def gs_nai(
g,
targets,
num_samples,
optimizer,
batch_size=4,
epochs=4,
bias=True,
dropout=0.0,
normalize="l2",
seed=0,
shuffle=True,
):
set_seed(seed)
tf.random.set_seed(seed)
if shuffle:
random.seed(seed)
nodes = list(g.nodes())
generator = GraphSAGENodeGenerator(g, batch_size, num_samples)
train_gen = generator.flow(nodes, targets, shuffle=True)
model = gs_nai_model(
num_samples, generator, targets, optimizer, bias, dropout, normalize
)
model.fit_generator(
train_gen,
epochs=epochs,
verbose=1,
use_multiprocessing=False,
workers=4,
shuffle=shuffle,
)
return model
def gs_link_prediction(
g,
edge_ids,
edge_labels,
num_samples,
optimizer,
batch_size=4,
epochs=4,
bias=True,
dropout=0.0,
normalize="l2",
seed=0,
shuffle=True,
):
set_seed(seed)
tf.random.set_seed(seed)
if shuffle:
random.seed(seed)
generator = GraphSAGELinkGenerator(g, batch_size, num_samples)
train_gen = generator.flow(edge_ids, edge_labels, shuffle=True)
model = gs_link_pred_model(num_samples, generator, optimizer, bias,
dropout, normalize)
model.fit(
train_gen,
epochs=epochs,
verbose=1,
use_multiprocessing=False,
workers=4,
shuffle=shuffle,
)
return model
def set_all_seeds(seed: int):
os.environ['PYTHONHASHSEED'] = str(seed)
random.seed(seed)
np.random.seed(seed)
tf.random.set_seed(seed)
sgrand.set_seed(seed)
session_conf = tf.compat.v1.ConfigProto(intra_op_parallelism_threads=0,
inter_op_parallelism_threads=0)
sess = tf.compat.v1.Session(graph=tf.compat.v1.get_default_graph(),
config=session_conf)
tf.compat.v1.keras.backend.set_session(sess)
def unsup_gs(
g,
num_samples,
optimizer,
batch_size=4,
epochs=4,
bias=True,
dropout=0.0,
normalize="l2",
number_of_walks=1,
walk_length=5,
seed=0,
shuffle=True,
):
set_seed(seed)
tf.random.set_seed(seed)
if shuffle:
random.seed(seed)
nodes = list(g.nodes())
unsupervised_samples = UnsupervisedSampler(g,
nodes=nodes,
length=walk_length,
number_of_walks=number_of_walks)
generator = GraphSAGELinkGenerator(g, batch_size, num_samples)
train_gen = generator.flow(unsupervised_samples)
model = unsup_gs_model(num_samples, generator, optimizer, bias, dropout,
normalize)
model.fit(
train_gen,
epochs=epochs,
verbose=1,
use_multiprocessing=False,
workers=4,
shuffle=shuffle,
)
return model
from sklearn import model_selection
from sklearn.linear_model import LogisticRegression
from sklearn.manifold import TSNE
from IPython.display import display, HTML
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.callbacks import EarlyStopping
import tensorflow as tf
from tensorflow.keras import Model
if tf.test.gpu_device_name():
print('Default GPU Device:{}'.format(tf.test.gpu_device_name()))
from pathlib import Path
from helper import Preprocess, Feature
set_seed(0)
tf.random.set_seed(0)
# %% [markdown]
# ## Load graph and node features
# %%
DATA_DIR = Path("../../data/")
FEATURE_DIR = Path("../../data/features/")
FEATURE_NAME = 'adjacentTFs'
MODEL_NAME='renamed_genes'
data_processor = Preprocess()
# %%