def test_import_dense_values_mat():
"""
Test values after saving and loading of .sparse format.
"""
x = np.random.rand(3, 2)
export_data('/tmp/test.mat', x)
assert np.array_equal(x, import_data('/tmp/test.mat'))
def test_import_dense_type_mat():
"""4
Test the type after saving and loading of .sparset1 format.
"""
x = np.random.rand(3, 2)
export_data('/tmp/test.mat', x)
assert x.dtype == import_data('/tmp/test.mat').dtype
def test_import_sparse_values_mat():
"""
Test values after saving and loading of .sparse format.
"""
x = sps.csr_matrix(np.random.rand(3, 2))
export_data('/tmp/test.mat', x)
assert np.array_equal(x.toarray(), import_data('/tmp/test.mat').toarray())
def test_import_type_sparsetxt():
"""4
Test the type after saving and loading of .sparset1 format.
"""
x = sps.csr_matrix(np.random.rand(3, 2))
export_data('/tmp/test.sparsetxt', x)
assert x.dtype == import_data('/tmp/test.sparsetxt').dtype
def test_import_type_densetxt():
"""
Test the type after saving and loading of .dense format.
"""
x = np.random.rand(7, 11)
export_data('/tmp/test.densetxt', x)
assert x.dtype == import_data('/tmp/test.densetxt').dtype
def test_import_values_dense():
"""
Test values after saving and loading of .dense format.
"""
x = np.random.rand(7, 11)
export_data('/tmp/test.dense', x)
assert np.array_equal(x, import_data('/tmp/test.dense'))
parser.add_argument('-item_list', default=[], nargs='+',
help='One or more item datafiles to use in the split.')
parser.add_argument('-user_list', default=[], nargs='+',
help='List of user datafiles to use in the split.')
args = parser.parse_args()
# slash ambivalent
if not args.readpath.endswith(slash):
args.readpath += slash
if not args.writepath.endswith(slash):
args.writepath += slash
loader.makedirs(args.writepath, cold=True)
# read utility matrix and independently shuffle rows and columns
ratings = loader.import_data(args.readpath + args.ratings)
num_users = ratings.shape[0]
num_items = ratings.shape[1]
num_ratings = ratings.getnnz()
item_order = range(num_items)
user_order = range(num_users)
random.shuffle(item_order)
random.shuffle(user_order)
# save shuffled orders
scipy.io.savemat(args.writepath+'item_order.mat', {'data': np.array(item_order)})
scipy.io.savemat(args.writepath+'user_order.mat', {'data': np.array(user_order)})
ratings = ratings[:, item_order]
ratings = ratings[user_order, :]
split_size = num_ratings*0.05
else:
zipcodes.append(0)
loader.export_data(args.outpath + 'features_sex.index', loader.HotIndex(numpy.array(sexes), 2))
loader.export_data(args.outpath + 'features_occ.index', loader.HotIndex(numpy.array(occupations), len(occlist) -1))
loader.export_data(args.outpath + 'features_zip.index', loader.HotIndex(numpy.array(zipcodes), 1000))
loader.export_data(args.outpath + 'features_age.mat', numpy.array(ages))
# inspect processed data
sex = loader.imatload(args.outpath + 'features_sex.index')
print('sex:')
print(sex.vec.shape, sex.dim)
print(sex.vec[0:10])
print('\n')
occ = loader.imatload(args.outpath + 'features_occ.index')
print('occ:')
print(occ.vec.shape, occ.dim)
print(occ.vec[0:10])
print('\n')
zip = loader.imatload(args.outpath + 'features_zip.index')
print('zip:')
print(zip.vec.shape, zip.dim)
print(zip.vec[0:10])
print('\n')
age = loader.import_data(args.outpath + 'features_age.mat')
print('age:')
print(age.shape)
print(age[0:10])
date = line[2].split('-')
month.append(monthmap[date[1]])
# year released==================================
year.append(float(int(date[2])))
genres = line[5:len(line)]
for i in range(len(genres)):
genres[i] = float(genres[i])
genre.append(genres)
# print(month_matrix.vec.shape, month_matrix.dim, genre_matrix.vec.shape, genre_matrix.dim, year_matrix.shape)
loader.export_data(args.outpath + 'features_month.index', loader.HotIndex(numpy.array(month), 12))
loader.export_data(args.outpath + 'features_year.mat', numpy.array(year))
loader.export_data(args.outpath + 'features_genre.mat', numpy.array(genre))
# inspect processed data
month = loader.import_data(args.outpath + 'features_month.index')
print('month:')
print(month.vec.shape, month.dim)
print(month.vec[0:20])
print('\n')
year = loader.import_data(args.outpath + 'features_year.mat')
print('year:')
print(year.shape)
print(year[0:10])
print('\n')
genre = loader.import_data(args.outpath + 'features_genre.mat')
print('genre:')
print(genre.shape)
print(genre[0:10])
import numpy
from antk.core import loader
import scipy.sparse as sps
from numpy.linalg import norm
genres = loader.import_data(
'/home/aarontuor/data/ml100k/item/features_genre.mat')
dev_item = loader.import_data(
'/home/aarontuor/data/ml100k/dev/features_item.index')
train_item = loader.import_data(
'/home/aarontuor/data/ml100k/train/features_item.index')
test_item = loader.import_data(
'/home/aarontuor/data/ml100k/test/features_item.index')
words = loader.import_data(
'/home/aarontuor/data/ml100k/item/features_bin_doc_term.mat')
genre_dist = genres / (norm(genres, axis=1, keepdims=True) *
norm(genres, axis=1, keepdims=True))
devgenre = genres[dev_item.vec]
testgenre = genres[test_item.vec]
traingenre = genres[train_item.vec]
devwords = words[dev_item.vec]
testwords = words[test_item.vec]
trainwords = words[train_item.vec]
print(devgenre.shape)
print(testgenre.shape)
print(traingenre.shape)
print(devwords.shape)
print(testwords.shape)
print(trainwords.shape)
