def infer(self, path):
'''
载入预测集
'''
logger.info("load inferset from %s" % path)
mode = TaskMode.create_infer()
return self._parse_creator(path, mode)
def train(self, path):
'''
载入数据集
'''
logger.info("load trainset from %s" % path)
mode = TaskMode.create_train()
return self._parse_creator(path, mode)
def test(self, path):
'''
载入测试集
'''
logger.info("load testset from %s" % path)
mode = TaskMode.create_test()
return self._parse_creator(path, mode)
def infer(self, path):
'''
Load infer set.
'''
logger.info("load inferset from %s" % path)
self.path = path
self.mode = TaskMode.create_infer()
return self._parse
def train(self, path):
'''
Load trainset.
'''
logger.info("load trainset from %s" % path)
self.mode = TaskMode.create_train()
self.path = path
return self._parse
def test(self, path):
'''
Load testset.
'''
logger.info("load testset from %s" % path)
self.path = path
self.mode = TaskMode.create_test()
return self._parse
def infer(self, path):
"""
load infer set
@path: infer set path
"""
logger.info("start infer reader from %s" % path)
mode = TaskMode.create_infer()
return self._reader(path, mode)
def test(self, path):
"""
load test set
@path: test set path
"""
logger.info("start test reader from %s" % path)
mode = TaskMode.create_test()
return self._reader(path, mode)
def train(self, path):
"""
load train set
@path: train set path
"""
logger.info("start train reader from %s" % path)
mode = TaskMode.create_train()
return self._reader(path, mode)
def infer(self):
'''
Load inferset.
'''
logger.info("load inferset from %s" % self.train_path)
self.mode = TaskMode.create_infer()
with open(self.train_path) as f:
reader = csv.DictReader(f)
for row_id, row in enumerate(reader):
rcd = self._parse_record(row)
if rcd:
yield rcd
def __init__(self,
train_path,
n_records_as_test=-1,
fields=None,
feature_dims=None):
self.train_path = train_path
self.n_records_as_test = n_records_as_test
self.fields = fields
# default is train mode.
self.mode = TaskMode.create_train()
self.categorial_dims = [
feature_dims[key] for key in categorial_features + ['hour']
]
self.id_dims = [feature_dims[key] for key in id_features]
def test(self):
'''
Load testset.
'''
logger.info("load testset from %s" % self.train_path)
self.mode = TaskMode.create_test()
with open(self.train_path) as f:
reader = csv.DictReader(f)
for row_id, row in enumerate(reader):
# skip top n lines
if self.n_records_as_test > 0 and row_id > self.n_records_as_test:
break
rcd = self._parse_record(row)
if rcd:
yield rcd
def train(self):
'''
载入训练集
'''
logger.info("load trainset from %s" % self.train_path)
self.mode = TaskMode.create_train()
with open(self.train_path) as f:
reader = csv.DictReader(f)
for row_id, row in enumerate(reader):
# 跳过前n条记录
if self.n_records_as_test > 0 and row_id < self.n_records_as_test:
continue
rcd = self._parse_record(row)
if rcd:
yield rcd
def __init__(self):
self.mode = TaskMode.create_train()