This file is indexed.

/usr/share/pyshared/mvpa/clfs/lars.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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
# 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.
#
### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ### ##
"""Least angle regression (LARS) classifier."""

__docformat__ = 'restructuredtext'

# system imports
import numpy as N

import mvpa.base.externals as externals

# do conditional to be able to build module reference
if externals.exists('rpy', raiseException=True) and \
   externals.exists('lars', raiseException=True):
    import rpy
    rpy.r.library('lars')


# local imports
from mvpa.clfs.base import Classifier, FailedToTrainError
from mvpa.measures.base import Sensitivity

from mvpa.base import warning
if __debug__:
    from mvpa.base import debug

known_models = ('lasso', 'stepwise', 'lar', 'forward.stagewise')

class LARS(Classifier):
    """Least angle regression (LARS) `Classifier`.

    LARS is the model selection algorithm from:

    Bradley Efron, Trevor Hastie, Iain Johnstone and Robert
    Tibshirani, Least Angle Regression Annals of Statistics (with
    discussion) (2004) 32(2), 407-499. A new method for variable
    subset selection, with the lasso and 'epsilon' forward stagewise
    methods as special cases.

    Similar to SMLR, it performs a feature selection while performing
    classification, but instead of starting with all features, it
    starts with none and adds them in, which is similar to boosting.

    This classifier behaves more like a ridge regression in that it
    returns prediction values and it treats the training labels as
    continuous.

    In the true nature of the PyMVPA framework, this algorithm is
    actually implemented in R by Trevor Hastie and wrapped via RPy.
    To make use of LARS, you must have R and RPy installed as well as
    the LARS contributed package. You can install the R and RPy with
    the following command on Debian-based machines:

    sudo aptitude install python-rpy python-rpy-doc r-base-dev

    You can then install the LARS package by running R as root and
    calling:

    install.packages()

    """

    # XXX from yoh: it is linear, isn't it?
    _clf_internals = [ 'lars', 'regression', 'linear', 'has_sensitivity',
                       'does_feature_selection',
                       ]
    def __init__(self, model_type="lasso", trace=False, normalize=True,
                 intercept=True, max_steps=None, use_Gram=False, **kwargs):
        """
        Initialize LARS.

        See the help in R for further details on the following parameters:

        :Parameters:
          model_type : string
            Type of LARS to run. Can be one of ('lasso', 'lar',
            'forward.stagewise', 'stepwise').
          trace : boolean
            Whether to print progress in R as it works.
          normalize : boolean
            Whether to normalize the L2 Norm.
          intercept : boolean
            Whether to add a non-penalized intercept to the model.
          max_steps : None or int
            If not None, specify the total number of iterations to run. Each
            iteration adds a feature, but leaving it none will add until
            convergence.
          use_Gram : boolean
            Whether to compute the Gram matrix (this should be false if you
            have more features than samples.)
        """
        # init base class first
        Classifier.__init__(self, **kwargs)

        if not model_type in known_models:
            raise ValueError('Unknown model %s for LARS is specified. Known' %
                             model_type + 'are %s' % `known_models`)

        # set up the params
        self.__type = model_type
        self.__normalize = normalize
        self.__intercept = intercept
        self.__trace = trace
        self.__max_steps = max_steps
        self.__use_Gram = use_Gram

        # pylint friendly initializations
        self.__lowest_Cp_step = None
        self.__weights = None
        """The beta weights for each feature."""
        self.__trained_model = None
        """The model object after training that will be used for
        predictions."""

        # It does not make sense to calculate a confusion matrix for a
        # regression
        # YOH: we do have summary statistics for regressions
        #self.states.enable('training_confusion', False)

    def __repr__(self):
        """String summary of the object
        """
        return "LARS(type='%s', normalize=%s, intercept=%s, trace=%s, " \
               "max_steps=%s, use_Gram=%s, regression=%s, " \
               "enable_states=%s)" % \
               (self.__type,
                self.__normalize,
                self.__intercept,
                self.__trace,
                self.__max_steps,
                self.__use_Gram,
                self.regression,
                str(self.states.enabled))


    def _train(self, data):
        """Train the classifier using `data` (`Dataset`).
        """
        if self.__max_steps is None:
            # train without specifying max_steps
            trained_model = rpy.r.lars(data.samples,
                                       data.labels[:,N.newaxis],
                                       type=self.__type,
                                       normalize=self.__normalize,
                                       intercept=self.__intercept,
                                       trace=self.__trace,
                                       use_Gram=self.__use_Gram)
        else:
            # train with specifying max_steps
            trained_model = rpy.r.lars(data.samples,
                                       data.labels[:,N.newaxis],
                                       type=self.__type,
                                       normalize=self.__normalize,
                                       intercept=self.__intercept,
                                       trace=self.__trace,
                                       use_Gram=self.__use_Gram,
                                       max_steps=self.__max_steps)

        # find the step with the lowest Cp (risk)
        # it is often the last step if you set a max_steps
        # must first convert dictionary to array
        try:
            Cp = trained_model['Cp']
            if '0' in Cp:
                # If there was any
                Cp_vals = N.asarray([Cp[str(x)] for x in range(len(Cp))])
            else:
                Cp_vals = None
        except TypeError, e:
            raise FailedToTrainError, \
                  "Failed to train %s on %s. Got '%s' while trying to access " \
                  "trained model %s" % (self, data, e, trained_model)

        if Cp_vals is None:
            # if there were no any -- just choose 0th
            lowest_Cp_step = 0
        elif N.isnan(Cp_vals[0]):
            # sometimes may come back nan, so just pick the last one
            lowest_Cp_step = len(Cp_vals)-1
        else:
            # determine the lowest
            lowest_Cp_step = Cp_vals.argmin()

        self.__lowest_Cp_step = lowest_Cp_step
        # set the weights to the lowest Cp step
        self.__weights = trained_model['beta'][lowest_Cp_step, :]

        self.__trained_model = trained_model # bind to an instance
#         # set the weights to the final state
#         self.__weights = self.__trained_model['beta'][-1,:]


    def _predict(self, data):
        """
        Predict the output for the provided data.
        """
        # predict with the final state (i.e., the last step)
        # predict with the lowest Cp step
        try:
            res = rpy.r.predict_lars(self.__trained_model,
                                     data,
                                     mode='step',
                                     s=self.__lowest_Cp_step)
                                 #s=self.__trained_model['beta'].shape[0])
            fit = N.atleast_1d(res['fit'])
        except rpy.RPyRException, e:
            warning("Failed to obtain predictions using %s on %s."
                    "Re-raising exception." % (self, data))
            raise

        self.values = fit
        return fit


    def _getFeatureIds(self):
        """Return ids of the used features
        """
        return N.where(N.abs(self.__weights)>0)[0]



    def getSensitivityAnalyzer(self, **kwargs):
        """Returns a sensitivity analyzer for LARS."""
        return LARSWeights(self, **kwargs)

    weights = property(lambda self: self.__weights)



class LARSWeights(Sensitivity):
    """`SensitivityAnalyzer` that reports the weights LARS trained
    on a given `Dataset`.
    """

    _LEGAL_CLFS = [ LARS ]

    def _call(self, dataset=None):
        """Extract weights from LARS classifier.

        LARS always has weights available, so nothing has to be computed here.
        """
        clf = self.clf
        weights = clf.weights

        if __debug__:
            debug('LARS',
                  "Extracting weights for LARS - "+
                  "Result: min=%f max=%f" %\
                  (N.min(weights), N.max(weights)))

        return weights