"""
Optional alternative loss function for printing or diagnostics.
"""
return roc_auc_score(y, np.array(self.predict_proba(X))[:, 1])
if __name__ == '__main__':
from datautil import load_raop_data
from transformers import ExtractBody, PrepAndVectorize
from sklearn.pipeline import Pipeline
all_train_df, all_train_labels, submit_df = load_raop_data()
wdim = 50
hdim = 10
context = 1
# need to make sure dropout equal to 0 for
# gradient check, otherwise will not work
# because it is stochastic
drop_p = 0.
X = Pipeline([('body', ExtractBody()), ('vec', PrepAndVectorize(d=wdim))
]).fit_transform(all_train_df[:4], y=1)
y = all_train_labels[:4]
nnmx = CNN2(wdim=wdim, hdim=hdim, drop_p=drop_p, context=context)
print("Numerical gradient check...")
nnmx.grad_check(X, y)
if __name__ == '__main__':
from datautil import load_raop_data
from transformers import ExtractBody, PrepAndVectorize
from sklearn.pipeline import Pipeline
all_train_df, all_train_labels, submit_df = load_raop_data()
wdim = 50
hdim = 10
# need to make sure dropout equal to 0 for
# gradient check, otherwise will not work
# because it is stochastic
drop_p = 0.
X = Pipeline([
('body', ExtractBody()),
('vec', PrepAndVectorize(d=wdim))
]).fit_transform(all_train_df[:4],y=1)
y = all_train_labels[:4]
nnmx = NNMX2(wdim=wdim,hdim=hdim,drop_p=drop_p)
print("Numerical gradient check...")
nnmx.grad_check(X, y)
def run(args=None):
usage = "usage : %prog [options]"
parser = optparse.OptionParser(usage=usage)
#parser.add_option("--test",action="store_true",dest="test",default=False)
#parser.add_option("--plotEpochs",action="store_true",dest="plotEpochs",default=False)
#parser.add_option("--plotWvecDim",action="store_true",dest="plotWvecDim",default=False)
# Optimizer
# minibatch of 0 means no minibatches, just iterate through
parser.add_option("--minibatch",dest="minibatch",type="int",default=0)
#parser.add_option("--optimizer",dest="optimizer",type="string",
# default="adagrad")
parser.add_option("--epochs",dest="epochs",type="int",default=50)
parser.add_option("--printevery",dest="printevery",type="int",default=4e4)
parser.add_option("--annealevery",dest="annealevery",type="int",default=0) # anneal every this many epochs
parser.add_option("--alpha",dest="alpha",type="float",default=0.005)
parser.add_option("--rho",dest="rho",type="float",default=1e-5)
parser.add_option("--drop_p",dest="drop_p",type="float",default=0.5)
parser.add_option("--wdim",dest="wdim",type="int",default=50)
parser.add_option("--hdim",dest="hdim",type="int",default=200)
parser.add_option("--odim",dest="odim",type="int",default=2)
parser.add_option("--rseed",dest="rseed",type="int",default=207)
parser.add_option("--context",dest="context",type="int",default=1)
#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="NNMX")
(opts,args)=parser.parse_args(args)
# name of folder to store results in
resfolder = '_'.join(
['{k}={v}'.format(k=k,v=v) for k,v in vars(opts).items()]
)
resfolder += '_timestamp={t}'.format(t=time.strftime('%Y%m%d%H%M%S'))
resfolder = 'results/'+resfolder
print(resfolder)
if not os.path.exists(resfolder):
os.makedirs(resfolder)
### Set up the training and test data to work with throughout the notebook:
np.random.seed(opts.rseed)
all_train_df, y, submit_df = load_raop_data()
# useful for sklearn scoring
#roc_scorer = make_scorer(roc_auc_score)
n_all = all_train_df.shape[0]
# set up kFolds to be used in the rest of the project
kf = KFold(n_all, n_folds = 10, random_state=opts.rseed)
body_vecs = Pipeline([
('body', ExtractBody()),
('vec', PrepAndVectorize(d=opts.wdim))
]).fit_transform(X=all_train_df,y=1)
for train, test in kf:
nn = init_model(opts)
if opts.minibatch == 0:
idxiter = list(train)*opts.epochs
annealevery=len(train)*opts.annealevery
printevery=opts.printevery
else:
idxiter = NNBase.randomiter(
N=opts.epochs*len(train)/opts.minibatch,
pickfrom=train,batch=opts.minibatch)
annealevery=len(train)*opts.annealevery/opts.minibatch
printevery=opts.printevery/opts.minibatch
nn.train_sgd(body_vecs, y, idxiter=idxiter,
devidx=test, savepath=resfolder,
costevery=printevery, printevery=printevery,
annealevery=annealevery)
save_all_results(resultpath = 'results', savepath = 'result_summary')