def test2():
"""finite mixture of discrete distributions"""
mixt1 = Mixture("data//mixture1.mixt")
mixt1 = Mixture(0.6, Distribution("B", 2, 18, 0.5), 0.4,
Distribution("NB", 10, 10, 0.5))
mixt_histo1 = Simulate(mixt1, 200)
Plot(mixt_histo1)
# extraction of histograms/frequency distributions corresponding
# to a given mixture component
# (i.e. elementary distributions which are combined by mixture)
histo10 = ExtractHistogram(mixt_histo1, "Component", 1)
histo11 = ExtractHistogram(mixt_histo1, "Component", 2)
_histo12 = Merge(histo10, histo11)
_histo13 = ExtractHistogram(mixt_histo1, "Weight")
# estimation
mixt2 = Estimate(mixt_histo1, "MIXTURE", "B", "NB", MinInfBound=0,
InfBoundStatus="Fixed", DistInfBoundStatus="Fixed")
_mixt_histo2 = ExtractData(mixt2)
_histo14 = ExtractHistogram(ExtractData(mixt2), "Component", 1)
_histo15 = ToHistogram(ExtractDistribution(mixt2, "Component", 1))
# estimation and selection of the number of components
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"))
#mixt3 = Estimate(meri1, "MIXTURE", Distribution("B", 6, 7, 0.5), "B")
mixt3 = Estimate(meri1, "MIXTURE", "B", "B")
Plot(mixt3)
# NbComponent="Fixed" (default) / "Estimated"
# Penalty="AIC"/ "AICc" / "BIC" / "BICc" (default), option
# valide if NbComponent="Estimated"
meri = Merge(meri1, meri2, meri3, meri4, meri5)
mixt2 = Estimate(meri, "MIXTURE", "B", "B", "B", "B",
NbComponent="Estimated", Penalty="BIC")
Display(mixt2, Detail=2)
dist_mixt = ExtractDistribution(mixt2, "Mixture")
Plot(dist_mixt)
def test_merge_histo(self):
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"))
meri = Merge(meri1, meri2, meri3, meri4, meri5)
assert meri
meri_bis = meri1.merge([meri2, meri3, meri4, meri5])
assert meri_bis
assert str(meri)==str(meri_bis)
Plot(meri)
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 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_extract_data(self):
"""todo : check if this test makes sense"""
h = Histogram(str(get_shared_data("meri1.his")))
e = h.estimate_nonparametric()
assert e
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_extract_data(self):
"""run and test the extract_data methods"""
h = Histogram(str(get_shared_data("meri2.his")))
m = h.estimate_DiscreteMixture("B", "NB")
d = m.extract_data()
assert d
def test_extract_data(self):
"""run and test the extract_data methods"""
h = Histogram(str(get_shared_data( "meri2.his")))
m = h.estimate_DiscreteMixture("B", "NB")
d = m.extract_data()
assert d
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_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_mixture_1(self):
distributions = ["B", "NB", "NB", "NB"]
h = Histogram(get_shared_data( "peup2.his"))
m1 = h.estimate_mixture(distributions, NbComponent="Estimated")
assert m1
types = []
for d in distributions:
temp = distribution_identifier_type[d]
types.append(temp)
c = h.mixture_estimation2(types, 0, True, True,
likelihood_penalty_type['AIC'])
assert str(c)==str(m1)
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_mixture(self):
h = Histogram(get_shared_data("meri2.his"))
mixt = h.estimate_mixture(["B", "NB"])
assert ExtractHistogram(mixt, "Weight") == \
mixt.extract_weight()
assert ExtractHistogram(mixt, "Mixture") == \
mixt.extract_mixture()
assert ExtractHistogram(mixt, "Component", 1) == \
mixt.extract_component(1)
assert ExtractHistogram(mixt, "Component", 2) == \
mixt.extract_component(2)
try:
ExtractHistogram(mixt, "Component", 3)
assert False
except: # Bas distrubition index
assert True
def test():
vec10 = Vectors(get_shared_data('chene_sessile.vec'))
vec15 = SelectVariable(vec10, [1, 3, 6], Mode="Reject")
vec9596 = ValueSelect(vec10, 1, 1995, 1996)
# computation of a distance matrix using a standardization procedure
matrix10 = Compare(vec15, VectorDistance("N", "N", "N"))
Plot(matrix10)
# clustering using a partitioning method
cluster = Clustering(matrix10, "Partition", 5)
Plot(cluster)
Display(Clustering(matrix10, "Partition", 2))
vec151 = SelectIndividual(vec10, \
[69, 48, 41, 44, 32, 47, 81, 95, 11, 36, 75, 108, 56, 83, 38, 98
, 113, 134, 110, 101, 77, 35, 74, 80, 50, 24, 89, 128, 5, 45, 8,
116, 119, 132, 61, 78, 53, 29, 131, 65, 90, 96, 104, 20, 86, 66,
42, 68, 125, 14, 23, 54, 33, 26, 71, 129, 102, 51, 70, 111, 138,
19, 127, 62, 117, 137, 2, 28, 17])
vec152 = SelectIndividual(vec10, \
[100, 13, 133, 105, 72, 9, 93, 109, 30, 115, 63, 7, 55, 37, 15,
114, 106, 46, 73, 18, 3, 87, 58, 43, 60, 76, 52, 6, 39, 31, 12,
99, 121, 123, 22, 79, 94, 88, 21, 97, 25, 40, 57, 136, 67, 49, 10,
4, 120, 92, 27, 91, 64, 124, 16, 130, 84, 107, 126, 103, 122, 112,
59, 1, 82, 34, 135, 118, 85])
Plot(ExtractHistogram(vec151, 4), ExtractHistogram(vec152, 4))
matrix11 = Compare(vec15, VectorDistance("N", "O", "N"))
Clustering(matrix10, "Hierarchy", Algorithm="Agglomerative")
Clustering(matrix10, "Hierarchy", Algorithm="Divisive")
vec16 = SelectVariable(vec9596, [1, 3], Mode="Reject")
matrix12 = Compare(vec16, VectorDistance("N", "N", "N", "N"))
matrix13 = Compare(vec16, VectorDistance("N", "O", "N", "N"))
def test():
vec10 = Vectors(get_shared_data('chene_sessile.vec'))
vec15 = SelectVariable(vec10, [1, 3, 6], Mode="Reject")
vec9596 = ValueSelect(vec10, 1, 1995, 1996)
# computation of a distance matrix using a standardization procedure
matrix10 = Compare(vec15, VectorDistance("N", "N", "N"))
Plot(matrix10)
# clustering using a partitioning method
cluster = Clustering(matrix10, "Partition", 5)
Plot(cluster)
Display(Clustering(matrix10, "Partition", 2))
vec151 = SelectIndividual(vec10, \
[69, 48, 41, 44, 32, 47, 81, 95, 11, 36, 75, 108, 56, 83, 38, 98
, 113, 134, 110, 101, 77, 35, 74, 80, 50, 24, 89, 128, 5, 45, 8,
116, 119, 132, 61, 78, 53, 29, 131, 65, 90, 96, 104, 20, 86, 66,
42, 68, 125, 14, 23, 54, 33, 26, 71, 129, 102, 51, 70, 111, 138,
19, 127, 62, 117, 137, 2, 28, 17])
vec152 = SelectIndividual(vec10, \
[100, 13, 133, 105, 72, 9, 93, 109, 30, 115, 63, 7, 55, 37, 15,
114, 106, 46, 73, 18, 3, 87, 58, 43, 60, 76, 52, 6, 39, 31, 12,
99, 121, 123, 22, 79, 94, 88, 21, 97, 25, 40, 57, 136, 67, 49, 10,
4, 120, 92, 27, 91, 64, 124, 16, 130, 84, 107, 126, 103, 122, 112,
59, 1, 82, 34, 135, 118, 85])
Plot(ExtractHistogram(vec151, 4), ExtractHistogram(vec152, 4))
matrix11 = Compare(vec15, VectorDistance("N", "O", "N"))
Clustering(matrix10, "Hierarchy", Algorithm="Agglomerative")
Clustering(matrix10, "Hierarchy", Algorithm="Divisive")
vec16 = SelectVariable(vec9596, [1, 3], Mode="Reject")
matrix12 = Compare(vec16, VectorDistance("N", "N", "N", "N"))
matrix13 = Compare(vec16, VectorDistance("N", "O", "N", "N"))
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")
def test_binomial(self):
"""BINOMIAL Distribution"""
h = Histogram(get_shared_data("meri5.his"))
assert h.estimate_parametric('B')
# transformation of histograms, extraction/filter
histo2 = Cluster(fagus, "Step", 2)
histo3 = Cluster(fagus, "Information", 0.8)
histo4 = Cluster(fagus, "Limit", [2, 4, 6, 8, 10])
histo5 = Transcode(fagus, [1, 2, 2, 3, 3, 4, 4, 5])
#Display(histo5, Detail=2)
histo7 = Shift(fagus, -2)
histo8 = ValueSelect(fagus, 2, 8)
dist3 = Estimate(fagus, "B")
# comparison of histograms
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"))
# Compare(meri1, meri2, meri3, meri4, meri5, "N", FileName="ASCII/meri.cmp")
Compare(meri1, meri2, meri3, meri4, meri5, "O")
ComparisonTest("F", meri1, meri2)
ComparisonTest("T", meri1, meri2)
ComparisonTest("W", meri1, meri2)
# fit of a known distribution to an histogram
dist5 = Fit(meri5, Distribution("B", 0, 10, 0.437879))
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")
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 get_mixture_2(self):
"""create another mixture data"""
h = Histogram(get_shared_data("meri2.his"))
m = h.estimate_mixture("B", "NB")
return m
def test_histo_extract_data(self):
h = Histogram(get_shared_data("meri2.his"))
mixt = h.estimate_mixture(["B", "NB"])
assert ExtractData(mixt)
assert mixt.extract_data() == ExtractData(mixt)
def test2():
"""finite mixture of discrete distributions"""
mixt1 = Mixture("data//mixture1.mixt")
mixt1 = Mixture(0.6, Distribution("B", 2, 18, 0.5), 0.4,
Distribution("NB", 10, 10, 0.5))
mixt_histo1 = Simulate(mixt1, 200)
Plot(mixt_histo1)
# extraction of histograms/frequency distributions corresponding
# to a given mixture component
# (i.e. elementary distributions which are combined by mixture)
histo10 = ExtractHistogram(mixt_histo1, "Component", 1)
histo11 = ExtractHistogram(mixt_histo1, "Component", 2)
_histo12 = Merge(histo10, histo11)
_histo13 = ExtractHistogram(mixt_histo1, "Weight")
# estimation
mixt2 = Estimate(mixt_histo1,
"MIXTURE",
"B",
"NB",
MinInfBound=0,
InfBoundStatus="Fixed",
DistInfBoundStatus="Fixed")
_mixt_histo2 = ExtractData(mixt2)
_histo14 = ExtractHistogram(ExtractData(mixt2), "Component", 1)
_histo15 = ToHistogram(ExtractDistribution(mixt2, "Component", 1))
# estimation and selection of the number of components
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"))
#mixt3 = Estimate(meri1, "MIXTURE", Distribution("B", 6, 7, 0.5), "B")
mixt3 = Estimate(meri1, "MIXTURE", "B", "B")
Plot(mixt3)
# NbComponent="Fixed" (default) / "Estimated"
# Penalty="AIC"/ "AICc" / "BIC" / "BICc" (default), option
# valide if NbComponent="Estimated"
meri = Merge(meri1, meri2, meri3, meri4, meri5)
mixt2 = Estimate(meri,
"MIXTURE",
"B",
"B",
"B",
"B",
NbComponent="Estimated",
Penalty="BIC")
Display(mixt2, Detail=2)
dist_mixt = ExtractDistribution(mixt2, "Mixture")
Plot(dist_mixt)
def test_fit_histogram(self):
meri5 = Histogram(get_shared_data( "meri5.his"))
dist1 = Fit(meri5, Distribution("B", 0, 10, 0.437879))
dist2 = meri5.fit(Distribution("B", 0, 10, 0.437879))
assert str(dist1)==str(dist2)
def build_data_2(self):
return Vectors(get_shared_data("chene_sessile.vec"))
# transformation of histograms, extraction/filter
histo2 = Cluster(fagus, "Step", 2)
histo3 = Cluster(fagus, "Information", 0.8)
histo4 = Cluster(fagus, "Limit", [2, 4, 6, 8, 10])
histo5 = Transcode(fagus, [1, 2, 2, 3, 3, 4, 4, 5])
#Display(histo5, Detail=2)
histo7 = Shift(fagus, -2)
histo8 = ValueSelect(fagus, 2, 8)
dist3 = Estimate(fagus, "B")
# comparison of histograms
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"))
# Compare(meri1, meri2, meri3, meri4, meri5, "N", FileName="ASCII/meri.cmp")
Compare(meri1, meri2, meri3, meri4, meri5, "O")
ComparisonTest("F", meri1, meri2)
ComparisonTest("T", meri1, meri2)
ComparisonTest("W", meri1, meri2)
# fit of a known distribution to an histogram
def __init__(self):
self.meri1 = Histogram(get_shared_data("meri1.his"))
self.meri2 = Histogram(get_shared_data("meri1.his"))
self.meri3 = Histogram(get_shared_data("meri1.his"))
def test_mixture_2(self):
h = Histogram(get_shared_data( "peup2.his"))
m2 = h.estimate_mixture([Binomial(0, 10, 0.5), "NB"])
assert m2
def get_mixture_2(self):
"""create another mixture data"""
h = Histogram(get_shared_data("meri2.his"))
m = h.estimate_mixture("B", "NB")
return m
def hist_data(self):
h = Histogram(get_shared_data( "meri2.his"))
return h
def __init__(self):
self.meri1 = Histogram(get_shared_data("meri1.his"))
self.meri2 = Histogram(get_shared_data("meri1.his"))
self.meri3 = Histogram(get_shared_data("meri1.his"))
def build_data_2(self):
return Vectors(get_shared_data("chene_sessile.vec"))
def __init__(self):
interface.__init__(self,
self.build_data(),
str(get_shared_data("peup1.his")),
Histogram)
def test_nonparametric(self):
h = Histogram(get_shared_data("meri1.his"))
e = h.estimate_nonparametric()
assert e
def test_container(self):
""" container / iterator"""
h = Histogram(str(get_shared_data("meri1.his")))
assert h[0] == 0
assert h[10] == 1
def test_nb(self):
"""NegativeBinomial"""
h = Histogram(get_shared_data("peup2.his"))
assert h.estimate_parametric('NB')
def test_value_select_float(self):
meri1 = Histogram(get_shared_data("meri1.his"))
# note keep=False is equivalent to Mode=keep,is this correct ?
assert str(ValueSelect(meri1, 0, 10, Mode="Keep"))==\
str(meri1.value_select( min=0, max=10, keep=True))
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")