def __init__(self, directory=None, train_size=0.3, textweight=0.8, size=300, seed=1, workers=1, passes=10, dm=0, min_count=3):
# Read the data
alldocs, docindex, classlabels = net.readNetworkData(directory)
print('%d documents, %d classes, training ratio=%f' % (len(alldocs), len(classlabels), train_size))
print('%d classes' % len(classlabels))
#Initilize Doc2Vec
if train_size > 0: #label information is available for learning
print('Adding Label Information')
train, test = train_test_split(alldocs, train_size=train_size, random_state=seed)
"""
Add supervised information to training data, use label information for learning
Specifically, the doc2vec algorithm used the tags information as document IDs,
and learn a vector representation for each tag (ID). We add the class label into the tags,
so each class label will acts as a ID and is used to learn the latent representation
"""
alldata = train[:]
for x in alldata:
x.tags.append('Label_'+x.labels)
alldata.extend(test)
else: # no label information is available, pure unsupervised learning
alldata = alldocs[:]
d2v = net.trainDoc2Vec(alldata, workers=workers, size=size, dm=dm, passes=passes, min_count=min_count)
raw_walks, netwalks = net.getdeepwalks(directory, number_walks=20, walk_length=8)
w2v = net.trainWord2Vec(raw_walks, buildvoc=1, passes=passes, size=size, workers=workers)
if train_size > 0: #Print out the initial results
print('Initialize Doc2Vec Model With Supervised Information...')
Evaluation.evaluationEmbedModelFromTrainTest(d2v, train, test, classifierStr='SVM')
print('Initialize Deep Walk Model')
Evaluation.evaluationEmbedModelFromTrainTest(w2v, train, test, classifierStr='SVM')
self.d2v = d2v
self.w2v = w2v
self.train(d2v, w2v, directory, alldata, passes=passes, weight=textweight)
if textweight > 0.5:
self.model = d2v
else:
self.model = w2v
def train(self, d2v, w2v, directory, alldata, passes=10, weight=0.9):
raw_walks, walks = net.getdeepwalks(directory, number_walks=20, walk_length=10)
for i in range(passes):
print('Iterative Runing %d' % i)
self.setWeights(d2v, w2v, weight=weight)
#Train Word2Vec
shuffle(raw_walks)
print("Update W2V...")
w2v.train(raw_walks,total_examples=w2v.corpus_count,epochs=w2v.epochs)
self.setWeights(w2v, d2v, weight=(1-weight))
print("Update D2V...")
shuffle(alldata) # shuffling gets best results
d2v.train(alldata,total_examples=d2v.corpus_count,epochs=d2v.epochs)
size=numFea,
dm=dm,
passes=passes,
min_count=3)
print('Classification Performance on Doc2Vec Model')
doc2vec_acc, doc2vec_macro_f1, doc_2vec_micro_f1 = \
Evaluation.evaluationEmbedModelFromTrainTest(doc2vec_model, train, test, classifierStr='SVM')
print("##################")
#### Baseline 2, Deep Walk Model
print("##################")
print("Baseline 2, Deep Walk Model")
raw_walks, netwalks = net.getdeepwalks(directory,
number_walks=20,
walk_length=8)
deepwalk_model = net.trainWord2Vec(raw_walks,
buildvoc=1,
sg=1,
passes=passes,
size=numFea,
workers=cores)
print('Classification Performance on DeepWalk Model')
doc2vec_acc, doc2vec_macro_f1, doc_2vec_micro_f1 = \
Evaluation.evaluationEmbedModelFromTrainTest(deepwalk_model, train, test, classifierStr='SVM')
print("##################")
### Baseline 3, D2V+DW
print("##################")
