def generate_blogcatalog_121_embedding():
import visualisation
s = datetime.datetime.now()
y_path = '../../local_resources/blogcatalog_121_sample/y.p'
y = utils.read_pickle(y_path)
log_path = '../../local_resources/tf_logs/run1/'
walk_path = '../../local_resources/blogcatalog_121_sample/walks.csv'
size = 2 # dimensionality of the embedding
params = Params(walk_path, batch_size=4, embedding_size=size, neg_samples=5, skip_window=5, num_pairs=1500,
statistics_interval=10.0,
initial_learning_rate=1.0, save_path=log_path, epochs=1, concurrent_steps=4)
path = '../../local_resources/blogcatalog_121_sample/embeddings/Win' + '_' + utils.get_timestamp() + '.csv'
embedding_in, embedding_out = HE.main(params)
visualisation.plot_poincare_embedding(embedding_in, y,
'../../results/blogcatalog_121_sample/figs/poincare_polar_Win' + '_' + utils.get_timestamp() + '.pdf')
visualisation.plot_poincare_embedding(embedding_out, y,
'../../results/blogcatalog_121_sample/figs/poincare_polar_Wout' + '_' + utils.get_timestamp() + '.pdf')
df_in = pd.DataFrame(data=embedding_in, index=np.arange(embedding_in.shape[0]))
df_in.to_csv(path, sep=',')
df_out = pd.DataFrame(data=embedding_out, index=np.arange(embedding_out.shape[0]))
df_out.to_csv(
'../../local_resources/blogcatalog_121_sample/embeddings/Wout' + '_' + utils.get_timestamp() + '.csv',
sep=',')
print('blogcatalog embedding 121 sample generated in: ', datetime.datetime.now() - s)
MLD.blogcatalog_121_scenario(path)
return path
def generate_karate_embedding():
import visualisation
y_path = '../../local_resources/karate/y.p'
targets = utils.read_pickle(y_path)
y = np.array(targets['cat'])
log_path = '../../local_resources/tf_logs/run4/'
walk_path = '../../local_resources/karate/walks_n1_l10.csv'
size = 2 # dimensionality of the embedding
params = Params(walk_path, batch_size=4, embedding_size=size, neg_samples=5, skip_window=5, num_pairs=1500,
statistics_interval=0.1,
initial_learning_rate=1.0, save_path=log_path, epochs=10, concurrent_steps=1)
path = '../../local_resources/karate/embeddings/tf_Win_polar' + '_' + utils.get_timestamp() + '.csv'
embedding_in, embedding_out = HE.main(params)
visualisation.plot_poincare_embedding(embedding_in, y,
'../../results/karate/figs/poincare_polar_Win' + '_' + utils.get_timestamp() + '.pdf')
visualisation.plot_poincare_embedding(embedding_out, y,
'../../results/karate/figs/poincare_polar_Wout' + '_' + utils.get_timestamp() + '.pdf')
df_in = pd.DataFrame(data=embedding_in, index=range(embedding_in.shape[0]))
df_in.to_csv(path, sep=',')
df_out = pd.DataFrame(data=embedding_out, index=range(embedding_out.shape[0]))
df_out.to_csv(
'../../local_resources/karate/embeddings/tf_Wout_polar' + '_' + utils.get_timestamp() + '.csv',
sep=',')
return path
def simulated_tree_scenario(branching_factor, levels):
import visualisation
folder = '../../local_resources/simulated_trees'
deepwalk_path = '../../local_resources/simulated_trees/deepwalk_z{}_l{}.emd'.format(
branching_factor, levels)
walk_path = '../../local_resources/simulated_trees/walks_long_z{}_l{}.emd'.format(
branching_factor, levels)
emb_path = create_adj_mat(folder, branching_factor, levels)
generate_simulated_tree(emb_path, walk_path, deepwalk_path)
deepwalk_emd = pd.read_csv(deepwalk_path,
header=None,
index_col=0,
skiprows=1,
sep=" ")
s = datetime.datetime.now()
# y_path = '../../local_resources/blogcatalog_121_sample/y.p'
# y = utils.read_pickle(y_path)
y = generate_y(branching_factor, levels)
log_path = '../../local_resources/tf_logs/sim_tree/'
# walk_path = '../../local_resources/simulated_trees/walks.csv'
size = 2 # dimensionality of the embedding
params = Params(walk_path,
batch_size=4,
embedding_size=size,
neg_samples=5,
skip_window=5,
num_pairs=1500,
statistics_interval=0.1,
initial_learning_rate=1.0,
save_path=log_path,
epochs=20,
concurrent_steps=4)
path = '../../local_resources/simulated_trees/embeddings/Win' + '_' + utils.get_timestamp(
) + '.csv'
embedding_in, embedding_out = HE.main(params)
visualisation.plot_deepwalk_embedding(
deepwalk_emd.values, y,
'../../results/simulated_trees/figs/deepwalk_z{}_l{}_{}.pdf'.format(
branching_factor, levels, utils.get_timestamp()))
visualisation.plot_poincare_embedding(
embedding_in, y,
'../../results/simulated_trees/figs/hyp_z{}_l{}_{}.pdf'.format(
branching_factor, levels, utils.get_timestamp()))
df_in = pd.DataFrame(data=embedding_in,
index=np.arange(embedding_in.shape[0]))
df_in.to_csv(path, sep=',')
return path