NAME

AI::XGBoost::CAPI - Perl wrapper for XGBoost C API https://github.com/dmlc/xgboost

VERSION

version 0.003

SYNOPSIS

use 5.010;
use AI::XGBoost::CAPI;
use FFI::Platypus;

my $silent = 0;
my ($dtrain, $dtest) = (0, 0);

AI::XGBoost::CAPI::XGDMatrixCreateFromFile('agaricus.txt.test', $silent, \$dtest);
AI::XGBoost::CAPI::XGDMatrixCreateFromFile('agaricus.txt.train', $silent, \$dtrain);

my ($rows, $cols) = (0, 0);
AI::XGBoost::CAPI::XGDMatrixNumRow($dtrain, \$rows);
AI::XGBoost::CAPI::XGDMatrixNumCol($dtrain, \$cols);
say "Dimensions: $rows, $cols";

my $booster = 0;

AI::XGBoost::CAPI::XGBoosterCreate( [$dtrain] , 1, \$booster);

for my $iter (0 .. 10) {
    AI::XGBoost::CAPI::XGBoosterUpdateOneIter($booster, $iter, $dtrain);
}

my $out_len = 0;
my $out_result = 0;

AI::XGBoost::CAPI::XGBoosterPredict($booster, $dtest, 0, 0, \$out_len, \$out_result);
my $ffi = FFI::Platypus->new();
my $predictions = $ffi->cast(opaque => "float[$out_len]", $out_result);

#say join "\n", @$predictions;

AI::XGBoost::CAPI::XGBoosterFree($booster);

DESCRIPTION

Wrapper for the C API.

The doc for the methods is extracted from doxygen comments: https://github.com/dmlc/xgboost/blob/master/include/xgboost/c_api.h

FUNCTIONS

XGBGetLastError

Get string message of the last error

All functions in this file will return 0 when success and -1 when an error occurred, XGBGetLastError can be called to retrieve the error

This function is thread safe and can be called by different thread

Returns string error information

XGDMatrixCreateFromFile

Load a data matrix

Parameters:

filename

the name of the file

silent

whether print messages during loading

out

a loaded data matrix

XGDMatrixCreateFromCSREx

Create a matrix content from CSR fromat

Parameters:

indptr

pointer to row headers

indices

findex

data

fvalue

nindptr

number of rows in the matrix + 1

nelem

number of nonzero elements in the matrix

num_col

number of columns; when it's set to 0, then guess from data

out

created dmatrix

XGDMatrixCreateFromCSCEx

Create a matrix content from CSC format

Parameters:

col_ptr

pointer to col headers

indices

findex

data

fvalue

nindptr

number of rows in the matrix + 1

nelem

number of nonzero elements in the matrix

num_row

number of rows; when it's set to 0, then guess from data

XGDMatrixCreateFromMat

Create matrix content from dense matrix

Parameters:

data

pointer to the data space

nrow

number of rows

ncol

number columns

missing

which value to represent missing value

out

created dmatrix

XGDMatrixSliceDMatrix

Create a new dmatrix from sliced content of existing matrix

Parameters:

handle

instance of data matrix to be sliced

idxset

index set

len

length of index set

out

a sliced new matrix

XGDMatrixNumRow

Get number of rows.

Parameters:

handle

the handle to the DMatrix

out

The address to hold number of rows.

XGDMatrixNumCol

Get number of cols.

Parameters:

handle

the handle to the DMatrix

out

The address to hold number of cols.

XGDMatrixSaveBinary

load a data matrix into binary file

Parameters:

handle

a instance of data matrix

fname

file name

silent

print statistics when saving

XGDMatrixSetFloatInfo

Set float vector to a content in info

Parameters:

handle

a instance of data matrix

field

field name, can be label, weight

array

pointer to float vector

len

length of array

XGDMatrixSetUIntInfo

Set uint32 vector to a content in info

Parameters:

handle

a instance of data matrix

field

field name, can be label, weight

array

pointer to unsigned int vector

len

length of array

XGDMatrixSetGroup

Set label of the training matrix

Parameters:

handle

a instance of data matrix

group

pointer to group size

len

length of the array

XGDMatrixGetFloatInfo

Get float info vector from matrix

Parameters:

handle

a instance of data matrix

field

field name

out_len

used to set result length

out_dptr

pointer to the result

XGDMatrixGetUIntInfo

Get uint32 info vector from matrix

Parameters:

handle

a instance of data matrix

field

field name

out_len

The length of the field

out_dptr

pointer to the result

XGDMatrixFree

Free space in data matrix

XGBoosterCreate

Create xgboost learner

Parameters:

dmats

matrices that are set to be cached

len

length of dmats

out

handle to the result booster

XGBoosterFree

Free obj in handle

Parameters:

handle

handle to be freed

XGBoosterSetParam

Update the model in one round using dtrain

Parameters:

handle

handle

name

parameter name

value

value of parameter

XGBoosterBoostOneIter

Update the modelo, by directly specify grandient and second order gradient, this can be used to replace UpdateOneIter, to support customized loss function

Parameters:

handle

handle

dtrain

training data

grad

gradient statistics

hess

second order gradinet statistics

len

length of grad/hess array

XGBoosterUpdateOneIter

Update the model in one round using dtrain

Parameters:

handle

handle

iter

current iteration rounds

dtrain

training data

XGBoosterPredict

Make prediction based on dmat

Parameters:

handle

handle

dmat

data matrix

option_mask

bit-mask of options taken in prediction, possible values

  • 0: normal prediction

  • 1: output margin instead of transformed value

  • 2: output leaf index of trees instead of leaf value, note leaf index is unique per tree

  • 4: output feature contributions to individual predictions

ntree_limit

limit number of trees used for prediction, this is only valid for boosted trees when the parameter is set to 0, we will use all the trees

out_len

used to store length of returning result

out_result

used to set a pointer to array

XGBoosterLoadModel

Load model form existing file

Parameters:

handle

handle

fname

file name

XGBoosterSaveModel

Save model into existing file

Parameters:

handle

handle

fname

file name

AUTHOR

Pablo Rodríguez González <pablo.rodriguez.gonzalez@gmail.com>

COPYRIGHT AND LICENSE

This software is Copyright (c) 2017 by Pablo Rodríguez González.

This is free software, licensed under:

The Apache License, Version 2.0, January 2004