def test_normalization_bywindow(self):
y = array([1, 2, 3, 4, 5], dtype='float16')
rdd = self.sc.parallelize([(0, y)])
data = TimeSeries(rdd, dtype='float16')
out = data.normalize('window', window=2)
vals = out.first()[1]
assert_equals('float64', str(vals.dtype))
b_true = array([1.2, 1.4, 2.4, 3.4, 4.2])
result_true = (y - b_true) / (b_true + 0.1)
assert(allclose(vals, result_true, atol=1e-3))
out = data.normalize('window', window=6)
vals = out.first()[1]
b_true = array([1.6, 1.8, 1.8, 1.8, 2.6])
result_true = (y - b_true) / (b_true + 0.1)
assert(allclose(vals, result_true, atol=1e-3))
out = data.normalize('window-fast', window=2)
vals = out.first()[1]
assert_equals('float64', str(vals.dtype))
b_true = array([1, 1, 2, 3, 4])
result_true = (y - b_true) / (b_true + 0.1)
assert(allclose(vals, result_true, atol=1e-3))
out = data.normalize('window-fast', window=5)
vals = out.first()[1]
b_true = array([1, 1, 2, 3, 4])
result_true = (y - b_true) / (b_true + 0.1)
assert(allclose(vals, result_true, atol=1e-3))
def test_normalization_bywindow(self):
y = array([1, 2, 3, 4, 5], dtype='float16')
rdd = self.sc.parallelize([(0, y)])
data = TimeSeries(rdd, dtype='float16')
out = data.normalize('window', window=2)
vals = out.first()[1]
assert_equals('float64', str(vals.dtype))
b_true = array([1.2, 1.4, 2.4, 3.4, 4.2])
result_true = (y - b_true) / (b_true + 0.1)
assert (allclose(vals, result_true, atol=1e-3))
out = data.normalize('window', window=6)
vals = out.first()[1]
b_true = array([1.6, 1.8, 1.8, 1.8, 2.6])
result_true = (y - b_true) / (b_true + 0.1)
assert (allclose(vals, result_true, atol=1e-3))
out = data.normalize('window-fast', window=2)
vals = out.first()[1]
assert_equals('float64', str(vals.dtype))
b_true = array([1, 1, 2, 3, 4])
result_true = (y - b_true) / (b_true + 0.1)
assert (allclose(vals, result_true, atol=1e-3))
out = data.normalize('window-fast', window=5)
vals = out.first()[1]
b_true = array([1, 1, 2, 3, 4])
result_true = (y - b_true) / (b_true + 0.1)
assert (allclose(vals, result_true, atol=1e-3))
def test_normalization_bypercentile(self):
rdd = self.sc.parallelize([(0, array([1, 2, 3, 4, 5], dtype='float16'))])
data = TimeSeries(rdd, dtype='float16')
out = data.normalize('percentile', perc=20)
vals = out.first()[1]
assert_equals('float16', str(vals.dtype))
assert(allclose(vals, array([-0.42105, 0.10526, 0.63157, 1.15789, 1.68421]), atol=1e-3))
def test_normalization_bymean(self):
rdd = self.sc.parallelize([(0, array([1, 2, 3, 4, 5], dtype='float16'))])
data = TimeSeries(rdd, dtype='float16')
out = data.normalize('mean')
vals = out.first()[1]
assert_equals('float16', str(vals.dtype))
assert(allclose(out.first()[1],
array([-0.64516, -0.32258, 0.0, 0.32258, 0.64516]), atol=1e-3))
def test_normalization_bypercentile(self):
rdd = self.sc.parallelize([(0, array([1, 2, 3, 4, 5],
dtype='float16'))])
data = TimeSeries(rdd, dtype='float16')
out = data.normalize('percentile', perc=20)
vals = out.first()[1]
assert_equals('float16', str(vals.dtype))
assert (allclose(vals,
array([-0.42105, 0.10526, 0.63157, 1.15789, 1.68421]),
atol=1e-3))
def test_normalization_bymean(self):
rdd = self.sc.parallelize([(0, array([1, 2, 3, 4, 5],
dtype='float16'))])
data = TimeSeries(rdd, dtype='float16')
out = data.normalize('mean')
vals = out.first()[1]
assert_equals('float16', str(vals.dtype))
assert (allclose(out.first()[1],
array([-0.64516, -0.32258, 0.0, 0.32258, 0.64516]),
atol=1e-3))
