def test_skll_convert_libsvm_map():
"""
Test to check whether the --reuse_libsvm_map option works for skll_convert
"""
# create some simple classification data
orig_fs, _ = make_classification_data(train_test_ratio=1.0,
one_string_feature=True)
# now write out this feature set as a libsvm file
orig_libsvm_file = join(_my_dir, 'other',
'test_skll_convert_libsvm_map.libsvm')
writer = LibSVMWriter(orig_libsvm_file, orig_fs, quiet=True)
writer.write()
# now make a copy of the dataset
swapped_fs = copy.deepcopy(orig_fs)
# now modify this new featureset to swap the first two columns
del swapped_fs.vectorizer.vocabulary_['f01']
del swapped_fs.vectorizer.vocabulary_['f02']
swapped_fs.vectorizer.vocabulary_['f01'] = 1
swapped_fs.vectorizer.vocabulary_['f02'] = 0
tmp = swapped_fs.features[:, 0]
swapped_fs.features[:, 0] = swapped_fs.features[:, 1]
swapped_fs.features[:, 1] = tmp
# now write out this new feature set as a MegaM file
swapped_megam_file = join(_my_dir, 'other',
'test_skll_convert_libsvm_map.megam')
writer = MegaMWriter(swapped_megam_file, swapped_fs, quiet=True)
writer.write()
# now run skll_convert to convert this into a libsvm file
# but using the mapping specified in the first libsvm file
converted_libsvm_file = join(_my_dir, 'other',
'test_skll_convert_libsvm_map2.libsvm')
# now call skll convert's main function
skll_convert_cmd = [
'--reuse_libsvm_map', orig_libsvm_file, '--quiet', orig_libsvm_file,
converted_libsvm_file
]
err = ''
try:
old_stderr = sys.stderr
sys.stderr = mystderr = StringIO()
sk.main(skll_convert_cmd)
err = mystderr.getvalue()
finally:
sys.stderr = old_stderr
print(err)
# now read the converted libsvm file into a featureset
reader = LibSVMReader(converted_libsvm_file, quiet=True)
converted_fs = reader.read()
# now ensure that this new featureset and the original
# featureset are the same
eq_(orig_fs, converted_fs)
def test_skll_convert_libsvm_map():
"""
Test to check whether the --reuse_libsvm_map option works for skll_convert
"""
# create some simple classification data
orig_fs, _ = make_classification_data(train_test_ratio=1.0,
one_string_feature=True)
# now write out this feature set as a libsvm file
orig_libsvm_file = join(_my_dir, 'other',
'test_skll_convert_libsvm_map.libsvm')
writer = LibSVMWriter(orig_libsvm_file, orig_fs, quiet=True)
writer.write()
# now make a copy of the dataset
swapped_fs = copy.deepcopy(orig_fs)
# now modify this new featureset to swap the first two columns
del swapped_fs.vectorizer.vocabulary_['f01']
del swapped_fs.vectorizer.vocabulary_['f02']
swapped_fs.vectorizer.vocabulary_['f01'] = 1
swapped_fs.vectorizer.vocabulary_['f02'] = 0
tmp = swapped_fs.features[:, 0]
swapped_fs.features[:, 0] = swapped_fs.features[:, 1]
swapped_fs.features[:, 1] = tmp
# now write out this new feature set as a MegaM file
swapped_megam_file = join(_my_dir, 'other',
'test_skll_convert_libsvm_map.megam')
writer = MegaMWriter(swapped_megam_file, swapped_fs, quiet=True)
writer.write()
# now run skll_convert to convert this into a libsvm file
# but using the mapping specified in the first libsvm file
converted_libsvm_file = join(_my_dir, 'other',
'test_skll_convert_libsvm_map2.libsvm')
# now call skll convert's main function
skll_convert_cmd = ['--reuse_libsvm_map', orig_libsvm_file,
'--quiet', orig_libsvm_file,
converted_libsvm_file]
err = ''
try:
old_stderr = sys.stderr
sys.stderr = mystderr = StringIO()
sk.main(skll_convert_cmd)
err = mystderr.getvalue()
finally:
sys.stderr = old_stderr
print(err)
# now read the converted libsvm file into a featureset
reader = LibSVMReader(converted_libsvm_file, quiet=True)
converted_fs = reader.read()
# now ensure that this new featureset and the original
# featureset are the same
eq_(orig_fs, converted_fs)
def check_convert_featureset(from_suffix, to_suffix):
num_feat_files = 5
# Create test data
make_conversion_data(num_feat_files, from_suffix, to_suffix)
# the path to the unmerged feature files
dirpath = os.path.join(_my_dir, 'train', 'test_conversion')
# get the feature name prefix
feature_name_prefix = '{}_to_{}'.format(from_suffix.lstrip('.'),
to_suffix.lstrip('.'))
# Load each unmerged feature file in the `from_suffix` format
# and convert it to the `to_suffix` format
for feature in range(num_feat_files):
input_file_path = os.path.join(
dirpath, '{}_{}{}'.format(feature_name_prefix, feature,
from_suffix))
output_file_path = os.path.join(
dirpath, '{}_{}{}'.format(feature_name_prefix, feature, to_suffix))
skll_convert.main(['--quiet', input_file_path, output_file_path])
# now load and merge all unmerged, converted features in the `to_suffix` format
featureset = [
'{}_{}'.format(feature_name_prefix, i) for i in range(num_feat_files)
]
merged_examples = _load_featureset(dirpath,
featureset,
to_suffix,
quiet=True)
# Load pre-merged data in the `to_suffix` format
featureset = ['{}_all'.format(feature_name_prefix)]
premerged_examples = _load_featureset(dirpath,
featureset,
to_suffix,
quiet=True)
# make sure that the pre-generated merged data in the to_suffix format
# is the same as the converted, merged data in the to_suffix format
assert np.all(merged_examples.ids == premerged_examples.ids)
assert np.all(merged_examples.classes == premerged_examples.classes)
assert np.all(merged_examples.features.todense() ==
premerged_examples.features.todense())
eq_(merged_examples.feat_vectorizer.feature_names_,
premerged_examples.feat_vectorizer.feature_names_)
eq_(merged_examples.feat_vectorizer.vocabulary_,
premerged_examples.feat_vectorizer.vocabulary_)
def check_convert_featureset(from_suffix, to_suffix):
num_feat_files = 5
# Create test data
make_conversion_data(num_feat_files, from_suffix, to_suffix)
# the path to the unmerged feature files
dirpath = join(_my_dir, 'train', 'test_conversion')
# get the feature name prefix
feature_name_prefix = '{}_to_{}'.format(from_suffix.lstrip('.'),
to_suffix.lstrip('.'))
# Load each unmerged feature file in the `from_suffix` format and convert
# it to the `to_suffix` format
for feature in range(num_feat_files):
input_file_path = join(
dirpath, '{}_{}{}'.format(feature_name_prefix, feature,
from_suffix))
output_file_path = join(
dirpath, '{}_{}{}'.format(feature_name_prefix, feature, to_suffix))
skll_convert.main(['--quiet', input_file_path, output_file_path])
# now load and merge all unmerged, converted features in the `to_suffix`
# format
featureset = [
'{}_{}'.format(feature_name_prefix, i) for i in range(num_feat_files)
]
merged_exs = _load_featureset(dirpath, featureset, to_suffix, quiet=True)
# Load pre-merged data in the `to_suffix` format
featureset = ['{}_all'.format(feature_name_prefix)]
premerged_exs = _load_featureset(dirpath,
featureset,
to_suffix,
quiet=True)
# make sure that the pre-generated merged data in the to_suffix format
# is the same as the converted, merged data in the to_suffix format
assert_array_equal(merged_exs.ids, premerged_exs.ids)
assert_array_equal(merged_exs.labels, premerged_exs.labels)
for (_, _, merged_feats), (_, _,
premerged_feats) in zip(merged_exs,
premerged_exs):
eq_(merged_feats, premerged_feats)
eq_(sorted(merged_exs.vectorizer.feature_names_),
sorted(premerged_exs.vectorizer.feature_names_))
def check_convert_featureset(from_suffix, to_suffix):
num_feat_files = 5
# Create test data
make_conversion_data(num_feat_files, from_suffix, to_suffix)
# the path to the unmerged feature files
dirpath = join(_my_dir, 'train', 'test_conversion')
# get the feature name prefix
feature_name_prefix = '{}_to_{}'.format(from_suffix.lstrip('.'),
to_suffix.lstrip('.'))
# Load each unmerged feature file in the `from_suffix` format and convert
# it to the `to_suffix` format
for feature in range(num_feat_files):
input_file_path = join(dirpath, '{}_{}{}'.format(feature_name_prefix,
feature,
from_suffix))
output_file_path = join(dirpath, '{}_{}{}'.format(feature_name_prefix,
feature, to_suffix))
skll_convert.main(['--quiet', input_file_path, output_file_path])
# now load and merge all unmerged, converted features in the `to_suffix`
# format
featureset = ['{}_{}'.format(feature_name_prefix, i) for i in
range(num_feat_files)]
merged_exs = _load_featureset(dirpath, featureset, to_suffix,
quiet=True)
# Load pre-merged data in the `to_suffix` format
featureset = ['{}_all'.format(feature_name_prefix)]
premerged_exs = _load_featureset(dirpath, featureset, to_suffix,
quiet=True)
# make sure that the pre-generated merged data in the to_suffix format
# is the same as the converted, merged data in the to_suffix format
assert_array_equal(merged_exs.ids, premerged_exs.ids)
assert_array_equal(merged_exs.labels, premerged_exs.labels)
for (_, _, merged_feats), (_, _, premerged_feats) in zip(merged_exs,
premerged_exs):
eq_(merged_feats, premerged_feats)
eq_(sorted(merged_exs.vectorizer.feature_names_),
sorted(premerged_exs.vectorizer.feature_names_))
def check_convert_featureset(from_suffix, to_suffix):
num_feat_files = 5
# Create test data
make_conversion_data(num_feat_files, from_suffix, to_suffix)
# the path to the unmerged feature files
dirpath = os.path.join(_my_dir, 'train', 'test_conversion')
# get the feature name prefix
feature_name_prefix = '{}_to_{}'.format(from_suffix.lstrip('.'), to_suffix.lstrip('.'))
# Load each unmerged feature file in the `from_suffix` format
# and convert it to the `to_suffix` format
for feature in range(num_feat_files):
input_file_path = os.path.join(dirpath, '{}_{}{}'.format(feature_name_prefix,
feature, from_suffix))
output_file_path = os.path.join(dirpath, '{}_{}{}'.format(feature_name_prefix,
feature, to_suffix))
skll_convert.main(['--quiet', input_file_path, output_file_path])
# now load and merge all unmerged, converted features in the `to_suffix` format
featureset = ['{}_{}'.format(feature_name_prefix, i) for i in range(num_feat_files)]
merged_examples = _load_featureset(dirpath, featureset, to_suffix, quiet=True)
# Load pre-merged data in the `to_suffix` format
featureset = ['{}_all'.format(feature_name_prefix)]
premerged_examples = _load_featureset(dirpath, featureset, to_suffix, quiet=True)
# make sure that the pre-generated merged data in the to_suffix format
# is the same as the converted, merged data in the to_suffix format
assert np.all(merged_examples.ids == premerged_examples.ids)
assert np.all(merged_examples.classes == premerged_examples.classes)
assert np.all(merged_examples.features.todense() ==
premerged_examples.features.todense())
eq_(merged_examples.feat_vectorizer.feature_names_,
premerged_examples.feat_vectorizer.feature_names_)
eq_(merged_examples.feat_vectorizer.vocabulary_,
premerged_examples.feat_vectorizer.vocabulary_)
def check_skll_convert(from_suffix, to_suffix):
# create some simple classification data
orig_fs, _ = make_classification_data(train_test_ratio=1.0,
one_string_feature=True)
# now write out this feature set in the given suffix
from_suffix_file = join(_my_dir, 'other',
'test_skll_convert_in{}'.format(from_suffix))
to_suffix_file = join(_my_dir, 'other',
'test_skll_convert_out{}'.format(to_suffix))
writer = EXT_TO_WRITER[from_suffix](from_suffix_file, orig_fs, quiet=True)
writer.write()
# now run skll convert to convert the featureset into the other format
skll_convert_cmd = [from_suffix_file, to_suffix_file, '--quiet']
# we need to capture stderr to make sure we don't miss any errors
err = ''
try:
old_stderr = sys.stderr
sys.stderr = mystderr = StringIO()
sk.main(skll_convert_cmd)
err = mystderr.getvalue()
finally:
sys.stderr = old_stderr
print(err)
# now read the converted file
reader = EXT_TO_READER[to_suffix](to_suffix_file, quiet=True)
converted_fs = reader.read()
# ensure that the original and the converted feature sets
# are the same
eq_(orig_fs, converted_fs)
def check_convert_featureset(from_suffix, to_suffix, with_labels=True):
num_feat_files = 5
# Create test data
make_conversion_data(num_feat_files,
from_suffix,
to_suffix,
with_labels=with_labels)
# the path to the unmerged feature files
dirpath = join(_my_dir, 'train', 'test_conversion')
# get the feature name prefix
feature_name_prefix = '{}_to_{}'.format(from_suffix.lstrip('.'),
to_suffix.lstrip('.'))
# use '_unlabeled' as part of any file names when not using labels
with_labels_part = '' if with_labels else '_unlabeled'
# Load each unmerged feature file in the `from_suffix` format and convert
# it to the `to_suffix` format
for feature in range(num_feat_files):
input_file_path = join(
dirpath, '{}_{}{}{}'.format(feature_name_prefix, feature,
with_labels_part, from_suffix))
output_file_path = join(
dirpath, '{}_{}{}{}'.format(feature_name_prefix, feature,
with_labels_part, to_suffix))
skll_convert_args = ['--quiet', input_file_path, output_file_path]
if not with_labels:
skll_convert_args.append('--no_labels')
skll_convert.main(skll_convert_args)
# now load and merge all unmerged, converted features in the `to_suffix`
# format
featureset = [
'{}_{}{}'.format(feature_name_prefix, i, with_labels_part)
for i in range(num_feat_files)
]
label_col = 'y' if with_labels else None
merged_exs = _load_featureset(dirpath,
featureset,
to_suffix,
label_col=label_col,
quiet=True)
# Load pre-merged data in the `to_suffix` format
featureset = ['{}{}_all'.format(feature_name_prefix, with_labels_part)]
premerged_exs = _load_featureset(dirpath,
featureset,
to_suffix,
label_col=label_col,
quiet=True)
# make sure that the pre-generated merged data in the to_suffix format
# is the same as the converted, merged data in the to_suffix format
# first check the IDs
assert_array_equal(merged_exs.ids, premerged_exs.ids)
assert_array_equal(merged_exs.labels, premerged_exs.labels)
for (_, _, merged_feats), (_, _,
premerged_feats) in zip(merged_exs,
premerged_exs):
eq_(merged_feats, premerged_feats)
eq_(sorted(merged_exs.vectorizer.feature_names_),
sorted(premerged_exs.vectorizer.feature_names_))
def check_convert_featureset(from_suffix, to_suffix, with_labels=True):
num_feat_files = 5
# Create test data
make_conversion_data(num_feat_files,
from_suffix,
to_suffix,
with_labels=with_labels)
# the path to the unmerged feature files
dirpath = join(_my_dir, 'train', 'test_conversion')
# get the feature name prefix
feature_name_prefix = '{}_to_{}'.format(from_suffix.lstrip('.'),
to_suffix.lstrip('.'))
# use '_unlabeled' as part of any file names when not using labels
with_labels_part = '' if with_labels else '_unlabeled'
# Load each unmerged feature file in the `from_suffix` format and convert
# it to the `to_suffix` format
for feature in range(num_feat_files):
input_file_path = join(dirpath, '{}_{}{}{}'.format(feature_name_prefix,
feature,
with_labels_part,
from_suffix))
output_file_path = join(dirpath, '{}_{}{}{}'.format(feature_name_prefix,
feature,
with_labels_part,
to_suffix))
skll_convert_args = ['--quiet', input_file_path, output_file_path]
if not with_labels:
skll_convert_args.append('--no_labels')
skll_convert.main(skll_convert_args)
# now load and merge all unmerged, converted features in the `to_suffix`
# format
featureset = ['{}_{}{}'.format(feature_name_prefix, i, with_labels_part) for i in
range(num_feat_files)]
label_col = 'y' if with_labels else None
merged_exs = _load_featureset(dirpath,
featureset,
to_suffix,
label_col=label_col,
quiet=True)
# Load pre-merged data in the `to_suffix` format
featureset = ['{}{}_all'.format(feature_name_prefix, with_labels_part)]
premerged_exs = _load_featureset(dirpath,
featureset,
to_suffix,
label_col=label_col,
quiet=True)
# make sure that the pre-generated merged data in the to_suffix format
# is the same as the converted, merged data in the to_suffix format
# first check the IDs
assert_array_equal(merged_exs.ids, premerged_exs.ids)
assert_array_equal(merged_exs.labels, premerged_exs.labels)
for (_, _, merged_feats), (_, _, premerged_feats) in zip(merged_exs,
premerged_exs):
eq_(merged_feats, premerged_feats)
eq_(sorted(merged_exs.vectorizer.feature_names_),
sorted(premerged_exs.vectorizer.feature_names_))
