Mlj.jl: Logistic Regression

Created on 22 Oct 2019 · 6Comments · Source: alan-turing-institute/MLJ.jl

Could someone confirm whether MLJ has Logistic Regression model?

Thank you!

Source

Sinansi

Most helpful comment

Use models() to list all models. See docs for refining your search.

julia> models()
95-element Array{NamedTuple,1}:
 (name = ARDRegressor, package_name = ScikitLearn, ... )             
 (name = AdaBoostClassifier, package_name = ScikitLearn, ... )       
 (name = AdaBoostRegressor, package_name = ScikitLearn, ... )        
 (name = BaggingClassifier, package_name = ScikitLearn, ... )        
 (name = BaggingRegressor, package_name = ScikitLearn, ... )         
 (name = BayesianRidgeRegressor, package_name = ScikitLearn, ... )   
 (name = BernoulliNBClassifier, package_name = ScikitLearn, ... )    
 (name = ComplementNBClassifier, package_name = ScikitLearn, ... )   
 (name = ConstantClassifier, package_name = MLJModels, ... )         
 (name = ConstantRegressor, package_name = MLJModels, ... )          
 ⋮                                                                   
 (name = Standardizer, package_name = MLJModels, ... )               
 (name = StaticTransformer, package_name = MLJModels, ... )          
 (name = TheilSenRegressor, package_name = ScikitLearn, ... )        
 (name = UnivariateBoxCoxTransformer, package_name = MLJModels, ... )
 (name = UnivariateDiscretizer, package_name = MLJModels, ... )      
 (name = UnivariateStandardizer, package_name = MLJModels, ... )     
 (name = XGBoostClassifier, package_name = XGBoost, ... )            
 (name = XGBoostCount, package_name = XGBoost, ... )                 
 (name = XGBoostRegressor, package_name = XGBoost, ... )

ablaom on 23 Oct 2019

❤1 👍1

All 6 comments

Yes via Sklearn and via MLJLinearModels.jl

vollmersj on 22 Oct 2019

👍1

Thank you!

Sinansi on 22 Oct 2019

julia> using MLJ
[ Info: Recompiling stale cache file /Users/anthony/.julia/compiled/v1.1/MLJ/rAU56.ji for MLJ [add582a8-e3ab-11e8-2d5e-e98b27df1bc7]
[ Info: Model metadata loaded from registry. 

julia> model = @load LogisticClassifier
LogisticClassifier(penalty = "l2",
                   dual = false,
                   tol = 0.0001,
                   C = 1.0,
                   fit_intercept = true,
                   intercept_scaling = 1.0,
                   class_weight = nothing,
                   random_state = nothing,
                   solver = "lbfgs",
                   max_iter = 100,
                   multi_class = "auto",
                   verbose = 0,
                   warm_start = false,
                   n_jobs = nothing,
                   l1_ratio = nothing,) @ 3…09

ablaom on 23 Oct 2019

❤1 👍1

julia> info("LogisticClassifier")
Logistic regression classifier.
→ based on [ScikitLearn](https://github.com/cstjean/ScikitLearn.jl).
→ do `@load LogisticClassifier pkg="ScikitLearn"` to use the model.
→ do `?LogisticClassifier` for documentation.
(name = "LogisticClassifier",
 package_name = "ScikitLearn",
 is_supervised = true,
 docstring = "Logistic regression classifier.\n→ based on [ScikitLearn](https://github.com/cstjean/ScikitLearn.jl).\n→ do `@load LogisticClassifier pkg=\"ScikitLearn\"` to use the model.\n→ do `?LogisticClassifier` for documentation.",
 hyperparameter_types = ["String", "Bool", "Float64", "Float64", "Bool", "Float64", "Any", "Any", "String", "Int64", "String", "Int64", "Bool", "Union{Nothing, Int64}", "Union{Nothing, Float64}"],
 hyperparameters = Symbol[:penalty, :dual, :tol, :C, :fit_intercept, :intercept_scaling, :class_weight, :random_state, :solver, :max_iter, :multi_class, :verbose, :warm_start, :n_jobs, :l1_ratio],
 implemented_methods = Symbol[:fit, :predict, :fitted_params],
 is_pure_julia = false,
 is_wrapper = false,
 load_path = "MLJModels.ScikitLearn_.LogisticClassifier",
 package_license = "BSD",
 package_url = "https://github.com/cstjean/ScikitLearn.jl",
 package_uuid = "3646fa90-6ef7-5e7e-9f22-8aca16db6324",
 prediction_type = :probabilistic,
 supports_weights = false,
 input_scitype = ScientificTypes.Table{_s13} where _s13<:(AbstractArray{_s12,1} where _s12<:Continuous),
 target_scitype = AbstractArray{_s443,1} where _s443<:Finite,)

ablaom on 23 Oct 2019

❤1 👍1

Use models() to list all models. See docs for refining your search.

julia> models()
95-element Array{NamedTuple,1}:
 (name = ARDRegressor, package_name = ScikitLearn, ... )             
 (name = AdaBoostClassifier, package_name = ScikitLearn, ... )       
 (name = AdaBoostRegressor, package_name = ScikitLearn, ... )        
 (name = BaggingClassifier, package_name = ScikitLearn, ... )        
 (name = BaggingRegressor, package_name = ScikitLearn, ... )         
 (name = BayesianRidgeRegressor, package_name = ScikitLearn, ... )   
 (name = BernoulliNBClassifier, package_name = ScikitLearn, ... )    
 (name = ComplementNBClassifier, package_name = ScikitLearn, ... )   
 (name = ConstantClassifier, package_name = MLJModels, ... )         
 (name = ConstantRegressor, package_name = MLJModels, ... )          
 ⋮                                                                   
 (name = Standardizer, package_name = MLJModels, ... )               
 (name = StaticTransformer, package_name = MLJModels, ... )          
 (name = TheilSenRegressor, package_name = ScikitLearn, ... )        
 (name = UnivariateBoxCoxTransformer, package_name = MLJModels, ... )
 (name = UnivariateDiscretizer, package_name = MLJModels, ... )      
 (name = UnivariateStandardizer, package_name = MLJModels, ... )     
 (name = XGBoostClassifier, package_name = XGBoost, ... )            
 (name = XGBoostCount, package_name = XGBoost, ... )                 
 (name = XGBoostRegressor, package_name = XGBoost, ... )

ablaom on 23 Oct 2019

❤1 👍1

Thanks alot Ablaom. I am much appreciated. Your reply have saved me alot of hours trying to figure things out. I am new to Julia, but thanks to developers like you who are trying to help new comers get introduced to Julia. Great work!

Sinansi on 23 Oct 2019

Was this page helpful?

0 / 5 - 0 ratings