def test(netFile,dataSet,trees=None):
if trees==None:
trees = tr.printtree(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)
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.alpha,opts.minibatch)
nn.initParams()
nn.fromFile(fid)
cost, Mis = nn.costAndGrad(trees,test=True)
print "Cost = %f, Acc = %f"%(cost, 1.0 - Mis)
return (1.0 - Mis)
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("--wvecDim",dest="wvecDim",type="int",default=30)
parser.add_option("--outputDim",dest="outputDim",type="int",default=2)
parser.add_option("--alpha",dest="alpha",type="int",default=0.2)
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="brae.pos")
parser.add_option("--dev",dest="dev",type="string",default="brae.dev")
parser.add_option("--wordMap",dest="map",type="string",default="brae.tot")
(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)
return
print "Loading data..."
train_accuracies = []
dev_accuracies = []
trees = tr.printtree(opts.data)
opts.numWords = len(tr.loadWordMap(opts.map))
nn = RNN(opts.wvecDim,opts.outputDim,opts.numWords,opts.alpha,opts.minibatch)
nn.initParams()
sgd = optimizer.SGD(nn,alpha=opts.step,minibatch=opts.minibatch,
optimizer=opts.optimizer)
dev_trees = tr.printtree(opts.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,opts.data,trees))
print "testing on dev set real quick"
dev_accuracies.append(test(opts.outFile,opts.dev,dev_trees))
if evaluate_accuracy_while_training:
pdb.set_trace()
print train_accuracies
print dev_accuracies
