def _train(train_raw):
models = {}
all_docs = {}
for topic in train_raw:
x_train = []
y_train = []
for inst in train_raw[topic]:
feature_vector = [
ext.extract(inst[0], inst[1])
for ext in self.extractors
]
x_train.append(feature_vector)
y_train.append(inst[2])
svm = Supervised(self.args, self.opts)
with open(
constants.get_path()['tmp'] +
'/ltr-features-%s' % topic, 'wb') as mf:
json.dump({
'x_train': x_train,
'y_train': y_train
},
mf,
indent=2)
svm.train(x_train, y_train)
models[topic.lower()] = svm
all_docs[topic] = [inst[1] for inst in train_raw[topic]]
return models, all_docs
def _train(train_raw):
models = {}
all_docs = {}
for topic in train_raw:
x_train = []
y_train = []
for inst in train_raw[topic]:
feature_vector = [
ext.extract(inst[0], inst[1])
for ext in self.extractors
]
x_train.append(feature_vector)
y_train.append(inst[2])
svm = Supervised(self.args, self.opts)
if not os.path.exists(constants.get_path()['tmp'] +
'/ltr-features-all'):
with open(constants.get_path()['tmp'] + '/ltr-features-all',
'wb') as mf:
json.dump({
'x_train': x_train,
'y_train': y_train
},
mf,
indent=2)
svm.train(x_train, y_train)
all_docs = [
inst[1] for topc in train_raw for inst in train_raw[topc]
]
return svm, all_docs
def _train(train_raw):
models = {}
all_docs = {}
for topic in train_raw:
x_train = []
y_train = []
for inst in train_raw[topic]:
feature_vector = [
ext.extract(inst[0], inst[1]) for ext in self.extractors]
x_train.append(feature_vector)
y_train.append(inst[2])
svm = Supervised(self.args, self.opts)
with open(constants.get_path()['tmp'] + '/ltr-features-%s' % topic, 'wb') as mf:
json.dump(
{'x_train': x_train, 'y_train': y_train}, mf, indent=2)
svm.train(x_train, y_train)
models[topic.lower()] = svm
all_docs[topic] = [inst[1] for inst in train_raw[topic]]
return models, all_docs
def _train(train_raw):
models = {}
all_docs = {}
for topic in train_raw:
x_train = []
y_train = []
for inst in train_raw[topic]:
feature_vector = [
ext.extract(inst[0], inst[1]) for ext in self.extractors]
x_train.append(feature_vector)
y_train.append(inst[2])
svm = Supervised(self.args, self.opts)
if not os.path.exists(constants.get_path()['tmp'] + '/ltr-features-all'):
with open(constants.get_path()['tmp'] + '/ltr-features-all', 'wb') as mf:
json.dump(
{'x_train': x_train, 'y_train': y_train}, mf, indent=2)
svm.train(x_train, y_train)
all_docs = [inst[1]
for topc in train_raw for inst in train_raw[topc]]
return svm, all_docs