def load(dir_path, load_to_memory=False):
"""
Loads the Rectangles dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'targets'``
* ``'length'``
"""
input_size = 784
dir_path = os.path.expanduser(dir_path)
targets = set(range(2))
def load_line(line):
tokens = line.split()
return (np.array([float(i)
for i in tokens[:-1]]), int(float(tokens[-1])))
train_file, valid_file, test_file = [
os.path.join(dir_path, 'rectangles_' + ds + '.amat')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [1000, 200, 50000]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [np.float64, int],
l)
for d, l in zip([train, valid, test], lengths)
]
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [np.float64, int],
l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l,
'targets': targets
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path,load_to_memory=False):
"""
Loads the CAData (California housing prices) dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'length'``
"""
input_size = 8
dir_path = os.path.expanduser(dir_path)
def load_line(line):
return mlio.libsvm_load_line(line, float, float, sparse=False, input_size=input_size)
train_file,valid_file,test_file = [os.path.join(dir_path, 'cadata_' + ds + '.libsvm') for ds in ['train','valid','test']]
# Get data
train,valid,test = [mlio.load_from_file(f,load_line) for f in [train_file,valid_file,test_file]]
lengths = [16512, 2064, 2064]
if load_to_memory:
train,valid,test = [mlio.MemoryDataset(d,[(input_size,),(1,)],[np.float64,int],l) for d,l in zip([train,valid,test],lengths)]
# Get metadata
train_meta,valid_meta,test_meta = [{'input_size':input_size, 'length':l} for l in lengths]
return {'train':(train,train_meta),'valid':(valid,valid_meta),'test':(test,test_meta)}
def load(dir_path,load_to_memory=False,fold=1):
"""
Loads the LETOR 4.0 MQ2007 dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
This dataset comes with 5 predefined folds, which can be specified
with option ``fold`` (default = 1).
**Defined metadata:**
* ``'input_size'``
* ``'scores'``
* ``'n_queries'``
* ``'length'``
"""
input_size=46
dir_path = os.path.expanduser(dir_path)
sparse=False
if fold not in [1,2,3,4,5]:
raise error('There are 5 predefined folds. Option fold should be an integer between 1 and 5')
def convert(feature,value):
if feature != 'qid':
raise ValueError('Unexpected feature')
return int(value)
def load_line(line):
return mlio.libsvm_load_line(line,convert,int,sparse,input_size)
n_queries = [ [ 1017, 339, 336 ],
[ 1017, 336, 339 ],
[ 1014, 339, 339 ],
[ 1014, 339, 339 ],
[ 1014, 339, 339 ] ]
lengths = [ [42158, 13813, 13652],
[41958, 13652, 14013],
[41320, 14013, 14290],
[41478, 14290, 13855],
[41955, 13855, 13813] ]
# Get data file paths
train_file,valid_file,test_file = [os.path.join(dir_path, 'MQ2007/Fold' + str(fold) + '/' + ds + '.txt') for ds in ['train','vali','test']]
# Get data
train,valid,test = [mlio.load_from_file(f,load_line) for f in [train_file,valid_file,test_file]]
if load_to_memory:
train,valid,test = [mlio.MemoryDataset(d,[(input_size,),(1,),(1,)],[np.float64,int,int],l) for d,l in zip([train,valid,test],lengths[fold-1])]
train_meta,valid_meta,test_meta = [{'input_size':input_size,
'scores':range(3),
'n_queries':nq,
'length':l,
'n_pairs':l} for nq,l in zip(n_queries[fold-1],lengths[fold-1])]
return {'train':(train,train_meta),'valid':(valid,valid_meta),'test':(test,test_meta)}
def load(dir_path, load_to_memory=False):
"""
Loads the DNA dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'targets'``
* ``'length'``
"""
input_size = 180
dir_path = os.path.expanduser(dir_path)
targets = set([0, 1, 2])
target_mapping = {'1': 0, '2': 1, '3': 2}
def convert_target(target):
return target_mapping[target]
def load_line(line):
return mlio.libsvm_load_line(line,
convert_target=convert_target,
sparse=False,
input_size=input_size)
train_file, valid_file, test_file = [
os.path.join(dir_path, 'dna_scale_' + ds + '.libsvm')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [1400, 600, 1186]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [np.float64, int],
l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l,
'targets': targets
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False):
"""
Loads the RCV1 dataset. This is actually a smaller version of it, with 150 inputs
and binary targets.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'targets'``
* ``'length'``
"""
input_size = 150
dir_path = os.path.expanduser(dir_path)
targets = set([0, 1])
target_mapping = {'0': 0, '1': 1}
def convert_target(target):
return target_mapping[target]
def load_line(line):
tokens = line.split()
return (np.array([int(i) for i in tokens[:-1]]), int(tokens[-1]))
train_file, valid_file, test_file = [
os.path.join(dir_path,
'rcv1_all_subset.binary_' + ds + '_voc_150.amat')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [40000, 10000, 150000]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [np.float64, int],
l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l,
'targets': targets
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False):
"""
Loads the Housing dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'length'``
"""
input_size = 13
#targets = set(range(2))
#targets = set([0,1])
#target_mapping = {'-1':0,'+1':1}
dir_path = os.path.expanduser(dir_path)
def load_line(line):
return mlio.libsvm_load_line(line,
float,
float,
sparse=False,
input_size=input_size)
#return mlio.libsvm_load_line(line,convert_target=convert_target,sparse=False,input_size=input_size)
train_file, valid_file, test_file = [
os.path.join(dir_path, 'housing_' + ds + '.libsvm')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [404, 51, 51]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )],
[np.float64, np.float64], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
#train_meta,valid_meta,test_meta = [{'input_size':input_size, 'length':l,'targets':targets} for l in lengths]
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False, dtype=np.float64):
"""
Loads the OCR letters dataset.
The data is given by a dictionary mapping from strings
'train', 'valid' and 'test' to the associated pair of data and metadata.
Defined metadata:
- 'input_size'
- 'targets'
- 'length'
References: Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest
Larochelle, Bengio and Turian
link: http://www.cs.toronto.edu/~larocheh/publications/NECO-10-09-1100R2-PDF.pdf
OCR dataset (web page)
link: http://www.seas.upenn.edu/~taskar/ocr/
"""
input_size = 128
targets = set(range(26))
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return (np.array([float(i) for i in tokens[:-1]]), int(tokens[-1]))
#return mlio.libsvm_load_line(line,float,int,sparse,input_size)
train_file, valid_file, test_file = [
os.path.join(dir_path, 'ocr_letters_' + ds + '.txt')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [32152, 10000, 10000]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [dtype, int], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l,
'targets': targets
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False):
"""
Loads the 20-newsgroups dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
The inputs have been put in binary format, and the vocabulary has been
restricted to 5000 words.
**Defined metadata:**
* ``'input_size'``
* ``'targets'``
* ``'length'``
"""
input_size = 5000
targets = set(range(20))
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return (np.array([float(i) for i in tokens[:-1]]), int(tokens[-1]))
train_file, valid_file, test_file = [
os.path.join(dir_path, '20newsgroups_' + ds + '_binary_5000_voc.txt')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [9578, 1691, 7505]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [np.float64, int],
l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l,
'targets': targets
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False):
"""
Loads the MNIST dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
The inputs have been normalized between 0 and 1.
**Defined metadata:**
* ``'input_size'``
* ``'targets'``
* ``'length'``
"""
input_size = 784
targets = set(range(10))
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return (np.array([float(i) for i in tokens[:-1]]), int(tokens[-1]))
#return mlio.libsvm_load_line(line,float,int,sparse,input_size)
train_file, valid_file, test_file = [
os.path.join(dir_path, 'mnist_' + ds + '.txt')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [50000, 10000, 10000]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [np.float64, int],
l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l,
'targets': targets
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False, dtype=np.float64):
"""
Loads the NIPS 0-12 dataset.
The data is given by a dictionary mapping from strings
'train', 'valid' and 'test' to the associated pair of data and metadata.
Defined metadata:
- 'input_size'
- 'length'
References: Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest
Larochelle, Bengio and Turian
link: http://www.cs.toronto.edu/~larocheh/publications/NECO-10-09-1100R2-PDF.pdf
LIBSVM Data: Classification, Regression, and Multi-label (web page)
link: http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/
"""
input_size = 500
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return np.array([int(i) for i in tokens[:-1]
]) #The last element is bogus (don't ask...)
train_file, valid_file, test_file = [
os.path.join(dir_path,
'nips-0-12_all_shuffled_bidon_target_' + ds + '.amat')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [400, 100, 1240]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, )], [dtype], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False):
"""
Loads the occluded MNIST dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
The inputs and targets have been converted to a binary format.
**Defined metadata:**
* ``'input_size'``
* ``'target_size'``
* ``'length'``
"""
input_size = 784
target_size = 784
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return (np.array([int(i) for i in tokens[:input_size]]),
np.array([int(i) for i in tokens[input_size:]]))
train_file, valid_file, test_file = [
os.path.join(dir_path, 'occluded_mnist_' + ds + '.txt')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [50000, 10000, 10000]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (target_size, )],
[np.float64, np.float64], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'target_size': target_size,
'length': l
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False, dtype=np.float64):
"""
Loads a binarized version of MNIST.
The data is given by a dictionary mapping from strings
'train', 'valid' and 'test' to the associated pair of data and metadata.
Defined metadata:
- 'input_size'
- 'length'
Reference: On the Quantitative Analysis of Deep Belief Networks
Salakhutdinov and Murray
link: http://www.mit.edu/~rsalakhu/papers/dbn_ais.pdf
The MNIST database of handwritten digits (web page)
Yann LeCun and Corinna Cortes
link: http://yann.lecun.com/exdb/mnist/
"""
input_size = 784
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return np.array([int(i) for i in tokens])
train_file, valid_file, test_file = [
os.path.join(dir_path, 'binarized_mnist_' + ds + '.amat')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [50000, 10000, 10000]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, )], [dtype], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False):
"""
SARCOS inverse dynamics dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'target_size'``
* ``'length'``
"""
input_size = 21
target_size = 7
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return (np.array([float(i) for i in tokens[:input_size]]),
np.array([float(i) for i in tokens[input_size:]]))
train_file, valid_file, test_file = [
os.path.join(dir_path, 'sarcos_' + ds + '.txt')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [40036, 4448, 4449]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (target_size, )],
[np.float64, np.float64], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'target_size': target_size,
'length': l
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False):
"""
Loads the NIPS 0-12 dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'length'``
"""
input_size = 500
dir_path = os.path.expanduser(dir_path)
def load_line(line):
tokens = line.split()
return np.array([int(i) for i in tokens[:-1]
]) #The last element is bogus (don't ask...)
train_file, valid_file, test_file = [
os.path.join(dir_path,
'nips-0-12_all_shuffled_bidon_target_' + ds + '.amat')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [400, 100, 1240]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, )], [np.float64], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path,load_to_memory=False,dtype=np.float64):
"""
Loads the DNA dataset.
The data is given by a dictionary mapping from strings
'train', 'valid' and 'test' to the associated pair of data and metadata.
Defined metadata:
- 'input_size'
- 'targets'
- 'length'
References: Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest
Larochelle, Bengio and Turian
link: http://www.cs.toronto.edu/~larocheh/publications/NECO-10-09-1100R2-PDF.pdf
LIBSVM Data: Classification, Regression, and Multi-label (web page)
link: http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/
"""
input_size=180
dir_path = os.path.expanduser(dir_path)
targets = set([0,1,2])
target_mapping = {'1':0,'2':1,'3':2}
def convert_target(target):
return target_mapping[target]
def load_line(line):
return mlio.libsvm_load_line(line,convert_target=convert_target,sparse=False,input_size=input_size)
train_file,valid_file,test_file = [os.path.join(dir_path, 'dna_scale_' + ds + '.libsvm') for ds in ['train','valid','test']]
# Get data
train,valid,test = [mlio.load_from_file(f,load_line) for f in [train_file,valid_file,test_file]]
lengths = [1400,600,1186]
if load_to_memory:
train,valid,test = [mlio.MemoryDataset(d,[(input_size,),(1,)],[dtype,int],l) for d,l in zip([train,valid,test],lengths)]
# Get metadata
train_meta,valid_meta,test_meta = [{'input_size':input_size,
'length':l,'targets':targets} for l in lengths]
return {'train':(train,train_meta),'valid':(valid,valid_meta),'test':(test,test_meta)}
def load(dir_path,load_to_memory=False):
"""
Loads the MajMin dataset.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
**Defined metadata:**
* ``'input_size'``
* ``'target_size'``
* ``'length'``
"""
input_size=389
target_size=96
dir_path = os.path.expanduser(dir_path)
def convert_target(target_str):
targets = np.zeros((target_size))
if target_str != '':
for l in target_str.split(','):
id = int(l)
targets[id] = 1
return targets
def load_line(line):
return mlio.libsvm_load_line(line,convert_target=convert_target,sparse=False,input_size=input_size)
train_file,valid_file,test_file = [os.path.join(dir_path, 'majmin_' + ds + '.libsvm') for ds in ['train','valid','test']]
# Get data
train,valid,test = [mlio.load_from_file(f,load_line) for f in [train_file,valid_file,test_file]]
lengths = [1587,471,480]
if load_to_memory:
train,valid,test = [mlio.MemoryDataset(d,[(input_size,),(target_size,)],[np.float64,bool],l) for d,l in zip([train,valid,test],lengths)]
# Get metadata
train_meta,valid_meta,test_meta = [{'input_size':input_size,'target_size':target_size,
'length':l} for l in lengths]
return {'train':(train,train_meta),'valid':(valid,valid_meta),'test':(test,test_meta)}
def load(dir_path, load_to_memory=False, dtype=np.float64):
"""
Loads the RCV1 dataset. This is actually a smaller version of it, with 150 inputs
and binary targets.
The data is given by a dictionary mapping from strings
'train', 'valid' and 'test' to the associated pair of data and metadata.
Defined metadata:
- 'input_size'
- 'targets'
- 'length'
References: Tractable Multivariate Binary Density Estimation and the Restricted Boltzmann Forest
Larochelle, Bengio and Turian
link: http://www.cs.toronto.edu/~larocheh/publications/NECO-10-09-1100R2-PDF.pdf
LIBSVM Data: Classification, Regression, and Multi-label (web page)
link: http://www.csie.ntu.edu.tw/~cjlin/libsvmtools/datasets/
"""
input_size = 150
dir_path = os.path.expanduser(dir_path)
targets = set([0, 1])
target_mapping = {'0': 0, '1': 1}
def convert_target(target):
return target_mapping[target]
def load_line(line):
tokens = line.split()
return (np.array([int(i) for i in tokens[:-1]]), int(tokens[-1]))
train_file, valid_file, test_file = [
os.path.join(dir_path,
'rcv1_all_subset.binary_' + ds + '_voc_150.amat')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
lengths = [40000, 10000, 150000]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, )], [dtype, int], l)
for d, l in zip([train, valid, test], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'length': l,
'targets': targets
} for l in lengths]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
def load(dir_path, load_to_memory=False, home_made_valid_split=False):
"""
Loads the Yahoo! Learning to Rank Challenge, Set 2 data.
The data is given by a dictionary mapping from strings
``'train'``, ``'valid'`` and ``'test'`` to the associated pair of data and metadata.
Option ``home_made_valid_split`` determines whether the original
training set should be further split into a "home made"
train/valid split (default: False). If True, the dictionary mapping
will contain 4 keys instead of 3: ``'train'`` (home made training set),
``'valid'`` (home made validation set), ``'test'`` (original validation set)
and ``'test2'`` (original test set).
**Defined metadata:**
* ``'input_size'``
* ``'scores'``
* ``'n_queries'``
* ``'n_pairs'``
* ``'length'``
"""
input_size = 700
dir_path = os.path.expanduser(dir_path)
sparse = False
def convert(feature, value):
if feature != 'qid':
raise ValueError('Unexpected feature')
return int(value)
def load_line(line):
return mlio.libsvm_load_line(line, convert, int, sparse, input_size)
if home_made_valid_split:
n_queries = [1000, 266, 1266, 3798]
lengths = [27244, 7571, 34881, 103174]
train_file, valid_file, test_file, test2_file = [
os.path.join(dir_path, 'set2.' + ds + '.txt')
for ds in ['in_house_train', 'in_house_valid', 'valid', 'test']
]
# Get data
train, valid, test, test2 = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file, test2_file]
]
if load_to_memory:
train, valid, test, test2 = [
mlio.MemoryDataset(d, [(input_size, ), (1, ), (1, )],
[np.float64, int, int], l)
for d, l in zip([train, valid, test, test2], lengths)
]
# Get metadata
train_meta, valid_meta, test_meta, test2_meta = [{
'input_size': input_size,
'scores': range(5),
'n_queries': nq,
'length': l,
'n_pairs': l
} for nq, l in zip(n_queries, lengths)]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta),
'test2': (test2, test2_meta)
}
else:
n_queries = [1266, 1266, 3798]
lengths = [34815, 34881, 103174]
# Get data file paths
train_file, valid_file, test_file = [
os.path.join(dir_path, 'set2.' + ds + '.txt')
for ds in ['train', 'valid', 'test']
]
# Get data
train, valid, test = [
mlio.load_from_file(f, load_line)
for f in [train_file, valid_file, test_file]
]
if load_to_memory:
train, valid, test = [
mlio.MemoryDataset(d, [(input_size, ), (1, ), (1, )],
[np.float64, int, int], l)
for d, l in zip([train, valid, test], lengths)
]
train_meta, valid_meta, test_meta = [{
'input_size': input_size,
'scores': range(5),
'n_queries': nq,
'length': l,
'n_pairs': l
} for nq, l in zip(n_queries, lengths)]
return {
'train': (train, train_meta),
'valid': (valid, valid_meta),
'test': (test, test_meta)
}
