def original_generate_token_graph():
corp = []
sentences = [] # Initialize an empty list of sentences
input_folders = [ sub_dir for sub_dir in listdir(dataset_folder) if isdir(join(dataset_folder, sub_dir)) ]
for folder in input_folders:
dir_path = dataset_folder + os.sep + folder + os.sep
files = [ f for f in listdir(dir_path) if isfile(join(dir_path,f)) ]
for file in files:
file_path = dir_path + file
file_name, file_extension = splitext(file_path)
doc = ""
if file_extension == ".pdf":
doc = convert_pdf_to_txt(file_path)
elif file_extension == ".docx":
doc = convert_docx_to_txt(file_path)
else:
continue
if doc != "":
doc = doc.decode("utf8")
#doc = words_to_phrases(doc)
doc = doc.lower()
doc = doc_to_wordlist(doc,True)
corp = it.chain(corp,doc)
#sentences += doc_to_sentences(doc, tokenizer, remove_stopwords=False)
corp = list(corp)
graph = nx.Graph()
weights = Counter()
edges = set()
window = corp[0:5]
for tup in it.permutations(window,2):
weights[tup] += 1
for i in range(3,len(corp)-2):
for j in range(i-2,i+2):
weights[(corp[j],corp[i+2])] += 1
weights[(corp[i+2],corp[j])] += 1
edges.add((corp[i+2],corp[j]))
for e in edges:
graph.add_edge(e[0], e[1], {'weight':weights[e]})
print graph
nx.write_weighted_edgelist(graph, "graph.g")
print nx.to_numpy_matrix(graph)
np.savetxt("graph.adj", nx.to_numpy_matrix(graph))
print "finished"
doc = ""
user = ""
if file_extension == ".pdf":
user = file.split("_")[0]
doc = convert_pdf_to_txt(file_path)
elif file_extension == ".docx":
user = file.split("_")[0]
doc = convert_docx_to_txt(file_path)
else:
continue
if doc != "":
doc = doc.decode("utf8")
doc = doc_to_wordlist(doc)
if users.has_key(user):
users[user] += doc
else:
users[user] = doc
print users.keys()
print "Number of users = " + str(len(users))
# Initial a vector of syn0 and syn1 for a vector of a label
new_syn0 = empty((1, model.layer1_size), dtype=REAL)
new_syn1 = empty((1, model.layer1_size), dtype=REAL)
files = [ f for f in listdir(subsub_dir_path) if isfile(join(subsub_dir_path,f)) if ".pdf" in f ]
for file_name in files:
file_paths.append(subsub_dir_path + file_name)
#print file_paths
#print len(file_paths)
label_i = 1
for file_path in file_paths:
doc = convert_pdf_to_txt(file_path)
if doc != "":
doc = doc.decode("utf8")
doc = doc_to_wordlist(doc, remove_stopwords=True)
label = str(folder) + "_" + str(label_i)
label_i = label_i + 1
doc_labels[label] = doc
# Initial a vector of syn0 and syn1 for a vector of a label
new_syn0 = empty((1, model.layer1_size), dtype=REAL)
new_syn1 = empty((1, model.layer1_size), dtype=REAL)
is_first = True
# Initialize and add a vector of syn0 and syn1 for a vector of a label
for doc_label in doc_labels:
def generate_token_group_graph(group="author",output="graph"):
corp = defaultdict(list)
sentences = [] # Initialize an empty list of sentences
input_folders = [ sub_dir for sub_dir in listdir(dataset_folder) if isdir(join(dataset_folder, sub_dir)) ]
for folder in input_folders:
dir_path = dataset_folder + os.sep + folder + os.sep
files = [ f for f in listdir(dir_path) if isfile(join(dir_path,f)) ]
for file in files:
file_path = dir_path + file
file_name, file_extension = splitext(file_path)
doc = ""
if file_extension == ".pdf":
doc = convert_pdf_to_txt(file_path)
elif file_extension == ".docx":
doc = convert_docx_to_txt(file_path)
elif file_extension == ".txt":
with open(file_path) as f:
for line in f:
doc = doc+" "+line
else:
continue
if doc != "":
# Extract the author name from the filename
if group is "author":
group = file_name.split("_")[0]
elif group is "document":
group = file_name
else:
group = ""
doc = doc.decode("utf8")
doc = doc.lower()
doc = doc_to_wordlist(doc,True)
corp[group] = it.chain(corp[group],doc)
#sentences += doc_to_sentences(doc, tokenizer, remove_stopwords=False)
graph = nx.Graph()
weights = Counter()
edges = set()
if group is "":
coll = list(corp[""])
window = coll[0:5]
for tup in it.permutations(window,2):
weights[tup] += 1
weights[(tup[1],tup[0])] += 1
edges.add(tup)
for i in range(2,len(coll)-2):
for j in range(i-2,i+2):
weights[(coll[j],coll[i+2])] += 1
weights[(coll[i+2],coll[j])] += 1
edges.add((coll[i+2],coll[j]))
for e in edges:
graph.add_edge(e[0], e[1], {'weight':weights[e]})
else:
for (g,coll) in corp:
coll = list(coll)
window = coll[0:5]
for tup in it.permutations(window,2):
weights[tup] += 1
weights[(tup[1],tup[0])] += 1
edges.add(tup)
for t in window:
if not (t is g):
weights[(g,t)] += 1
weights[(t,g)] += 1
edges.add((g,t))
for i in range(2,len(coll)-2):
for j in range(i-2,i+2):
if not (coll[i+2] is g):
weights[(g,coll[i+2])] += 1
weights[(coll[i+2],g)] += 1
edges.add((g,coll[i+2]))
weights[(coll[j],coll[i+2])] += 1
weights[(coll[i+2],coll[j])] += 1
edges.add((coll[i+2],coll[j]))
for e in edges:
graph.add_edge(e[0], e[1], {'weight':weights[e]})
nx.write_weighted_edgelist(graph, output+".g")
print nx.to_numpy_matrix(graph)
np.savetxt(output+".adj", nx.to_numpy_matrix(graph))
generate_graph_statistics(graph,output)
print "finished"
def generate_token_group_bigraph(group="author",output="graph", threshold=5):
corp = defaultdict(list)
sentences = [] # Initialize an empty list of sentences
input_folders = [ sub_dir for sub_dir in listdir(dataset_folder) if isdir(join(dataset_folder, sub_dir)) ]
for folder in input_folders:
dir_path = dataset_folder + os.sep + folder + os.sep
files = [ f for f in listdir(dir_path) if isfile(join(dir_path,f)) ]
for file in files:
file_path = dir_path + file
file_name, file_extension = splitext(file_path)
doc = ""
if file_extension == ".pdf":
doc = convert_pdf_to_txt(file_path)
elif file_extension == ".docx":
doc = convert_docx_to_txt(file_path)
elif file_extension == ".txt":
with open(file_path) as f:
for line in f:
doc = doc+" "+line
else:
continue
if doc != "":
# Extract the author name from the filename
if group is "author":
# Before I just consider the author another token.
# Now I need to distinguish the author tokens from
# the author identifier
group = "a_"+file_name.split("_")[0]
elif group is "document":
group = file_name
else:
group = ""
doc = doc.decode("utf8")
doc = doc.lower()
doc = doc_to_wordlist(doc,True)
corp[group] = it.chain(corp[group],doc)
#sentences += doc_to_sentences(doc, tokenizer, remove_stopwords=False)
graph = nx.Graph()
weights = Counter()
edges = set()
if group is "":
coll = list(corp[""])
window = coll[0:5]
for tup in it.permutations(window,2):
weights[tup] += 1
weights[(tup[1],tup[0])] += 1
edges.add(tup)
for i in range(2,len(coll)-2):
for j in range(i-2,i+2):
weights[(coll[j],coll[i+2])] += 1
weights[(coll[i+2],coll[j])] += 1
edges.add((coll[i+2],coll[j]))
for e in edges:
graph.add_edge(e[0], e[1], {'weight':weights[e]})
else:
for (g,coll) in corp.iteritems():
coll = list(coll)
window = coll[0:5]
"""
This code adds edges from one token
to every other token. Need to remove
for tup in it.permutations(window,2):
weights[tup] += 1
weights[(tup[1],tup[0])] += 1
edges.add(tup)
"""
for t in window:
if not (t is g):
weights[(g,t)] += 1
weights[(t,g)] += 1
edges.add((g,t))
for i in range(2,len(coll)-2):
for j in range(i-2,i+2):
if not (coll[i+2] is g):
weights[(g,coll[i+2])] += 1
weights[(coll[i+2],g)] += 1
edges.add((g,coll[i+2]))
"""
This code also adds token to token edges
weights[(coll[j],coll[i+2])] += 1
weights[(coll[i+2],coll[j])] += 1
edges.add((coll[i+2],coll[j]))
"""
for e in edges:
# Bimax and biclique detection techniques do not use weights, so just
# create threshed edges
if weights[e] > threshold:
graph.add_edge(e[0], e[1])
#nx.write_weighted_edgelist(graph, output+"_b.g")
#print nx.to_numpy_matrix(graph)
#np.savetxt(output+"_b.adj", nx.to_numpy_matrix(graph))
generate_graph_statistics(graph,output+"_b")
print "finished"
def generate_token_group_bigraph_from_amazon_imdb_dataset(output="graph", threshold=5):
#This function is used to create a graph from the imdb/amazon dataset
#and store it a file called edgelist.graph in the folder in which the code is being run.
corp = []
input_folders = [ sub_dir for sub_dir in listdir(dataset_folder) if isdir(join(dataset_folder, sub_dir)) ]
for folder in input_folders:
dir_path = dataset_folder + os.sep + folder + os.sep
files = [ f for f in listdir(dir_path) if isfile(join(dir_path,f)) ]
for file in files:
file_path = dir_path + file
file_name, file_extension = splitext(file_path)
doc = ""
if file_extension == ".txt":
with open(file_path) as f:
for line in f:
doc = doc+" "+line
else:
continue
if doc != "":
doc = doc.decode("utf8")
doc = doc.lower()
doc = doc_to_wordlist(doc,True)
corp = it.chain(corp,doc)
graph = nx.Graph()
weights = Counter()
edges = set()
coll = list(corp)
window = coll[0:5]
for tup in it.permutations(window,2):
weights[tup] += 1
weights[(tup[1],tup[0])] += 1
edges.add(tup)
for i in range(2,len(coll)-2):
for j in range(i-2,i+2):
weights[(coll[j],coll[i+2])] += 1
weights[(coll[i+2],coll[j])] += 1
edges.add((coll[i+2],coll[j]))
for e in edges:
graph.add_edge(e[0], e[1], {'weight':weights[e]})
#nx.write_weighted_edgelist(graph, output+"_b.g")
#print nx.to_numpy_matrix(graph)
#np.savetxt(output+"_b.adj", nx.to_numpy_matrix(graph))
nx.write_edgelist(graph, "edgelist.graph", data=['weight'])
print "finished"
#generate_token_group_bigraph_from_amazon_imdb_dataset(group="",output="agraph")
#generate_graph_statistics_from_file("edgelist.graph")
#parsereviewfile()
def generate_token_group_bigraph_from_amazon_imdb_dataset(output="graph", threshold=5):
#This function is used to create a graph from the imdb/amazon dataset
#and store it a file called edgelist.graph in the folder in which the code is being run.
corp = []
input_folders = [ sub_dir for sub_dir in listdir(dataset_folder) if isdir(join(dataset_folder, sub_dir)) ]
for folder in input_folders:
dir_path = dataset_folder + os.sep + folder + os.sep
files = [ f for f in listdir(dir_path) if isfile(join(dir_path,f)) ]
print "Looking inside: " + dir_path
for file in files:
file_path = dir_path + file
file_name, file_extension = splitext(file_path)
print 'Scanning File: ', file_path
doc = ""
if file_extension == ".txt":
with open(file_path) as f:
print 'Copying data from: ', file_path
for line in f:
doc = doc+" "+line
else:
continue
if doc != "":
#doc = doc.decode("utf8")
doc = doc.lower()
doc = doc_to_wordlist(doc,True)
print 'Words retrived: ', doc
corp = it.chain(corp,doc)
graph = nx.Graph()
weights = Counter()
edges = list()
coll = list(corp)
wordList = list(set(coll))
wordDict = {}
revWordDict = {}
for i in range(len(wordList)):
wordDict['text'+str(i)]=wordList[i];
revWordDict[wordList[i]]='text'+str(i);
window = coll[0:5]
for tup in it.permutations(window,2):
weights[tup] += 1
weights[(tup[1],tup[0])] += 1
print 'Trying to add edge: ', [revWordDict[tup[0]],revWordDict[tup[1]]]
edges.append([revWordDict[tup[0]],revWordDict[tup[1]]])
for i in range(2,len(coll)-2):
for j in range(i-2,i+2):
edges.append([revWordDict[coll[i+2]],revWordDict[coll[j]]])
for e in edges:
print 'Trying to add edge: ', e[0],e[1]
graph.add_edge(e[0], e[1])
#nx.write_weighted_edgelist(graph, output+"_b.g")
#print nx.to_numpy_matrix(graph)
#np.savetxt(output+"_b.adj", nx.to_numpy_matrix(graph))
nx.write_edgelist(graph, "corpusEdgelist.graph")
g = open('index2word.pkl', 'w')
cPickle.dump(wordDict, g, -1)
g.close()
g = open('word2index.pkl', 'w')
cPickle.dump(revWordDict, g, -1)
g.close()
print "finished"
