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

"""

From the .MBOX file, this function extracts the email content is extracted using two predefined classes

available in the Python Standard Library: Mailbox and Message. Feature vectors are created for all the authors

by obtaining meaningful words from the mail content, after removing the stop words, using NLTK libraries.

def conversation_refresh_times(headers_filename, nodelist_filename, edgelist_filename, foldername, time_ubound = None, time_lbound = None, plot=False, ignore_lat = False):

"""

:param headers_filename: The JSON file containing the headers.

:param nodelist_filename: The csv file containing the nodes.

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

"""

This function performs vertex clustering on the dataset passed in the parameters and saves the dendrogram resulting

from the vertex clustering as a PDF along with the visualization of the vertex cluster itself. It is recommended to

limit these graphs to 200 authors as the visualization becomes incompehensible beyond that.

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

"""

:param json_data: The JSON file containing the headers.

:param output_filename: Stores authors' email address,score and rank.

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

"""

This module is used to generate the author version of the width height table. The width height table for the

authors is a representation of the number of total and new authors in a thread aggregated at a given generation.

The table, which itself is temporarily stored in a two dimensional array, is then written into a CSV file. These

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

"""

Generate the distribution of hyperedges for messages in a certain time limit, stores it as hyperedge_distribution.csv based on edge frequency and generates a diagram stored in plots.

:param nodelist_filename: The csv file containing the nodes.

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

"""

Generates and plots statistics for inter-arrival of consecutive messages and distribution of length of each disccussion thread.

:param nodelist_filename: The csv file containing the nodes.

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

"""

Generate the thread width height table, which is a representation of the number of nodes in the graph that have a

given height and a given number of children in a tabular form. This table provides an aggregate statistical view of

def generate_edge_list(author_nodes, author_edges, graph_nodes,

graph_edges, threads_json, author_json, ignore_lat=True):

"""

:param author_nodes: The csv file containing the author nodes data.

:param author_edges: The csv file containing the author edges data.

def generate(ignore_lat=False, time_limit=None):

"""

This function generate a table containing the number of mails in a thread and the corresponding aggregate count

of the number of threads that have that number of mails in them, along with the total number of authors who have

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

"""

Prints the number of strongly connected components,weekly connected components, number of nodes and edges from the author graph.

:param clean_data: Path to clean_data.json file

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

"""

Calls other functions to generate graphs that show the interaction between authors either through multiple edges or

through edge weights.

def generate_hyperedges():

"""

Generates hyperedges from the discussion graph obtained from the nodes and edges stored in graph_nodes.csv and graph_edges.csv.

All email header information can be represented as one hyperedge of a hypergraph.

def remove_invalid_references(input_json_filename, output_json_filename, ref_toggle=False):

"""

This function is used to remove headers associated with invalid references.

:param input_json_filename: The json file containing all the references.

def get_mail_header(to_get, range_=True, uid_map_filename='thread_uid_map.json'):

"""

This function fetches the emails from the IMAP server as per the parameters passed.

:param to_get: List of UIDs of the mails to get. Default value is 2000.

def generate_message_activity_heatmaps(clean_headers_filename, foldername, timeline=True):

"""

Extract header information and call functions to generate various timelines or heatmaps.

:param clean_headers_filename: The JSON file containing cleaned headers.

def get_message_body(message):

"""

Gets the message body of the message passed as a parameter.

:param message: The message whose body is to be extracted.

def get_message_body(message):

"""

Gets the message body of the message.

:param message: The message whose body is to be extracted.

def extract_mail_header(mbox_filename, json_filename='headers.json', thread_uid_filename='thread_uid_map.json', author_uid_filename='author_uid_map.json'):

"""

From the .MBOX file, this function extracts the header information is extracted using two predefined classes

available in the Python Standard Library: Mailbox and Message, for accessing and manipulating on-disk mailboxes

and the messages they contain respectively. The headers are then saved to a JSON file. an unique Message-ID is

def digraph():

"""

This function is used to generate a thread-wise view of the entire mailing list by saving the a graph representing the

messages in a thread as a tree using the References and In-Reply-TO fields from the mail headers. The thread graphs are

then saved to GEXF, DOT and PNG formats. All authors of a thread are identified and each author is given a unique color.