This file is indexed.

/usr/share/pyshared/mvpa/datasets/mapped.py is in python-mvpa 0.4.8-1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
# emacs: -*- mode: python; py-indent-offset: 4; indent-tabs-mode: nil -*-
# vi: set ft=python sts=4 ts=4 sw=4 et:
### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ##
#
#   See COPYING file distributed along with the PyMVPA package for the
#   copyright and license terms.
#
### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ##
"""Mapped dataset"""

__docformat__ = 'restructuredtext'

import mvpa.support.copy as copy

from mvpa.datasets import Dataset
from mvpa.base.dochelpers import enhancedDocString
from mvpa.misc.exceptions import DatasetError

class MappedDataset(Dataset):
    """A `Dataset` which is created by applying a `Mapper` to the data.

    Upon contruction `MappedDataset` uses a `Mapper` to transform the
    samples from their original into the two-dimensional matrix
    representation that is required by the `Dataset` class.

    This class enhanced the `Dataset` interface with two additional
    methods: `mapForward()` and `mapReverse()`. Both take arbitrary data
    arrays (with matching shape) and transform them using the embedded
    mapper from the original dataspace into a one- or two-dimensional
    representation (for arrays corresponding to the shape of a single or
    multiple samples respectively) or vice versa.

    Most likely, this class will not be used directly, but rather
    indirectly through one of its subclasses (e.g. `MaskedDataset`).
    """

    def __init__(self, samples=None, mapper=None, dsattr=None, **kwargs):
        """
        If `samples` and `mapper` arguments are not `None` the mapper is
        used to forward-map the samples array and the result is passed
        to the `Dataset` constructor.

        :Parameters:
          mapper: Instance of `Mapper`
            This mapper will be embedded in the dataset and is used and
            updated, by all subsequent mapping or feature selection
            procedures.
          **kwargs:
            All other arguments are simply passed to and handled by
            the constructor of `Dataset`.
        """
        # there are basically two mode for the constructor:
        # 1. internal mode - only data and dsattr dict
        # 2. user mode - samples != None # and mapper != None

        # see if dsattr is none, if so, set to empty dict
        if dsattr is None:
            dsattr = {}

        # if a mapper was passed, store it in dsattr dict that gets passed
        # to base Dataset
        if not mapper is None:
            # TODO: check mapper for compliance with dimensionality within _data
            #       may be only within __debug__
            dsattr['mapper'] = mapper

        # if the samples are passed to the special arg, use the mapper to
        # transform them.
        if not samples is None:
            if not dsattr.has_key('mapper') or dsattr['mapper'] is None:
                raise DatasetError, \
                      "Constructor of MappedDataset requires a mapper " \
                      "if unmapped samples are provided."
            Dataset.__init__(self,
                             samples=mapper.forward(samples),
                             dsattr=dsattr,
                             **(kwargs))
        else:
            Dataset._checkCopyConstructorArgs(samples=samples,
                                              dsattr=dsattr,
                                              **kwargs)
            Dataset.__init__(self, dsattr=dsattr, **(kwargs))


    __doc__ = enhancedDocString('MappedDataset', locals(), Dataset)


    def mapForward(self, data):
        """Map data from the original dataspace into featurespace.
        """
        return self.mapper.forward(data)


    def mapReverse(self, data):
        """Reverse map data from featurespace into the original dataspace.
        """
        return self.mapper.reverse(data)


    def mapSelfReverse(self):
        """Reverse samples from featurespace into the original dataspace.
        """
        return self.mapper.reverse(self.samples)

    def selectFeatures(self, ids, plain=False, sort=False):
        """Select features given their ids.

        The methods behaves similar to Dataset.selectFeatures(), but
        additionally takes care of adjusting the embedded mapper
        appropriately.

        :Parameters:
          ids: sequence
            Iterable container to select ids
          plain: boolean
            Flag whether to return MappedDataset (or just Dataset)
          sort: boolean
            Flag whether to sort Ids. Order matters and selectFeatures
            assumes incremental order. If not such, in non-optimized
            code selectFeatures would verify the order and sort
        """

        # call base method to get selected feature subset
        if plain:
            sdata = Dataset(self._data, self._dsattr, check_data=False,
                            copy_samples=False, copy_data=False,
                            copy_dsattr=False)
            return sdata.selectFeatures(ids=ids, sort=sort)
        else:
            sdata = Dataset.selectFeatures(self, ids=ids, sort=sort)
            # since we have new DataSet we better have a new mapper
            sdata._dsattr['mapper'] = copy.deepcopy(sdata._dsattr['mapper'])
            if sort:
                sdata._dsattr['mapper'].selectOut(sorted(ids))
            else:
                sdata._dsattr['mapper'].selectOut(ids)
            return sdata


    # read-only class properties
    mapper = property(fget=lambda self: self._dsattr['mapper'])
    samples_original = property(fget=mapSelfReverse,
                                doc="Return samples in the original shape")

    # syntactic sugarings
    O = property(fget=mapSelfReverse,
                 doc="Return samples in the original shape")