from sklearn.manifold import TSNE
from sc_dm.datasets import *
import torch
from ptsdae.sdae import StackedDenoisingAutoEncoder as SDAE
if __name__ == '__main__':
# #############################################################################
dset = sys.argv[1]
#raw_data = DuoBenchmark('data/datasets/'+dset+'.csv')
raw_data = FromPickle('data/embeddings/mouse-pca-15000-log1p-True.pickle')
model = SDAE([raw_data.dims, 7500, 500, 2000, 50])
#model.load_state_dict(torch.load('data/models/'+dset+'.pt'))
model.load_state_dict(torch.load(sys.argv[1]))
if int(torch.__version__.split('.')[1]) == 3:
var = torch.autograd.variable.Variable(torch.Tensor(raw_data.data))
else:
var = torch.Tensor(raw_data.data)
embedding = model.encoder(var).data.numpy()
labels = DBSCAN().fit(embedding).labels_
tsne_embedding = TSNE(n_components=2).fit_transform(embedding)
# #############################################################################
plt_file = 'data/plots/mouse_SDAE.pdf'
plt.scatter(tsne_embedding[:, 0],
ds_path = os.path.join('data/datasets', ds_name + '.csv')
dataset = DuoBenchmark(ds_path, log1p=log, split_head=False)
for scale in [True]:
# Do scaling second as the function will
# overwrite the existing data
# yes - yes I know this is bad design but it's too late now
mlist = model_dict[ds_name][log][scale]
# Given all of the pre-existing conditions ...
# cycle through each of the models that match this criteria
for model in mlist:
filename = model[0]
print(filename)
if scale:
scale_dataset(dataset)
# get parameter information
model_path = os.path.join(model_dir, filename)
layers = model[1]
# prepare the model
model = SDAE([dataset.dims] + layers)
model.load_state_dict(
torch.load(model_path, map_location='cpu'))
# generate the embedding
inputs = torch.Tensor(dataset.data)
embedding = model.encoder(inputs).data.numpy()
# save the embedding
with open(
os.path.join('data/sdae_embeddings',
filename + '.pickle'), 'wb') as fh:
pickle.dump(embedding, fh, protocol=4)
