"which tagger to use; change the default to the one you want to use on q 3.2"
)
try:
args = parser.parse_args()
except IOError as msg:
parser.error(str(msg))
data = read_twitter(trainfile=args.train, evalfiles=args.eval)
import tagger
if args.tagger == "logreg":
tagger = tagger.LogisticRegressionTagger()
elif args.tagger == "crf":
tagger = tagger.CRFPerceptron()
else:
sys.stderr.write("Did not properly select tagger!")
sys.exit(1)
# Train the tagger
tagger.fit_data(data.train_sents, data.train_labels)
# Evaluation (also writes out predictions)
trainoutfile = "{}/{}.pred".format(args.outdir,
os.path.basename(args.train))
print "### Train evaluation; writing to {}".format(trainoutfile)
data.train_preds = tagger.evaluate_data(data.train_sents,
data.train_labels)
write_preds(trainoutfile, data.train_sents, data.train_labels,
data.train_preds)
type=int,
default=4,
help="batch size")
try:
args = parser.parse_args()
except IOError as msg:
parser.error(str(msg))
# print os.getcwd() #
data = read_twitter(trainfile=args.train, evalfiles=args.eval)
import tagger
if args.tagger == "logreg":
tagger = tagger.LogisticRegressionTagger()
elif args.tagger == "crf":
tagger = tagger.CRFPerceptron(args.epochs, args.batch_size)
else:
sys.stderr.write("Did not properly select tagger!")
sys.exit(1)
# Train the tagger
tagger.fit_data(data.train_sents, data.train_labels)
# Evaluation (also writes out predictions)
for evalstr, evalset in zip(args.eval, data.eval):
evaloutfile = "{}/{}.pred".format(args.outdir,
os.path.basename(evalstr))
print("### evaluation of {}; writing to {}".format(
evalstr, evaloutfile))
preds = tagger.evaluate_data(evalset["sents"], evalset["labels"])
write_preds(evaloutfile, evalset["sents"], evalset["labels"], preds)