def test_shift_vector(self):
vn = Vectors([[0.2, 1., 2, 3],
[4.2, 5, 6, 7]])
v1 = Vectors([[1.]])
assert Shift(v1, 2)
assert Shift(vn, 1, 2)
assert str(Shift(vn, 1, 2)) == str(vn.shift(1, 2))
def build_data(self):
v = Vectors([[1, 2, 3], [1, 3, 1]])
assert 2 == v.nb_vector
assert 3 == v.nb_variable
assert [1, 2] == v.get_identifiers()
assert v
return v
def build_data(self):
v = Vectors([[1, 2, 3], [1, 3, 1]])
assert 2 == v.nb_vector
assert 3 == v.nb_variable
assert [1, 2] == v.get_identifiers()
assert v
return v
def create_data(self):
seq0 = Sequences(get_shared_data("chene_sessile_15pa.seq"))
vec10 = Vectors(seq0)
vec95 = ValueSelect(vec10, 1, 95)
vec96 = ValueSelect(vec10, 1, 96)
vec97 = ValueSelect(vec10, 1, 97)
return [vec95, vec96, vec97]
def build_data(self):
vec10 = Vectors(get_shared_data("chene_sessile.vec"))
vec15 = SelectVariable(vec10, [1, 3, 6], Mode="Reject")
matrix10 = Compare(vec15, VectorDistance("N", "N", "N"))
assert 138 == matrix10.nb_row
assert 138 == matrix10.nb_column
return matrix10
def test_constructor_identifiers_failure(self):
try:
# should be Vectors([[1,2,3], Identifiers=[1])
v = Vectors([1, 2, 3], Identifiers=[1, 2])
assert False
except ValueError:
assert True
def build_data(self):
vec10 = Vectors(get_shared_data("chene_sessile.vec"))
vec15 = SelectVariable(vec10, [1, 3, 6], Mode="Reject")
matrix10 = Compare(vec15, VectorDistance("N", "N", "N"))
c1 = Clustering(matrix10, "Partition", 3, Prototypes=[1, 3, 12],
Algorithm="Divisive")
return ToDistanceMatrix(c1)
def test_merge_vectors(self):
v1 = self.int_vector_data()
b = [[2, 78, 45],
[6, 2, 122],
[3, 4, 31],]
v2 = Vectors(b)
v = Merge(v1, v2)
assert v
a = v1.merge([v2])
b = v2.merge([v1])
assert str(a)==str(b)
assert str(a)==str(v)
Plot(v)
def test_cluster_vectors_badtype(self):
v = Vectors([[1, 2, 3], [1, 3, 1], [4, 5, 6]])
try:
# should be step, cluster, information
Cluster(v, "BadName", 2)
assert False
except KeyError:
assert True
def test_cluster_vectors_information_failure(self):
v = Vectors([[1, 2, 3], [1, 3, 1], [4, 5, 6]])
try:
# if v is vectors, information does not exist
Cluster(v, "Information", 2)
assert False
except KeyError:
assert True
def test_vectors_container(self):
"""vector container : len"""
v = Vectors([[0, 1, 2, 3], [4, 5, 6, 7]])
assert len(v) == 2
for i in v:
assert len(i) == 4
assert v[0] == range(4)
assert v[1][1] == 5
def test_compare_vectors(self):
vec10 = Vectors(get_shared_data("chene_sessile.vec"))
vec15 = SelectVariable(vec10, [1, 3, 6], Mode="Reject")
assert vec15
matrix10 = Compare(vec15, VectorDistance("N", "N", "N"))
assert matrix10
assert str(vec15.compare(VectorDistance("N", "N", "N"),
True)) == str(matrix10)
def test_clustering(self):
vec10 = Vectors(get_shared_data("chene_sessile.vec"))
vec15 = SelectVariable(vec10, [1, 3, 6], Mode="Reject")
assert vec15
matrix10 = Compare(vec15, VectorDistance("N", "N", "N"))
c1 = Clustering(matrix10,
"Partition",
3,
Prototypes=[1, 3, 12],
Algorithm="Divisive")
c1_bis = Clustering(matrix10,
"Partition",
3,
Prototypes=[1, 3, 12],
Algorithm="Ordering")
c2 = Clustering(matrix10, "Hierarchy", Algorithm="Agglomerative")
c3 = Clustering(matrix10, "Hierarchy", Algorithm="Divisive")
c4 = Clustering(matrix10, "Hierarchy", Algorithm="Ordering")
assert c1
assert c2
assert c3
assert c4
assert ToDistanceMatrix(c1)
# first argument is the Algorithm
# * 0 for agglomerative
# * 1 for divisive
# Second argument is the criterion
# * 2 for averaging
#those 3 tests works on my laptop (TC, April 2009) but not on buildbot
#assert c2 == matrix10.hierarchical_clustering(0, 2, "test", "test")
#assert c3 == matrix10.hierarchical_clustering(1, 1, "test", "test")
#assert c4 == matrix10.hierarchical_clustering(2, 0, "test", "test")
# 1 for initialisation and 1 for divisive
assert str(c1) == \
str(matrix10.partitioning_prototype(3, [1, 3, 12], 1, 1))
assert str(c1_bis) == \
str(matrix10.partitioning_prototype(3, [1, 3, 12], 1, 2))
def test_vectors_pylist(self):
"""test vector constructor from list"""
v = Vectors([[0, 1, 2, 3], [4, 5, 6, 7]])
assert v
v = Vectors([[1.2, 0.34], [1.2, 0.34]])
assert v
v = Vectors([[1]])
assert v
v = Vectors([[0, 1, 2, 3], [4, 5, 6, 7], [1, 2, 3, 4]])
assert v
try:
v = Vectors([[0, 1, 2, 3], [4, 5, 6, 7], [1, 2, 3]])
assert False
except:
assert True
try:
v = Vectors([[0, 1, 2, 3], [4, 5, 6, 7], [1.2, 2, 3]])
assert False
except:
assert True
def _test_cluster_vectors1(self):
v = Vectors([[1], [2], [3]])
assert str(Cluster(v, "Step", 2)) == str(v.cluster_step(1, 2))
assert str(Cluster(v, "Limit", [2])) == str(v.cluster_limit(1, [2]))
def test_constructor_one_variable(self):
v = Vectors([1, 2, 3])
assert v.nb_variable == 3
def test_types(self):
v2 = Vectors([[1, 2., 3.], [1, 5., 1.]], Identifiers=[1, 2])
def test_identifiers(self):
v = Vectors([[1, 2, 3], [4, 5, 6], [7, 8, 9]], Identifiers=[1, 2, 4])
assert v.get_identifiers() == [1, 2, 4]
def build_data_2(self):
return Vectors(get_shared_data("chene_sessile.vec"))
class TestRegression(interface):
"""a simple unittest class"""
def __init__(self):
self.vector = Vectors([[0, 0], [1, 1], [2, 2], [3, 3]])
interface.__init__(self, self.build_data(), None, Regression)
def build_data(self):
# vector = Vectors([[0, 0], [1, 1], [2, 2], [3, 3]])
r1 = Regression(self.vector, "Linear", 1, 2)
assert r1.nb_vector == 4
return r1
def test_build_bad_algorithm_failure(self):
try:
_r1 = Regression(self.vector, "Moving", 1, 2, 1, Weighting=False)
assert False
except:
assert True
def test_get_residuals(self):
for ii in range(0, self.data.nb_vector):
assert self.data.get_residual(ii) == 0
def test_print(self):
self.print_data()
def test_display(self):
self.display()
self.display_versus_ascii_write()
self.display_versus_str()
def test_len(self):
"""not implemented; irrelevant?"""
assert self.data.nb_vector == 4
def test_plot(self):
self.plot()
def test_save(self):
self.save(skip_reading=True)
def test_plot_write(self):
self.plot_write()
def test_file_ascii_write(self):
self.file_ascii_write()
def test_spreadsheet_write(self):
self.spreadsheet_write()
def test_extract(self):
pass
def test_extract_data(self):
pass
def test_linear_regression(self):
r1 = self.data
# compare with the direct usage of linear regression
r = self.vector.linear_regression(1, 2)
assert r
assert r1
assert str(r) == str(r1)
def test_moving_average(self):
r1 = Regression(self.vector, "MovingAverage", 1, 2, [1])
r = self.vector.moving_average_regression_values(1, 2, [1], "a")
assert r
assert r1
assert str(r) == str(r1)
def test_moving_average_failure(self):
try:
Regression(self.vector, "MovingAverage", 1, 2, [1], Algorithm="badAlgorithmName")
assert False
except:
assert True
def _test_moving_average_and_compound(self):
"""test to be implemented"""
compound = Compound(Binomial(1, 10, 0.5), Binomial(1, 5, 0.4))
Regression(self.vector, "MovingAverage", 1, 2, compound)
def test_nearest_neighbours(self):
r1 = Regression(self.vector, "NearestNeighbors", 1, 2, 1, Weighting=False)
r = self.vector.nearest_neighbours_regression(1, 2, 1.0, False)
assert r
assert r1
assert str(r) == str(r1)
def test_badtype(self):
try:
Regression(self.vector, "N", 1, 2, [1])
assert False
except TypeError:
assert True
def create_data(self):
v = Vectors([[1], [1], [4]])
return v
def _test_cluster_vectors1(self):
v = Vectors([[1], [2], [3]])
assert str(Cluster(v, "Step", 2)) == str(v.cluster_step(1, 2))
assert str(Cluster(v, "Limit", [2])) == \
str(v.cluster_limit(1,[2]))
def test_vectors(self):
v = Vectors([[1, 2, 3, 4, 5, 6, 7]])
ExtractHistogram(v, 1)
v = Vectors([[1, 2], [3, 4]])
ExtractHistogram(v, 1)
def test_identifiers(self):
v = Vectors([[1, 2, 3], [4, 5, 6], [7, 8, 9]], Identifiers=[1, 2, 4])
assert v.get_identifiers() == [1, 2, 4]
class TestRegression(interface):
"""a simple unittest class"""
def __init__(self):
self.vector = Vectors([[0, 0], [1, 1], [2, 2], [3, 3]])
interface.__init__(self, self.build_data(), None, Regression)
def build_data(self):
#vector = Vectors([[0, 0], [1, 1], [2, 2], [3, 3]])
r1 = Regression(self.vector, "Linear", 1, 2)
assert r1.nb_vector == 4
return r1
def test_build_bad_algorithm_failure(self):
try:
_r1 = Regression(self.vector, "Moving", 1, 2, 1, Weighting=False)
assert False
except:
assert True
def test_get_residuals(self):
for ii in range(0, self.data.nb_vector):
assert self.data.get_residual(ii) == 0
def test_print(self):
self.print_data()
def test_display(self):
self.display()
self.display_versus_ascii_write()
self.display_versus_str()
def test_len(self):
"""not implemented; irrelevant?"""
assert self.data.nb_vector == 4
def test_plot(self):
self.plot()
def test_save(self):
self.save(skip_reading=True)
def test_plot_write(self):
self.plot_write()
def test_file_ascii_write(self):
self.file_ascii_write()
def test_spreadsheet_write(self):
self.spreadsheet_write()
def test_extract(self):
pass
def test_extract_data(self):
pass
def test_linear_regression(self):
r1 = self.data
#compare with the direct usage of linear regression
r = self.vector.linear_regression(1, 2)
assert r
assert r1
assert str(r) == str(r1)
def test_moving_average(self):
r1 = Regression(self.vector, "MovingAverage", 1, 2, [
1,
])
r = self.vector.moving_average_regression_values(1, 2, [
1,
], 'a')
assert r
assert r1
assert str(r) == str(r1)
def test_moving_average_failure(self):
try:
Regression(self.vector,
"MovingAverage",
1,
2, [
1,
],
Algorithm="badAlgorithmName")
assert False
except:
assert True
def _test_moving_average_and_compound(self):
"""test to be implemented"""
compound = Compound(Binomial(1, 10, 0.5), Binomial(1, 5, 0.4))
Regression(self.vector, "MovingAverage", 1, 2, compound)
def test_nearest_neighbours(self):
r1 = Regression(self.vector,
"NearestNeighbors",
1,
2,
1,
Weighting=False)
r = self.vector.nearest_neighbours_regression(1, 2, 1., False)
assert r
assert r1
assert str(r) == str(r1)
def test_badtype(self):
try:
Regression(self.vector, "N", 1, 2, [
1,
])
assert False
except TypeError:
assert True
def __init__(self):
self.vector = Vectors([[0, 0], [1, 1], [2, 2], [3, 3]])
interface.__init__(self, self.build_data(), None, Regression)
def create_data(self):
v = Vectors([[1, 2, 3], [1, 3, 1], [4, 5, 6]])
return v
def test_cluster_vectors(self):
v = Vectors([[1, 2, 3], [1, 3, 1], [4, 5, 6]])
assert str(Cluster(v, "Step", 1, 2)) == str(v.cluster_step(1, 2))
assert str(Cluster(v, "Limit", 1, [2, 4, 6])) == str(v.cluster_limit(1, [2, 4, 6]))
def create_data(self):
seq0 = Sequences(get_shared_data("chene_sessile_15pa.seq"))
vec10 = Vectors(seq0)
return vec10
def _test_transcode_vectors(self):
vec = Vectors([[1, 2, 3], [1, 3, 1], [4, 5, 6]])
assert str(vec.transcode(1, [1, 2, 3, 4])) == str(Transcode(vec, 1, [1, 2, 3, 4]))
def test_cluster_vectors(self):
v = Vectors([[1, 2, 3], [1, 3, 1], [4, 5, 6]])
assert str(Cluster(v, "Step", 1, 2)) == str(v.cluster_step(1, 2))
assert str(Cluster(v, "Limit", 1, [2, 4, 6])) == \
str(v.cluster_limit(1, [2, 4 ,6]))
def __init__(self):
self.vector = Vectors([[0, 0], [1, 1], [2, 2], [3, 3]])
interface.__init__(self, self.build_data(), None, Regression)
def int_vector_data(self):
a = [[1, 3, 4],
[4, 12, 2],
[8, 7, 3],]
v = Vectors(a)
return v
def float_vector_data(self):
v = Vectors([[0.1, 0.3, 4.2],
[0.5, 2.3, 1.2],
[4.5, 6.3, 3.2],
])
return v
def _test_transcode_vectors(self):
vec = Vectors([[1, 2, 3], [1, 3, 1], [4, 5, 6]])
assert str(vec.transcode(1, [1, 2, 3, 4]))==\
str(Transcode(vec, 1, [1, 2, 3, 4]))
def test():
vec10 = Vectors("data/chene_sessile.vec")
Plot(vec10)
# plot of the pointwise averages
Plot(Regression(vec10, "MovingAverage", 1, 2, [1]))
vec95 = ValueSelect(vec10, 1, 1995)
vec96 = ValueSelect(vec10, 1, 1996)
vec97 = ValueSelect(vec10, 1, 1997)
VarianceAnalysis(vec10, 1, 2, "N")
Compare(ExtractHistogram(vec95, 2), ExtractHistogram(vec96, 2), \
ExtractHistogram(vec95, 2), "N")
Plot(ExtractHistogram(vec95, 2), ExtractHistogram(vec96, 2), \
ExtractHistogram(vec97, 2))
ContingencyTable(vec10, 1, 4)
# one-way variance analysis based on ranks
VarianceAnalysis(vec10, 1, 4, "O")
Compare(ExtractHistogram(vec95, 4), ExtractHistogram(vec96, 4), \
ExtractHistogram(vec95, 4), "O")
# looks like it is not plotted
Plot(ExtractHistogram(vec95, 4), ExtractHistogram(vec96, 4),
ExtractHistogram(vec97, 4))
Plot(ExtractHistogram(vec95, 5), ExtractHistogram(vec96, 5),
ExtractHistogram(vec97, 5))
Plot(ExtractHistogram(vec95, 6), ExtractHistogram(vec96, 6),
ExtractHistogram(vec97, 6))
vec11 = ValueSelect(vec10, 4, 1)
vec12 = ValueSelect(vec10, 4, 2)
vec13 = ValueSelect(vec10, 4, 3, 4)
Plot(ExtractHistogram(vec11, 2), ExtractHistogram(vec12, 2),
ExtractHistogram(vec13, 2))
Plot(ExtractHistogram(vec11, 5), ExtractHistogram(vec12, 5),
ExtractHistogram(vec13, 5))
mixt20 = Estimate(ExtractHistogram(vec10, 2), \
"MIXTURE", "NB", "NB", "NB", "NB", \
NbComponent="Estimated")
Display(mixt20)
Plot(mixt20)
Plot(ExtractDistribution(mixt20, "Mixture"))
_mixt21 = Estimate(ExtractHistogram(vec10, 5), \
"MIXTURE", "NB", "NB", "NB", "NB", \
NbComponent="Estimated")
vec9596 = ValueSelect(vec10, 1, 1995, 1996)
Plot(ExtractHistogram(ValueSelect(vec9596, 4, 1), 6), \
ExtractHistogram(ValueSelect(vec9596, 4, 2), 6), \
ExtractHistogram(ValueSelect(vec9596, 4, 3, 4), 6))
# linear regression
regress10 = Regression(vec10, "Linear", 5, 2)
Display(regress10)
Plot(regress10)
# nonparametric regression (loess smoother)
_regress11 = Regression(vec10, "NearestNeighbors", 5, 2, 0.3)
_regress12 = Regression(vec9596, "Linear", 5, 6)
_regress13 = Regression(vec9596, "NearestNeighbors", 5, 6, 0.5)
_vec15 = SelectVariable(vec10, [1, 3, 6], Mode="Reject")
