def test_message_number_graph(self, log_data, nicks, nick_same_list):
update_expected_output_directory(log_data)
msg_number_graph = network.message_number_graph(
log_data, nicks, nick_same_list)
self.assertTrue(compare_graph_outputs(msg_number_graph,
"message_number_graph.gpickle"),
msg=None)
def test_community_analysis_single_channel_cutoff_20(self):
log_data = reader.linux_input(self.log_data_dir, ["#kubuntu-devel"],
self.start_date, self.end_date)
expected_result = util.load_from_disk(
self.current_directory +
'/data/output/community_analysis_single_channel_cutoff_20')
nicks, nick_same_list = nickTracker.nick_tracker(log_data)
default_cutoff = config.THRESHOLD_MESSAGE_NUMBER_GRAPH
config.THRESHOLD_MESSAGE_NUMBER_GRAPH = 20
message_number_graph = network.message_number_graph(
log_data, nicks, nick_same_list, False)
saver.save_net_nx_graph(
message_number_graph, self.current_directory,
"message-exchange-" + self.start_date + "-cutoff-" +
str(config.THRESHOLD_MESSAGE_NUMBER_GRAPH))
expected_output = community.infomap_igraph(
ig_graph=None,
net_file_location=self.current_directory + "/message-exchange-" +
self.start_date + "-cutoff-" +
str(config.THRESHOLD_MESSAGE_NUMBER_GRAPH) + '.net')
os.remove(self.current_directory + "/message-exchange-" +
self.start_date + "-cutoff-" +
str(config.THRESHOLD_MESSAGE_NUMBER_GRAPH) + '.net')
config.THRESHOLD_MESSAGE_NUMBER_GRAPH = default_cutoff
self.assertTrue(expected_result[0].isomorphic(expected_output[0]))
self.assertEqual(
compare_communities(expected_result[1], expected_output[1]), 0)
def test_degree_analysis_on_nodes(self, log_data, nicks, nick_same_list):
update_expected_output_directory(log_data)
message_number_graph = network.message_number_graph(
log_data, nicks, nick_same_list)
message_time_graph = network.message_time_graph(
log_data, nicks, nick_same_list)
nick_change_graph = user.nick_change_graph(log_data)
degree_anal_message_number = network.degree_analysis_on_graph(
message_number_graph)
degree_anal_message_time = network.degree_analysis_on_graph(
message_time_graph)
degree_anal_nick_change = network.degree_analysis_on_graph(
nick_change_graph)
expected_analysis_msg_number = []
expected_analysis_msg_time = []
expected_analysis_nick_change = []
unjson('degree_anal_message_number.json', expected_analysis_msg_number)
unjson('degree_anal_message_time.json', expected_analysis_msg_time)
unjson('degree_anal_nick_change.json', expected_analysis_nick_change)
self.assertDictEqual(degree_anal_message_number,
expected_analysis_msg_number[0],
msg=None)
self.assertDictEqual(degree_anal_message_time,
expected_analysis_msg_time[0],
msg=None)
self.assertDictEqual(degree_anal_nick_change,
expected_analysis_nick_change[0],
msg=None)
def box_plot_for_degree(log_directory, output_directory, channel_name):
cutoff = 0
for channel_name_iter in channel_name:
out_degree_fit_parameters = np.zeros((12, 4))
in_degree_fit_parameters = np.zeros((12, 4))
total_degree_fit_parameters = np.zeros((12, 4))
for month in range(1, 13):
log_data = reader.linux_input(log_directory, channel_name_iter,
"2013-" + str(month) + "-1",
"2013-" + str(month) + "-31")
nicks, nick_same_list = nickTracker.nick_tracker(log_data)
message_number_graph = network.message_number_graph(
log_data, nicks, nick_same_list, False)
degree_anal_message_number = network.degree_analysis_on_graph(
message_number_graph)
out_degree_fit_parameters[month - 1] = vis.generate_log_plots(
degree_anal_message_number["out_degree"]["raw_for_vis"],
output_directory, channel_name_iter[0])
in_degree_fit_parameters[month - 1] = vis.generate_log_plots(
degree_anal_message_number["in_degree"]["raw_for_vis"],
output_directory, channel_name_iter[0])
total_degree_fit_parameters[month - 1] = vis.generate_log_plots(
degree_anal_message_number["total_degree"]["raw_for_vis"],
output_directory, channel_name_iter[0])
parameters = ['slope', 'intercept', 'r_square']
for para_ind in range(len(parameters)):
vis.box_plot(
out_degree_fit_parameters[:, para_ind], output_directory,
"out_degree_" + str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
vis.box_plot(
in_degree_fit_parameters[:, para_ind], output_directory,
"in_degree_" + str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
vis.box_plot(
total_degree_fit_parameters[:, para_ind], output_directory,
"total_degree_" + str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
saver.save_csv([out_degree_fit_parameters[:, para_ind].tolist()],
output_directory, "out_degree_" +
str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
saver.save_csv([in_degree_fit_parameters[:, para_ind].tolist()],
output_directory, "in_degree_" +
str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
saver.save_csv([total_degree_fit_parameters[:, para_ind].tolist()],
output_directory, "total_degree_" +
str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
def test_message_exchange_network(self):
log_data = reader.linux_input(self.log_data_dir, ["#kubuntu-devel"],
self.start_date, self.end_date)
expected_result = util.load_from_disk(
self.current_directory +
'/data/output/degree_anal_message_number_graph_kubuntu-devel')
nicks, nick_same_list = nickTracker.nick_tracker(log_data)
message_number_graph = network.message_number_graph(
log_data, nicks, nick_same_list, False)
expected_output = network.degree_analysis_on_graph(
message_number_graph)
self.assertEqual(expected_result, expected_output)
def test_reduced_networks_cutoff_20(self):
default_config = config.THRESHOLD_MESSAGE_NUMBER_GRAPH
config.THRESHOLD_MESSAGE_NUMBER_GRAPH = 20
log_data = reader.linux_input(self.log_data_dir, ["#kubuntu-devel"],
self.start_date, self.end_date)
expected_result = util.load_from_disk(
self.current_directory +
'/data/output/message_number_graph_cutoff_20')
nicks, nick_same_list = nickTracker.nick_tracker(log_data, False)
expected_output = network.message_number_graph(log_data, nicks,
nick_same_list, False)
config.THRESHOLD_MESSAGE_NUMBER_GRAPH = default_config
self.assertTrue(nx.is_isomorphic(expected_result, expected_output))
def test_message_number_graph_day_analysis(self, mock_get_nick_sen_rec,
mock_rec_list_splice,
mock_correctLastCharCR,
mock_check_if_msg_line,
mock_create_connected_nick_list,
mock_to_graph):
to_graph_ret = util.load_from_disk(
self.current_directory + "/data/message_number_graph/to_graph")
conn_list = list(connected_components(to_graph_ret))
mock_to_graph.return_value = to_graph_ret
mock_rec_list_splice.side_effect = util.load_from_disk(
self.current_directory +
"/data/message_number_graph/rec_list_splice")
mock_create_connected_nick_list.return_value = util.load_from_disk(
self.current_directory +
"/data/message_number_graph/conn_comp_list")
mock_check_if_msg_line.side_effect = util.load_from_disk(
self.current_directory +
"/data/message_number_graph/check_if_msg_line")
mock_correctLastCharCR.side_effect = util.load_from_disk(
self.current_directory +
"/data/message_number_graph/correctLastCharCR")
mock_get_nick_sen_rec.side_effect = util.load_from_disk(
self.current_directory +
"/data/message_number_graph/get_nick_sen_rec")
capturedOutput = StringIO.StringIO()
sys.stdout = capturedOutput
ret = network.message_number_graph(self.log_data,
self.nicks,
self.nick_same_list,
DAY_BY_DAY_ANALYSIS=True)
expected_graph_list = util.load_from_disk(
self.current_directory +
"/data/message_number_graph/message_number_day_list")
sys.stdout = sys.__stdout__
capturedOutput.close()
mock_to_graph.assert_called_once_with(self.nick_same_list)
mock_create_connected_nick_list.assert_called_once_with(conn_list)
self.assertTrue(nx.is_isomorphic(ret[0][0], expected_graph_list[0][0]))
self.assertTrue(nx.is_isomorphic(ret[1][0], expected_graph_list[1][0]))
def test_message_number_graph(self):
capturedOutput = StringIO.StringIO()
sys.stdout = capturedOutput
graph = network.message_number_graph(self.log_data,
self.nicks,
self.nick_same_list,
DAY_BY_DAY_ANALYSIS=False)
sys.stdout = sys.__stdout__
capturedOutput.close()
self.assertTrue(
nx.is_isomorphic(
graph,
util.load_from_disk(
self.test_data_dir +
"message_number_graph/aggregate_message_number_graph")))
def test_message_number_graph_day_analysis(self):
capturedOutput = StringIO.StringIO()
sys.stdout = capturedOutput
graph = network.message_number_graph(self.log_data,
self.nicks,
self.nick_same_list,
DAY_BY_DAY_ANALYSIS=True)
expected_graph_list = util.load_from_disk(
self.test_data_dir +
"message_number_graph/message_number_day_list")
sys.stdout = sys.__stdout__
capturedOutput.close()
self.assertTrue(
nx.is_isomorphic(graph[0][0], expected_graph_list[0][0]))
self.assertTrue(
nx.is_isomorphic(graph[1][0], expected_graph_list[1][0]))
def test_degree_distribution_message_exchange_network(self):
degree_type = ["out_degree", "in_degree", "total_degree"]
log_data = reader.linux_input(self.log_data_dir, ["#kubuntu-devel"],
self.start_date, self.end_date)
expected_result = util.load_from_disk(
self.current_directory +
'/data/output/message_exchange_network_curve_fit')
nicks, nick_same_list = nickTracker.nick_tracker(log_data)
message_number_graph = network.message_number_graph(
log_data, nicks, nick_same_list, False)
degree_anal_message_number = network.degree_analysis_on_graph(
message_number_graph)
expected_output = {}
for dtype in degree_type:
expected_output[dtype] = vis.generate_log_plots(
degree_anal_message_number[dtype]["raw_for_vis"],
self.current_directory, "#kubuntu-devel" + dtype)
os.remove(self.current_directory + "/#kubuntu-devel" + dtype +
".png")
self.assertEqual(expected_result, expected_output)
def codelengths(log_directory, output_directory, channel_name):
codelengths = []
for month in xrange(1, 13):
log_data_m1 = reader.linux_input(log_directory, channel_name,
"2013-" + str(month) + "-1",
"2013-" + str(month) + "-31")
nicks_m1, nick_same_list_m1 = nickTracker.nick_tracker(log_data_m1)
message_number_graph_m1 = network.message_number_graph(
log_data_m1, nicks_m1, nick_same_list_m1, False)
try:
#FOS is a reserved word in igraph and if 'fos' is a username in the nx graph, it generates an error
saver.save_net_nx_graph(message_number_graph_m1, output_directory,
"message-exchange-" + str(month))
msg_igraph, msg_community = community.infomap_igraph(
ig_graph=None,
net_file_location=output_directory + "message-exchange-" +
str(month) + '.net')
codelengths.append(msg_community.codelength)
except:
node_labels = message_number_graph_m1.nodes()
labels = {}
for label in node_labels:
if label == "fos":
labels[label] = "fos_"
else:
labels[label] = label
message_number_graph_m1 = nx.relabel_nodes(message_number_graph_m1,
labels)
saver.save_net_nx_graph(message_number_graph_m1, output_directory,
"message-exchange-" + str(month))
print "error in", month
msg_igraph, msg_community = community.infomap_igraph(
ig_graph=None,
net_file_location=output_directory + "message-exchange-" +
str(month) + '.net')
codelengths.append(msg_community.codelength)
vis.box_plot(codelengths, output_directory, "codelengths2013")
saver.save_csv([codelengths], output_directory, "codelengths2013")
def test_degree_analysis_on_nodes(self, log_data, nicks, nick_same_list):
update_expected_output_directory(log_data)
message_number_graph = network.message_number_graph(log_data, nicks, nick_same_list)
message_time_graph = network.message_time_graph(log_data, nicks, nick_same_list)
nick_change_graph = user.nick_change_graph(log_data)
degree_anal_message_number = network.degree_analysis_on_graph(message_number_graph)
degree_anal_message_time = network.degree_analysis_on_graph(message_time_graph)
degree_anal_nick_change = network.degree_analysis_on_graph(nick_change_graph)
expected_analysis_msg_number = []
expected_analysis_msg_time = []
expected_analysis_nick_change = []
unjson('degree_anal_message_number.json', expected_analysis_msg_number)
unjson('degree_anal_message_time.json', expected_analysis_msg_time)
unjson('degree_anal_nick_change.json', expected_analysis_nick_change)
self.assertDictEqual(degree_anal_message_number, expected_analysis_msg_number[0], msg=None)
self.assertDictEqual(degree_anal_message_time, expected_analysis_msg_time[0], msg=None)
self.assertDictEqual(degree_anal_nick_change, expected_analysis_nick_change[0], msg=None)
from lib.in_out import reader, saver from lib import nickTracker, config, vis, validate from lib.analysis import network, channel, user, community log_directory = config.LOG_DIRECTORY channel_name = config.CHANNEL_NAME starting_date = config.STARTING_DATE ending_date = config.ENDING_DATE output_directory = config.OUTPUT_DIRECTORY # ============== INPUT================== log_data = reader.linux_input(log_directory, channel_name, starting_date, ending_date) nicks, nick_same_list = nickTracker.nick_tracker(log_data) # ============== ANALYSIS ============= message_number_graph = network.message_number_graph(log_data, nicks, nick_same_list, False) message_number_graph_day_list = network.message_number_graph(log_data, nicks, nick_same_list, True) degree_anal_message_numder = network.degree_analysis_on_graph(message_number_graph) message_time_graph_list = network.message_time_graph(log_data, nicks, nick_same_list, True) message_time_graph = network.message_time_graph(log_data, nicks, nick_same_list, False) out_degree_node_number, in_degree_node_number, total_degree_node_number = network.degree_node_number_csv(log_data, nicks, nick_same_list) nick_change_graph_list = user.nick_change_graph(log_data, True) bin_matrix, total_messages = network.message_number_bins_csv(log_data, nicks, nick_same_list) conv_len, conv_ref_time = channel.conv_len_conv_refr_time(log_data, nicks, nick_same_list) resp_time = channel.response_time(log_data, nicks, nick_same_list) user.keywords_clusters(log_data, nicks, nick_same_list) network.degree_analysis_on_graph(message_number_graph) # adjCC_graph, adjCC_membership = community.infomap_igraph(ig_graph=None, net_file_location="/home/rohan/Desktop/adjCC.net")
def test_message_number_graph(self, log_data, nicks, nick_same_list):
update_expected_output_directory(log_data)
msg_number_graph = network.message_number_graph(log_data, nicks, nick_same_list)
self.assertTrue(compare_graph_outputs(msg_number_graph, "message_number_graph.gpickle"), msg=None)
def codelengths(log_directory, output_directory, channel_name, start_date,
end_date):
"""
The function iterate through the months in the given date range and computes the infomap number. It then plots a
box plot for the infomap numbers of all the whole months in the given time period.
Args:
log_directory(str): path to the location of Logs
output_directory(str): path to the location where the results are to be stored
channel_name(list): channels for which the analysis is to be done
start_date(datetime): starting date for the logs to be analysed. This has to be the beginning of the month.
end_date(datetime): ending date for which the logs are to be analysed. This has to be the end of the month.
Returns:
null
"""
start_date = start_date.strptime('%Y-%m-%d')
end_date = end_date.strptime('%Y-%m-%d')
codelengths = []
for dt in rrule(MONTHLY, dtstart=start_date, until=end_date):
last_day_of_the_month1 = dt + relativedelta(
months=1) - datetime.timedelta(days=1)
log_data_m1 = reader.linux_input(
log_directory, channel_name, dt.strftime("%Y-%m-%d"),
last_day_of_the_month1.strftime("%Y-%m-%d"))
nicks_m1, nick_same_list_m1 = nickTracker.nick_tracker(log_data_m1)
message_number_graph_m1 = network.message_number_graph(
log_data_m1, nicks_m1, nick_same_list_m1, False)
try:
#FOS is a reserved word in igraph and if 'fos' is a username in the nx graph, it generates an error
saver.save_net_nx_graph(message_number_graph_m1, output_directory,
"message-exchange-" + str(dt.month))
msg_igraph, msg_community = community.infomap_igraph(
ig_graph=None,
net_file_location=output_directory + "message-exchange-" +
str(dt.month) + '.net')
codelengths.append(msg_community.codelength)
except:
node_labels = message_number_graph_m1.nodes()
labels = {}
for label in node_labels:
if label == "fos":
labels[label] = "fos_"
else:
labels[label] = label
message_number_graph_m1 = nx.relabel_nodes(message_number_graph_m1,
labels)
saver.save_net_nx_graph(message_number_graph_m1, output_directory,
"message-exchange-" + str(dt.month))
print "error in", dt.month
msg_igraph, msg_community = community.infomap_igraph(
ig_graph=None,
net_file_location=output_directory + "message-exchange-" +
str(dt.month) + '.net')
codelengths.append(msg_community.codelength)
vis.box_plot(codelengths, output_directory, "codelengths2013")
saver.save_csv([codelengths], output_directory, "codelengths2013")
from lib import nickTracker, config, vis, validate
from lib.analysis import network, channel, user, community
log_directory = config.LOG_DIRECTORY
channel_name = config.CHANNEL_NAME
starting_date = config.STARTING_DATE
ending_date = config.ENDING_DATE
output_directory = config.OUTPUT_DIRECTORY
# ============== INPUT==================
log_data = reader.linux_input(log_directory, channel_name, starting_date,
ending_date)
nicks, nick_same_list = nickTracker.nick_tracker(log_data)
# ============== ANALYSIS =============
message_number_graph = network.message_number_graph(log_data, nicks,
nick_same_list, False)
message_number_graph_day_list = network.message_number_graph(
log_data, nicks, nick_same_list, True)
degree_anal_message_numder = network.degree_analysis_on_graph(
message_number_graph)
message_time_graph_list = network.message_time_graph(log_data, nicks,
nick_same_list, True)
message_time_graph = network.message_time_graph(log_data, nicks,
nick_same_list, False)
out_degree_node_number, in_degree_node_number, total_degree_node_number = network.degree_node_number_csv(
log_data, nicks, nick_same_list)
nick_change_graph_list = user.nick_change_graph(log_data, True)
bin_matrix, total_messages = network.message_number_bins_csv(
log_data, nicks, nick_same_list)
conv_len, conv_ref_time = channel.conv_len_conv_refr_time(
log_data, nicks, nick_same_list)
def box_plot_for_degree(log_directory, output_directory, channel_name,
start_date, end_date):
"""
Correlational : statistical distribution of curve fit parameters generated for degree distribution. The function
takes the given time duration and selects one month at a time for generation of a degree distribution sample. Each
degree distribution sample shall have 3 curve fit parameters namely slope, intercept & r_square. The function collects these parameters
for all the months of the given time duration. The function produces box plot separately for each parameter.
Args:
log_directory(str): path to the location of Logs
output_directory(str): path to the location where the results are to be stored
channel_name(list): channels for which the analysis is to be done.
start_date(datetime): starting date for the logs to be analysed. This has to be the beginning of the month.
end_date(datetime): ending date for which the logs are to be analysed. This has to be the end of the month.
Returns:
null
"""
start_date = start_date.strptime('%Y-%m-%d')
end_date = end_date.strptime('%Y-%m-%d')
cutoff = 0
for channel_name_iter in channel_name:
out_degree_fit_parameters = np.zeros((12, 4))
in_degree_fit_parameters = np.zeros((12, 4))
total_degree_fit_parameters = np.zeros((12, 4))
for dt in rrule(MONTHLY, dtstart=start_date, until=end_date):
last_day_of_the_month = dt + relativedelta(
months=1) - datetime.timedelta(days=1)
# for month in range(1, 13):
log_data = reader.linux_input(
log_directory, channel_name_iter, dt.strftime("%Y-%m-%d"),
last_day_of_the_month.strftime("%Y-%m-%d"))
nicks, nick_same_list = nickTracker.nick_tracker(log_data)
message_number_graph = network.message_number_graph(
log_data, nicks, nick_same_list, False)
degree_anal_message_number = network.degree_analysis_on_graph(
message_number_graph)
out_degree_fit_parameters[dt.month - 1] = vis.generate_log_plots(
degree_anal_message_number["out_degree"]["raw_for_vis"],
output_directory, channel_name_iter[0])
in_degree_fit_parameters[dt.month - 1] = vis.generate_log_plots(
degree_anal_message_number["in_degree"]["raw_for_vis"],
output_directory, channel_name_iter[0])
total_degree_fit_parameters[dt.month - 1] = vis.generate_log_plots(
degree_anal_message_number["total_degree"]["raw_for_vis"],
output_directory, channel_name_iter[0])
parameters = ['slope', 'intercept', 'r_square']
for para_ind in range(len(parameters)):
vis.box_plot(
out_degree_fit_parameters[:, para_ind], output_directory,
"out_degree_" + str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
vis.box_plot(
in_degree_fit_parameters[:, para_ind], output_directory,
"in_degree_" + str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
vis.box_plot(
total_degree_fit_parameters[:, para_ind], output_directory,
"total_degree_" + str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
saver.save_csv([out_degree_fit_parameters[:, para_ind].tolist()],
output_directory, "out_degree_" +
str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
saver.save_csv([in_degree_fit_parameters[:, para_ind].tolist()],
output_directory, "in_degree_" +
str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
saver.save_csv([total_degree_fit_parameters[:, para_ind].tolist()],
output_directory, "total_degree_" +
str(parameters[para_ind]) + "_2013_" +
channel_name_iter[0] + "_cut_" + str(cutoff))
