def test_linear_regress(self):
data = Series(self.sc.parallelize([(1, array([1.5, 2.3, 6.2, 5.1, 3.4, 2.1]))]))
x = array([
array([1, 0, 0, 0, 0, 0]),
array([0, 1, 0, 0, 0, 0])
])
model = RegressionModel.load(x, "linear")
result = model.fit(data)
assert(allclose(result.select('betas').values().collect()[0], array([-2.7, -1.9])))
assert(allclose(result.select('stats').values().collect()[0], array([0.42785299])))
assert(allclose(result.select('resid').values().collect()[0], array([0, 0, 2, 0.9, -0.8, -2.1])))
def test_linearRegress(self):
data = Series(self.sc.parallelize([(1, array([1.5, 2.3, 6.2, 5.1, 3.4, 2.1]))]))
x = array([
array([1, 0, 0, 0, 0, 0]),
array([0, 1, 0, 0, 0, 0])
])
model = RegressionModel.load(x, "linear")
result = model.fit(data)
# check accuracy of results
assert(allclose(result.select('betas').values().collect()[0], array([-2.7, -1.9])))
assert(allclose(result.select('stats').values().collect()[0], array([0.42785299])))
assert(allclose(result.select('resid').values().collect()[0], array([0, 0, 2, 0.9, -0.8, -2.1])))
# check indexing of outputs
assert(allclose(result.select('betas').index, array([0, 1])))
assert(allclose(result.select('resid').index, array([0, 1, 2, 3, 4, 5])))
assert(result.select('stats').index == 'stats')
def test_blinear_regress(self):
data = Series(self.sc.parallelize([(1, array([1.5, 2.3, 6.2, 5.1, 3.4, 2.1]))]))
x1 = array([
array([1, 0, 1, 0, 1, 0]),
array([0, 1, 0, 1, 0, 1])
])
x2 = array([
array([1, 1, 0, 0, 0, 0]),
array([0, 0, 1, 1, 0, 0]),
array([0, 0, 0, 0, 1, 1])
])
model = RegressionModel.load((x1, x2), "bilinear")
result = model.fit(data)
tol = 1E-4 # to handle rounding errors
assert(allclose(result.select('betas').values().collect()[0], array([-3.1249, 5.6875, 0.4375]), atol=tol))
assert(allclose(result.select('stats').values().collect()[0], array([0.6735]), tol))
assert(allclose(result.select('resid').values().collect()[0], array([0, -0.8666, 0, 1.9333, 0, -1.0666]), atol=tol))
def test_linearRegress(self):
data = Series(
self.sc.parallelize([(1, array([1.5, 2.3, 6.2, 5.1, 3.4, 2.1]))]))
x = array([array([1, 0, 0, 0, 0, 0]), array([0, 1, 0, 0, 0, 0])])
model = RegressionModel.load(x, "linear")
result = model.fit(data)
# check accuracy of results
assert (allclose(
result.select('betas').values().collect()[0], array([-2.7, -1.9])))
assert (allclose(
result.select('stats').values().collect()[0], array([0.42785299])))
assert (allclose(
result.select('resid').values().collect()[0],
array([0, 0, 2, 0.9, -0.8, -2.1])))
# check indexing of outputs
assert (allclose(result.select('betas').index, array([0, 1])))
assert (allclose(
result.select('resid').index, array([0, 1, 2, 3, 4, 5])))
assert (result.select('stats').index == ['stats'])
def test_bilinearRegress(self):
data = Series(
self.sc.parallelize([(1, array([1.5, 2.3, 6.2, 5.1, 3.4, 2.1]))]))
x1 = array([array([1, 0, 1, 0, 1, 0]), array([0, 1, 0, 1, 0, 1])])
x2 = array([
array([1, 1, 0, 0, 0, 0]),
array([0, 0, 1, 1, 0, 0]),
array([0, 0, 0, 0, 1, 1])
])
model = RegressionModel.load((x1, x2), "bilinear")
result = model.fit(data)
tol = 1E-4 # to handle rounding errors
assert (allclose(result.select('betas').values().collect()[0],
array([-3.1249, 5.6875, 0.4375]),
atol=tol))
assert (allclose(
result.select('stats').values().collect()[0], array([0.6735]),
tol))
assert (allclose(result.select('resid').values().collect()[0],
array([0, -0.8666, 0, 1.9333, 0, -1.0666]),
atol=tol))
