Avoid deeply nested control flow statements.

Open

                    if edge[0] in msgs_before_time and edge[1] in msgs_before_time:
                        try:
                            discussion_graph.node[edge[0]]['sender']
                            discussion_graph.node[edge[1]]['sender']
                            discussion_graph.add_edge(*edge)

Avoid deeply nested control flow statements.

Open

                    if json_obj['Time'] < time_limit:
                        # 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 test_generate_cl_curve_fits has 6 arguments (exceeds 4 allowed). Consider refactoring.

Open

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

Avoid deeply nested control flow statements.

Open

                    if not jfile['References'] == "":
                        # The references are stored as a comma separated string. We have to split it at the ',' to get a list.
                        if ref_toggle:
                            ref_list = jfile['References'].split(',')
                        else:

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

Open

    def remove_duplicate_headers(self,to_remove=duplicate_uid, json_headers="headers.json", output_file="headers.json"):
        """

        This function removes all the duplicate entries of the UIDs specified in the to_remove parameter. By default,
        it removes all the duplicate entries in the JSON file.

• Read up
  Read up

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

Open

    def replace_invalid_headers(self,to_replace=invalid_uid, json_headers="headers.json", output_file="headers.json", unwanted_uid_filename="unwanted_uid.txt", uid_map_filename="thread_uid_map.json"):
        """

        This function removes the mail headers that have insufficient attributes and fetches those headers again.
        If an attribute is missing in the original mail header or if the mail has been deleted, this function ignores that UID.

• Read up
  Read up

Avoid deeply nested control flow statements.

Open

                        if isinstance(response_part, tuple):

                            # response_part contains the required info as a byte stream. This has to be converted to a message stream.
                            # This is done using the email module
                            original = email.message_from_bytes(response_part[1])

Avoid deeply nested control flow statements.

Open

                    if author_graph[node['From'], to_addr] == 0:
                        author_graph.add_edge(node['From'], to_addr, weight=1)
                    else:
                        author_graph[node['From'], to_addr] += 1
            if node['Cc'] is None:

Avoid deeply nested control flow statements.

Open

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

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

Open

def generate_wh_table_threads(nodelist_filename, edgelist_filename, output_filename, ignore_lat=False, time_limit=None):

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

Open

    def replace_invalid_headers(self,to_replace=invalid_uid, json_headers="headers.json", output_file="headers.json", unwanted_uid_filename="unwanted_uid.txt", uid_map_filename="thread_uid_map.json"):

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

Open

def add_to_weighted_graph(graph_obj, discussion_graph, json_data, nbunch, node_enum=list()):

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

Open

def weighted_multigraph(graph_nodes, graph_edges, clean_data, output_dir, ignore_lat = False):

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

Open

def generate_kmeans_clustering(mbox_filename, output_filename, author_uid_filename, json_filename, top_n = None):

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

Open

def generate_wh_table_authors(nodelist_filename, edgelist_filename, output_filename, ignore_lat=False, time_limit=None):

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

Open

def get(json_filename, output_filename, active_score, passive_score, write_to_file=True):

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

Open

def add_to_multigraph(graph_obj, discussion_graph, json_data, nbunch, label_prefix=''):

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

Open

def author_interaction(clean_data, graph_nodes, graph_edges, pajek_file, ignore_lat=True):

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

Open

    def write_uid_map(self,from_index=1, to_index=last_uid_read, uid_map_filename="thread_uid_map.json"):
        """
    
        To ensure that references are correctly recorded in the JSON file such that there are no references to mails that
        do not exist and to ease the processing of headers, a map with the string in the Message-Id field of the header to

• Read up
  Read up