Function mask_test_edges has a Cognitive Complexity of 32 (exceeds 5 allowed). Consider refactoring.

Open

def mask_test_edges(adj):
    # Function to build test set with 10% positive links
    # NOTE: Splits are randomized and results might slightly deviate from reported numbers in the paper.
    # TODO: Clean up.

• Read up
  Read up

File csv_to_npz.py has 329 lines of code (exceeds 250 allowed). Consider refactoring.

Open

"""Process the output of data-to-csv.sh to produce an npz file usable
by an2vec.

This script gets the mutual mention largest connected component of a
weighted edgelist, computes Word2Vec vectors, clusters them,

File scenarios-exploration-asymmetric-n_nodes=1000.py has 253 lines of code (exceeds 250 allowed). Consider refactoring.

Open

# Explore the effect of overlap size in slicing embeddings for scenarios having different network-feature correlation

##
## Imports and setup
##

Function build_uid2tweets has a Cognitive Complexity of 14 (exceeds 5 allowed). Consider refactoring.

Open

def build_uid2tweets(args, uid2orig, orig2lcc):
    """Build the association of user ids to user tweets (split on words,
    filtered for useless words)."""

    # Prepare output variables

• Read up
  Read up

Function mask_test_edges has 30 lines of code (exceeds 25 allowed). Consider refactoring.

Open

def mask_test_edges(adj):
    # Function to build test set with 10% positive links
    # NOTE: Splits are randomized and results might slightly deviate from reported numbers in the paper.
    # TODO: Clean up.

Function build_user_features_lcc has a Cognitive Complexity of 10 (exceeds 5 allowed). Consider refactoring.

Open

def build_user_features_lcc(uid2orig, orig2lcc, uid2tweets, word2cluster):
    """Build the COO matrix of user features, for users in
    the mutual mention largest connected component."""

    logging.info("Build user feature matrix from word/hashtag clustering")

• Read up
  Read up

Function __init__ has 7 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, input_dim, output_dim, adj, features_nonzero, dropout=0., act=tf.nn.relu, **kwargs):

Function __init__ has 6 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, input_dim, output_dim, adj, dropout=0., act=tf.nn.relu, **kwargs):

Avoid deeply nested control flow statements.

Open

                for model_type in tqdm([MODEL_OVERLAP, MODEL_NOOVERLAP]):
                    if model_type == MODEL_OVERLAP:
                        dim_ξ_adj = dim_ξ_ov_adj
                        dim_ξ_v = dim_ξ_ov_v
                        q_overlap = ov

Function make_train_vae has 6 arguments (exceeds 4 allowed). Consider refactoring.

Open

def make_train_vae(dims, q_overlap, p_ξ_slices, skey, with_progress=True):

Function __init__ has 6 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, preds, labels, model, num_nodes, pos_weight, norm):

Function __init__ has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, placeholders, num_features, num_nodes, features_nonzero, **kwargs):

Function make_vae has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

def make_vae(n_nodes, dims, q_overlap, p_ξ_slices):

Function train has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

def train(model, A, labels, features, with_progress=True):

Function csv_to_adj has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

def csv_to_adj(filepath):
    """Read a `weight,src,dst` csv file into a COO adjacency matrix.

    Return the adjacency matrix in COO format, and the map of node ids in
    the file to ids in the matrix.

• Read up
  Read up

Function load_files has a Cognitive Complexity of 6 (exceeds 5 allowed). Consider refactoring.

Open

def load_files(name, clean):
    # Load features
    parts = {}
    for part_name in DATASET_PARTS:
        with open(INPATH + '/ind.{}.{}'.format(name, part_name), 'rb') as f:

• Read up
  Read up