view release on metacpan or  search on metacpan

xgboost/python-package/xgboost/core.py  view on Meta::CPAN

# coding: utf-8
# pylint: disable=too-many-arguments, too-many-branches, invalid-name
# pylint: disable=too-many-branches, too-many-lines, W0141
"""Core XGBoost Library."""
from __future__ import absolute_import

import sys
import os
import ctypes
import collections
import re

import numpy as np
import scipy.sparse

from .libpath import find_lib_path

from .compat import STRING_TYPES, PY3, DataFrame, py_str, PANDAS_INSTALLED

# c_bst_ulong corresponds to bst_ulong defined in xgboost/c_api.h
c_bst_ulong = ctypes.c_uint64


class XGBoostError(Exception):
    """Error thrown by xgboost trainer."""
    pass


class EarlyStopException(Exception):
    """Exception to signal early stopping.

    Parameters
    ----------
    best_iteration : int
        The best iteration stopped.
    """
    def __init__(self, best_iteration):
        super(EarlyStopException, self).__init__()
        self.best_iteration = best_iteration


# Callback environment used by callbacks
CallbackEnv = collections.namedtuple(
    "XGBoostCallbackEnv",
    ["model",
     "cvfolds",
     "iteration",
     "begin_iteration",
     "end_iteration",
     "rank",
     "evaluation_result_list"])


def from_pystr_to_cstr(data):
    """Convert a list of Python str to C pointer

    Parameters
    ----------
    data : list
        list of str
    """

    if isinstance(data, list):
        pointers = (ctypes.c_char_p * len(data))()
        if PY3:
            data = [bytes(d, 'utf-8') for d in data]
        else:
            data = [d.encode('utf-8') if isinstance(d, unicode) else d
                    for d in data]
        pointers[:] = data
        return pointers
    else:
        # copy from above when we actually use it
        raise NotImplementedError


def from_cstr_to_pystr(data, length):
    """Revert C pointer to Python str

    Parameters
    ----------
    data : ctypes pointer
        pointer to data
    length : ctypes pointer
        pointer to length of data
    """
    if PY3:
        res = []
        for i in range(length.value):
            try:
                res.append(str(data[i].decode('ascii')))
            except UnicodeDecodeError:
                res.append(str(data[i].decode('utf-8')))
    else:
        res = []
        for i in range(length.value):
            try:
                res.append(str(data[i].decode('ascii')))
            except UnicodeDecodeError:
                res.append(unicode(data[i].decode('utf-8')))
    return res