def get_validation_data(self):
if self.validation_text_set is not None:
return self.validation_text_set.get_samples().map(
lambda sample: Sample.from_jtensor(
features=sample.features + sample.labels,
labels=JTensor.from_ndarray(np.array([0.0]))))
return None
def to_jtensor(i):
if isinstance(i, np.ndarray):
return JTensor.from_ndarray(i)
elif isinstance(i, JTensor):
return i
else:
raise Exception("Error unknown input type %s" % type(i))
def get_training_data(self):
sample_rdd = self.text_set.get_samples().map(
lambda sample: Sample.from_jtensor(
features=sample.features + sample.labels,
labels=JTensor.from_ndarray(np.array([0.0]))))
return FeatureSet.sample_rdd(sample_rdd,
sequential_order=self.sequential_order,
shuffle=self.shuffle)
def get_prediction_data(self):
rdd = self.text_set.get_samples().map(
lambda sample: Sample.from_jtensor(features=sample.features,
labels=JTensor.from_ndarray(
np.array([0.0]))))
rdd_wrapper = callZooFunc("float", "zooRDDSampleToMiniBatch", rdd,
self.batch_per_thread)
return rdd_wrapper.value().toJavaRDD()
def get_validation_data(self):
if self.validation_text_set is not None:
sample_rdd = self.validation_text_set.get_samples().map(
lambda sample: Sample.from_jtensor(
features=sample.features + sample.labels,
labels=JTensor.from_ndarray(np.array([0.0]))))
return FeatureSet.sample_rdd(
sample_rdd,
sequential_order=self.sequential_order,
shuffle=self.shuffle)
return None
def get_validation_data(self):
if self.validation_text_set is not None:
sample_rdd = self.validation_text_set.get_samples().map(
lambda sample: Sample.from_jtensor(
features=sample.features + sample.labels,
labels=JTensor.from_ndarray(np.array([0.0]))))
fs = FeatureSet.sample_rdd(sample_rdd,
sequential_order=self.sequential_order,
shuffle=self.shuffle)
fs = fs.transform(SampleToMiniBatch(self.batch_size))
return fs
return None
def get_training_data(self):
return self.text_set.get_samples().map(
lambda sample: Sample.from_jtensor(features=sample.features + sample.labels,
labels=JTensor.from_ndarray(np.array([0.0]))))