def testDataset3(self):
"""Dataset with only missing values"""
mean = compute_mean(self.dataset3, -9999)
self.assertEquals(mean, -9999)
std = compute_mean(self.dataset3, -9999)
self.assertAlmostEquals(std, -9999, delta=1e-3)
def testDataset1(self):
"""Dataset with one missing value"""
mean = compute_mean(self.dataset1, -9999)
self.assertEquals(mean, 40.0)
std = compute_std(self.dataset1, -9999)
self.assertAlmostEquals(std, 18.2574, delta=1e-3)
def testDataset2(self):
"""Dataset with no missing values"""
mean = compute_mean(self.dataset2, -9999)
self.assertEquals(mean, 45.0)
std = compute_std(self.dataset2, -9999)
self.assertAlmostEquals(std, 18.7082, delta=1e-3)
def standardize(data, missing_val=-9999):
"""Standardize a subset of data using a normal score.
Computes the normal score for a set of data necessary for performing
the standard normal homogenity test. The normal scores are defined as
Z_i = (Q_i - Qbar) / sigma_Q,
For more information, please refer to Alexandersson and Moberg, 1997,
Int'l Journal of Climatology Vol. 17, pp 25-34.
This is a direct port of splitmerge.v21f.f > subroutine 'standard'.
:Param data:
The dataset to standardize.
:Param missing_val:
The placeholder for missing data.
:Return:
A list of length (right-left), with the standardized reference
values computed here.
"""
## Find the valid data to use to compute the data_mean, etc.
valid_data = get_valid_data(data, missing_val)
num_vals = len(valid_data)
data_mean = compute_mean(valid_data, valid=True)
## Compute the sum the squared error for each term (variance)
variance_sum = 0.0
for d in valid_data:
variance_sum = variance_sum + (d-data_mean)**2
## The standard deviation is the root of the sum of the squared error
sum_std = sqrt(variance_sum/(num_vals-2))
## Normalize each data value using this standard deviation
standardized_data = []
#for d in data[left:right+1]:
for d in data:
if d!= missing_val:
standardized_data.append((d-data_mean)/sum_std)
else:
standardized_data.append(missing_val)
return standardized_data