Source code for lib.NickChangeGraph
import os.path
import re
import networkx as nx
import numpy as np
import matplotlib.pyplot as plt
import pylab
import pygraphviz as pygraphviz
import os
import ext.util
[docs]def createNickChangesGraph(log_directory, channel_name, output_directory, startingDate, startingMonth, endingDate, endingMonth):
""" creates a graph which tracks the nick changes of the users
where each edge has a time stamp denoting the time
at which the nick was changed by the user
Args:
log_directory (str): Location of the logs (Assumed to be arranged in directory structure as : <year>/<month>/<day>/<log-file-for-channel>.txt)
channel_name (str): Channel to be perform analysis on
output_directory (str): Location of output directory
startingDate (int): Date to start the analysis (in conjunction with startingMonth)
startingMonth (int): Date to start the analysis (in conjunction with startingDate)
endingDate (int): Date to end the analysis (in conjunction with endingMonth)
endingMonth (int): Date to end the analysis (in conjunction with endingDate)
Returns:
null
"""
# out_dir_nick_change = output_directory+"nick-changes/"
out_dir_nick_change = output_directory
if not os.path.exists(os.path.dirname(out_dir_nick_change)):
try:
os.makedirs(os.path.dirname(out_dir_nick_change))
except OSError as exc: # Guard against race condition
if exc.errno != errno.EEXIST:
raise
rem_time= None #remembers the time of the last message of the file parsed before the current file
for folderiterator in range(startingMonth, endingMonth + 1):
temp1 = "0" if folderiterator < 10 else ""
for fileiterator in range(startingDate if folderiterator == startingMonth else 1, endingDate + 1 if folderiterator == endingMonth else 32):
temp2 = "0" if fileiterator < 10 else ""
filePath=log_directory+temp1+str(folderiterator)+"/"+temp2+str(fileiterator)+"/"+channel_name+".txt"
if not os.path.exists(filePath):
if not((folderiterator==2 and (fileiterator ==29 or fileiterator ==30 or fileiterator ==31)) or ((folderiterator==4 or folderiterator==6 or folderiterator==9 or folderiterator==11) and fileiterator==31 )):
print "[Error] Path "+filePath+" doesn't exist"
continue
with open(filePath) as f:
content = f.readlines() #contents stores all the lines of the file channel_name
nicks = [] #list of all the nicknames
'''
Getting all the nicknames in a list nicks[]
'''
for i in content:
if(i[0] != '=' and "] <" in i and "> " in i):
m = re.search(r"\<(.*?)\>", i)
if m.group(0) not in nicks:
nicks.append(m.group(0)) #used regex to get the string between <> and appended it to the nicks list
for i in xrange(0,len(nicks)):
nicks[i] = nicks[i][1:-1] #removed <> from the nicknames
for i in xrange(0,len(nicks)):
nicks[i]=ext.util.correctLastCharCR(nicks[i])
for line in content:
if(line[0]=='=' and "changed the topic of" not in line): #excluding the condition when user changes the topic. Search for only nick changes
nick1=ext.util.correctLastCharCR(line[line.find("=")+1:line.find(" is")][3:])
nick2=ext.util.correctLastCharCR(line[line.find("wn as")+1:line.find("\n")][5:])
if nick1 not in nicks:
nicks.append(nick1)
if nick2 not in nicks:
nicks.append(nick2)
#print("printing nicks***********************************")
#print(nicks)
'''
Forming list of lists for avoiding nickname duplicacy
'''
nick_same_list=[[] for i in range(len(nicks))] #list of list with each list having all the nicks for that particular person
for line in content:
if(line[0]=='=' and "changed the topic of" not in line):
line1=line[line.find("=")+1:line.find(" is")][3:]
line2=line[line.find("wn as")+1:line.find("\n")][5:]
line1=ext.util.correctLastCharCR(line1)
line2=ext.util.correctLastCharCR(line2)
for i in range(5000):
if line1 in nick_same_list[i] or line2 in nick_same_list[i]:
nick_same_list[i].append(line1)
nick_same_list[i].append(line2)
break
if not nick_same_list[i]:
nick_same_list[i].append(line1)
nick_same_list[i].append(line2)
break
#print("printing nick_same_list****************************")
#print(nick_same_list)
'''=========================== Plotting the nickname changes graph =========================== '''
graph_nickchanges=nx.MultiDiGraph() #using networkx
y=-1
for i in content:
y=y+1
if(i[0] =='=' and "changed the topic of" not in i): #excluding the condition when user changes the topic. Search for only nick changes
nick1=ext.util.correctLastCharCR(i[i.find("=")+1:i.find(" is")][3:])
nick2=ext.util.correctLastCharCR(i[i.find("wn as")+1:i.find("\n")][5:])
z=y
while z>=0:
z=z-1
if(content[z][0]!='='):
graph_nickchanges.add_edge(nick1,nick2,weight=content[z][1:6])
break # these lines extract the from-to nicknames and strip them appropriately to make
if(z==-1):
graph_nickchanges.add_edge(nick1,nick2,weight=rem_time) #edge between them
count=len(content)-1 #setting up the rem_time for next file, by noting the last message sent on that file.
while(count>=0):
if(content[count][0]!='='):
rem_time=content[count][1:6]
break
count=count-1
for u,v,d in graph_nickchanges.edges(data=True):
d['label'] = d.get('weight','')
output_file=out_dir_nick_change+channel_name+"_"+str(folderiterator)+"_"+str(fileiterator)+"_nick_change.png"
print "Generated "+ output_file
A = nx.drawing.nx_agraph.to_agraph(graph_nickchanges)
A.layout(prog='dot')
A.draw(output_file) #graphviz helps to convert a dot file to PNG format for visualization