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

Open

def add_thread_nodes(thread_authors, nbunch, parent_id, curr_height, json_data, thread_nodes, conn_subgraph):

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

Open

    def __init__(self, msg_id=0, height=-1, parent_id=0, time=None, from_addr=None, to_addr=None, cc_addr=None):

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

Open

def generate_edge_list(author_nodes, author_edges, graph_nodes,

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

Open

def generate_time_stats_threads(nodelist_filename, edgelist_filename, clean_headers_filename, foldername, time_lbound=None, time_ubound=None, plot=False):

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

Open

def generate_keyword_digest(mbox_filename, output_filename, author_uid_filename, json_filename, top_n = None, console_output=True):

Avoid deeply nested control flow statements.

Open

                        if console_output:
                            print("\n-----\n")
                        else:
                            out_file.write("\n-----\n")
        else:

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

Open

def test_generate_crt_curve_fits(mock_figure, mock_plot, mock_legend, mock_ylabel, mock_xlabel, mock_savefig):

Avoid deeply nested control flow statements.

Open

                    if time_lbound <= json_obj['Time'] < time_ubound:
                        # print("\nFrom", json_obj['From'], "\nTo", json_obj['To'], "\nCc", json_obj['Cc'])
                        from_addr = email_re.search(json_obj['From'])
                        json_obj['From'] = from_addr.group(0) if from_addr is not None else json_obj['From']
                        json_obj['To'] = set(email_re.findall(json_obj['To']))

Avoid deeply nested control flow statements.

Open

                        if console_output:
                            print("\n-----\n")
                        else:
                            out_file.write("\n-----\n")
            # with open("author_top_index.json", 'w') as json_file:

Function remove_unwanted_headers has a Cognitive Complexity of 8 (exceeds 5 allowed). Consider refactoring.

Open

    def remove_unwanted_headers(self, to_remove=unwanted_uid, json_headers="headers.json", output_file="headers.json"):
        """

        This function removes all the UIDs specified in the to_remove parameter. By default, it removes all the unwanted
        entries in the JSON file, i.e. the list of UIDs of mails that are not forwarded from LKML subscription.

• Read up
  Read up

Avoid deeply nested control flow statements.

Open

                    if to_addr not in author_map:
                        author_map[to_addr] = index
                        author_graph.add_vertex(name=to_addr, label=to_addr)
                        index += 1
                    if author_graph[node['From'], to_addr] == 0:

Avoid deeply nested control flow statements.

Open

                    if edge[0] in msgs_before_time and edge[1] in msgs_before_time:
                        discussion_graph.add_edge(*edge)
            edge_file.close()

Avoid deeply nested control flow statements.

Open

                    if time_lbound <= json_obj['Time'] < time_ubound:
                        # print("\nFrom", json_obj['From'], "\nTo", json_obj['To'], "\nCc", json_obj['Cc'])
                        from_addr = email_re.search(json_obj['From'])
                        json_obj['From'] = from_addr.group(0) if from_addr is not None else json_obj['From']
                        json_obj['To'] = set(email_re.findall(json_obj['To']))

Avoid deeply nested control flow statements.

Open

                    if edge[0] in msgs_before_time and edge[1] in msgs_before_time:
                        discussion_graph.add_edge(*edge)
            edge_file.close()

Avoid deeply nested control flow statements.

Open

                    if to_addr not in author_map:
                        author_map[to_addr] = index
                        author_graph.add_vertex(name=to_addr, label=to_addr)
                        index += 1
                    if author_graph[node['From'], to_addr] == 0:

Avoid deeply nested control flow statements.

Open

                    if time_lbound <= json_obj['Time'] < time_ubound:
                        # print("\nFrom", json_obj['From'], "\nTo", json_obj['To'], "\nCc", json_obj['Cc'])
                        from_addr = email_re.search(json_obj['From'])
                        json_obj['From'] = from_addr.group(0) if from_addr is not None else json_obj['From']
                        json_obj['To'] = set(email_re.findall(json_obj['To']))

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

Open

def generate_hyperedge_distribution(nodelist_filename, edgelist_filename, clean_headers_filename, foldername, time_limit=None, ignore_lat=False):

Avoid deeply nested control flow statements.

Open

                    if edge[0] in msgs_before_time and edge[1] in msgs_before_time:
                        discussion_graph.add_edge(*edge)
            edge_file.close()

Avoid deeply nested control flow statements.

Open

                        if not console_output:
                            out_file.write(author_email + "\n")
                            author_features = list()
                            for i in indices:
                                author_features.append(feature_names[i])

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

Open

def vertex_clustering(json_filename, nodelist_filename, edgelist_filename, foldername, time_limit=None, ignore_lat=False):