class TestSAX(object):
def setUp(self):
# All tests will be run with 6 letter words
# and 5 letter alphabet
self.sax = SAX(6, 5, 1e-6)
def test_to_letter_rep(self):
arr = [7, 1, 4, 4, 4, 4]
(letters, indices) = self.sax.to_letter_rep(arr)
assert letters == 'eacccc'
def test_long_to_letter_rep(self):
long_arr = [
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 6, 6, 6, 6, 10,
100
]
(letters, indices) = self.sax.to_letter_rep(long_arr)
assert letters == 'bbbbce'
def test_compare_strings(self):
base_string = 'aaabbc'
similar_string = 'aabbbc'
dissimilar_string = 'ccddbc'
similar_score = self.sax.compare_strings(base_string, similar_string)
dissimilar_score = self.sax.compare_strings(base_string,
dissimilar_string)
assert similar_score < dissimilar_score
class TestSAX(object):
def setUp(self):
# All tests will be run with 6 letter words
# and 5 letter alphabet
self.sax = SAX(6, 5, 1e-6)
def test_to_letter_rep(self):
arr = [7, 1, 4, 4, 4, 4]
(letters, indices) = self.sax.to_letter_rep(arr)
assert letters == 'eacccc'
def test_to_letter_rep_missing(self):
arr = [7, 1, 4, 4, np.nan, 4]
(letters, indices) = self.sax.to_letter_rep(arr)
assert letters == 'eacc-c'
def test_long_to_letter_rep(self):
long_arr = [
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 6, 6, 6, 6, 10,
100
]
(letters, indices) = self.sax.to_letter_rep(long_arr)
assert letters == 'bbbbce'
def test_long_to_letter_rep_missing(self):
long_arr = [
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, np.nan, 1, 1, 6, 6, 6, 6,
10, 100
]
(letters, indices) = self.sax.to_letter_rep(long_arr)
assert letters == 'bbb-ce'
def test_compare_strings(self):
base_string = 'aaabbc'
similar_string = 'aabbbc'
dissimilar_string = 'ccddbc'
similar_score = self.sax.compare_strings(base_string, similar_string)
dissimilar_score = self.sax.compare_strings(base_string,
dissimilar_string)
assert similar_score < dissimilar_score
def test_compare_strings_missing(self):
assert self.sax.compare_strings('a-b-c-', 'b-c-d-') == 0
def test_normalize_missing(self):
# two arrays which should normalize to the same result
# except one should contain a nan value in place of the input nan value
incomplete_arr_res = self.sax.normalize([1, 0, 0, 0, 0, 1, np.nan])
complete_arr_res = self.sax.normalize([1, 0, 0, 0, 0, 1])
assert np.array_equal(incomplete_arr_res[:-1], complete_arr_res)
assert np.isnan(incomplete_arr_res[-1])
def test_normalize_under_epsilon(self):
array_under_epsilon = self.sax.normalize([1e-7, 2e-7, 1.5e-7])
assert np.array_equal(array_under_epsilon, [0, 0, 0])
class TestSAX(object):
def setUp(self):
# All tests will be run with 6 letter words
# and 5 letter alphabet
self.sax = SAX(6, 5, 1e-6)
def test_to_letter_rep(self):
arr = [7, 1, 4, 4, 4, 4]
(letters, indices, letter_boundries) = self.sax.to_letter_rep(arr)
assert letters == 'eacccc'
def test_long_to_letter_rep(self):
long_arr = [
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 6, 6, 6, 6, 10,
100
]
(letters, indices, letter_boundries) = self.sax.to_letter_rep(long_arr)
assert letters == 'bbbbce'
def test_compare_strings(self):
base_string = 'aaabbc'
similar_string = 'aabbbc'
dissimilar_string = 'ccddbc'
similar_score = self.sax.compare_strings(base_string, similar_string)
dissimilar_score = self.sax.compare_strings(base_string,
dissimilar_string)
assert similar_score < dissimilar_score
def test_from_letter_rep(self):
arr = [7, 1, 4, 4, 4, 4]
(letters, indices, letter_boundries) = self.sax.to_letter_rep(arr)
reconstructed = self.sax.from_letter_rep(letters, indices,
letter_boundries)
assert allclose(reconstructed, [6.21, 1.78, 4.0, 4.0, 4.0, 4.0],
atol=0.01)
def test_breakpoints(self):
assert allclose(self.sax.breakpoints(3), [-0.43, 0.43], atol=0.01)
assert allclose(self.sax.breakpoints(2), [0], atol=0.01)
assert allclose(self.sax.breakpoints(20), [
-1.64, -1.28, -1.04, -0.84, -0.67, -0.52, -0.39, -0.25, -0.13, 0,
0.13, 0.25, 0.39, 0.52, 0.67, 0.84, 1.04, 1.28, 1.64
],
atol=0.01)
def test_interval_centres(self):
assert allclose(self.sax.interval_centres(2), [-0.67, 0.67], atol=0.01)
assert allclose(self.sax.interval_centres(3), [-0.96, 0.0, 0.96],
atol=0.01)
assert allclose(self.sax.interval_centres(30), [
-2.12, -1.64, -1.38, -1.19, -1.03, -0.90, -0.78, -0.67, -0.57,
-0.47, -0.38, -0.29, -0.21, -0.12, -0.04, 0.04, 0.12, 0.21, 0.29,
0.38, 0.47, 0.57, 0.67, 0.78, 0.90, 1.03, 1.19, 1.38, 1.64, 2.12
],
atol=0.01)
def ComputeSax(sample_data, sample_data2):
sample_data = sample_data.as_matrix()
sample_data2 = sample_data2.as_matrix()
#########################################
# SAX - Symbolic aggregate approximation
#http://www.cs.ucr.edu/~eamonn/SAX.pdf
##########################################
#PARAMETERS:
#W: The number of PAA segments representing the time series - aka the len()
# of the string representing the timeseries - useful for dimensionality reduction
#Alphabet size: Alphabet size (e.g., for the alphabet = {a,b,c} = 3)
downsample_ratio = 200
word_length = len(sample_data[:, 1]) / downsample_ratio
alphabet_size = 7
s = SAX(word_length, alphabet_size)
mic_distances = []
for mic in range(1, 5):
(x1String, x1Indices) = s.to_letter_rep(sample_data[:, mic])
(x2String, x2Indices) = s.to_letter_rep(sample_data2[:, mic])
#print x1String
x1x2ComparisonScore = s.compare_strings(x1String, x2String)
mic_distances.append(x1x2ComparisonScore)
#print "Mic: " + str(mic) + ", distance= " + str(x1x2ComparisonScore)
return mic_distances
class TestSAX(object):
def setUp(self):
# All tests will be run with 6 letter words
# and 5 letter alphabet
self.sax = SAX(6, 5, 1e-6)
def test_to_letter_rep(self):
arr = [7,1,4,4,4,4]
(letters, indices) = self.sax.to_letter_rep(arr)
assert letters == 'eacccc'
def test_to_letter_rep_missing(self):
arr = [7,1,4,4,np.nan,4]
(letters, indices) = self.sax.to_letter_rep(arr)
assert letters == 'eacc-c'
def test_long_to_letter_rep(self):
long_arr = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,6,6,6,6,10,100]
(letters, indices) = self.sax.to_letter_rep(long_arr)
assert letters == 'bbbbce'
def test_long_to_letter_rep_missing(self):
long_arr = [1,1,1,1,1,1,1,1,1,1,1,1,1,1,np.nan,1,1,6,6,6,6,10,100]
(letters, indices) = self.sax.to_letter_rep(long_arr)
assert letters == 'bbb-ce'
def test_compare_strings(self):
base_string = 'aaabbc'
similar_string = 'aabbbc'
dissimilar_string = 'ccddbc'
similar_score = self.sax.compare_strings(base_string, similar_string)
dissimilar_score = self.sax.compare_strings(base_string, dissimilar_string)
assert similar_score < dissimilar_score
def test_compare_strings_missing(self):
assert self.sax.compare_strings('a-b-c-', 'b-c-d-') == 0
def test_normalize_missing(self):
# two arrays which should normalize to the same result
# except one should contain a nan value in place of the input nan value
incomplete_arr_res = self.sax.normalize([1,0,0,0,0,1,np.nan])
complete_arr_res = self.sax.normalize([1,0,0,0,0,1])
assert np.array_equal(incomplete_arr_res[:-1], complete_arr_res)
assert np.isnan(incomplete_arr_res[-1])
def test_normalize_under_epsilon(self):
array_under_epsilon = self.sax.normalize([1e-7, 2e-7, 1.5e-7])
assert np.array_equal(array_under_epsilon, [0,0,0])
class TestSAX(object):
def setUp(self):
# All tests will be run with 6 letter words
# and 5 letter alphabet
self.sax = SAX(6, 5, 1e-6)
def test_to_letter_rep(self):
arr = [7, 1, 4, 4, 4, 4]
(letters, indices) = self.sax.to_letter_rep(arr)
assert letters == "eacccc"
def test_long_to_letter_rep(self):
long_arr = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 6, 6, 6, 6, 10, 100]
(letters, indices) = self.sax.to_letter_rep(long_arr)
assert letters == "bbbbce"
def test_compare_strings(self):
base_string = "aaabbc"
similar_string = "aabbbc"
dissimilar_string = "ccddbc"
similar_score = self.sax.compare_strings(base_string, similar_string)
dissimilar_score = self.sax.compare_strings(base_string, dissimilar_string)
assert similar_score < dissimilar_score
def min_dist_sax(t1String,t2String,word,alpha,eps=0.000001):
s=SAX(word,alpha,eps)
return s.compare_strings(t1String,t2String)
def min_dist_sax(t1String, t2String, word, alpha, eps=0.000001):
s = SAX(word, alpha, eps)
return s.compare_strings(t1String, t2String)
