Mercurial > pylearn

comparison statscollector.py @ 1:2cd82666b9a7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Added statscollector and started writing dataset and learner.
author bengioy@esprit.iro.umontreal.ca
date Fri, 14 Mar 2008 11:28:08 -0400
parents
children f62a03c9d485
comparison
equal deleted inserted replaced
0:586dcaa4b2df 1:2cd82666b9a7
1
2 from numpy import *
3
4 class StatsCollector(object):
5 """A StatsCollector object is used to record performance statistics during training
6 or testing of a learner. It can be configured to measure different things and
7 accumulate the appropriate statistics. From these statistics it can be interrogated
8 to obtain performance measures of interest (such as maxima, minima, mean, standard
9 deviation, standard error, etc.). Optionally, the observations can be weighted
10 (yielded weighted mean, weighted variance, etc., where applicable). The statistics
11 that are desired can be specified among a list supported by the StatsCollector
12 class or subclass. When some statistics are requested, others become automatically
13 available (e.g., sum or mean)."""
14
15 default_statistics = [mean,standard_deviation,min,max]
16
17 __init__(self,n_quantities_observed, statistics=default_statistics):
18 self.n_quantities_observed=n_quantities_observed
19
20 clear(self):
21 raise NotImplementedError
22
23 update(self,observations):
24 """The observations is a numpy vector of length n_quantities_observed. Some
25 entries can be 'missing' (with a NaN entry) and will not be counted in the
26 statistics."""
27 raise NotImplementedError
28
29 __getattr__(self, statistic)
30 """Return a particular statistic, which may be inferred from the collected statistics.
31 The argument is a string naming that statistic."""
32
33
34
35
36
37