils/utils.jl")
+# # Filters
+# include("filters/limiter.jl")
+# include("filters/interface.jl")
+# include("filters/univariate/randomfilter.jl")
+# include("filters/univariate/statisticalfilter.jl")
+# include("filters/univariate/variancefilter.jl")
+# include("filters/univariate/chi2filter.jl")
+# include("filters/univariate/pearsoncorfilter.jl")
+# include("filters/univariate/mutualinformationclassif.jl")
+# include("filters/univariate/suplapscorefiler.jl")
+# include("filters/univariate/fisherscorefilter.jl")
+# include("filters/univariate/utils.jl")
+# include("filters/multivariate/correlationfilter.jl")
+# # Experimental
+# include("experimental/Experimental.jl")
+# import .Experimental
 
 end # module