def test_loading_unordered_feature_lists(tmpdir):
d = {
'a/N': [('f1', 1), ('f2', 2), ('f3', 3)],
'b/N': [('f3', 3), ('f1', 1), ('f2', 2), ],
'c/N': [('f3', 3), ('f2', 2), ('f1', 1)],
} # three identical vectors
v = Vectors(d)
filename = str(tmpdir.join('outfile.txt'))
v.to_tsv(filename)
v1 = v.from_tsv(filename)
assert v.columns == v1.columns # rows can be in any order, but columns need to be sorted
for word in d.keys():
assert_array_equal(v.get_vector(word).A, v1.get_vector(word).A)
def test_loading_dict_of_dicts():
d = {
'monday': {
'det:the': 23,
'amod:terrible': 321
},
'tuesday': {
'amod:awful': 231,
'det:a': 12
}
}
v = Vectors(d)
v1 = v.from_dict_of_dicts(d)
assert v.columns == v1.columns
for word in d.keys():
assert_array_equal(v.get_vector(word).A, v1.get_vector(word).A)