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 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_comparison_wrong_argument_1(self):
meri1 = self.meri1
try:
Compare("N")
assert False
except NotImplementedError:
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"))
assert 138 == matrix10.nb_row
assert 138 == matrix10.nb_column
return 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_comparison_histo_filename(self):
meri1 = self.meri1
meri2 = self.meri2
meri3 = self.meri3
_c1 = Compare(meri1, meri2, meri3, 'N', Filename='result.dat')
os.remove('result.dat')
_c1 = Compare(meri1, meri2, meri3, 'N', Filename='result.dat', \
Format='ASCII')
os.remove('result.dat')
_c1 = Compare(meri1, meri2, meri3, 'N', Filename='result.dat', \
Format='SpreadSheet')
os.remove('result.dat')
try:
_c1 = Compare(meri1, meri2, meri3, 'N', Filename='result.dat', \
Format='badname')
assert False
except ValueError:
assert True
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_comparison_histo(self):
# check both the long and short argument (O, S, N)
meri1 = self.meri1
meri2 = self.meri2
meri3 = self.meri3
c1 = Compare(meri1, meri2, meri3, 'N')
c2 = Compare(meri1, meri2, meri3, 'O')
c3 = Compare(meri1, meri2, meri3, 'S')
c1_long = Compare(meri1, meri2, meri3, 'NUMERIC')
c2_long = Compare(meri1, meri2, meri3, 'ORDINAL')
c3_long = Compare(meri1, meri2, meri3, 'SYMBOLIC')
assert c1 == c1_long
assert c2 == c2_long
assert c3 == c3_long
assert meri1.compare_histo(meri2, meri3, "N") == c1
assert meri1.compare_histo(meri2, meri3, "S") == c3
assert meri1.compare_histo(meri2, meri3, "O") == c2
assert meri1.compare_histo(meri2, meri3, "N") == c1_long
assert meri1.compare_histo(meri2, meri3, "S") == c3_long
assert meri1.compare_histo(meri2, meri3, "O") == c2_long
def test():
meri1 = Histogram(get_shared_data("meri1.his"))
meri2 = Histogram(get_shared_data("meri2.his"))
meri3 = Histogram(get_shared_data("meri3.his"))
meri4 = Histogram(get_shared_data("meri4.his"))
meri5 = Histogram(get_shared_data("meri5.his"))
Plot(meri1, meri2, meri3, meri4, meri5)
Compare(meri1, meri2, meri3, meri4, meri5, "N")
ComparisonTest("F", meri1, meri2)
ComparisonTest("T", meri1, meri2)
ComparisonTest("W", meri1, meri2)
ComparisonTest("F", meri1, meri3)
ComparisonTest("T", meri1, meri3)
ComparisonTest("W", meri1, meri3)
# Estimation of a mixture of two distributions assuming a first
# sub-population of GUs made only of a preformed part and a second
# sub-population made of both a preformed part and a neoformed part
_mixt1 = Estimate(meri2, "MIXTURE", "B", "B")
meri = Merge(meri1, meri2, meri3, meri4, meri5)
#model selection approach: estimation of both the mixture parameters and
# the number of components
mixt2 = Estimate(meri,
"MIXTURE",
"B",
"B",
"B",
"B",
NbComponent="Estimated")
mixt2 = Estimate(meri, "MIXTURE", "NB", "NB")
Plot(mixt2)
Plot(ExtractDistribution(mixt2, "Mixture"))
print type(ExtractDistribution(mixt2, "Component", 1))
Plot(ExtractDistribution(mixt2, "Component", 1),
ExtractDistribution(mixt2, "Component", 2))
Display(mixt2)
_mixt_data = ExtractData(mixt2)
dist5 = Estimate(meri5, "BINOMIAL")
Display(dist5, Detail=2)
Plot(dist5)
histo5 = Simulate(dist5, 100)
Display(histo5, Detail=2)
Plot(histo5)
peup1 = Histogram(get_shared_data("peup1.his"))
peup2 = Histogram(get_shared_data("peup2.his"))
peup3 = Histogram(get_shared_data("peup3.his"))
peup4 = Histogram(get_shared_data("peup4.his"))
peup5 = Histogram(get_shared_data("peup5.his"))
peup6 = Histogram(get_shared_data("peup6.his"))
_mixt10 = Estimate(peup2,
"MIXTURE",
"B",
"NB",
"NB",
"NB",
NbComponent="Estimated")
peup = Merge(peup1, peup2, peup3, peup4, peup5, peup6)
_histo1 = Shift(peup, -1)
_histo2 = Cluster(peup, "Information", 0.8)
_histo3 = Cluster(peup, "Step", 10)
histo4 = Cluster(peup, "Limit", [13, 24])
Display(histo4, Detail=2)
Plot(histo4)
_mixt11 = Estimate(peup,
"MIXTURE",
"B",
"NB",
"NB",
"NB",
NbComponent="Estimated")
_mixt11 = Estimate(peup, "MIXTURE", "B", "NB")
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")
def test():
"""Mixture tests from exploratory.aml
#
# Frequency distributions
#
# Objective: Analyzing the number of nodes of growth units in selected architectural
# position considering the respective roles of preformation and neoformation,
#
# Methods: comparison tests, one-way variance analysis,
# estimation of finite mixture of distributions.
#
# Wild cherry tree: number of nodes per growth unit (GU)
#
# Data: Dominique Fournier
#
# meri1.his: order 1,
# meri1.his: order 2,
# meri1.his: order 3, GU 1,
# meri1.his: order 3, GU 2,
# meri5.his: short shoots.
#
#
# Poplar: number of nodes per growth unit
#
# Data: Yves Caraglio and Herve Rey
#
# peup1.his: order 2,
# peup2.his: order 3,
# peup3.his: order 4,
# peup4.his: order 5,
# peup5.his: order 3, GU 4,
# peup6.his: order 3, acrotony.
#
#########################################################################
"""
plot.DISABLE_PLOT = DISABLE_PLOT
meri1 = Histogram(get_shared_data("meri1.his"))
meri2 = Histogram(get_shared_data("meri2.his"))
meri3 = Histogram(get_shared_data("meri3.his"))
meri4 = Histogram(get_shared_data("meri4.his"))
meri5 = Histogram(get_shared_data("meri5.his"))
Plot(meri1, meri2, meri3, meri4, meri5)
Compare(meri1, meri2, meri3, meri4, meri5, "N")
ComparisonTest("F", meri1, meri2)
ComparisonTest("T", meri1, meri2)
ComparisonTest("W", meri1, meri2)
ComparisonTest("F", meri1, meri3)
ComparisonTest("T", meri1, meri3)
ComparisonTest("W", meri1, meri3)
# Estimation of a mixture of two distributions assuming a first
# sub-population of GUs made only of a preformed part and a second
# sub-population made of both a preformed part and a neoformed part
_mixt1 = Estimate(meri2, "MIXTURE", "B", "B")
meri = Merge(meri1, meri2, meri3, meri4, meri5)
# model selection approach: estimation of both the mixture parameters and
# the number of components"""
mixt2 = Estimate(meri,
"MIXTURE",
"B",
"B",
"B",
"B",
NbComponent="Estimated")
mixt2 = Estimate(meri, "MIXTURE", "NB", "NB")
Plot(mixt2)
Plot(ExtractDistribution(mixt2, "Mixture"))
Plot(ExtractDistribution(mixt2, "Component", 1),
ExtractDistribution(mixt2, "Component", 2))
Display(mixt2)
_mixt_data = ExtractData(mixt2)
dist5 = Estimate(meri5, "BINOMIAL")
Display(dist5, Detail=2)
Plot(dist5)
histo5 = Simulate(dist5, 100)
Display(histo5, Detail=2)
Plot(histo5)
peup1 = Histogram(get_shared_data("peup1.his"))
peup2 = Histogram(get_shared_data("peup2.his"))
peup3 = Histogram(get_shared_data("peup3.his"))
peup4 = Histogram(get_shared_data("peup4.his"))
peup5 = Histogram(get_shared_data("peup5.his"))
peup6 = Histogram(get_shared_data("peup6.his"))
_mixt10 = Estimate(peup2,
"MIXTURE",
"B",
"NB",
"NB",
"NB",
NbComponent="Estimated")
peup = Merge(peup1, peup2, peup3, peup4, peup5, peup6)
_histo1 = Shift(peup, -1)
_histo2 = Cluster(peup, "Information", 0.8)
_histo3 = Cluster(peup, "Step", 10)
histo4 = Cluster(peup, "Limit", [13, 24])
Display(histo4, Detail=2)
Plot(histo4)
_mixt11 = Estimate(peup,
"MIXTURE",
"B",
"NB",
"NB",
"NB",
NbComponent="Estimated")
_mixt11 = Estimate(peup, "MIXTURE", "B", "NB")