def test_serialize(self):
sv = SparseVector(4, {1: 1, 3: 2})
dv = array([1., 2., 3., 4.])
lst = [1, 2, 3, 4]
self.assertTrue(sv is _convert_vector(sv))
self.assertTrue(dv is _convert_vector(dv))
self.assertTrue(array_equal(dv, _convert_vector(lst)))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(sv)))
self.assertTrue(array_equal(dv, _deserialize_double_vector(_serialize_double_vector(dv))))
self.assertTrue(array_equal(dv, _deserialize_double_vector(_serialize_double_vector(lst))))
def test_serialize(self):
sv = SparseVector(4, {1: 1, 3: 2})
dv = array([1., 2., 3., 4.])
lst = [1, 2, 3, 4]
self.assertTrue(sv is _convert_vector(sv))
self.assertTrue(dv is _convert_vector(dv))
self.assertTrue(array_equal(dv, _convert_vector(lst)))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(sv)))
self.assertTrue(array_equal(dv, _deserialize_double_vector(_serialize_double_vector(dv))))
self.assertTrue(array_equal(dv, _deserialize_double_vector(_serialize_double_vector(lst))))
def test_serialize(self):
from scipy.sparse import lil_matrix
lil = lil_matrix((4, 1))
lil[1, 0] = 1
lil[3, 0] = 2
sv = SparseVector(4, {1: 1, 3: 2})
self.assertEquals(sv, _convert_vector(lil))
self.assertEquals(sv, _convert_vector(lil.tocsc()))
self.assertEquals(sv, _convert_vector(lil.tocoo()))
self.assertEquals(sv, _convert_vector(lil.tocsr()))
self.assertEquals(sv, _convert_vector(lil.todok()))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil)))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil.tocsc())))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil.tocsr())))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil.todok())))
def test_serialize(self):
from scipy.sparse import lil_matrix
lil = lil_matrix((4, 1))
lil[1, 0] = 1
lil[3, 0] = 2
sv = SparseVector(4, {1: 1, 3: 2})
self.assertEquals(sv, _convert_vector(lil))
self.assertEquals(sv, _convert_vector(lil.tocsc()))
self.assertEquals(sv, _convert_vector(lil.tocoo()))
self.assertEquals(sv, _convert_vector(lil.tocsr()))
self.assertEquals(sv, _convert_vector(lil.todok()))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil)))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil.tocsc())))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil.tocsr())))
self.assertEquals(sv, _deserialize_double_vector(_serialize_double_vector(lil.todok())))
def predict(self, x):
"""
Predict the label of one or more examples.
:param x: Data point (feature vector),
or an RDD of data points (feature vectors).
"""
pythonAPI = self._sc._jvm.PythonMLLibAPI()
if isinstance(x, RDD):
# Bulk prediction
if x.count() == 0:
return self._sc.parallelize([])
dataBytes = _get_unmangled_double_vector_rdd(x, cache=False)
jSerializedPreds = \
pythonAPI.predictDecisionTreeModel(self._java_model,
dataBytes._jrdd)
serializedPreds = RDD(jSerializedPreds, self._sc, NoOpSerializer())
return serializedPreds.map(lambda bytes: _deserialize_double(bytearray(bytes)))
else:
# Assume x is a single data point.
x_ = _serialize_double_vector(x)
return pythonAPI.predictDecisionTreeModel(self._java_model, x_)
def predict(self, x):
"""
Predict the label of one or more examples.
:param x: Data point (feature vector),
or an RDD of data points (feature vectors).
"""
pythonAPI = self._sc._jvm.PythonMLLibAPI()
if isinstance(x, RDD):
# Bulk prediction
if x.count() == 0:
return self._sc.parallelize([])
dataBytes = _get_unmangled_double_vector_rdd(x, cache=False)
jSerializedPreds = \
pythonAPI.predictDecisionTreeModel(self._java_model,
dataBytes._jrdd)
serializedPreds = RDD(jSerializedPreds, self._sc, NoOpSerializer())
return serializedPreds.map(lambda bytes: _deserialize_double(bytearray(bytes)))
else:
# Assume x is a single data point.
x_ = _serialize_double_vector(x)
return pythonAPI.predictDecisionTreeModel(self._java_model, x_)
def predict(self, point):
serialized = _serialize_double_vector(point)
return self._model.predict(serialized)
def predict(self, point):
serialized = _serialize_double_vector(point)
return self._model.predict(serialized)
