# HG changeset patch
# User Pierre-Antoine Manzagol <pierre.antoine.manzagol@gmail.com>
# Date 1265388828 18000
# Node ID 257a39cce72c758d4b8a680072d43d98e9ea20e7
# Parent  032911ac4941d822117061672ba545eedf55ad04
Provides a ``Dataset`` for the nist reshuffled digits dataset.

diff -r 032911ac4941 -r 257a39cce72c pylearn/datasets/nist_sd.py
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/pylearn/datasets/nist_sd.py	Fri Feb 05 11:53:48 2010 -0500
@@ -0,0 +1,56 @@
+"""
+Provides a Dataset to access the nist digits_reshuffled dataset. 
+"""
+
+import os, numpy
+from pylearn.io import filetensor as ft
+from pylearn.datasets.config import data_root # config
+from pylearn.datasets.dataset import Dataset
+
+
+def load(dataset = 'train', attribute = 'data'):
+  """Load the filetensor corresponding to the set and attribute.
+
+  :param dataset: str that is 'train', 'valid' or 'test'
+  :param attribute: str that is 'data' or 'labels'
+  """
+  fn = 'digits_reshuffled_' + dataset + '_' + attribute + '.ft'
+  fn = os.path.join(data_root(), 'nist', 'by_class', 'digits_reshuffled', fn)
+
+  fd = open(fn)
+  data = ft.read(fd)
+  fd.close()
+
+  return data
+
+def train_valid_test(ntrain=285661, nvalid=58646, ntest=58646, path=None):
+  """
+  Load the nist reshuffled digits dataset as a Dataset.
+
+  @note: the examples are uint8 and the labels are int32.
+  @todo: possibility of loading part of the data.
+  """
+  rval = Dataset()
+
+  # 
+  rval.n_classes = 10
+  rval.img_shape = (32,32)
+
+  # train
+  examples = load(dataset = 'train', attribute = 'data')
+  labels = load(dataset = 'train', attribute = 'labels')
+  rval.train = Dataset.Obj(x=examples[:ntrain], y=labels[:ntrain])
+
+  # valid
+  examples = load(dataset = 'valid', attribute = 'data')
+  labels = load(dataset = 'valid', attribute = 'labels')
+  rval.valid = Dataset.Obj(x=examples[:nvalid], y=labels[:nvalid])
+
+  # test
+  examples = load(dataset = 'test', attribute = 'data')
+  labels = load(dataset = 'test', attribute = 'labels')
+  rval.test = Dataset.Obj(x=examples[:ntest], y=labels[:ntest])
+  
+  return rval
+
+