Internals

Documentation of internals

Modules

PredictMD.PredictMD — Module.
source
PredictMD.Cleaning — Module.
source
PredictMD.Compilation — Module.
source
PredictMD.GPU — Module.
source
PredictMD.Server — Module.
source

Constants

Types

PredictMD.CrossValidation — Type.
source
PredictMD.DataFrameFeatureContrasts — Type.
source
PredictMD.DataFrameFeatureContrasts — Method.
source
PredictMD.DecisionTreeModel — Type.
source
PredictMD.GLMModel — Type.
source
PredictMD.ImmutableDataFrame2GLMSingleLabelBinaryClassTransformer — Type.
source
PredictMD.ImmutableFeatureArrayTransposerTransformer — Type.
source
PredictMD.ImmutablePackageMultiLabelPredictionTransformer — Type.
source
PredictMD.ImmutablePackageSingleLabelPredictProbaTransformer — Type.
source
PredictMD.ImmutablePackageSingleLabelPredictionTransformer — Type.
source
PredictMD.ImmutablePredictProbaSingleLabelInt2StringTransformer — Type.
source
PredictMD.ImmutablePredictionsSingleLabelInt2StringTransformer — Type.
source
PredictMD.KnetModel — Type.
source
PredictMD.LIBSVMModel — Type.
source
PredictMD.MutableDataFrame2ClassificationKnetTransformer — Type.
source
PredictMD.MutableDataFrame2DecisionTreeTransformer — Type.
source
PredictMD.MutableDataFrame2RegressionKnetTransformer — Type.
source
PredictMD.SimplePipeline — Type.
source
PredictMD.SimplePipeline — Method.
source

Functions

PredictMD.DataFrame2LIBSVMTransformer — Method.
source
PredictMD.accuracy — Method.
source
PredictMD.auprc — Method.
source
PredictMD.aurocc — Method.
source
PredictMD.averageprecisionscore — Method.
source
PredictMD.avg_precision — Method.
source
PredictMD.binary_brier_score — Method.
binary_brier_score(ytrue, yscore)

Computes the binary formulation of the Brier score, defined as:

\[\frac{1}{N}\sum\limits _{t=1}^{N}(f_t-o_t)^2 \,\!\]

Lower values are better. Best value is 0.

source
PredictMD.calculate_smote_pct_under — Method.
source
PredictMD.check_column_types — Method.
source
PredictMD.cohen_kappa — Method.
source
PredictMD.cohen_kappa — Method.
source
PredictMD.cohen_kappa — Method.
source
PredictMD.compute_contingency_table — Method.
source
PredictMD.compute_contingency_table — Method.
source
PredictMD.convert_value_to_missing! — Function.
source
PredictMD.delete_nothings! — Method.
source
PredictMD.f1score — Method.
source
PredictMD.false_negative_rate — Method.
source
PredictMD.false_positive_rate — Method.
source
PredictMD.fbetascore — Method.
source
PredictMD.filename_extension — Method.
source
PredictMD.fit! — Function.
source
PredictMD.fit! — Function.
source
PredictMD.fit! — Function.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fit! — Method.
source
PredictMD.fix_column_types! — Method.
source
PredictMD.fix_type — Function.
source
PredictMD.flatten — Method.
source
PredictMD.generate_feature_contrasts — Method.
source
PredictMD.generate_formula — Method.
source
PredictMD.generate_formula — Method.
source
PredictMD.generate_formula — Method.
source
PredictMD.get_binary_thresholds — Method.
source
PredictMD.get_history — Method.
source
PredictMD.get_history — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.get_underlying — Method.
source
PredictMD.getallrocnums — Method.
source
PredictMD.getlabelint2stringmap — Method.
source
PredictMD.getlabelstring2intmap — Method.
source
PredictMD.icd9_code_to_single_level_dx_ccs — Method.
source
PredictMD.inverse — Method.
source
PredictMD.is_ci — Function.
source
PredictMD.is_ci_or_runtests — Function.
source
PredictMD.is_ci_or_runtests_or_docs_or_examples — Function.
source
PredictMD.is_deploy_docs — Function.
source
PredictMD.is_docs_or_examples — Function.
source
PredictMD.is_make_docs — Function.
source
PredictMD.is_make_examples — Function.
source
PredictMD.is_nothing — Function.
source
PredictMD.is_one_to_one — Method.
source
PredictMD.is_runtests — Function.
source
PredictMD.is_square — Method.
source
PredictMD.is_travis_ci — Function.
source
PredictMD.is_travis_ci_on_linux — Function.
source
PredictMD.isflat — Function.
source
PredictMD.ispipeline — Function.
source
PredictMD.load_model — Method.
source
PredictMD.mean_square_error — Method.
mean_square_error(ytrue, ypred)
source
PredictMD.multilabelprobabilitiestopredictions — Method.
source
PredictMD.multilabelprobabilitiestopredictions — Method.
source
PredictMD.negative_predictive_value — Method.
source
PredictMD.open_plots_during_tests — Function.
source
PredictMD.package_directory — Method.
package_directory(parts...)::String

Equivalent to abspath(joinpath(abspath(package_directory()), parts...)).

source
PredictMD.package_directory — Method.
package_directory()::String

Return the PredictMD package directory.

source
PredictMD.parse_functions! — Method.
source
PredictMD.plot_probability_calibration_curve — Method.
source
PredictMD.plot_probability_calibration_curve — Method.
source
PredictMD.plotlearningcurve — Function.
source
PredictMD.plotlearningcurve — Function.
source
PredictMD.plotlearningcurve — Method.
source
PredictMD.plotprcurve — Method.
source
PredictMD.plotprcurve — Method.
source
PredictMD.plotroccurve — Method.
source
PredictMD.plotroccurve — Method.
source
PredictMD.plotsinglelabelbinaryclassifierhistogram — Method.
source
PredictMD.plotsinglelabelregressiontrueversuspredicted — Method.
source
PredictMD.positive_predictive_value — Method.
source
PredictMD.prcurve — Method.
source
PredictMD.prcurve — Method.
source
PredictMD.precision — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predict_proba — Method.
source
PredictMD.predictionsassoctodataframe — Function.
source
PredictMD.probability_calibration_metrics — Function.
source
PredictMD.probability_calibration_metrics — Method.
source
PredictMD.probability_calibration_scores_and_fractions — Method.
source
PredictMD.probability_calibration_scores_and_fractions — Method.
source
PredictMD.r2_score — Method.
r2_score(ytrue, ypred)

Computes coefficient of determination. Higher values are better. Best value is 1.

source
PredictMD.recall — Method.
source
PredictMD.risk_score_cutoff_values — Method.
source
PredictMD.risk_score_cutoff_values — Method.
source
PredictMD.roccurve — Method.
source
PredictMD.roccurve — Method.
source
PredictMD.root_mean_square_error — Method.
root_mean_square_error(ytrue, ypred)
source
PredictMD.save_model — Method.
source
PredictMD.sensitivity — Method.
source
PredictMD.set_feature_contrasts! — Method.
source
PredictMD.set_feature_contrasts! — Method.
source
PredictMD.set_feature_contrasts! — Method.
source
PredictMD.set_feature_contrasts! — Method.
source
PredictMD.set_max_epochs! — Method.
source
PredictMD.set_max_epochs! — Method.
source
PredictMD.shuffle_rows! — Method.
source
PredictMD.shuffle_rows! — Method.
source
PredictMD.simple_linear_regression — Method.
simple_linear_regression(x::AbstractVector, y::AbstractVector)

Simple linear regression - given a set of two-dimensional points (x, y), use the ordinary least squares method to find the best fit line of the form y = a + b*x (where a and b are real numbers) and return the tuple (a, b).

source
PredictMD.simple_moving_average — Method.
source
PredictMD.single_labeldataframeknetregression — Method.
source
PredictMD.single_labeldataframeknetregression_Knet — Method.
source
PredictMD.single_labeldataframelinearregression — Method.
source
PredictMD.single_labeldataframelinearregression_GLM — Method.
source
PredictMD.single_labeldataframerandomforestregression — Method.
source
PredictMD.single_labeldataframerandomforestregression_DecisionTree — Method.
source
PredictMD.single_labeldataframesvmregression — Method.
source
PredictMD.single_labeldataframesvmregression_LIBSVM — Method.
source
PredictMD.single_labelmulticlassdataframeknetclassifier — Method.
source
PredictMD.single_labelmulticlassdataframeknetclassifier_Knet — Method.
source
PredictMD.single_labelmulticlassdataframerandomforestclassifier — Method.
source
PredictMD.single_labelmulticlassdataframesvmclassifier — Method.
source
PredictMD.single_labelmulticlassdataframesvmclassifier_LIBSVM — Method.
source
PredictMD.single_labelmulticlassdfrandomforestclassifier_DecisionTree — Method.
source
PredictMD.single_labelprobabilitiestopredictions — Method.
source
PredictMD.singlelabelbinaryclassdataframelogisticclassifier — Method.
source
PredictMD.singlelabelbinaryclassdataframelogisticclassifier_GLM — Method.
source
PredictMD.singlelabelbinaryclassificationmetrics — Method.
source
PredictMD.singlelabelbinaryclassificationmetrics — Method.
source
PredictMD.singlelabelbinaryclassificationmetrics_resultdict — Method.
source
PredictMD.singlelabelbinaryclassificationmetrics_tunableparam — Method.
source
PredictMD.singlelabelbinaryyscore — Method.
source
PredictMD.singlelabelbinaryytrue — Method.
source
PredictMD.singlelabelregressionmetrics — Method.
source
PredictMD.singlelabelregressionmetrics — Method.
source
PredictMD.singlelabelregressionmetrics_resultdict — Method.
source
PredictMD.singlelabelregressionypred — Method.
source
PredictMD.singlelabelregressionytrue — Method.
source
PredictMD.smote — Method.
source
PredictMD.smote — Method.
source
PredictMD.specificity — Method.
source
PredictMD.split_data — Method.
source
PredictMD.split_data — Method.
source
PredictMD.transform — Function.
source
PredictMD.transform — Function.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform — Method.
source
PredictMD.transform_columns! — Function.
source
PredictMD.trapz — Function.
trapz(x, y)

Compute the area under the curve of 2-dimensional points (x, y) using the trapezoidal method.

source
PredictMD.true_negative_rate — Method.
source
PredictMD.true_positive_rate — Method.
source
PredictMD.tuplify — Function.
source
PredictMD.version — Method.
version()::VersionNumber

Return the version number of PredictMD.

source
PredictMD.version_codename — Method.
version_codename()::String

Return the version code name of PredictMD.

source
PredictMD.Cleaning.ccs_onehot_names — Function.

Given a dataframe, return the column names corresponding to CCS "one-hot" columns.

Examples

import CSVFiles
import FileIO
import PredictMD

df = DataFrames.DataFrame(
    FileIO.load(
        MY_CSV_FILE_NAME;
        type_detect_rows = 30_000,
        )
    )

@info(PredictMD.Cleaning.ccs_onehot_names(df))
@info(PredictMD.Cleaning.ccs_onehot_names(df, "ccs_onehot_"))
source
PredictMD.Cleaning.clean_hcup_nis_csv_icd9 — Method.

Given a single ICD 9 code, import the relevant patients from the Health Care Utilization Project (HCUP) National Inpatient Sample (NIS) database.

Examples:

import CSVFiles
import FileIO
import PredictMD

icd_code_list = ["8841"]
icd_code_type=:procedure
input_file_name_list = [
    "./data/nis_2012_core.csv",
    "./data/nis_2013_core.csv",
    "./data/nis_2014_core.csv",
    ]
output_file_name = "./output/hcup_nis_pr_8841.csv"

PredictMD.Cleaning.clean_hcup_nis_csv_icd9(
    icd_code_list,
    input_file_name_list,
    output_file_name;
    icd_code_type=icd_code_type,
    rows_for_type_detect = 30_000,
    )

df = DataFrames.DataFrame(
    FileIO.load(
        output_file_name;
        type_detect_rows = 30_000,
        )
    )

@info(PredictMD.Cleaning.ccs_onehot_names(df))
source
PredictMD.Cleaning.column_names_with_prefix — Method.
source
PredictMD.Cleaning.symbol_begins_with — Method.
source
PredictMD.Cleaning.x_contains_y — Method.
source

Macros

Index