def build_feed_dict(self, in_node, is_training=True):
nodes_list = []
tr.leftTraverse(in_node, lambda node, args: args.append(node), nodes_list)
if is_training:
feed_dict = {
self.is_a_leaf : [ n.isLeaf for n in nodes_list ],
self.left_child : [ nodes_list.index(n.left) if not n.isLeaf else -1 for n in nodes_list ],
self.right_child : [ nodes_list.index(n.right) if not n.isLeaf else -1 for n in nodes_list ],
self.word_index : [ self.vocab.encode(n.word) if n.word else -1 for n in nodes_list ],
self.labelholder : [ n.label for n in nodes_list ],
self.learning_rate : self.config.lr,
self.l2_reg : self.config.l2
}
else:
feed_dict = {
self.is_a_leaf : [ n.isLeaf for n in nodes_list ],
self.left_child : [ nodes_list.index(n.left) if not n.isLeaf else -1 for n in nodes_list ],
self.right_child : [ nodes_list.index(n.right) if not n.isLeaf else -1 for n in nodes_list ],
self.word_index : [ self.vocab.encode(n.word) if n.word else -1 for n in nodes_list ],
self.labelholder : [ n.label for n in nodes_list ],
self.learning_rate : self.config.lr,
self.l2_reg : 0.
}
return feed_dict
def build_feed_dict(self, batch_data):
is_leaf = []
left_children = []
right_children = []
node_word_indices = []
labels = []
tree_size = []
for _, atree in enumerate(batch_data):
nodes_list = []
tree.leftTraverse(atree.root, lambda node, args: args.append(node), nodes_list)
node_to_index = OrderedDict()
for i in range(len(nodes_list)):
node_to_index[nodes_list[i]] = i
nodes_list += (self.config.max_tree_nodes-len(nodes_list))*[None]
is_leaf.append([False if node is None else node.isLeaf for node in nodes_list])
left_children.append([-1 if node is None or node.isLeaf else node_to_index[node.left] for node in nodes_list])
right_children.append([-1 if node is None or node.isLeaf else node_to_index[node.right] for node in nodes_list])
node_word_indices.append([-1 if node is None or not node.word else self.vocab.encode(node.word) for node in nodes_list])
labels.append([-1 if node is None else node.label for node in nodes_list])
tree_size.append(atree.num_nodes)
feed_dict = {
self.is_leaf_placeholder: is_leaf,
self.left_children_placeholder: left_children,
self.right_children_placeholder: right_children,
self.node_word_indices_placeholder: node_word_indices,
self.labels_placeholder: labels,
self.tree_size_placeholder: tree_size
}
return feed_dict
def build_feed_dict(self, in_node):
nodes_list = []
tr.leftTraverse(in_node, lambda node, args: args.append(node), nodes_list)
node_to_index = OrderedDict()
for idx, i in enumerate(nodes_list):
node_to_index[i] = idx
feed_dict = {
self.is_a_leaf : [ n.isLeaf for n in nodes_list ],
self.left_child : [ node_to_index[n.left] if not n.isLeaf else -1 for n in nodes_list ],
self.right_child : [ node_to_index[n.right] if not n.isLeaf else -1 for n in nodes_list ],
self.word_index : [ self.vocab.encode(n.word) if n.word else -1 for n in nodes_list ],
self.labelholder : [ n.label for n in nodes_list ]
}
return feed_dict
def build_feed_dict(self, in_node, is_training=True):
nodes_list = []
tr.leftTraverse(in_node, lambda node, args: args.append(node),
nodes_list)
if is_training:
feed_dict = {
self.is_a_leaf: [n.isLeaf for n in nodes_list],
self.left_child: [
nodes_list.index(n.left) if not n.isLeaf else -1
for n in nodes_list
],
self.right_child: [
nodes_list.index(n.right) if not n.isLeaf else -1
for n in nodes_list
],
self.word_index: [
self.vocab.encode(n.word) if n.word else -1
for n in nodes_list
],
self.labelholder: [n.label for n in nodes_list],
self.learning_rate:
self.config.lr,
self.l2_reg:
self.config.l2
}
else:
feed_dict = {
self.is_a_leaf: [n.isLeaf for n in nodes_list],
self.left_child: [
nodes_list.index(n.left) if not n.isLeaf else -1
for n in nodes_list
],
self.right_child: [
nodes_list.index(n.right) if not n.isLeaf else -1
for n in nodes_list
],
self.word_index: [
self.vocab.encode(n.word) if n.word else -1
for n in nodes_list
],
self.labelholder: [n.label for n in nodes_list],
self.learning_rate:
self.config.lr,
self.l2_reg:
0.
}
return feed_dict
def build_feed_dict(self, node):
nodes_list = []
tree.leftTraverse(node, lambda node, args: args.append(node), nodes_list)
node_to_index = OrderedDict()
for i in range(len(nodes_list)):
node_to_index[nodes_list[i]] = i
feed_dict = {
self.is_leaf_placeholder: [node.isLeaf for node in nodes_list],
self.left_children_placeholder: [node_to_index[node.left] if
not node.isLeaf else -1
for node in nodes_list],
self.right_children_placeholder: [node_to_index[node.right] if
not node.isLeaf else -1
for node in nodes_list],
self.node_word_indices_placeholder: [self.vocab.encode(node.word) if
node.word else -1
for node in nodes_list],
self.labels_placeholder: [node.label for node in nodes_list]
}
return feed_dict
def build_feed_dict(self, trees):
batch_node_lists = []
for tree_instance in trees:
tree_root = tree_instance.root
nodes_list = []
tree.leftTraverse(tree_root,
lambda tree_root, args: args.append(tree_root),
nodes_list)
batch_node_lists.extend(nodes_list)
node_to_index = OrderedDict()
num_nodes = len(batch_node_lists)
for i in xrange(num_nodes):
node_to_index[batch_node_lists[i]] = i
feed_dict = {
self.node_level_placeholder:
[node.level for node in batch_node_lists],
self.root_indeces_placeholder:
[node_to_index[node] for node in batch_node_lists if node.isRoot],
self.node_word_indices_placeholder: [
self.vocab.encode(node.word) if node.word else -1
for node in batch_node_lists
],
self.left_children_placeholder: [
node_to_index[node.left] if node.left else -1
for node in batch_node_lists
],
self.right_children_placeholder: [
node_to_index[node.right] if node.right else -1
for node in batch_node_lists
],
self.labels_placeholder: [node.label for node in batch_node_lists],
self.number_of_examples_placeholder:
len(trees)
}
return feed_dict
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option("--test",
action="store_true",
dest="test",
default=False)
# Optimizer
parser.add_option("--minibatch", dest="minibatch", type="int", default=30)
parser.add_option("--optimizer",
dest="optimizer",
type="string",
default="adagrad")
parser.add_option("--epochs", dest="epochs", type="int", default=50)
parser.add_option("--step", dest="step", type="float", default=1e-2)
parser.add_option("--middleDim", dest="middleDim", type="int", default=10)
parser.add_option("--outputDim", dest="outputDim", type="int", default=5)
parser.add_option("--wvecDim", dest="wvecDim", type="int", default=30)
# for DCNN only
parser.add_option("--ktop", dest="ktop", type="int", default=5)
parser.add_option("--m1", dest="m1", type="int", default=10)
parser.add_option("--m2", dest="m2", type="int", default=7)
parser.add_option("--n1", dest="n1", type="int", default=6)
parser.add_option("--n2", dest="n2", type="int", default=12)
parser.add_option("--outFile",
dest="outFile",
type="string",
default="models/test.bin")
parser.add_option("--inFile",
dest="inFile",
type="string",
default="models/test.bin")
parser.add_option("--data", dest="data", type="string", default="train")
parser.add_option("--model", dest="model", type="string", default="RNN")
(opts, args) = parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch, makes things faster!
evaluate_accuracy_while_training = True
# Testing
if opts.test:
test(opts.inFile, opts.data, opts.model)
return
print "Loading data..."
train_accuracies = []
dev_accuracies = []
# load training data
trees = tr.loadTrees('train')
opts.numWords = len(tr.loadWordMap())
if (opts.model == 'RNTN'):
nn = RNTN(opts.wvecDim, opts.outputDim, opts.numWords, opts.minibatch)
elif (opts.model == 'RNN'):
nn = RNN(opts.wvecDim, opts.outputDim, opts.numWords, opts.minibatch)
elif (opts.model == 'RNN2'):
nn = RNN2(opts.wvecDim, opts.middleDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (opts.model == 'RNN3'):
nn = RNN3(opts.wvecDim, opts.middleDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (opts.model == 'DCNN'):
nn = DCNN(opts.wvecDim,
opts.ktop,
opts.m1,
opts.m2,
opts.n1,
opts.n2,
0,
opts.outputDim,
opts.numWords,
2,
opts.minibatch,
rho=1e-4)
trees = cnn.tree2matrix(trees)
else:
raise '%s is not a valid neural network so far only RNTN, RNN, RNN2, RNN3, and DCNN' % opts.model
nn.initParams()
sgd = optimizer.SGD(nn,
alpha=opts.step,
minibatch=opts.minibatch,
optimizer=opts.optimizer)
dev_trees = tr.loadTrees("dev")
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d" % e
sgd.run(trees)
end = time.time()
print "Time per epoch : %f" % (end - start)
with open(opts.outFile, 'w') as fid:
pickle.dump(opts, fid)
pickle.dump(sgd.costt, fid)
nn.toFile(fid)
if evaluate_accuracy_while_training:
print "testing on training set real quick"
train_accuracies.append(
test(opts.outFile, "train", opts.model, trees))
print "testing on dev set real quick"
dev_accuracies.append(
test(opts.outFile, "dev", opts.model, dev_trees))
# clear the fprop flags in trees and dev_trees
for tree in trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
print "fprop in trees cleared"
if evaluate_accuracy_while_training:
pdb.set_trace()
print train_accuracies
print dev_accuracies
def run( args = None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option("--test",action="store_true",dest="test",default=False)
# Optimizer
parser.add_option("--minibatch",dest="minibatch",type="int",default=30)
parser.add_option("--optimizer",dest="optimizer",type="string",default="adagrad")
parser.add_option("--epochs",dest="epochs",type="int",default=50)
parser.add_option("--step",dest="step",type="float",default=1e-2)
parser.add_option("--middleDim",dest="middleDim",type="int",default=10)
parser.add_option("--outputDim",dest="outputDim",type="int",default=5)
parser.add_option("--wvecDim",dest="wvecDim",type="int",default=30)
# for DCNN only
parser.add_option("--ktop",dest="ktop",type="int",default=5)
parser.add_option("--m1",dest="m1",type="int",default=10)
parser.add_option("--m2",dest="m2",type="int",default=7)
parser.add_option("--n1",dest="n1",type="int",default=6)
parser.add_option("--n2",dest="n2",type="int",default=12)
parser.add_option("--outFile",dest="outFile",type="string",default="models/test.bin")
parser.add_option("--inFile",dest="inFile",type="string",default="models/test.bin")
parser.add_option("--data",dest="data",type="string",default="train")
parser.add_option("--model",dest="model",type="string",default="RNN")
(opts,args)=parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch, makes things faster!
evaluate_accuracy_while_training = True
# Testing
if opts.test:
test(opts.inFile, opts.data, opts.model)
return
print "Loading data..."
train_accuracies = []
dev_accuracies = []
# load training data
trees = tr.loadTrees('train')
opts.numWords = len(tr.loadWordMap())
if (opts.model=='RNTN'):
nn = RNTN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='RNN'):
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='RNN2'):
nn = RNN2(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='RNN3'):
nn = RNN3(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='DCNN'):
nn = DCNN(opts.wvecDim,opts.ktop,opts.m1,opts.m2, opts.n1, opts.n2,0, opts.outputDim,opts.numWords, 2, opts.minibatch,rho=1e-4)
trees = cnn.tree2matrix(trees)
else:
raise '%s is not a valid neural network so far only RNTN, RNN, RNN2, RNN3, and DCNN'%opts.model
nn.initParams()
sgd = optimizer.SGD(nn, alpha=opts.step, minibatch=opts.minibatch, optimizer=opts.optimizer)
dev_trees = tr.loadTrees("dev")
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d"%e
sgd.run(trees)
end = time.time()
print "Time per epoch : %f" %(end-start)
with open(opts.outFile,'w') as fid:
pickle.dump(opts,fid)
pickle.dump(sgd.costt,fid)
nn.toFile(fid)
if evaluate_accuracy_while_training:
print "testing on training set real quick"
train_accuracies.append(test(opts.outFile,"train",opts.model,trees))
print "testing on dev set real quick"
dev_accuracies.append(test(opts.outFile,"dev",opts.model,dev_trees))
# clear the fprop flags in trees and dev_trees
for tree in trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
print "fprop in trees cleared"
if evaluate_accuracy_while_training:
pdb.set_trace()
print train_accuracies
print dev_accuracies
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option("--test",
action="store_true",
dest="test",
default=False)
# Optimizer
parser.add_option("--minibatch", dest="minibatch", type="int", default=30)
parser.add_option("--optimizer",
dest="optimizer",
type="string",
default="adagrad")
parser.add_option("--epochs", dest="epochs", type="int", default=50)
parser.add_option("--step", dest="step", type="float", default=1e-2)
parser.add_option("--middleDim", dest="middleDim", type="int", default=10)
parser.add_option("--outputDim", dest="outputDim", type="int", default=5)
parser.add_option("--wvecDim", dest="wvecDim", type="int", default=30)
# By @tiagokv, just to ease the first assignment test
parser.add_option("--wvecDimBatch",
dest="wvecDimBatch",
type="string",
default="")
# for DCNN only
parser.add_option("--ktop", dest="ktop", type="int", default=5)
parser.add_option("--m1", dest="m1", type="int", default=10)
parser.add_option("--m2", dest="m2", type="int", default=7)
parser.add_option("--n1", dest="n1", type="int", default=6)
parser.add_option("--n2", dest="n2", type="int", default=12)
parser.add_option("--outFile",
dest="outFile",
type="string",
default="models/test.bin")
parser.add_option("--inFile",
dest="inFile",
type="string",
default="models/test.bin")
parser.add_option("--data", dest="data", type="string", default="train")
parser.add_option("--model", dest="model", type="string", default="RNN")
(opts, args) = parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch, makes things faster!
evaluate_accuracy_while_training = True
# Testing
if opts.test:
test(opts.inFile, opts.data, opts.model)
return
print "Loading data..."
train_accuracies = []
dev_accuracies = []
# load training data
trees = tr.loadTrees('train')
opts.numWords = len(tr.loadWordMap())
if (opts.model == 'RNTN'):
nn = RNTN(opts.wvecDim, opts.outputDim, opts.numWords, opts.minibatch)
elif (opts.model == 'RNN'):
nn = RNN(opts.wvecDim, opts.outputDim, opts.numWords, opts.minibatch)
elif (opts.model == 'RNN2'):
nn = RNN2(opts.wvecDim, opts.middleDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (opts.model == 'RNN3'):
nn = RNN3(opts.wvecDim, opts.middleDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (opts.model == 'DCNN'):
nn = DCNN(opts.wvecDim,
opts.ktop,
opts.m1,
opts.m2,
opts.n1,
opts.n2,
0,
opts.outputDim,
opts.numWords,
2,
opts.minibatch,
rho=1e-4)
trees = cnn.tree2matrix(trees)
else:
raise '%s is not a valid neural network so far only RNTN, RNN, RNN2, RNN3, and DCNN' % opts.model
nn.initParams()
sgd = optimizer.SGD(nn,
alpha=opts.step,
minibatch=opts.minibatch,
optimizer=opts.optimizer)
# assuring folder for plots exists
if (os.path.isdir('plots') == False): os.makedirs('test')
if (os.path.isdir('plots/' + opts.model) == False):
os.makedirs('plots/' + opts.model)
dev_trees = tr.loadTrees("dev")
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d" % e
sgd.run(trees)
end = time.time()
print "Time per epoch : %f" % (end - start)
with open(opts.outFile, 'w') as fid:
pickle.dump(opts, fid)
pickle.dump(sgd.costt, fid)
nn.toFile(fid)
if evaluate_accuracy_while_training:
print "testing on training set real quick"
train_accuracies.append(
test(opts.outFile, "train", opts.model, trees))
print "testing on dev set real quick"
dev_accuracies.append(
test(opts.outFile, "dev", opts.model, dev_trees))
# clear the fprop flags in trees and dev_trees
for tree in trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
print "fprop in trees cleared"
if evaluate_accuracy_while_training:
#pdb.set_trace()
plt.figure()
#Lets set up the plot
plt.title('Accuracy in set per epochs')
plt.plot(range(opts.epochs), train_accuracies, label='train')
plt.plot(range(opts.epochs), dev_accuracies, label='dev')
with open('dev_accu' + opts.model, 'a') as fid:
fid.write(
str(opts.wvecDim) + ',' + str(opts.middleDim) + ',' +
str(dev_accuracies[-1]) + ';')
#plt.axis([0,opts.epochs,0,1])
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.legend(loc=2, borderaxespad=0.)
#always save with middleDim, even if it's a one-layer RNN
plt.savefig('plots/' + opts.model + '/accuracy_wvec_' +
str(opts.wvecDim) + '_middleDim_' + str(opts.middleDim) +
' .png')
print 'image saved at %s' % os.getcwd()
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option("--test",action="store_true",dest="test",default=False)
# Optimizer
parser.add_option("--minibatch",dest="minibatch",type="int",default=30)
parser.add_option("--optimizer",dest="optimizer",type="string",
default="adagrad")
parser.add_option("--epochs",dest="epochs",type="int",default=50)
parser.add_option("--step",dest="step",type="float",default=1e-2)
parser.add_option("--middleDim",dest="middleDim",type="int",default=10)
parser.add_option("--outputDim",dest="outputDim",type="int",default=5)
parser.add_option("--wvecDim",dest="wvecDim",type="int",default=30)
# By @tiagokv, just to ease the first assignment test
parser.add_option("--wvecDimBatch",dest="wvecDimBatch",type="string",default="")
# for DCNN only
parser.add_option("--ktop",dest="ktop",type="int",default=5)
parser.add_option("--m1",dest="m1",type="int",default=10)
parser.add_option("--m2",dest="m2",type="int",default=7)
parser.add_option("--n1",dest="n1",type="int",default=6)
parser.add_option("--n2",dest="n2",type="int",default=12)
parser.add_option("--outFile",dest="outFile",type="string",
default="models/test.bin")
parser.add_option("--inFile",dest="inFile",type="string",
default="models/test.bin")
parser.add_option("--data",dest="data",type="string",default="train")
parser.add_option("--model",dest="model",type="string",default="RNN")
(opts,args)=parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch, makes things faster!
evaluate_accuracy_while_training = True
# Testing
if opts.test:
test(opts.inFile,opts.data,opts.model)
return
print "Loading data..."
train_accuracies = []
dev_accuracies = []
# load training data
trees = tr.loadTrees('train')
opts.numWords = len(tr.loadWordMap())
if (opts.model=='RNTN'):
nn = RNTN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='RNN'):
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='RNN2'):
nn = RNN2(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='RNN3'):
nn = RNN3(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(opts.model=='DCNN'):
nn = DCNN(opts.wvecDim,opts.ktop,opts.m1,opts.m2, opts.n1, opts.n2,0, opts.outputDim,opts.numWords, 2, opts.minibatch,rho=1e-4)
trees = cnn.tree2matrix(trees)
else:
raise '%s is not a valid neural network so far only RNTN, RNN, RNN2, RNN3, and DCNN'%opts.model
nn.initParams()
sgd = optimizer.SGD(nn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)
# assuring folder for plots exists
if( os.path.isdir('plots') == False ): os.makedirs('test')
if( os.path.isdir('plots/' + opts.model ) == False ): os.makedirs('plots/' + opts.model)
dev_trees = tr.loadTrees("dev")
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d"%e
sgd.run(trees)
end = time.time()
print "Time per epoch : %f"%(end-start)
with open(opts.outFile,'w') as fid:
pickle.dump(opts,fid)
pickle.dump(sgd.costt,fid)
nn.toFile(fid)
if evaluate_accuracy_while_training:
print "testing on training set real quick"
train_accuracies.append(test(opts.outFile,"train",opts.model,trees))
print "testing on dev set real quick"
dev_accuracies.append(test(opts.outFile,"dev",opts.model,dev_trees))
# clear the fprop flags in trees and dev_trees
for tree in trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
print "fprop in trees cleared"
if evaluate_accuracy_while_training:
#pdb.set_trace()
plt.figure()
#Lets set up the plot
plt.title('Accuracy in set per epochs')
plt.plot(range(opts.epochs),train_accuracies,label='train')
plt.plot(range(opts.epochs),dev_accuracies,label='dev')
with open('dev_accu' + opts.model,'a') as fid:
fid.write(str(opts.wvecDim) + ',' + str(opts.middleDim) + ',' + str(dev_accuracies[-1]) + ';')
#plt.axis([0,opts.epochs,0,1])
plt.xlabel('epochs')
plt.ylabel('accuracy')
plt.legend(loc=2, borderaxespad=0.)
#always save with middleDim, even if it's a one-layer RNN
plt.savefig('plots/' + opts.model + '/accuracy_wvec_' + str(opts.wvecDim) + '_middleDim_' + str(opts.middleDim) + ' .png')
print 'image saved at %s' % os.getcwd()
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option("--test",action="store_true",dest="test",default=False)
# Optimizer
parser.add_option("--minibatch",dest="minibatch",type="int",default=30)
parser.add_option("--optimizer",dest="optimizer",type="string",
default="adagrad")
parser.add_option("--epochs",dest="epochs",type="int",default=50)
parser.add_option("--step",dest="step",type="float",default=1e-2)
parser.add_option("--init",dest="init",type="float",default=0.01)
parser.add_option("--outputDim",dest="outputDim",type="int",default=5)
parser.add_option("--wvecDim",dest="wvecDim",type="int",default=30)
parser.add_option("--rho",dest="rho",type="float",default=1e-6)
parser.add_option("--outFile",dest="outFile",type="string",
default="models/test.bin")
parser.add_option("--inFile",dest="inFile",type="string",
default="models/test.bin")
parser.add_option("--data",dest="data",type="string",default="train")
parser.add_option("--model",dest="model",type="string",default="RNTN")
parser.add_option("--maxTrain",dest="maxTrain", type="int", default=-1)
parser.add_option("--activation",dest="acti", type="string", default="tanh")
parser.add_option("--partial",action="store_true",dest="partial",default=False)
parser.add_option("--w2v",dest="w2vmodel", type="string")
(opts,args)=parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch, makes things faster!
evaluate_accuracy_while_training = True
# Testing
if opts.test:
cmfile = opts.inFile + ".confusion_matrix-" + opts.data + ".png"
test(opts.inFile,opts.data,opts.model,acti=opts.acti)
return
print "Loading data..."
embedding = None
wordMap = None
if opts.w2vmodel is not None:
print "Loading pre-trained word2vec model from %s" % opts.w2vmodel
w2v = models.Word2Vec.load(opts.w2vmodel)
embedding, wordMap = readW2v(w2v,opts.wvecDim)
train_accuracies = []
train_rootAccuracies = []
dev_accuracies = []
dev_rootAccuracies = []
# load training data
trees = tr.loadTrees('train',wordMap=wordMap)[:opts.maxTrain] #train.full.15
if opts.maxTrain > -1:
print "Training only on %d trees" % opts.maxTrain
opts.numWords = len(tr.loadWordMap())
if opts.partial==True:
print "Only partial feedback"
if (opts.model=='RNTN'):
nn = RNTN(wvecDim=opts.wvecDim,outputDim=opts.outputDim,numWords=opts.numWords,
mbSize=opts.minibatch,rho=opts.rho, acti=opts.acti, init=opts.init, partial=opts.partial)
else:
raise '%s is not a valid neural network so far only RNTN, RNN'%opts.model
nn.initParams(embedding=embedding)
sgd = optimizer.SGD(nn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)
dev_trees = tr.loadTrees("dev") #dev.full.15
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d"%e
sgd.run(trees)
end = time.time()
print "Time per epoch : %f"%(end-start)
with open(opts.outFile,'w') as fid:
pickle.dump(opts,fid)
pickle.dump(sgd.costt,fid)
nn.toFile(fid)
if evaluate_accuracy_while_training:
print "testing on training set"
acc, sacc = test(opts.outFile,"train",opts.model,trees, acti=opts.acti)
train_accuracies.append(acc)
train_rootAccuracies.append(sacc)
print "testing on dev set"
dacc, dsacc = test(opts.outFile,"dev",opts.model,dev_trees, acti=opts.acti)
dev_accuracies.append(dacc)
dev_rootAccuracies.append(dsacc)
# clear the fprop flags and dev_trees
for tree in trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
print "fprop in trees cleared"
if evaluate_accuracy_while_training:
pdb.set_trace()
print train_accuracies
print dev_accuracies
print "on sentence-level:"
print train_rootAccuracies
print dev_rootAccuracies
# Plot train/dev_accuracies
plt.figure()
plt.plot(range(len(train_accuracies)), train_accuracies, label='Train')
plt.plot(range(len(dev_accuracies)), dev_accuracies, label='Dev')
plt.xlabel("Epoch")
plt.ylabel("Accuracy")
plt.legend()
# plot.show()
plt.savefig(opts.outFile + ".accuracy_plot.png")
# Plot train/dev_accuracies
plt.figure()
plt.plot(range(len(train_rootAccuracies)), train_rootAccuracies, label='Train')
plt.plot(range(len(dev_rootAccuracies)), dev_rootAccuracies, label='Dev')
plt.xlabel("Epoch")
plt.ylabel("Accuracy")
plt.legend()
# plot.show()
plt.savefig(opts.outFile + ".sent.accuracy_plot.png")
def run():
print "Loading data..."
model = "RNN"
trees = tr.loadTrees('train')
dev_trees = tr.loadTrees('dev')
wvecDimList = [5, 15, 25, 35, 45]
#wvecDimList = [10,20,40]
accuracy_per_wvecDim = []
epochs = 100
outFileText = "./param/%s/%s_cost_and_acc" % (model, model)
f = open(outFileText, 'w')
for wvecDim in wvecDimList:
nn = RNN(wvecDim, 5, len(tr.loadWordMap()), 30)
nn.initParams()
sgd = optimizer.SGD(nn, alpha=0.01, minibatch=30, optimizer="adagrad")
outFile = "./param/%s/%s_wvecDim_%d_epochs_%d_step_001.bin" % (
model, model, wvecDim, epochs)
train_cost = []
train_acc = []
dev_cost = []
dev_acc = []
cost = 0
accuracy = 0
for e in range(epochs):
start = time.time()
sgd.run(trees)
end = time.time()
print "Time per epoch : %f" % (end - start)
with open(outFile, 'w') as fid:
hyperparam = {}
hyperparam['alpha'] = 0.01
hyperparam['minibatch'] = 30
hyperparam['wvecDim'] = wvecDim
pickle.dump(hyperparam, fid)
nn.toFile(fid)
cost, accuracy = test(nn, trees)
train_cost.append(cost)
train_acc.append(accuracy)
cost, accuracy = test(nn, dev_trees)
dev_cost.append(cost)
dev_acc.append(accuracy)
for tree in trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
print "fprop in trees cleared"
plot_cost_acc(
train_cost, dev_cost,
"./figures/%s/%s_Cost_Figure_%d" % (model, model, wvecDim), epochs)
plot_cost_acc(
train_acc, dev_acc,
"./figures/%s/%s_Accuracy_Figure_%d" % (model, model, wvecDim),
epochs)
anwser = "Cost = %f, Acc= %f" % (cost, accuracy)
f.write(anwser)
accuracy_per_wvecDim.append(accuracy)
f.close()
plt.figure(figsize=(6, 4))
plt.title(r"Accuracies and vector Dimension")
plt.xlabel("vector Dimension")
plt.ylabel(r"Accuracy")
plt.ylim(ymin=min(accuracy_per_wvecDim) * 0.8,
ymax=max(accuracy_per_wvecDim) * 1.2)
plt.plot(wvecDimList,
accuracy_per_wvecDim,
color='b',
marker='o',
linestyle='-')
plt.savefig("./figures/%s/%s_Accuracy_and_vectorDimsension.png" %
(model, model))
plt.close()
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option("--test",action="store_true",dest="test",default=False)
# Optimizer
parser.add_option("--minibatch",dest="minibatch",type="int",default=30)
parser.add_option("--optimizer",dest="optimizer",type="string",
default="adagrad")
parser.add_option("--epochs",dest="epochs",type="int",default=50)
parser.add_option("--step",dest="step",type="float",default=1e-2)
parser.add_option("--middleDim",dest="middleDim",type="int",default=10)
parser.add_option("--outputDim",dest="outputDim",type="int",default=3)
parser.add_option("--wvecDim",dest="wvecDim",type="int",default=30)
# for DCNN only
parser.add_option("--ktop",dest="ktop",type="int",default=5)
parser.add_option("--m1",dest="m1",type="int",default=10)
parser.add_option("--m2",dest="m2",type="int",default=7)
parser.add_option("--n1",dest="n1",type="int",default=6)
parser.add_option("--n2",dest="n2",type="int",default=12)
parser.add_option("--outFile",dest="outFile",type="string",
default="models/test.bin")
parser.add_option("--inFile",dest="inFile",type="string",
default="models/test.bin")
parser.add_option("--data",dest="data",type="string",default="train")
parser.add_option("--model",dest="model",type="string",default="RNN")
(opts,args)=parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch, makes things faster!
evaluate_accuracy_while_training = True
# Testing
if opts.test:
cmfile = opts.inFile + ".confusion_matrix-" + opts.data
test(opts.inFile,opts.data,None,opts.model,confusion_matrix_file=cmfile,full=True)
return
print "Loading data..."
train_accuracies = []
dev_accuracies = []
# load training data
trees = tr.loadTrees('train')
opts.numWords = len(tr.loadWordMap())
#Load word embeddings
L = tr.loadWordEmbedding()
if(opts.model=='RNN2'):
nn = RNN2(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch)
else:
raise '%s is not a valid neural network, only RNN2'%opts.model
nn.initParams(L)
sgd = optimizer.SGD(nn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)
dev_trees = tr.loadTrees("dev")
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d"%e
sgd.run(trees)
end = time.time()
print "Time per epoch : %f"%(end-start)
with open(opts.outFile,'w') as fid:
pickle.dump(opts,fid)
pickle.dump(sgd.costt,fid)
nn.toFile(fid)
if evaluate_accuracy_while_training:
print "testing on training set real quick"
train_accuracies.append(test(opts.outFile,"train",L,opts.model,trees))
print "testing on dev set real quick"
dev_accuracies.append(test(opts.outFile,"dev",L,opts.model,dev_trees))
# clear the fprop flags in trees and dev_trees
for tree in trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root,nodeFn=tr.clearFprop)
print "fprop in trees cleared"
if evaluate_accuracy_while_training:
# pdb.set_trace()
print train_accuracies
print dev_accuracies
# Plot train/dev_accuracies here?
plt.figure()
plt.plot(range(len(train_accuracies)), train_accuracies, label='Train')
plt.plot(range(len(dev_accuracies)), dev_accuracies, label='Dev')
plt.xlabel("Epoch")
plt.ylabel("Accuracy")
plt.legend()
# plot.show()
plt.savefig(opts.outFile + ".accuracy_plot.png")
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
parser.add_option("--test",
action="store_true",
dest="test",
default=False)
# Optimizer
parser.add_option("--minibatch", dest="minibatch", type="int", default=30)
parser.add_option("--optimizer",
dest="optimizer",
type="string",
default="adagrad")
parser.add_option("--epochs", dest="epochs", type="int", default=50)
parser.add_option("--step", dest="step", type="float", default=1e-2)
parser.add_option("--init", dest="init", type="float", default=0.01)
parser.add_option("--outputDim", dest="outputDim", type="int", default=5)
parser.add_option("--wvecDim", dest="wvecDim", type="int", default=30)
parser.add_option("--rho", dest="rho", type="float", default=1e-6)
parser.add_option("--outFile",
dest="outFile",
type="string",
default="models/test.bin")
parser.add_option("--inFile",
dest="inFile",
type="string",
default="models/test.bin")
parser.add_option("--data", dest="data", type="string", default="train")
parser.add_option("--model", dest="model", type="string", default="RNTN")
parser.add_option("--maxTrain", dest="maxTrain", type="int", default=-1)
parser.add_option("--activation",
dest="acti",
type="string",
default="tanh")
parser.add_option("--partial",
action="store_true",
dest="partial",
default=False)
parser.add_option("--w2v", dest="w2vmodel", type="string")
(opts, args) = parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch, makes things faster!
evaluate_accuracy_while_training = True
# Testing
if opts.test:
cmfile = opts.inFile + ".confusion_matrix-" + opts.data + ".png"
test(opts.inFile, opts.data, opts.model, acti=opts.acti)
return
print "Loading data..."
embedding = None
wordMap = None
if opts.w2vmodel is not None:
print "Loading pre-trained word2vec model from %s" % opts.w2vmodel
w2v = models.Word2Vec.load(opts.w2vmodel)
embedding, wordMap = readW2v(w2v, opts.wvecDim)
train_accuracies = []
train_rootAccuracies = []
dev_accuracies = []
dev_rootAccuracies = []
# load training data
trees = tr.loadTrees('train',
wordMap=wordMap)[:opts.maxTrain] #train.full.15
if opts.maxTrain > -1:
print "Training only on %d trees" % opts.maxTrain
opts.numWords = len(tr.loadWordMap())
if opts.partial == True:
print "Only partial feedback"
if (opts.model == 'RNTN'):
nn = RNTN(wvecDim=opts.wvecDim,
outputDim=opts.outputDim,
numWords=opts.numWords,
mbSize=opts.minibatch,
rho=opts.rho,
acti=opts.acti,
init=opts.init,
partial=opts.partial)
else:
raise '%s is not a valid neural network so far only RNTN, RNN' % opts.model
nn.initParams(embedding=embedding)
sgd = optimizer.SGD(nn,
alpha=opts.step,
minibatch=opts.minibatch,
optimizer=opts.optimizer)
dev_trees = tr.loadTrees("dev") #dev.full.15
for e in range(opts.epochs):
start = time.time()
print "Running epoch %d" % e
sgd.run(trees)
end = time.time()
print "Time per epoch : %f" % (end - start)
with open(opts.outFile, 'w') as fid:
pickle.dump(opts, fid)
pickle.dump(sgd.costt, fid)
nn.toFile(fid)
if evaluate_accuracy_while_training:
print "testing on training set"
acc, sacc = test(opts.outFile,
"train",
opts.model,
trees,
acti=opts.acti)
train_accuracies.append(acc)
train_rootAccuracies.append(sacc)
print "testing on dev set"
dacc, dsacc = test(opts.outFile,
"dev",
opts.model,
dev_trees,
acti=opts.acti)
dev_accuracies.append(dacc)
dev_rootAccuracies.append(dsacc)
# clear the fprop flags and dev_trees
for tree in trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
for tree in dev_trees:
tr.leftTraverse(tree.root, nodeFn=tr.clearFprop)
print "fprop in trees cleared"
if evaluate_accuracy_while_training:
pdb.set_trace()
print train_accuracies
print dev_accuracies
print "on sentence-level:"
print train_rootAccuracies
print dev_rootAccuracies
# Plot train/dev_accuracies
plt.figure()
plt.plot(range(len(train_accuracies)), train_accuracies, label='Train')
plt.plot(range(len(dev_accuracies)), dev_accuracies, label='Dev')
plt.xlabel("Epoch")
plt.ylabel("Accuracy")
plt.legend()
# plot.show()
plt.savefig(opts.outFile + ".accuracy_plot.png")
# Plot train/dev_accuracies
plt.figure()
plt.plot(range(len(train_rootAccuracies)),
train_rootAccuracies,
label='Train')
plt.plot(range(len(dev_rootAccuracies)),
dev_rootAccuracies,
label='Dev')
plt.xlabel("Epoch")
plt.ylabel("Accuracy")
plt.legend()
# plot.show()
plt.savefig(opts.outFile + ".sent.accuracy_plot.png")