def test(netFile, dataSet, model='RNN', trees=None):
if trees == None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s" % netFile
with open(netFile, 'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if (model == 'RNTN'):
nn = RNTN(opts.wvecDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (model == 'RNN'):
nn = RNN(opts.wvecDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (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 (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()
nn.fromFile(fid)
print "Testing %s..." % model
cost, correct, guess, total = nn.costAndGrad(trees, test=True)
correct_sum = 0
for i in xrange(0, len(correct)):
correct_sum += (guess[i] == correct[i])
# TODO
# Plot the confusion matrix?
conf_arr = np.zeros((5, 5))
for i in xrange(0, len(correct)):
current_correct = correct[i]
current_guess = guess[i]
conf_arr[current_correct][current_guess] += 1.0
makeconf(conf_arr, model, dataSet)
print "Cost %f, Acc %f" % (cost, correct_sum / float(total))
return correct_sum / float(total)
def validate(rnn, results_dir):
# log.info(rnn.W)
trees = tr.loadTrees("dev")
log.info("Validation...")
cost, correct, total, df = rnn.costAndGrad(trees, test = True)
log.info("Validation: Cost %f, Correct %d/%d, Acc %f" % (cost, correct, total, correct / float(total)))
return df, cost, correct / float(total)
def test(netFile, dataSet, model='RNN', trees=None):
if trees == None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s" % netFile
opts = None
with open(netFile, 'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if (model == 'RNTN'):
nn = RNTN(opts.wvecDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (model == 'RNN'):
nn = RNN(opts.wvecDim, opts.outputDim, opts.numWords,
opts.minibatch)
elif (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 (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()
nn.fromFile(fid)
print "Testing %s..." % model
cost, correct, guess, total = nn.costAndGrad(trees, test=True)
correct_sum = 0
for i in xrange(0, len(correct)):
correct_sum += (guess[i] == correct[i])
cm = confusion_matrix(correct, guess)
makeconf(cm)
plt.savefig("plots/" + opts.model + "/confusion_matrix_" + model +
"wvecDim_" + str(opts.wvecDim) + "_middleDim_" +
str(opts.middleDim) + ".png")
print "Cost %f, Acc %f" % (cost, correct_sum / float(total))
return correct_sum / float(total)
def test(netFile,
dataSet,
model='RNN',
trees=None,
confusion_matrix_file=None,
acti=None):
if trees == None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s" % netFile
with open(netFile, 'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if (model == 'RNTN'):
nn = RNTN(wvecDim=opts.wvecDim,
outputDim=opts.outputDim,
numWords=opts.numWords,
mbSize=opts.minibatch,
rho=opts.rho,
acti=acti)
elif (model == 'RNN'):
nn = RNN(opts.wvecDim, opts.outputDim, opts.numWords,
opts.minibatch)
else:
raise '%s is not a valid neural network so far only RNTN, RNN' % opts.model
nn.initParams()
nn.fromFile(fid)
print "Testing %s..." % model
cost, correct, guess, total = nn.costAndGrad(trees, test=True)
correct_sum = 0
for i in xrange(0, len(correct)):
correct_sum += (guess[i] == correct[i])
correctSent = 0
for tree in trees:
sentLabel = tree.root.label
sentPrediction = tree.root.prediction
if sentLabel == sentPrediction:
correctSent += 1
# Generate confusion matrix
#if confusion_matrix_file is not None:
# cm = confusion_matrix(correct, guess)
# makeconf(cm, confusion_matrix_file)
print "%s: Cost %f, Acc %f, Sentence-Level: Acc %f" % (
dataSet, cost, correct_sum / float(total),
correctSent / float(len(trees)))
return (correct_sum / float(total), correctSent / float(len(trees)))
def test(netFile,dataSet):
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
with open(netFile,'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
rnn = nnet.RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
rnn.initParams()
rnn.fromFile(fid)
print "Testing..."
cost,correct,total = rnn.costAndGrad(trees,test=True)
print "Cost %f, Correct %d/%d, Acc %f"%(cost,correct,total,correct/float(total))
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("--outputDim",dest="outputDim",type="int",default=5)
parser.add_option("--wvecDim",dest="wvecDim",type="int",default=30)
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")
(opts,args)=parser.parse_args(args)
# Testing
if opts.test:
test(opts.inFile,opts.data)
return
print "Loading data..."
# load training data
trees = tr.loadTrees()
opts.numWords = len(tr.loadWordMap())
rnn = nnet.RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
rnn.initParams()
sgd = optimizer.SGD(rnn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)
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)
rnn.toFile(fid)
def test(netFile, dataSet, model="RNN", trees=None):
if trees == None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s" % netFile
with open(netFile, "r") as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if model == "RNTN":
nn = RNTN(opts.wvecDim, opts.outputDim, opts.numWords, opts.minibatch)
elif model == "RNN":
nn = RNN(opts.wvecDim, opts.outputDim, opts.numWords, opts.minibatch)
elif 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 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()
nn.fromFile(fid)
print "Testing %s..." % model
cost, correct, guess, total = nn.costAndGrad(trees, test=True)
correct_sum = 0
for i in xrange(0, len(correct)):
correct_sum += guess[i] == correct[i]
# TODO
# Plot the confusion matrix?
print "Cost %f, Acc %f" % (cost, correct_sum / float(total))
return correct_sum / float(total)
def test(netFile, dataSet):
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
with open(netFile, 'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
rnn = nnet.RNN(opts.wvecDim, opts.outputDim, opts.numWords,
opts.minibatch)
rnn.initParams()
rnn.fromFile(fid)
print "Testing..."
cost, correct, total = rnn.costAndGrad(trees, test=True)
print "Cost %f, Correct %d/%d, Acc %f" % (cost, correct, total,
correct / float(total))
def test(netFile,dataSet, model='RNN', trees=None,e=100):
if trees==None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s"%netFile
with open(netFile,'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if (model=='RNTN'):
nn = RNTN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout)
elif(model=='RNN'):
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout)
elif(model=='RNN2'):
nn = RNN2(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout)
elif(model=='RNN2TANH'):
nn = RNN2TANH(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout)
elif(model=='RNN3'):
nn = RNN3(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout)
elif(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, and DCNN'%opts.model
nn.initParams()
nn.fromFile(fid)
print "Testing %s..."%model
cost,correct, guess, total = nn.costAndGrad(trees,test=True)
correct_sum = 0
for i in xrange(0,len(correct)):
correct_sum+=(guess[i]==correct[i])
if e%10==0:
labels = range(max(set(correct))+1)
correct = np.array(correct)
guess = np.array(guess)
conf_arr = []
for i in labels:
sub_arr = []
for j in labels:
sub_arr.append(sum((correct == i) & (guess==j)))
conf_arr.append(sub_arr)
makeconf(conf_arr,'temp/'+model+'_conf_mat_'+dataSet+'_'+str(e)+'.')
print "Cost %f, Acc %f"%(cost,correct_sum/float(total)),
print "Pos F1 %f"%(evaluateF1(correct, guess, 2)), "Neg F1 %f"%(evaluateF1(correct, guess, 0))
return correct_sum/float(total)
def test(netFile,dataSet, model='RNN', trees=None):
if trees==None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s"%netFile
with open(netFile,'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if (model=='RNTN'):
nn = RNTN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(model=='RNN'):
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(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(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()
nn.fromFile(fid)
print "Testing %s..."%model
cost,correct, guess, total = nn.costAndGrad(trees,test=True)
correct_sum = 0
for i in xrange(0,len(correct)):
correct_sum+=(guess[i]==correct[i])
# TODO
# Plot the confusion matrix?
conf_arr = np.zeros((5,5))
for i in xrange(0,len(correct)):
current_correct = correct[i]
current_guess = guess[i]
conf_arr[current_correct][current_guess] += 1.0
makeconf(conf_arr, model, dataSet)
print "Cost %f, Acc %f"%(cost,correct_sum/float(total))
return correct_sum/float(total)
def test(model_dir, dataSet):
trees = tr.loadTrees(dataSet)
total_df = pd.DataFrame()
assert model_dir is not None, "Must give model to test"
with open(model_dir + "/checkpoint.bin", 'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
rnn = nnet.RNN(opts.wvecDim, opts.outputDim, opts.numWords, opts.optimizer_settings['minibatch'])
rnn.initParams()
rnn.fromFile(fid)
log.info("Testing...")
cost, correct, total, df = rnn.costAndGrad(trees, test = True)
total_df = total_df.append(df, ignore_index = True)
total_df.to_csv(model_dir + "/test_preds.csv", header = True, index = False)
test_performance = pd.DataFrame()
row = {"Cost": cost, "Correct": correct, "Total": total, "Accuracy": correct / float(total)}
test_performance = test_performance.append(row, ignore_index = True)
test_performance.to_csv(model_dir + "/test_performance.csv", header = True, index = False)
log.info("Cost %f, Correct %d/%d, Acc %f" % (cost, correct, total, correct / float(total)))
def test(netFile,dataSet, model='RNN', trees=None):
if trees==None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s"%netFile
opts = None
with open(netFile,'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if (model=='RNTN'):
nn = RNTN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(model=='RNN'):
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
elif(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(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()
nn.fromFile(fid)
print "Testing %s..."%model
cost,correct, guess, total = nn.costAndGrad(trees,test=True)
correct_sum = 0
for i in xrange(0,len(correct)):
correct_sum+=(guess[i]==correct[i])
cm = confusion_matrix(correct, guess)
makeconf(cm)
plt.savefig("plots/" + opts.model + "/confusion_matrix_" + model + "wvecDim_" + str(opts.wvecDim) + "_middleDim_" + str(opts.middleDim) + ".png")
print "Cost %f, Acc %f"%(cost,correct_sum/float(total))
return correct_sum/float(total)
def test(netFile,dataSet, model='RNN', trees=None, confusion_matrix_file=None, acti=None):
if trees==None:
trees = tr.loadTrees(dataSet)
assert netFile is not None, "Must give model to test"
print "Testing netFile %s"%netFile
with open(netFile,'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if (model=='RNTN'):
nn = RNTN(wvecDim=opts.wvecDim,outputDim=opts.outputDim,numWords=opts.numWords,mbSize=opts.minibatch,rho=opts.rho, acti=acti)
elif(model=='RNN'):
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
else:
raise '%s is not a valid neural network so far only RNTN, RNN'%opts.model
nn.initParams()
nn.fromFile(fid)
print "Testing %s..."%model
cost,correct, guess, total = nn.costAndGrad(trees,test=True)
correct_sum = 0
for i in xrange(0,len(correct)):
correct_sum+=(guess[i]==correct[i])
correctSent = 0
for tree in trees:
sentLabel = tree.root.label
sentPrediction = tree.root.prediction
if sentLabel == sentPrediction:
correctSent += 1
# Generate confusion matrix
#if confusion_matrix_file is not None:
# cm = confusion_matrix(correct, guess)
# makeconf(cm, confusion_matrix_file)
print "%s: Cost %f, Acc %f, Sentence-Level: Acc %f"%(dataSet,cost,correct_sum/float(total),correctSent/float(len(trees)))
return (correct_sum/float(total), correctSent/float(len(trees)))
def test_RNN():
"""Test RVNN model implementation.
"""
### Training process ###
'''
config = Config()
model = RNN_Model(config)
start_time = time.time()
stats = model.train(verbose=True)
print 'Training time: {}'.format(time.time() - start_time)
plt.plot(stats['loss_history'])
plt.title('Loss history')
plt.xlabel('Iteration')
plt.ylabel('Loss')
loss_filename = config.model_name + "loss_history" + ".png"
plt.savefig(loss_filename)
print 'Test'
print '=-=-='
'''
### Training process End ###
### Testing process ###
#predictions, _ = model.predict(model.test_data, './weights/%s'%model.config.model_name)
config = Config()
model = RNN_Model(config, LOAD_DATA=False)
#test_trees = tr.loadTrees('testing_data.txt.treerevised.txt', predicting_test=True)
test_trees = tr.loadTrees(FLAGS.revised_tree, predicting_test=True)
predictions, _ = model.predict(
test_trees,
'./weights/rnn_embed=200_l2=0.020000_lr=0.010000_epoch=50.weights')
f = open(FLAGS.outputfile_name, "w")
for prediction in predictions:
f.write(str(int(prediction)))
f.write("\n")
def test(netFile, dataSet, L, model='RNN', trees=None, confusion_matrix_file=None, full=False):
if trees==None:
trees = tr.loadTrees(dataSet)
if L is None:
L = tr.loadWordEmbedding()
assert netFile is not None, "Must give model to test"
print "Testing netFile %s"%netFile
with open(netFile,'r') as fid:
opts = pickle.load(fid)
_ = pickle.load(fid)
if(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)
nn.fromFile(fid)
print "Testing %s..."%model
cost, correct, guess, total, actss = nn.costAndGrad(trees,test=True)
if full:
#pass
import pickle as pkl
with open('{}_actss_{}.pkl'.format(netFile, dataSet),'w') as fid:
pkl.dump(actss,fid)
correct_sum = 0
for i in xrange(0,len(correct)):
correct_sum+=(guess[i]==correct[i])
# Generate confusion matrix
if confusion_matrix_file is not None:
cm = confusion_matrix(correct, guess)
makeconf(cm, confusion_matrix_file)
print "Cost %f, Acc %f"%(cost,correct_sum/float(total))
return correct_sum/float(total)
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(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("--outputDim", dest="outputDim", type="int", default=5)
parser.add_option("--wvecDim", dest="wvecDim", type="int", default=30)
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")
(opts, args) = parser.parse_args(args)
# Testing
if opts.test:
test(opts.inFile, opts.data)
return
print "Loading data..."
# load training data
trees = tr.loadTrees()
opts.numWords = len(tr.loadWordMap())
rnn = nnet.RNN(opts.wvecDim, opts.outputDim, opts.numWords, opts.minibatch)
rnn.initParams()
sgd = optimizer.SGD(rnn,
alpha=opts.step,
minibatch=opts.minibatch,
optimizer=opts.optimizer)
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)
rnn.toFile(fid)
default="sgd")
parser.add_option("--epochs",dest="epochs",type="int",default=50)
parser.add_option("--step",dest="step",type="float",default=1e-2)
parser.add_option("--outputDim",dest="outputDim",type="int",default=5)
parser.add_option("--wvecDim",dest="wvecDim",type="int",default=30)
parser.add_option("--outFile",dest="outFile",type="string",
default="models/distrntn.bin")
parser.add_option("--inFile",dest="inFile",type="string",
default="models/distrntn.bin")
parser.add_option("--data",dest="data",type="string",default="train")
(opts,args)=parser.parse_args(None)
print "Loading data..."
# load training data
trees = tr.loadTrees()
opts.numWords = len(tr.loadWordMap())
#setup the rntn
rnn = nnet.RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch)
rnn.initParams()
sgd = optimizer.SGD(rnn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)
#setup spark
if mode == "local":
# Set heap space size for java
#os.environ["_JAVA_OPTIONS"] = "-Xmx1g"
conf = (SparkConf()
.setMaster("local[*]")
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=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=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("--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
costP, _ = self.costAndGrad(data)
L[i, j] -= epsilon
numGrad = (costP - cost) / epsilon
err = np.abs(dL[j][i] - numGrad)
err2 += err
count += 1
if 0.001 > err2 / count:
print "Grad Check Passed for dL"
else:
print "Grad Check Failed for dL: Sum of Error = %.9f" % (err2 /
count)
if __name__ == '__main__':
import tree as treeM
train = treeM.loadTrees()
numW = len(treeM.loadWordMap())
wvecDim = 10
outputDim = 5
rnn = RNN(wvecDim, outputDim, numW, mbSize=4)
rnn.initParams()
mbData = train[:4]
print "Numerical gradient check..."
rnn.check_grad(mbData)
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage = usage)
parser.add_option("--test", action = "store_true", dest = "test", default = False)
# Paramsfile includes hyperparameters for training
parser.add_option('--params_file', dest = "params_file", default = './params/exp_params.json',
help = "Path to the file containing the training settings")
parser.add_option('--data_dir', dest = "data_dir", default = './trees',
help = "Directory containing the trees")
# Directory containing the model to test
parser.add_option("--model_directory", dest = "test_dir", type = "string")
parser.add_option("--data", dest = "data", type = "string", default = "train")
(opts, args) = parser.parse_args(args)
results_dir = "./results"
if opts.test:
pass
else:
results_dir_current_job = os.path.join(results_dir, utils.now_as_str_f())
while os.path.isdir(results_dir_current_job): # generate a new timestamp if the current one already exists
results_dir_current_job = os.path.join(results_dir, utils.now_as_str_f())
os.makedirs(results_dir_current_job)
# Load training settings (e.g. hyperparameters)
params = utils.Params(opts.params_file)
if opts.test:
pass
else:
# Copy the settings file into the results directory
copyfile(opts.params_file, os.path.join(results_dir_current_job, os.path.basename(opts.params_file)))
# Get the logger
if opts.test:
log_path = os.path.join(opts.test_dir, 'testing.log')
else:
log_path = os.path.join(results_dir_current_job, 'training.log')
log_level = params.log_level if hasattr(params, 'log_level') else logging.DEBUG
log = utils.get_logger(log_path, log_level)
if opts.test:
log.info("Testing directory: " + opts.test_dir)
log.info("Dataset used for testing: " + opts.data)
else:
log.info("Results directory: " + results_dir_current_job)
log.info("Minibatch: " + str(params.optimizer_settings['minibatch']))
log.info("Optimizer: " + params.optimizer)
log.info("Epsilon: " + str(params.optimizer_settings['epsilon']))
log.info("Alpha: " + str(params.optimizer_settings['alpha']))
log.info("Number of samples used: " + str(params.sample_size))
# Testing
if opts.test:
test(opts.test_dir, opts.data)
return
log.info("Loading data...")
# load training data
trees = tr.loadTrees(sample_size = params.sample_size)
params.numWords = len(tr.loadWordMap())
overall_performance = pd.DataFrame()
rnn = nnet.RNN(params.wvecDim, params.outputDim, params.numWords, params.optimizer_settings['minibatch'])
rnn.initParams()
sgd = optimizer.SGD(rnn, alpha = params.optimizer_settings['alpha'],
minibatch = params.optimizer_settings['minibatch'],
optimizer = params.optimizer, epsilon = params.optimizer_settings['epsilon'])
best_val_cost = float('inf')
best_epoch = 0
for e in range(params.num_epochs):
start = time.time()
log.info("Running epoch %d" % e)
df, updated_model, train_cost, train_acc = sgd.run(trees)
end = time.time()
log.info("Time per epoch : %f" % (end - start))
log.info("Training accuracy : %f" % train_acc)
# VALIDATION
val_df, val_cost, val_acc = validate(updated_model, results_dir_current_job)
if val_cost < best_val_cost:
# best validation cost we have seen so far
log.info("Validation score improved, saving model")
best_val_cost = val_cost
best_epoch = e
best_epoch_row = {"epoch": e, "train_cost": train_cost, "val_cost": val_cost, "train_acc": train_acc,
"val_acc": val_acc}
with open(results_dir_current_job + "/checkpoint.bin", 'w') as fid:
pickle.dump(params, fid)
pickle.dump(sgd.costt, fid)
rnn.toFile(fid)
val_df.to_csv(results_dir_current_job + "/validation_preds_epoch_ " + str(e) + ".csv", header = True, index = False)
df.to_csv(results_dir_current_job + "/training_preds_epoch_" + str(e) + ".csv", header = True, index = False)
row = {"epoch": e, "train_cost": train_cost, "val_cost": val_cost, "train_acc": train_acc, "val_acc": val_acc}
overall_performance = overall_performance.append(row, ignore_index = True)
# break if no val loss improvement in the last epochs
if (e - best_epoch) >= params.num_epochs_early_stop:
log.tinfo("No improvement in the last {num_epochs_early_stop} epochs, stop training.".format(num_epochs_early_stop=params.num_epochs_early_stop))
break
overall_performance = overall_performance.append(best_epoch_row, ignore_index = True)
overall_performance.to_csv(results_dir_current_job + "/train_val_costs.csv", header = True, index = False)
log.info("Experiment end")
L[i,j] -= epsilon
numGrad = (costP - cost)/epsilon
err = np.abs(dL[j][i] - numGrad)
#print "Analytic %.9f, Numerical %.9f, Relative Error %.9f"%(dL[j][i],numGrad,err)
err2+=err
count+=1
if 0.001 > err2/count:
print "Passed :)"
else:
print "Failed : Sum of Error = %.9f" % (err2/count)
if __name__ == '__main__':
import tree as treeM
train = treeM.loadTrees()
numW = len(treeM.loadWordMap())
wvecDim = 10
outputDim = 5
nn = RNTN(wvecDim,outputDim,numW,mbSize=4)
nn.initParams()
mbData = train[:1]
#cost, grad = nn.costAndGrad(mbData)
print "Numerical gradient check..."
nn.check_grad(mbData)
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("--rho",dest="rho",type="float",default=1e-4)
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")
parser.add_option("--pretrain",dest="pretrain",default=False)
parser.add_option("--dropout",dest="dropout",default=False)
(opts,args)=parser.parse_args(args)
# make this false if you dont care about your accuracies per epoch
evaluate_accuracy_while_training = True
# Testing
if opts.test:
test(opts.inFile,opts.data,opts.model,e=1000)
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,opts.pretrain,opts.dropout,opts.rho)
elif(opts.model=='RNN'):
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout,opts.rho)
elif(opts.model=='RNN2'):
nn = RNN2(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout,opts.rho)
elif(opts.model=='RNN2TANH'):
nn = RNN2(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout,opts.rho)
elif(opts.model=='RNN3'):
nn = RNN3(opts.wvecDim,opts.middleDim,opts.outputDim,opts.numWords,opts.minibatch,opts.pretrain,opts.dropout,opts.rho)
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, and DCNN'%opts.model
nn.initParams()
sgd = optimizer.SGD(nn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)
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,e))
print "testing on dev set real quick"
dev_accuracies.append(test(opts.outFile,"dev",opts.model,e=e))
if e%10==0:
if evaluate_accuracy_while_training:
print train_accuracies
print dev_accuracies
plt.figure()
plt.plot(train_accuracies,label = 'Train')
plt.plot(dev_accuracies,label = 'Dev')
plt.legend()
plt.savefig('temp/train_dev_accuracies_'+str(opts.model)+'_middle_'+str(opts.middleDim)+'.png')
if evaluate_accuracy_while_training:
print train_accuracies
print dev_accuracies
plt.figure()
plt.plot(train_accuracies,label = 'Train')
plt.plot(dev_accuracies,label = 'Dev')
plt.legend()
plt.savefig('temp/train_dev_accuracies_'+str(opts.model)+'_middle_'+str(opts.middleDim)+'.png')
