##### Beginning of file

# This file was generated by PredictMD version 0.19.0
# For help, please visit https://www.predictmd.net

import PredictMD

### Begin project-specific settings

PredictMD.require_julia_version("v0.6")

PredictMD.require_predictmd_version("0.19.0")

# PredictMD.require_predictmd_version("0.19.0", "0.20.0-")

PROJECT_OUTPUT_DIRECTORY = PredictMD.project_directory(
    homedir(),
    "Desktop",
    "breast_cancer_biopsy_example",
    )

### End project-specific settings

### Begin logistic classifier code

import CSV
import Compat
import DataFrames
import FileIO
import JLD2

srand(999)

trainingandvalidation_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "trainingandvalidation_features_df.csv",
    )
trainingandvalidation_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "trainingandvalidation_labels_df.csv",
    )
testing_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "testing_features_df.csv",
    )
testing_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "testing_labels_df.csv",
    )
training_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "training_features_df.csv",
    )
training_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "training_labels_df.csv",
    )
validation_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "validation_features_df.csv",
    )
validation_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "validation_labels_df.csv",
    )
trainingandvalidation_features_df = CSV.read(
    trainingandvalidation_features_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
trainingandvalidation_labels_df = CSV.read(
    trainingandvalidation_labels_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
testing_features_df = CSV.read(
    testing_features_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
testing_labels_df = CSV.read(
    testing_labels_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
training_features_df = CSV.read(
    training_features_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
training_labels_df = CSV.read(
    training_labels_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
validation_features_df = CSV.read(
    validation_features_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
validation_labels_df = CSV.read(
    validation_labels_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )

smoted_training_features_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "smoted_training_features_df.csv",
    )
smoted_training_labels_df_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "smoted_training_labels_df.csv",
    )
smoted_training_features_df = CSV.read(
    smoted_training_features_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )
smoted_training_labels_df = CSV.read(
    smoted_training_labels_df_filename,
    DataFrames.DataFrame;
    rows_for_type_detect = 100,
    )

categorical_feature_names_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "categorical_feature_names.jld2",
    )
continuous_feature_names_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "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)

feature_contrasts = PredictMD.generate_feature_contrasts(
    smoted_training_features_df,
    feature_names,
    )

logistic_classifier =
        PredictMD.singlelabelbinaryclassdataframelogisticclassifier(
        feature_names,
        single_label_name,
        single_label_levels;
        package = :GLM,
        intercept = true,
        interactions = 1,
        name = "Logistic regression",
        )

PredictMD.fit!(
    logistic_classifier,
    smoted_training_features_df,
    smoted_training_labels_df,
    )

PredictMD.get_underlying(logistic_classifier)

logistic_hist_training =
        PredictMD.plotsinglelabelbinaryclassifierhistogram(
        logistic_classifier,
        smoted_training_features_df,
        smoted_training_labels_df,
        single_label_name,
        single_label_levels,
        )
PredictMD.open_plot(logistic_hist_training)

logistic_hist_testing =
    PredictMD.plotsinglelabelbinaryclassifierhistogram(
        logistic_classifier,
        testing_features_df,
        testing_labels_df,
        single_label_name,
        single_label_levels,
        )
PredictMD.open_plot(logistic_hist_testing)

PredictMD.singlelabelbinaryclassificationmetrics(
    logistic_classifier,
    smoted_training_features_df,
    smoted_training_labels_df,
    single_label_name,
    positive_class;
    sensitivity = 0.95,
    )

PredictMD.singlelabelbinaryclassificationmetrics(
    logistic_classifier,
    testing_features_df,
    testing_labels_df,
    single_label_name,
    positive_class;
    sensitivity = 0.95,
    )

logistic_calibration_curve =
    PredictMD.plot_probability_calibration_curve(
        logistic_classifier,
        smoted_training_features_df,
        smoted_training_labels_df,
        single_label_name,
        positive_class;
        window = 0.2,
        )
PredictMD.open_plot(logistic_calibration_curve)

PredictMD.probability_calibration_metrics(
    logistic_classifier,
    testing_features_df,
    testing_labels_df,
    single_label_name,
    positive_class;
    window = 0.1,
    )

logistic_cutoffs, logistic_risk_group_prevalences =
    PredictMD.risk_score_cutoff_values(
        logistic_classifier,
        testing_features_df,
        testing_labels_df,
        single_label_name,
        positive_class;
        average_function = mean,
        )
Compat.@info(
    string(
        "Low risk: 0 to $(logistic_cutoffs[1]).",
        " Medium risk: $(logistic_cutoffs[1]) to $(logistic_cutoffs[2]).",
        " High risk: $(logistic_cutoffs[2]) to 1.",
        )
    )
Compat.@info(logistic_risk_group_prevalences)
logistic_cutoffs, logistic_risk_group_prevalences =
    PredictMD.risk_score_cutoff_values(
        logistic_classifier,
        testing_features_df,
        testing_labels_df,
        single_label_name,
        positive_class;
        average_function = median,
        )
Compat.@info(
    string(
        "Low risk: 0 to $(logistic_cutoffs[1]).",
        " Medium risk: $(logistic_cutoffs[1]) to $(logistic_cutoffs[2]).",
        " High risk: $(logistic_cutoffs[2]) to 1.",
        )
    )
Compat.@info(logistic_risk_group_prevalences)

logistic_classifier_filename = joinpath(
    PROJECT_OUTPUT_DIRECTORY,
    "logistic_classifier.jld2",
    )

PredictMD.save_model(logistic_classifier_filename, logistic_classifier)

### End logistic classifier code

##### End of file

Info: Starting to train GLM model.
Info: Finished training GLM model.
Info: Low risk: 0 to 0.05857493355870247. Medium risk: 0.05857493355870247 to 0.9342752695083618. High risk: 0.9342752695083618 to 1.
Info: 3×3 DataFrames.DataFrame
│ Row │ Risk_group  │ Arithmetic_mean │ Median │
├─────┼─────────────┼─────────────────┼────────┤
│ 1   │ Low risk    │ 0.0             │ 0.0    │
│ 2   │ Medium risk │ 0.473684        │ 0.0    │
│ 3   │ High risk   │ 0.943396        │ 1.0    │
Info: Low risk: 0 to 0.0027055598329752684. Medium risk: 0.0027055598329752684 to 0.9998404383659363. High risk: 0.9998404383659363 to 1.
Info: 3×3 DataFrames.DataFrame
│ Row │ Risk_group  │ Arithmetic_mean │ Median │
├─────┼─────────────┼─────────────────┼────────┤
│ 1   │ Low risk    │ 0.0             │ 0.0    │
│ 2   │ Medium risk │ 0.326087        │ 0.0    │
│ 3   │ High risk   │ 1.0             │ 1.0    │
Info: Attempting to save model...
Info: Saved model to file "/tmp/tmpxV7LRJ/PREDICTMDTEMPDIRECTORY/logistic_classifier.jld2"

This page was generated using Literate.jl.