Add Accelerated Failure Time loss for survival analysis task (#4763)
* [WIP] Add lower and upper bounds on the label for survival analysis * Update test MetaInfo.SaveLoadBinary to account for extra two fields * Don't clear qids_ for version 2 of MetaInfo * Add SetInfo() and GetInfo() method for lower and upper bounds * changes to aft * Add parameter class for AFT; use enum's to represent distribution and event type * Add AFT metric * changes to neg grad to grad * changes to binomial loss * changes to overflow * changes to eps * changes to code refactoring * changes to code refactoring * changes to code refactoring * Re-factor survival analysis * Remove aft namespace * Move function bodies out of AFTNormal and AFTLogistic, to reduce clutter * Move function bodies out of AFTLoss, to reduce clutter * Use smart pointer to store AFTDistribution and AFTLoss * Rename AFTNoiseDistribution enum to AFTDistributionType for clarity The enum class was not a distribution itself but a distribution type * Add AFTDistribution::Create() method for convenience * changes to extreme distribution * changes to extreme distribution * changes to extreme * changes to extreme distribution * changes to left censored * deleted cout * changes to x,mu and sd and code refactoring * changes to print * changes to hessian formula in censored and uncensored * changes to variable names and pow * changes to Logistic Pdf * changes to parameter * Expose lower and upper bound labels to R package * Use example weights; normalize log likelihood metric * changes to CHECK * changes to logistic hessian to standard formula * changes to logistic formula * Comply with coding style guideline * Revert back Rabit submodule * Revert dmlc-core submodule * Comply with coding style guideline (clang-tidy) * Fix an error in AFTLoss::Gradient() * Add missing files to amalgamation * Address @RAMitchell's comment: minimize future change in MetaInfo interface * Fix lint * Fix compilation error on 32-bit target, when size_t == bst_uint * Allocate sufficient memory to hold extra label info * Use OpenMP to speed up * Fix compilation on Windows * Address reviewer's feedback * Add unit tests for probability distributions * Make Metric subclass of Configurable * Address reviewer's feedback: Configure() AFT metric * Add a dummy test for AFT metric configuration * Complete AFT configuration test; remove debugging print * Rename AFT parameters * Clarify test comment * Add a dummy test for AFT loss for uncensored case * Fix a bug in AFT loss for uncensored labels * Complete unit test for AFT loss metric * Simplify unit tests for AFT metric * Add unit test to verify aggregate output from AFT metric * Use EXPECT_* instead of ASSERT_*, so that we run all unit tests * Use aft_loss_param when serializing AFTObj This is to be consistent with AFT metric * Add unit tests for AFT Objective * Fix OpenMP bug; clarify semantics for shared variables used in OpenMP loops * Add comments * Remove AFT prefix from probability distribution; put probability distribution in separate source file * Add comments * Define kPI and kEulerMascheroni in probability_distribution.h * Add probability_distribution.cc to amalgamation * Remove unnecessary diff * Address reviewer's feedback: define variables where they're used * Eliminate all INFs and NANs from AFT loss and gradient * Add demo * Add tutorial * Fix lint * Use 'survival:aft' to be consistent with 'survival:cox' * Move sample data to demo/data * Add visual demo with 1D toy data * Add Python tests Co-authored-by: Philip Cho <chohyu01@cs.washington.edu>
This commit is contained in:
Avinash Barnwal
GitHub
94
src/common/probability_distribution.h
Normal file
94
src/common/probability_distribution.h
Normal file
@@ -0,0 +1,94 @@
|
||||
/*!
|
||||
* Copyright 2020 by Contributors
|
||||
* \file probability_distribution.h
|
||||
* \brief Implementation of a few useful probability distributions
|
||||
* \author Avinash Barnwal and Hyunsu Cho
|
||||
*/
|
||||
|
||||
#ifndef XGBOOST_COMMON_PROBABILITY_DISTRIBUTION_H_
|
||||
#define XGBOOST_COMMON_PROBABILITY_DISTRIBUTION_H_
|
||||
|
||||
namespace xgboost {
|
||||
namespace common {
|
||||
|
||||
namespace probability_constant {
|
||||
|
||||
/*! \brief Constant PI */
|
||||
const double kPI = 3.14159265358979323846;
|
||||
/*! \brief The Euler-Mascheroni_constant */
|
||||
const double kEulerMascheroni = 0.57721566490153286060651209008240243104215933593992;
|
||||
|
||||
} // namespace probability_constant
|
||||
|
||||
/*! \brief Enum encoding possible choices of probability distribution */
|
||||
enum class ProbabilityDistributionType : int {
|
||||
kNormal = 0, kLogistic = 1, kExtreme = 2
|
||||
};
|
||||
|
||||
/*! \brief Interface for a probability distribution */
|
||||
class ProbabilityDistribution {
|
||||
public:
|
||||
/*!
|
||||
* \brief Evaluate Probability Density Function (PDF) at a particular point
|
||||
* \param z point at which to evaluate PDF
|
||||
* \return Value of PDF evaluated
|
||||
*/
|
||||
virtual double PDF(double z) = 0;
|
||||
/*!
|
||||
* \brief Evaluate Cumulative Distribution Function (CDF) at a particular point
|
||||
* \param z point at which to evaluate CDF
|
||||
* \return Value of CDF evaluated
|
||||
*/
|
||||
virtual double CDF(double z) = 0;
|
||||
/*!
|
||||
* \brief Evaluate first derivative of PDF at a particular point
|
||||
* \param z point at which to evaluate first derivative of PDF
|
||||
* \return Value of first derivative of PDF evaluated
|
||||
*/
|
||||
virtual double GradPDF(double z) = 0;
|
||||
/*!
|
||||
* \brief Evaluate second derivative of PDF at a particular point
|
||||
* \param z point at which to evaluate second derivative of PDF
|
||||
* \return Value of second derivative of PDF evaluated
|
||||
*/
|
||||
virtual double HessPDF(double z) = 0;
|
||||
|
||||
/*!
|
||||
* \brief Factory function to instantiate a new probability distribution object
|
||||
* \param dist kind of probability distribution
|
||||
* \return Reference to the newly created probability distribution object
|
||||
*/
|
||||
static ProbabilityDistribution* Create(ProbabilityDistributionType dist);
|
||||
};
|
||||
|
||||
/*! \brief The (standard) normal distribution */
|
||||
class NormalDist : public ProbabilityDistribution {
|
||||
public:
|
||||
double PDF(double z) override;
|
||||
double CDF(double z) override;
|
||||
double GradPDF(double z) override;
|
||||
double HessPDF(double z) override;
|
||||
};
|
||||
|
||||
/*! \brief The (standard) logistic distribution */
|
||||
class LogisticDist : public ProbabilityDistribution {
|
||||
public:
|
||||
double PDF(double z) override;
|
||||
double CDF(double z) override;
|
||||
double GradPDF(double z) override;
|
||||
double HessPDF(double z) override;
|
||||
};
|
||||
|
||||
/*! \brief The extreme distribution, also known as the Gumbel (minimum) distribution */
|
||||
class ExtremeDist : public ProbabilityDistribution {
|
||||
public:
|
||||
double PDF(double z) override;
|
||||
double CDF(double z) override;
|
||||
double GradPDF(double z) override;
|
||||
double HessPDF(double z) override;
|
||||
};
|
||||
|
||||
} // namespace common
|
||||
} // namespace xgboost
|
||||
|
||||
#endif // XGBOOST_COMMON_PROBABILITY_DISTRIBUTION_H_
|
||||
Reference in New Issue
Block a user