# This file was generated by PredictMD version 0.34.21
# For help, please visit https://predictmd.net

using PredictMDExtra
PredictMDExtra.import_all()

using PredictMD
PredictMD.import_all()



### Begin project-specific settings

DIRECTORY_CONTAINING_THIS_FILE = @__DIR__
PROJECT_DIRECTORY = dirname(
    joinpath(splitpath(DIRECTORY_CONTAINING_THIS_FILE)...)
    )
PROJECT_OUTPUT_DIRECTORY = joinpath(
    PROJECT_DIRECTORY,
    "output",
    )
mkpath(PROJECT_OUTPUT_DIRECTORY)
mkpath(joinpath(PROJECT_OUTPUT_DIRECTORY, "data"))
mkpath(joinpath(PROJECT_OUTPUT_DIRECTORY, "models"))
mkpath(joinpath(PROJECT_OUTPUT_DIRECTORY, "plots"))



### End project-specific settings

### Begin Knet neural network classifier code

Random.seed!(999)

trainingandtuning_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "trainingandtuning_features_df.csv",
    )
trainingandtuning_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "trainingandtuning_labels_df.csv",
    )
testing_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "testing_features_df.csv",
    )
testing_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "testing_labels_df.csv",
    )
training_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "training_features_df.csv",
    )
training_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "training_labels_df.csv",
    )
tuning_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "tuning_features_df.csv",
    )
tuning_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "tuning_labels_df.csv",
    )
trainingandtuning_features_df = DataFrames.DataFrame(
    FileIO.load(
        trainingandtuning_features_df_filename;
        type_detect_rows = 100,
        )
    )
trainingandtuning_labels_df = DataFrames.DataFrame(
    FileIO.load(
        trainingandtuning_labels_df_filename;
        type_detect_rows = 100,
        )
    )
testing_features_df = DataFrames.DataFrame(
    FileIO.load(
        testing_features_df_filename;
        type_detect_rows = 100,
        )
    )
testing_labels_df = DataFrames.DataFrame(
    FileIO.load(
        testing_labels_df_filename;
        type_detect_rows = 100,
        )
    )
training_features_df = DataFrames.DataFrame(
    FileIO.load(
        training_features_df_filename;
        type_detect_rows = 100,
        )
    )
training_labels_df = DataFrames.DataFrame(
    FileIO.load(
        training_labels_df_filename;
        type_detect_rows = 100,
        )
    )
tuning_features_df = DataFrames.DataFrame(
    FileIO.load(
        tuning_features_df_filename;
        type_detect_rows = 100,
        )
    )
tuning_labels_df = DataFrames.DataFrame(
    FileIO.load(
        tuning_labels_df_filename;
        type_detect_rows = 100,
        )
    )

smoted_training_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "smoted_training_features_df.csv",
    )
smoted_training_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "smoted_training_labels_df.csv",
    )
smoted_training_features_df = DataFrames.DataFrame(
    FileIO.load(
        smoted_training_features_df_filename;
        type_detect_rows = 100,
        )
    )
smoted_training_labels_df = DataFrames.DataFrame(
    FileIO.load(
        smoted_training_labels_df_filename;
        type_detect_rows = 100,
        )
    )

categorical_feature_names_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "categorical_feature_names.jld2",
    )
continuous_feature_names_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "data",
    "continuous_feature_names.jld2",
    )
categorical_feature_names = FileIO.load(
    categorical_feature_names_filename,
    "categorical_feature_names",
    )
continuous_feature_names = FileIO.load(
    continuous_feature_names_filename,
    "continuous_feature_names",
    )
feature_names = vcat(categorical_feature_names, continuous_feature_names)

single_label_name = :Class
negative_class = "benign"
positive_class = "malignant"
single_label_levels = [negative_class, positive_class]

categorical_label_names = Symbol[single_label_name]
continuous_label_names = Symbol[]
label_names = vcat(categorical_label_names, continuous_label_names)

knet_mlp_predict_function_source = """
function knetmlp_predict(
        w,
        x0::AbstractArray;
        probabilities::Bool = true,
        )
    x1 = Knet.relu.( w[1]*x0 .+ w[2] )
    x2 = Knet.relu.( w[3]*x1 .+ w[4] )
    x3 = w[5]*x2 .+ w[6]
    unnormalizedlogprobs = x3
    if probabilities
        normalizedlogprobs = Knet.logp(unnormalizedlogprobs; dims = 1)
        normalizedprobs = exp.(normalizedlogprobs)
        return normalizedprobs
    else
        return unnormalizedlogprobs
    end
end
"""

knet_mlp_loss_function_source = """
function knetmlp_loss(
        predict::Function,
        modelweights,
        x::AbstractArray,
        ytrue::AbstractArray;
        L1::Real = Float64(0),
        L2::Real = Float64(0),
        )
    loss = Knet.nll(
        predict(
            modelweights,
            x;
            probabilities = false,
            ),
        ytrue;
        dims = 1,
        )
    if L1 != 0
        loss += L1 * sum(sum(abs, w_i) for w_i in modelweights[1:2:end])
    end
    if L2 != 0
        loss += L2 * sum(sum(abs2, w_i) for w_i in modelweights[1:2:end])
    end
    return loss
end
"""

feature_contrasts = PredictMD.generate_feature_contrasts(
    smoted_training_features_df,
    feature_names,
    )

knetmlp_modelweights = Any[
    Float64.(
        0.1f0*randn(Float64,64,feature_contrasts.num_array_columns_without_intercept)
        ),
    Float64.(
        fill(Float64(0),64,1)
        ),
    Float64.(
        0.1f0*randn(Float64,32,64)
        ),
    Float64.(
        fill(Float64(0),32,1)
        ),
    Float64.(
        0.1f0*randn(Float64,2,32)
        ),
    Float64.(
        fill(Float64(0),2,1)
        ),
    ]

knetmlp_losshyperparameters = Dict()
knetmlp_losshyperparameters[:L1] = Float64(0.0)
knetmlp_losshyperparameters[:L2] = Float64(0.0)

knetmlp_optimizationalgorithm = :Momentum
knetmlp_optimizerhyperparameters = Dict()
knetmlp_minibatchsize = 48

knet_mlp_classifier =
    PredictMD.single_labelmulticlassdataframeknetclassifier(
        feature_names,
        single_label_name,
        single_label_levels;
        package = :Knet,
        name = "Knet MLP",
        predict_function_source = knet_mlp_predict_function_source,
        loss_function_source = knet_mlp_loss_function_source,
        losshyperparameters = knetmlp_losshyperparameters,
        optimizationalgorithm = knetmlp_optimizationalgorithm,
        optimizerhyperparameters = knetmlp_optimizerhyperparameters,
        minibatchsize = knetmlp_minibatchsize,
        modelweights = knetmlp_modelweights,
        printlosseverynepochs = 1,
        maxepochs = 50,
        feature_contrasts = feature_contrasts,
        )

PredictMD.parse_functions!(knet_mlp_classifier)

PredictMD.fit!(
    knet_mlp_classifier,
    smoted_training_features_df,
    smoted_training_labels_df,
    tuning_features_df,
    tuning_labels_df,
    )

PredictMD.set_max_epochs!(knet_mlp_classifier, 100)

PredictMD.fit!(
    knet_mlp_classifier,
    smoted_training_features_df,
    smoted_training_labels_df,
    tuning_features_df,
    tuning_labels_df,
    )

knet_learningcurve_lossvsepoch = PredictMD.plotlearningcurve(
    knet_mlp_classifier,
    :loss_vs_epoch;
    );



display(knet_learningcurve_lossvsepoch)
PredictMD.save_plot(
    joinpath(
        PROJECT_OUTPUT_DIRECTORY,
        "plots",
        "knet_learningcurve_lossvsepoch.pdf",
        ),
    knet_learningcurve_lossvsepoch,
    )

knet_learningcurve_lossvsepoch_skip10epochs = PredictMD.plotlearningcurve(
    knet_mlp_classifier,
    :loss_vs_epoch;
    startat = 10,
    endat = :end,
    );



display(knet_learningcurve_lossvsepoch_skip10epochs)
PredictMD.save_plot(
    joinpath(
        PROJECT_OUTPUT_DIRECTORY,
        "plots",
        "knet_learningcurve_lossvsepoch_skip10epochs.pdf",
        ),
    knet_learningcurve_lossvsepoch_skip10epochs,
    )

knet_learningcurve_lossvsiteration = PredictMD.plotlearningcurve(
    knet_mlp_classifier,
    :loss_vs_iteration;
    window = 50,
    sampleevery = 10,
    );



display(knet_learningcurve_lossvsiteration)
PredictMD.save_plot(
    joinpath(
        PROJECT_OUTPUT_DIRECTORY,
        "plots",
        "knet_learningcurve_lossvsiteration.pdf",
        ),
    knet_learningcurve_lossvsiteration,
    )

knet_learningcurve_lossvsiteration_skip100iterations =
    PredictMD.plotlearningcurve(
        knet_mlp_classifier,
        :loss_vs_iteration;
        window = 50,
        sampleevery = 10,
        startat = 100,
        endat = :end,
        );



display(knet_learningcurve_lossvsiteration_skip100iterations)
PredictMD.save_plot(
    joinpath(
        PROJECT_OUTPUT_DIRECTORY,
        "plots",
        "knet_learningcurve_lossvsiteration_skip100iterations.pdf",
        ),
    knet_learningcurve_lossvsiteration_skip100iterations,
    )

knet_mlp_classifier_hist_training =
    PredictMD.plotsinglelabelbinaryclassifierhistogram(
        knet_mlp_classifier,
        smoted_training_features_df,
        smoted_training_labels_df,
        single_label_name,
        single_label_levels,
        );



display(knet_mlp_classifier_hist_training)
PredictMD.save_plot(
    joinpath(
        PROJECT_OUTPUT_DIRECTORY,
        "plots",
        "knet_mlp_classifier_hist_training.pdf",
        ),
    knet_mlp_classifier_hist_training,
    )

knet_mlp_classifier_hist_testing =
        PredictMD.plotsinglelabelbinaryclassifierhistogram(
        knet_mlp_classifier,
        testing_features_df,
        testing_labels_df,
        single_label_name,
        single_label_levels,
        );



display(knet_mlp_classifier_hist_testing)
PredictMD.save_plot(
    joinpath(
        PROJECT_OUTPUT_DIRECTORY,
        "plots",
        "knet_mlp_classifier_hist_testing.pdf",
        ),
    knet_mlp_classifier_hist_testing,
    )

show(
    PredictMD.singlelabelbinaryclassificationmetrics(
        knet_mlp_classifier,
        smoted_training_features_df,
        smoted_training_labels_df,
        single_label_name,
        positive_class;
        sensitivity = 0.95,
        );
    allrows = true,
    allcols = true,
    splitcols = false,
    )

show(
    PredictMD.singlelabelbinaryclassificationmetrics(
        knet_mlp_classifier,
        testing_features_df,
        testing_labels_df,
        single_label_name,
        positive_class;
        sensitivity = 0.95,
        );
    allrows = true,
    allcols = true,
    splitcols = false,
    )

knet_mlp_classifier_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "models",
    "knet_mlp_classifier.jld2",
    )

PredictMD.save_model(knet_mlp_classifier_filename, knet_mlp_classifier)



### End Knet neural network classifier code



# This file was generated by PredictMD version 0.34.21
# For help, please visit https://predictmd.net

This page was generated using Literate.jl.