##### 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 random forest 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,
)
random_forest_classifier =
PredictMD.single_labelmulticlassdataframerandomforestclassifier(
feature_names,
single_label_name,
single_label_levels;
nsubfeatures = 4,
ntrees = 200,
package = :DecisionTree,
name = "Random forest",
feature_contrasts = feature_contrasts,
)
PredictMD.fit!(
random_forest_classifier,
smoted_training_features_df,
smoted_training_labels_df,
)
random_forest_classifier_hist_training =
PredictMD.plotsinglelabelbinaryclassifierhistogram(
random_forest_classifier,
smoted_training_features_df,
smoted_training_labels_df,
single_label_name,
single_label_levels,
)
PredictMD.open_plot(random_forest_classifier_hist_training)
random_forest_classifier_hist_testing =
PredictMD.plotsinglelabelbinaryclassifierhistogram(
random_forest_classifier,
testing_features_df,
testing_labels_df,
single_label_name,
single_label_levels,
)
PredictMD.open_plot(random_forest_classifier_hist_testing)
PredictMD.singlelabelbinaryclassificationmetrics(
random_forest_classifier,
smoted_training_features_df,
smoted_training_labels_df,
single_label_name,
positive_class;
sensitivity = 0.95,
)
PredictMD.singlelabelbinaryclassificationmetrics(
random_forest_classifier,
testing_features_df,
testing_labels_df,
single_label_name,
positive_class;
sensitivity = 0.95,
)
random_forest_classifier_filename = joinpath(
PROJECT_OUTPUT_DIRECTORY,
"random_forest_classifier.jld2",
)
PredictMD.save_model(
random_forest_classifier_filename,
random_forest_classifier,
)
### End random forest classifier code
##### End of file
Info: Starting to train DecisionTree model.
Info: Finished training DecisionTree model.
Info: Attempting to save model...
Info: Saved model to file "/tmp/tmpxV7LRJ/PREDICTMDTEMPDIRECTORY/random_forest_classifier.jld2"
This page was generated using Literate.jl.