def test_numpy_format():
maybe_build_index()
td = TrainingData('pcode_abs')
td.load_disk_cache(TMP_DIR, 150)
assert td.songs[0][1][0][0].flags['OWNDATA'] == True
assert not td.songs[0][1][0][0].base
def test_random_rel_ofs():
td = TrainingData('pcode_abs')
td.load_mod_file(TEST_PATH / 'zodiak_-_gasp.mod')
for _ in range(10):
s_i, ss_i, t_i, o = random_rel_ofs(td, 10_000)
transp = td.songs[s_i][ss_i][t_i]
assert len(transp) < o + 10_000
def test_split():
maybe_build_index()
td = TrainingData('pcode_abs')
td.load_disk_cache(TMP_DIR, 150)
train, valid, test = td.split_3way(0.8, 0.1)
assert len(train.songs) + len(valid.songs) + len(test.songs) \
== len(td.songs)
assert train.songs[0][1][0][0].flags['OWNDATA']
assert not train.songs[0][1][0][0].base
def test_pcode_rel():
maybe_build_index()
td = TrainingData('pcode_rel')
td.load_disk_cache(TMP_DIR, 150)
assert len(td.songs) == 26
# end_idx = td.encoder.encode_char((INSN_END, 0), False)
subsongs_per_song = {
'beast2-ingame-st.mod' : 5,
'entity.mod' : 2
}
for name, subsongs in td.songs:
n_subsongs = subsongs_per_song.get(name, 1)
assert len(subsongs) == n_subsongs
def test_pcode_td():
td = TrainingData('pcode_abs')
td.load_mod_file(TEST_PATH / 'zodiak_-_gasp.mod')
# end_idx = td.encoder.encode_char((INSN_END, 0), False)
assert len(td.songs) == 1
assert td.songs[0][0] == 'zodiak_-_gasp.mod'
first_subsong = td.songs[0][1][0]
assert sum(transp.shape[0] for transp in first_subsong) == 13423 * 5
code = td.encoder.decode_chars(first_subsong[0][:120])
code = [(c, a) for (c, a) in code if c == INSN_PITCH]
assert code == [('P', 24), ('P', 24),
('P', 27), ('P', 27),
('P', 24)]
transp0 = first_subsong[0]
n_code = len(transp0)
for transp in first_subsong[1:]:
assert len(transp) == n_code
assert not np.array_equal(transp, transp0)
def main():
# Prologue
args = docopt(__doc__, version = 'Model stats 1.0')
SP.enabled = args['--verbose']
root_path = Path(args['<root-path>'])
# Kind of code
g = get_code_generator(args['<model>'])
# Load training data
td = TrainingData(g['code-type'])
td.load_disk_cache(root_path, 150)
stats_path = root_path / 'stats'
stats_path.mkdir(exist_ok = True)
png_path = stats_path / ('tokens-%s.png' % g['code-type'])
token_distribution_plot(td, png_path)
weights_dir = root_path / 'weights'
log_path = weights_dir / log_file(g)
png_path = stats_path / ('loss-%s.png' % file_stem(g))
loss_plot(log_path, png_path)
def test_save_generated_sequences():
g = get_code_generator('orig-pcode')
output_path = TMP_DIR / 'generated'
if output_path.exists():
rmtree(output_path)
output_path.mkdir(parents = True)
td = TrainingData('pcode_abs')
td.load_disk_cache(TMP_DIR, 150)
offsets = [random_rel_ofs(td, 100)]
seqs = [np.array([1, 2, 3, 4, 5])]
log_probs = [-100]
skews = [('top-p', 0.98)]
save_generated_sequences(g, output_path, td, seqs, offsets,
log_probs, skews)
files = list(output_path.glob('*.pickle.gz'))
assert len(files) == 1
parts = files[0].stem.split('-')
rel_ofs = [int(p) for p in parts[:4]]
for p in rel_ofs:
assert p >= 0
def test_dcode():
maybe_build_index()
td = TrainingData('dcode')
td.load_disk_cache(TMP_DIR, 150)
assert len(td.songs) == 26
def test_histogram():
td = TrainingData('pcode_abs')
td.load_mod_file(TEST_PATH / 'im_a_hedgehog.mod')
print_histogram(td)
def test_abs_to_rel_ofs():
td = TrainingData('pcode_abs')
td.load_mod_file(TEST_PATH / 'zodiak_-_gasp.mod')
rel_ofs = abs_ofs_to_rel_ofs(td, 36000)
assert rel_ofs == (0, 0, 2, 9154)