diff --git a/Rcodes/real_data/CoOPLBM_completion_analyze.html b/Rcodes/real_data/CoOPLBM_completion_analyze.html deleted file mode 100644 index c70e932..0000000 --- a/Rcodes/real_data/CoOPLBM_completion_analyze.html +++ /dev/null @@ -1,543 +0,0 @@ - - - - - - - - - - - - - -Netclustering analysis with the CoOPLBM completion - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
- - - - - - -
- -
- -
-

Context of this analysis

-

After performing a netclustering on the raw data, we will see if the detect structure resulting in the clustering comes from the sampling effort. To test this we will use the CoOPLBM model by Anakok et al. (2022) to complete the data.

-

The CoOPLBM model assumes that the observed incidence matrix \(R\) is an element-wise product of an \(M\) matrix following an LBM and an \(N\) matrix which elements follow Poisson distributions independent on \(M\).

-

The model gives us the \(\widehat{M}\) matrix, the elements of which are:

-

\[\widehat{M_{ij}} = \mathbb{P}(M_{ij} = 1)\]

-

Note that if \(R_{ij} = 1\) then \(\widehat{M_{ij}} = 1\)

- -

This completed matrix can be used in different manners to be fed to the colSBM model.

-
-
-

Threshold based completions

-

With the thresholds, the infered incidence matrix obtained by CoOPLBM is used to generate a completed incidence matrix by the following procedure : \[X_{ij} = \begin{cases} - 1 & \text{if the value is over the threshold} \\ - 0 & \text{else} \\ -\end{cases}\]

-
-

0.5 completed threshold

-

Here, the completion threshold is set to \(0.5\).

-

First we will compute an ARI on the collection id given by the raw data and the completed matrix.

- - - - - - - - - - - - - - - - - - - - - - - - - -
ARI with uncompleted data
iid0.1142823
pi0.0263660
rho0.0933340
pirho0.2158747
-
-
-

0.2 completed threshold

-

The \(0.2\) threshold adds a lot of interactions compared to raw matrix.

- - - - - - - - - - - - - - - - - - - - - - - - - -
ARI with uncompleted data
iid0.0429465
pi0.0330057
rho0.0187305
pirho0.0357728
-
-
-
-

Sample based completions

-

The \(M\) matrix is used to sample a new \(X\) matrix which elements are the realisation of Bernoulli distributions of probability \(M_{i,j}\). \[\mathbb{P}(X_{i,j} = 1) = M_{i,j} \]

- - - - - - - - - - - - - - - - - - - - - - - - - -
ARI with uncompleted data
iid0.0148172
pi0.0265793
rho0.0051536
pirho0.0152299
-
- - - - -
- - - - - - - - - - - - - - - diff --git a/Rcodes/real_data/CoOPLBM_completion_analyze.pdf b/Rcodes/real_data/CoOPLBM_completion_analyze.pdf deleted file mode 100644 index 5f78011..0000000 Binary files a/Rcodes/real_data/CoOPLBM_completion_analyze.pdf and /dev/null differ diff --git a/Rcodes/real_data/presentation_dore.html b/Rcodes/real_data/presentation_dore.html deleted file mode 100644 index a5b4e32..0000000 --- a/Rcodes/real_data/presentation_dore.html +++ /dev/null @@ -1,2691 +0,0 @@ - - - - - - - - - - - - - -Présentation de l’application de colSBM sur Doré et al. 2020 - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
- - - - - - -
- -
- -
-

Clustering avec le modèle iid

-

Avec le modèle iid nous obtenons les 5 collections et les structures suivantes:

-

Pour la collection 1

-
-Collection 1 - iid -

-Collection 1 - iid -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
arroyo1982_1+arroyo1982_2+arroyo3
eberling1999
kato1990
petanidou1991
Junker2013
bartomeus2008
Benadi2013_1(950m)+Benadi2013_2(1170m)+Benadi2013_6(2020m)
Benadi2013_4(1700m)+Benadi2013_5(1800m)
Struck1994
Kato2000
Albrecht2010_49yr+Albrecht2010_63yr+Albrecht2010_84yr+Albrecht2010_109yr+Albrecht2010_130yr
Baldock2011_TB+Baldock2011_JN
Dattilo2016
Devoto2005_PP+Devoto2005_AP
Devoto2005_VT
Devoto2005_LL+Devoto2005_CT
Freitas2006
Gibson2006_TA2
Jedrzejewska2013_Ochata+Jedrzejewska2013_Kabaty
MonteroCastano2017_Albufera+MonteroCastano2017_Llimpa+MonteroCastano2017_Tirant
Kehinde2014_Joostenberg_Conv+Kehinde2014_Joostenberg_Org+Kehinde2014_Joostenberg_Nat+Kehinde2014_Laibach_Conv+Kehinde2014_Laibach_Org+Kehinde2014_Laibach_Nat+Kehinde2014_Spier_Conv+Kehinde2014_Spier_Nat
Pinheiro2008
Watts2016_Chicon+Watts2016_Mantanay+Watts2016_Choquebamba+Watts2016_Huaran+Watts2016_Piscacucho+Watts2016_Poques+Watts2016_Pumamarca+Watts2016_Tiaparo+Watts2016_Yanacocha
Kato1993
KatoMiura1996
Kakutani1990
Inoue1990
Fragoso_RA2+Fragoso_RA3+Fragoso_RD1+Fragoso_RD3
Souza_cerrado
Souza_chaco
Souza_pantanal
Souza_vereda
Adedoja2019
Oleques2019
Baldock2019_Bristol
Baldock2019_Edinburgh
Baldock2019_Leeds
Baldock2019_Reading
-

Pour la collection 2

-
-Collection 2 - iid -

-Collection 2 - iid -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
dupont2003
herrera1988
inouye1988
medan2002ld
medan2002rb
ramirez1992
ramirez1989
Burkle2013
Olito-Fox2014
Benadi2013_3(1340m)
Aizen2008_Challhuaco_U+Aizen2008_Challhuaco_D
Aizen2008_Cerro Otto_U+Aizen2008_Cerro Otto_D
Aizen2008_Llao-llao_U+Aizen2008_Llao-llao_D
Chamberlain_cr1+Chamberlain_cr2+Chamberlain_fs1+Chamberlain_fs2+Chamberlain_go1+Chamberlain_go2+Chamberlain_mm1+Chamberlain_mm2+Chamberlain_mz1+Chamberlain_mz2+Chamberlain_sm1+Chamberlain_sm2
Chamberlain_HLU+Chamberlain_HLG+Chamberlain_OKU+Chamberlain_OKG+Chamberlain_WLU+Chamberlain_WLG+Chamberlain_SOU+Chamberlain_SOG
Devoto2005_LQ
Devoto2005_LT+Devoto2005_LH
LemusJimenez2003
Lundgren2005
Marrero2013
Trojelsgaard2015_La Gomera
Trojelsgaard2015_Gran Canaria
Zackenberg
Yoshihara2008
Fragoso_RA1+Fragoso_RD2
PopicThesis
Pornon2017
Orford_B1+Orford_B2+Orford_B3+Orford_B4+Orford_B5+Orford_B10
Orford_B6+Orford_B7+Orford_B8+Orford_B9
Blumel2016
Kantsa2018
Bennett2018
Adedoja2018b_baseZone+Adedoja2018b_MidZone+Adedoja2018b_HighZone+Adedoja2018b_PeakZone
CordenizPicanco2018_NatVeg
CordenizPicanco2018_ExoFor
Benadi2018
Hackett2019_NZ_salt_marsh+Hackett2019_NZ_sand_dune+Hackett2019_NZ_scrub_coprosma
Jolls2019
Traveset2013_Fernandina
Traveset2013_Pinta
Traveset2013_Santiago
Traveset2013_SantaCruz
Traveset2013_SanCristobal
Simanonok2014
Son2019_a1+Son2019_a2+Son2019_a3+Son2019_a4+Son2019_a5+Son2019_a6+Son2019_a7+Son2019_a8+Son2019_F1+Son2019_F2+Son2019_F3+Son2019_F4+Son2019_F5+Son2019_F6+Son2019_F7+Son2019_F8
-

Pour la collection 3

-
-Collection 3 - iid -

-Collection 3 - iid -

-
- - - - - - - - - - - -
Networks
small1976
-

Pour la collection 4

-
-Collection 4 - iid -

-Collection 4 - iid -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
smith-ramirez2005
Weiner2011
Kaiser_control+Kaiser_restored
Gilarranz2014_amarante+Gilarranz2014_barrosa+Gilarranz2014_cincocerros+Gilarranz2014_difuntito+Gilarranz2014_difuntos+Gilarranz2014_elmorro+Gilarranz2014_labrava+Gilarranz2014_lachata+Gilarranz2014_lapaja+Gilarranz2014_piedraalta+Gilarranz2014_vigilancia+Gilarranz2014_volcan
Kaiser-Bunbury2017_Bernica+Kaiser-Bunbury2017_Casse-dent+Kaiser-Bunbury2017_Copolia+Kaiser-Bunbury2017_La-Reserve+Kaiser-Bunbury2017_Rosebelle+Kaiser-Bunbury2017_Salazie+Kaiser-Bunbury2017_Tea-Plantation+Kaiser-Bunbury2017_Trois-Freres
Fang2012
Aizen2008_Puerto Blest_U+Aizen2008_Puerto Blest_D
Chamberlain_Site1+Chamberlain_Site2+Chamberlain_Site3+Chamberlain_Site4+Chamberlain_Site5+Chamberlain_Site6
Dupont2009_IsenBjerg+Dupont2009_Other
Gibson2006_GA1
Gibson2006_TA1
LaraRomero2016_pe?alara_EP+LaraRomero2016_pe?alara_PA+LaraRomero2016_nevero_EP+LaraRomero2016_nevero_PA
Trojelsgaard2015_Tenerife Teno Bajo+Trojelsgaard2015_Tenerife Fasnia
Vanbergen2013_balfarm+Vanbergen2013_bridgend+Vanbergen2013_dalhaikie+Vanbergen2013_netherton+Vanbergen2013_backhill+Vanbergen2013_corntulloch+Vanbergen2013_allancreich
Pfeiffer_CNE+Pfeiffer_CNM+Pfeiffer_CNT+Pfeiffer_CPB+Pfeiffer_CPM+Pfeiffer_CPR+Pfeiffer_CPS+Pfeiffer_M2+Pfeiffer_RP1+Pfeiffer_RP2+Pfeiffer_LM+Pfeiffer_LO+Pfeiffer_BD+Pfeiffer_BH+Pfeiffer_BS
Carstensen_Gigante+Carstensen_Paulino+Carstensen_Tinkerbell+Carstensen_Midway+Carstensen_Cedro+Carstensen_Elefante+Carstensen_Soizig
Welti_ID+Welti_K1B+Welti_K4A+Welti_4B+Welti_20B+Welti_20C+Welti_N1A+Welti_N1B+Welti_N4A+Welti_N4B+Welti_N20A+Welti_N20B
Grass2013_1+Grass2013_2+Grass2013_3+Grass2013_4+Grass2013_5+Grass2013_6+Grass2013_7+Grass2013_8+Grass2013_9+Grass2013_10+Grass2013_11+Grass2013_12+Grass2013_13+Grass2013_14+Grass2013_15+Grass2013_16+Grass2013_17
Hackett2019_UK_sand_dune+Hackett2019_UK_grassland+Hackett2019_UK_heathland+Hackett2019_UK_woodland+Hackett2019_UK_salt_marsh+Hackett2019_UK_scrub
Neli2014
-

Pour la collection 5

-
-Collection 5 - iid -

-Collection 5 - iid -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
olensen2002aig
olensen2002flo
vazquez2002
Shay2016
Gibson2006_GA2
Gibson2006_SG
Trojelsgaard2015_El Hierro
Trojelsgaard2015_Fuerteventura
Trojelsgaard2015_Western Sahara
Robinson2018
CordenizPicanco2018_NatFor
CordenizPicanco2018_SemiPast
CordenizPicanco2018_IntPast
Biella2019
Nel2017
Villalobos2019
LaraRomero2019_blanca+LaraRomero2019_rajada+LaraRomero2019_refugio+LaraRomero2019_torre
Ferrero2013
Sritongchuay2019_near+Sritongchuay2019_far
-

Et voici donc les valeurs numériques pour les \(\alpha\) (paramètres de connectivité).

-

Pour la collection 1 : \[\begin{bmatrix} 1 &0.83 &0.43 &0.73 &0.2 &0.5 &0.05 &0.18 \\1 &0.67 &0.36 &0.51 &0.22 &0.3 &0.05 &0.07 \\1 &0.53 &1 &0.01 &0.02 &0.89 &0 &0 \\0.97 &0.45 &0.62 &0.18 &0.47 &0.06 &0.2 &0.03 \\0.76 &0.46 &0.1 &0.27 &0.1 &0.14 &0.02 &0.03 \\0.96 &0.2 &0.37 &0.03 &0.24 &0.01 &0.09 &0.01 \\0.54 &0.28 &0.04 &0.12 &0.03 &0.05 &0.01 &0.01 \\0.69 &0.1 &0.3 &0.02 &0.06 &0.01 &0.03 &0 \\ \end{bmatrix}\] Pour la collection 2 : \[\begin{bmatrix} 0.84 &0.69 &0.13 &0.32 \\0.71 &0.49 &0.11 &0.14 \\0.54 &0.26 &0.14 &0.05 \\0.26 &0.07 &0.14 &0.01 \\ \end{bmatrix}\] Pour la collection 3 : \[\begin{bmatrix} 0.87 &0.33 \\0.11 &0.09 \\ \end{bmatrix}\] Pour la collection 4 : \[\begin{bmatrix} 0.96 &0.83 &0.96 &0.39 &0.8 &0.16 &0.66 \\0.98 &0.86 &0.83 &0.51 &0.56 &0.19 &0.09 \\0.8 &0.46 &0.74 &0.12 &0.4 &0.05 &0.13 \\0.89 &0.69 &0.44 &0.35 &0.15 &0.07 &0.01 \\0.7 &0.29 &0.35 &0.03 &0.15 &0.01 &0.03 \\0.66 &0.43 &0.1 &0.17 &0.03 &0.02 &0 \\0.32 &0.12 &0.02 &0.04 &0 &0 &0 \\ \end{bmatrix}\] Pour la collection 5 : \[\begin{bmatrix} 0.71 &0.9 &0.57 &0.83 \\0.74 &0.22 &0.7 &0.33 \\0.09 &0.44 &0.07 &0.02 \\ \end{bmatrix}\] ### Comparaison avec des infos supplémentaires

-

-
-

Répartition dans les clusters selon la taxonomie

-
-Pollinators repartition for the iid model regarding taxonomy -

-Pollinators repartition for the iid model regarding taxonomy -

-
-
-Pollinators repartition for the iid model regarding taxonomy -

-Pollinators repartition for the iid model regarding taxonomy -

-
-
-Plants repartition for the iid model regarding taxonomy -

-Plants repartition for the iid model regarding taxonomy -

-
-
-Plants repartition for the iid model regarding taxonomy -

-Plants repartition for the iid model regarding taxonomy -

-
-
-

Tables

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
TaxonCollection_1_Bloc_1Collection_1_Bloc_2Collection_1_Bloc_3Collection_1_Bloc_4Collection_1_Bloc_5Collection_1_Bloc_6Collection_1_Bloc_7Collection_1_Bloc_8Collection_2_Bloc_1Collection_2_Bloc_2Collection_2_Bloc_3Collection_2_Bloc_4Collection_3_Bloc_1Collection_3_Bloc_2Collection_4_Bloc_1Collection_4_Bloc_2Collection_4_Bloc_3Collection_4_Bloc_4Collection_4_Bloc_5Collection_4_Bloc_6Collection_4_Bloc_7Collection_5_Bloc_1Collection_5_Bloc_2Collection_5_Bloc_3
Hymenoptera2401756871311582168425661193121011181151031492451
Diptera90833417912677571563018015291387514921047711183
n.i.8011163055676625722350234159080762976320217
Lepidoptera7065292431815371002NANANANANANANA2451
Coleoptera000153670NANANANA022136279522514710217
Other0000000000000010120816000
BirdsNANANANANANANANA30834NANA004351355NANANA
HemipteraNANANANANANANANANANANANANANA00220819NANANA
SquamataNANANANANANANANANANANANANANANANANANANANANA1314
-
-
-
-
-

Clustering avec le modèle pi

-

Avec le modèle pi nous obtenons les 2 collections et les structures suivantes:

-

Pour la collection 1

-
-Collection 1 - pi -

-Collection 1 - pi -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
arroyo1982_1+arroyo1982_2+arroyo3
eberling1999
inouye1988
kato1990
ramirez1992
petanidou1991
ramirez1989
smith-ramirez2005
Junker2013
Kaiser_control+Kaiser_restored
bartomeus2008
Olito-Fox2014
Benadi2013_1(950m)+Benadi2013_2(1170m)+Benadi2013_6(2020m)
Benadi2013_3(1340m)
Benadi2013_4(1700m)+Benadi2013_5(1800m)
Kaiser-Bunbury2017_Bernica+Kaiser-Bunbury2017_Casse-dent+Kaiser-Bunbury2017_Copolia+Kaiser-Bunbury2017_La-Reserve+Kaiser-Bunbury2017_Rosebelle+Kaiser-Bunbury2017_Salazie+Kaiser-Bunbury2017_Tea-Plantation+Kaiser-Bunbury2017_Trois-Freres
Fang2012
Shay2016
Struck1994
Kato2000
Aizen2008_Cerro Otto_U+Aizen2008_Cerro Otto_D
Aizen2008_Llao-llao_U+Aizen2008_Llao-llao_D
Aizen2008_Puerto Blest_U+Aizen2008_Puerto Blest_D
Albrecht2010_49yr+Albrecht2010_63yr+Albrecht2010_84yr+Albrecht2010_109yr+Albrecht2010_130yr
Baldock2011_TB+Baldock2011_JN
Chamberlain_cr1+Chamberlain_cr2+Chamberlain_fs1+Chamberlain_fs2+Chamberlain_go1+Chamberlain_go2+Chamberlain_mm1+Chamberlain_mm2+Chamberlain_mz1+Chamberlain_mz2+Chamberlain_sm1+Chamberlain_sm2
Chamberlain_HLU+Chamberlain_HLG+Chamberlain_OKU+Chamberlain_OKG+Chamberlain_WLU+Chamberlain_WLG+Chamberlain_SOU+Chamberlain_SOG
Chamberlain_Site1+Chamberlain_Site2+Chamberlain_Site3+Chamberlain_Site4+Chamberlain_Site5+Chamberlain_Site6
Dattilo2016
Devoto2005_PP+Devoto2005_AP
Devoto2005_VT
Devoto2005_LL+Devoto2005_CT
Dupont2009_IsenBjerg+Dupont2009_Other
Freitas2006
Gibson2006_TA1
Gibson2006_TA2
Jedrzejewska2013_Ochata+Jedrzejewska2013_Kabaty
LaraRomero2016_pe?alara_EP+LaraRomero2016_pe?alara_PA+LaraRomero2016_nevero_EP+LaraRomero2016_nevero_PA
LemusJimenez2003
Marrero2013
MonteroCastano2017_Albufera+MonteroCastano2017_Llimpa+MonteroCastano2017_Tirant
Kehinde2014_Joostenberg_Conv+Kehinde2014_Joostenberg_Org+Kehinde2014_Joostenberg_Nat+Kehinde2014_Laibach_Conv+Kehinde2014_Laibach_Org+Kehinde2014_Laibach_Nat+Kehinde2014_Spier_Conv+Kehinde2014_Spier_Nat
Pinheiro2008
Trojelsgaard2015_La Gomera
Trojelsgaard2015_Tenerife Teno Bajo+Trojelsgaard2015_Tenerife Fasnia
Vanbergen2013_balfarm+Vanbergen2013_bridgend+Vanbergen2013_dalhaikie+Vanbergen2013_netherton+Vanbergen2013_backhill+Vanbergen2013_corntulloch+Vanbergen2013_allancreich
Zackenberg
Yoshihara2008
Watts2016_Chicon+Watts2016_Mantanay+Watts2016_Choquebamba+Watts2016_Huaran+Watts2016_Piscacucho+Watts2016_Poques+Watts2016_Pumamarca+Watts2016_Tiaparo+Watts2016_Yanacocha
Kato1993
KatoMiura1996
Kakutani1990
Inoue1990
Fragoso_RA2+Fragoso_RA3+Fragoso_RD1+Fragoso_RD3
PopicThesis
Pfeiffer_CNE+Pfeiffer_CNM+Pfeiffer_CNT+Pfeiffer_CPB+Pfeiffer_CPM+Pfeiffer_CPR+Pfeiffer_CPS+Pfeiffer_M2+Pfeiffer_RP1+Pfeiffer_RP2+Pfeiffer_LM+Pfeiffer_LO+Pfeiffer_BD+Pfeiffer_BH+Pfeiffer_BS
Carstensen_Gigante+Carstensen_Paulino+Carstensen_Tinkerbell+Carstensen_Midway+Carstensen_Cedro+Carstensen_Elefante+Carstensen_Soizig
Orford_B1+Orford_B2+Orford_B3+Orford_B4+Orford_B5+Orford_B10
Orford_B6+Orford_B7+Orford_B8+Orford_B9
Blumel2016
Welti_ID+Welti_K1B+Welti_K4A+Welti_4B+Welti_20B+Welti_20C+Welti_N1A+Welti_N1B+Welti_N4A+Welti_N4B+Welti_N20A+Welti_N20B
Souza_cerrado
Souza_chaco
Souza_pantanal
Souza_vereda
Grass2013_1+Grass2013_2+Grass2013_3+Grass2013_4+Grass2013_5+Grass2013_6+Grass2013_7+Grass2013_8+Grass2013_9+Grass2013_10+Grass2013_11+Grass2013_12+Grass2013_13+Grass2013_14+Grass2013_15+Grass2013_16+Grass2013_17
Bennett2018
Adedoja2018b_baseZone+Adedoja2018b_MidZone+Adedoja2018b_HighZone+Adedoja2018b_PeakZone
Adedoja2019
CordenizPicanco2018_NatVeg
Benadi2018
Hackett2019_NZ_salt_marsh+Hackett2019_NZ_sand_dune+Hackett2019_NZ_scrub_coprosma
Oleques2019
Jolls2019
Traveset2013_Fernandina
Traveset2013_Santiago
Traveset2013_SantaCruz
Traveset2013_SanCristobal
Simanonok2014
Son2019_a1+Son2019_a2+Son2019_a3+Son2019_a4+Son2019_a5+Son2019_a6+Son2019_a7+Son2019_a8+Son2019_F1+Son2019_F2+Son2019_F3+Son2019_F4+Son2019_F5+Son2019_F6+Son2019_F7+Son2019_F8
Baldock2019_Bristol
Baldock2019_Edinburgh
Baldock2019_Leeds
Baldock2019_Reading
-

Pour la collection 2

-
-Collection 2 - pi -

-Collection 2 - pi -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
dupont2003
herrera1988
medan2002ld
medan2002rb
olensen2002aig
olensen2002flo
small1976
vazquez2002
Burkle2013
Weiner2011
Gilarranz2014_amarante+Gilarranz2014_barrosa+Gilarranz2014_cincocerros+Gilarranz2014_difuntito+Gilarranz2014_difuntos+Gilarranz2014_elmorro+Gilarranz2014_labrava+Gilarranz2014_lachata+Gilarranz2014_lapaja+Gilarranz2014_piedraalta+Gilarranz2014_vigilancia+Gilarranz2014_volcan
Aizen2008_Challhuaco_U+Aizen2008_Challhuaco_D
Devoto2005_LQ
Devoto2005_LT+Devoto2005_LH
Gibson2006_GA1
Gibson2006_GA2
Gibson2006_SG
Lundgren2005
Trojelsgaard2015_El Hierro
Trojelsgaard2015_Gran Canaria
Trojelsgaard2015_Fuerteventura
Trojelsgaard2015_Western Sahara
Fragoso_RA1+Fragoso_RD2
Pornon2017
Kantsa2018
Robinson2018
CordenizPicanco2018_NatFor
CordenizPicanco2018_ExoFor
CordenizPicanco2018_SemiPast
CordenizPicanco2018_IntPast
Hackett2019_UK_sand_dune+Hackett2019_UK_grassland+Hackett2019_UK_heathland+Hackett2019_UK_woodland+Hackett2019_UK_salt_marsh+Hackett2019_UK_scrub
Biella2019
Nel2017
Villalobos2019
LaraRomero2019_blanca+LaraRomero2019_rajada+LaraRomero2019_refugio+LaraRomero2019_torre
Traveset2013_Pinta
Ferrero2013
Neli2014
Sritongchuay2019_near+Sritongchuay2019_far
-

Et voici donc les valeurs numériques pour les \(\alpha\) (paramètres de connectivité).

-

Pour la collection 1 : \[\begin{bmatrix} 1 &0.9 &0.92 &0.55 &0.75 &0.57 &0.17 \\0.1 &0.21 &0.81 &0.86 &0.7 &0.4 &0.54 \\0.38 &0.12 &0.03 &0.09 &0.92 &0.65 &0.17 \\0.76 &0.5 &0.1 &0.33 &0.17 &0.04 &0.65 \\0.71 &0.5 &0.18 &0.28 &0.19 &0.04 &0.01 \\0.03 &0.89 &0.4 &0.05 &0.53 &0.2 &0.03 \\0.22 &0.07 &0.01 &0.22 &0.35 &0.21 &0.06 \\0.11 &0.07 &0.01 &0.01 &0.01 &0.6 &0.15 \\0.02 &0.21 &0.06 &0.01 &0.06 &0.01 &0 \\ \end{bmatrix}\] Pour la collection 2 : \[\begin{bmatrix} 0.84 &0.99 &0.66 &0.99 &0.38 &0.79 \\0.79 &0.5 &0.01 &0.19 &0.46 &0.51 \\0.15 &0.02 &0.08 &0.83 &0.22 &0.44 \\0 &0.05 &0.49 &0.07 &0.15 &0 \\0.01 &0.16 &0 &0.04 &0 &0 \\ \end{bmatrix}\]

-
-

Répartition dans les clusters selon la taxonomie

-
-Pollinators repartition for the pi model regarding taxonomy -

-Pollinators repartition for the pi model regarding taxonomy -

-
-
-Pollinators repartition for the pi model regarding taxonomy -

-Pollinators repartition for the pi model regarding taxonomy -

-
-
-Plants repartition for the pi model regarding taxonomy -

-Plants repartition for the pi model regarding taxonomy -

-
-
-Plants repartition for the pi model regarding taxonomy -

-Plants repartition for the pi model regarding taxonomy -

-
-
-
-
-

Clustering avec le modèle rho

-

Avec le modèle rho nous obtenons les 1 collections et les structures suivantes:

-

Pour la collection 1

-
-Collection 1 - rho -

-Collection 1 - rho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
arroyo1982_1+arroyo1982_2+arroyo3
dupont2003
eberling1999
herrera1988
inouye1988
kato1990
medan2002ld
medan2002rb
olensen2002aig
olensen2002flo
ramirez1992
small1976
vazquez2002
petanidou1991
ramirez1989
smith-ramirez2005
Burkle2013
Junker2013
Weiner2011
Kaiser_control+Kaiser_restored
bartomeus2008
Olito-Fox2014
Gilarranz2014_amarante+Gilarranz2014_barrosa+Gilarranz2014_cincocerros+Gilarranz2014_difuntito+Gilarranz2014_difuntos+Gilarranz2014_elmorro+Gilarranz2014_labrava+Gilarranz2014_lachata+Gilarranz2014_lapaja+Gilarranz2014_piedraalta+Gilarranz2014_vigilancia+Gilarranz2014_volcan
Benadi2013_1(950m)+Benadi2013_2(1170m)+Benadi2013_6(2020m)
Benadi2013_3(1340m)
Benadi2013_4(1700m)+Benadi2013_5(1800m)
Kaiser-Bunbury2017_Bernica+Kaiser-Bunbury2017_Casse-dent+Kaiser-Bunbury2017_Copolia+Kaiser-Bunbury2017_La-Reserve+Kaiser-Bunbury2017_Rosebelle+Kaiser-Bunbury2017_Salazie+Kaiser-Bunbury2017_Tea-Plantation+Kaiser-Bunbury2017_Trois-Freres
Fang2012
Shay2016
Struck1994
Kato2000
Aizen2008_Challhuaco_U+Aizen2008_Challhuaco_D
Aizen2008_Cerro Otto_U+Aizen2008_Cerro Otto_D
Aizen2008_Llao-llao_U+Aizen2008_Llao-llao_D
Aizen2008_Puerto Blest_U+Aizen2008_Puerto Blest_D
Albrecht2010_49yr+Albrecht2010_63yr+Albrecht2010_84yr+Albrecht2010_109yr+Albrecht2010_130yr
Baldock2011_TB+Baldock2011_JN
Chamberlain_cr1+Chamberlain_cr2+Chamberlain_fs1+Chamberlain_fs2+Chamberlain_go1+Chamberlain_go2+Chamberlain_mm1+Chamberlain_mm2+Chamberlain_mz1+Chamberlain_mz2+Chamberlain_sm1+Chamberlain_sm2
Chamberlain_HLU+Chamberlain_HLG+Chamberlain_OKU+Chamberlain_OKG+Chamberlain_WLU+Chamberlain_WLG+Chamberlain_SOU+Chamberlain_SOG
Chamberlain_Site1+Chamberlain_Site2+Chamberlain_Site3+Chamberlain_Site4+Chamberlain_Site5+Chamberlain_Site6
Dattilo2016
Devoto2005_LQ
Devoto2005_PP+Devoto2005_AP
Devoto2005_LT+Devoto2005_LH
Devoto2005_VT
Devoto2005_LL+Devoto2005_CT
Dupont2009_IsenBjerg+Dupont2009_Other
Freitas2006
Gibson2006_GA1
Gibson2006_GA2
Gibson2006_SG
Gibson2006_TA1
Gibson2006_TA2
Jedrzejewska2013_Ochata+Jedrzejewska2013_Kabaty
LaraRomero2016_pe?alara_EP+LaraRomero2016_pe?alara_PA+LaraRomero2016_nevero_EP+LaraRomero2016_nevero_PA
LemusJimenez2003
Lundgren2005
Marrero2013
MonteroCastano2017_Albufera+MonteroCastano2017_Llimpa+MonteroCastano2017_Tirant
Kehinde2014_Joostenberg_Conv+Kehinde2014_Joostenberg_Org+Kehinde2014_Joostenberg_Nat+Kehinde2014_Laibach_Conv+Kehinde2014_Laibach_Org+Kehinde2014_Laibach_Nat+Kehinde2014_Spier_Conv+Kehinde2014_Spier_Nat
Pinheiro2008
Trojelsgaard2015_El Hierro
Trojelsgaard2015_La Gomera
Trojelsgaard2015_Gran Canaria
Trojelsgaard2015_Fuerteventura
Trojelsgaard2015_Tenerife Teno Bajo+Trojelsgaard2015_Tenerife Fasnia
Trojelsgaard2015_Western Sahara
Vanbergen2013_balfarm+Vanbergen2013_bridgend+Vanbergen2013_dalhaikie+Vanbergen2013_netherton+Vanbergen2013_backhill+Vanbergen2013_corntulloch+Vanbergen2013_allancreich
Zackenberg
Yoshihara2008
Watts2016_Chicon+Watts2016_Mantanay+Watts2016_Choquebamba+Watts2016_Huaran+Watts2016_Piscacucho+Watts2016_Poques+Watts2016_Pumamarca+Watts2016_Tiaparo+Watts2016_Yanacocha
Kato1993
KatoMiura1996
Kakutani1990
Inoue1990
Fragoso_RA1+Fragoso_RD2
Fragoso_RA2+Fragoso_RA3+Fragoso_RD1+Fragoso_RD3
PopicThesis
Pfeiffer_CNE+Pfeiffer_CNM+Pfeiffer_CNT+Pfeiffer_CPB+Pfeiffer_CPM+Pfeiffer_CPR+Pfeiffer_CPS+Pfeiffer_M2+Pfeiffer_RP1+Pfeiffer_RP2+Pfeiffer_LM+Pfeiffer_LO+Pfeiffer_BD+Pfeiffer_BH+Pfeiffer_BS
Carstensen_Gigante+Carstensen_Paulino+Carstensen_Tinkerbell+Carstensen_Midway+Carstensen_Cedro+Carstensen_Elefante+Carstensen_Soizig
Pornon2017
Orford_B1+Orford_B2+Orford_B3+Orford_B4+Orford_B5+Orford_B10
Orford_B6+Orford_B7+Orford_B8+Orford_B9
Blumel2016
Welti_ID+Welti_K1B+Welti_K4A+Welti_4B+Welti_20B+Welti_20C+Welti_N1A+Welti_N1B+Welti_N4A+Welti_N4B+Welti_N20A+Welti_N20B
Kantsa2018
Souza_cerrado
Souza_chaco
Souza_pantanal
Souza_vereda
Grass2013_1+Grass2013_2+Grass2013_3+Grass2013_4+Grass2013_5+Grass2013_6+Grass2013_7+Grass2013_8+Grass2013_9+Grass2013_10+Grass2013_11+Grass2013_12+Grass2013_13+Grass2013_14+Grass2013_15+Grass2013_16+Grass2013_17
Robinson2018
Bennett2018
Adedoja2018b_baseZone+Adedoja2018b_MidZone+Adedoja2018b_HighZone+Adedoja2018b_PeakZone
Adedoja2019
CordenizPicanco2018_NatFor
CordenizPicanco2018_NatVeg
CordenizPicanco2018_ExoFor
CordenizPicanco2018_SemiPast
CordenizPicanco2018_IntPast
Benadi2018
Hackett2019_NZ_salt_marsh+Hackett2019_NZ_sand_dune+Hackett2019_NZ_scrub_coprosma
Hackett2019_UK_sand_dune+Hackett2019_UK_grassland+Hackett2019_UK_heathland+Hackett2019_UK_woodland+Hackett2019_UK_salt_marsh+Hackett2019_UK_scrub
Oleques2019
Biella2019
Jolls2019
Nel2017
Villalobos2019
LaraRomero2019_blanca+LaraRomero2019_rajada+LaraRomero2019_refugio+LaraRomero2019_torre
Traveset2013_Fernandina
Traveset2013_Pinta
Traveset2013_Santiago
Traveset2013_SantaCruz
Traveset2013_SanCristobal
Ferrero2013
Simanonok2014
Son2019_a1+Son2019_a2+Son2019_a3+Son2019_a4+Son2019_a5+Son2019_a6+Son2019_a7+Son2019_a8+Son2019_F1+Son2019_F2+Son2019_F3+Son2019_F4+Son2019_F5+Son2019_F6+Son2019_F7+Son2019_F8
Neli2014
Sritongchuay2019_near+Sritongchuay2019_far
Baldock2019_Bristol
Baldock2019_Edinburgh
Baldock2019_Leeds
Baldock2019_Reading
-

Et voici donc les valeurs numériques pour les \(\alpha\) (paramètres de connectivité).

-

Pour la collection 1 : \[\begin{bmatrix} 0.77 &0.91 &0.64 &0.73 &0.09 &0.34 &0.98 &0.9 &0.41 \\0.63 &0.09 &0.15 &0.94 &0.56 &0.6 &0.25 &0.24 &0.05 \\0.59 &0.73 &0.19 &0.38 &0.04 &0.09 &0.51 &0.22 &0.46 \\0.07 &0.19 &0.02 &0.73 &0.58 &0.2 &0.22 &0.04 &0.03 \\0.69 &0.13 &0.34 &0.03 &0.1 &0.01 &0.53 &0.33 &0.08 \\0.09 &0.02 &0.01 &0.27 &0.06 &0.12 &0.01 &0.04 &0 \\ \end{bmatrix}\]

-
-

Répartition dans les clusters selon la taxonomie

-
-Pollinators repartition for the rho model regarding taxonomy -

-Pollinators repartition for the rho model regarding taxonomy -

-
-
-Pollinators repartition for the rho model regarding taxonomy -

-Pollinators repartition for the rho model regarding taxonomy -

-
-
-Plants repartition for the rho model regarding taxonomy -

-Plants repartition for the rho model regarding taxonomy -

-
-
-Plants repartition for the rho model regarding taxonomy -

-Plants repartition for the rho model regarding taxonomy -

-
-
-
-
-

Clustering avec le modèle pirho

-

Avec le modèle pirho nous obtenons les 15 collections et les structures suivantes:

-

Pour la collection 1

-
-Collection 1 - pirho -

-Collection 1 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
arroyo1982_1+arroyo1982_2+arroyo3
dupont2003
petanidou1991
Aizen2008_Challhuaco_U+Aizen2008_Challhuaco_D
Aizen2008_Llao-llao_U+Aizen2008_Llao-llao_D
Jedrzejewska2013_Ochata+Jedrzejewska2013_Kabaty
Pinheiro2008
Souza_pantanal
Robinson2018
Jolls2019
Traveset2013_Fernandina
Baldock2019_Leeds
Baldock2019_Reading
-

Pour la collection 2

-
-Collection 2 - pirho -

-Collection 2 - pirho -

-
- - - - - - - - - - - - - - - - - -
Networks
Benadi2013_3(1340m)
Trojelsgaard2015_La Gomera
CordenizPicanco2018_SemiPast
-

Pour la collection 3

-
-Collection 3 - pirho -

-Collection 3 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
Kato2000
Freitas2006
Inoue1990
Souza_cerrado
Adedoja2019
Baldock2019_Bristol
-

Pour la collection 4

-
-Collection 4 - pirho -

-Collection 4 - pirho -

-
- - - - - - - - - - - - - - -
Networks
Aizen2008_Puerto Blest_U+Aizen2008_Puerto Blest_D
LemusJimenez2003
-

Pour la collection 5

-
-Collection 5 - pirho -

-Collection 5 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
inouye1988
Junker2013
Kehinde2014_Joostenberg_Conv+Kehinde2014_Joostenberg_Org+Kehinde2014_Joostenberg_Nat+Kehinde2014_Laibach_Conv+Kehinde2014_Laibach_Org+Kehinde2014_Laibach_Nat+Kehinde2014_Spier_Conv+Kehinde2014_Spier_Nat
Watts2016_Chicon+Watts2016_Mantanay+Watts2016_Choquebamba+Watts2016_Huaran+Watts2016_Piscacucho+Watts2016_Poques+Watts2016_Pumamarca+Watts2016_Tiaparo+Watts2016_Yanacocha
Kakutani1990
Fragoso_RA1+Fragoso_RD2
Souza_chaco
Oleques2019
-

Pour la collection 6

-
-Collection 6 - pirho -

-Collection 6 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
medan2002ld
small1976
smith-ramirez2005
Benadi2013_1(950m)+Benadi2013_2(1170m)+Benadi2013_6(2020m)
Shay2016
Aizen2008_Cerro Otto_U+Aizen2008_Cerro Otto_D
Lundgren2005
Zackenberg
Carstensen_Gigante+Carstensen_Paulino+Carstensen_Tinkerbell+Carstensen_Midway+Carstensen_Cedro+Carstensen_Elefante+Carstensen_Soizig
Welti_ID+Welti_K1B+Welti_K4A+Welti_4B+Welti_20B+Welti_20C+Welti_N1A+Welti_N1B+Welti_N4A+Welti_N4B+Welti_N20A+Welti_N20B
Bennett2018
CordenizPicanco2018_NatFor
CordenizPicanco2018_ExoFor
CordenizPicanco2018_IntPast
Benadi2018
Villalobos2019
Traveset2013_Santiago
Traveset2013_SantaCruz
Son2019_a1+Son2019_a2+Son2019_a3+Son2019_a4+Son2019_a5+Son2019_a6+Son2019_a7+Son2019_a8+Son2019_F1+Son2019_F2+Son2019_F3+Son2019_F4+Son2019_F5+Son2019_F6+Son2019_F7+Son2019_F8
Sritongchuay2019_near+Sritongchuay2019_far
-

Pour la collection 7

-
-Collection 7 - pirho -

-Collection 7 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
medan2002rb
olensen2002flo
vazquez2002
Trojelsgaard2015_Gran Canaria
Trojelsgaard2015_Western Sahara
LaraRomero2019_blanca+LaraRomero2019_rajada+LaraRomero2019_refugio+LaraRomero2019_torre
-

Pour la collection 8

-
-Collection 8 - pirho -

-Collection 8 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
Weiner2011
Kaiser_control+Kaiser_restored
Gilarranz2014_amarante+Gilarranz2014_barrosa+Gilarranz2014_cincocerros+Gilarranz2014_difuntito+Gilarranz2014_difuntos+Gilarranz2014_elmorro+Gilarranz2014_labrava+Gilarranz2014_lachata+Gilarranz2014_lapaja+Gilarranz2014_piedraalta+Gilarranz2014_vigilancia+Gilarranz2014_volcan
Kaiser-Bunbury2017_Bernica+Kaiser-Bunbury2017_Casse-dent+Kaiser-Bunbury2017_Copolia+Kaiser-Bunbury2017_La-Reserve+Kaiser-Bunbury2017_Rosebelle+Kaiser-Bunbury2017_Salazie+Kaiser-Bunbury2017_Tea-Plantation+Kaiser-Bunbury2017_Trois-Freres
Fang2012
Gibson2006_SG
Gibson2006_TA1
Trojelsgaard2015_Fuerteventura
Pfeiffer_CNE+Pfeiffer_CNM+Pfeiffer_CNT+Pfeiffer_CPB+Pfeiffer_CPM+Pfeiffer_CPR+Pfeiffer_CPS+Pfeiffer_M2+Pfeiffer_RP1+Pfeiffer_RP2+Pfeiffer_LM+Pfeiffer_LO+Pfeiffer_BD+Pfeiffer_BH+Pfeiffer_BS
Biella2019
Nel2017
Ferrero2013
Neli2014
-

Pour la collection 9

-
-Collection 9 - pirho -

-Collection 9 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
eberling1999
ramirez1992
Struck1994
Albrecht2010_49yr+Albrecht2010_63yr+Albrecht2010_84yr+Albrecht2010_109yr+Albrecht2010_130yr
Devoto2005_PP+Devoto2005_AP
Devoto2005_VT
Gibson2006_TA2
MonteroCastano2017_Albufera+MonteroCastano2017_Llimpa+MonteroCastano2017_Tirant
Yoshihara2008
PopicThesis
Orford_B1+Orford_B2+Orford_B3+Orford_B4+Orford_B5+Orford_B10
Souza_vereda
Adedoja2018b_baseZone+Adedoja2018b_MidZone+Adedoja2018b_HighZone+Adedoja2018b_PeakZone
Hackett2019_NZ_salt_marsh+Hackett2019_NZ_sand_dune+Hackett2019_NZ_scrub_coprosma
-

Pour la collection 10

-
-Collection 10 - pirho -

-Collection 10 - pirho -

-
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Networks
herrera1988
Burkle2013
bartomeus2008
Olito-Fox2014
Benadi2013_4(1700m)+Benadi2013_5(1800m)
Baldock2011_TB+Baldock2011_JN
Chamberlain_HLU+Chamberlain_HLG+Chamberlain_OKU+Chamberlain_OKG+Chamberlain_WLU+Chamberlain_WLG+Chamberlain_SOU+Chamberlain_SOG
Chamberlain_Site1+Chamberlain_Site2+Chamberlain_Site3+Chamberlain_Site4+Chamberlain_Site5+Chamberlain_Site6
Devoto2005_LQ
Devoto2005_LT+Devoto2005_LH
Devoto2005_LL+Devoto2005_CT
Dupont2009_IsenBjerg+Dupont2009_Other
Gibson2006_GA1
LaraRomero2016_pe?alara_EP+LaraRomero2016_pe?alara_PA+LaraRomero2016_nevero_EP+LaraRomero2016_nevero_PA
Marrero2013
Trojelsgaard2015_Tenerife Teno Bajo+Trojelsgaard2015_Tenerife Fasnia
Vanbergen2013_balfarm+Vanbergen2013_bridgend+Vanbergen2013_dalhaikie+Vanbergen2013_netherton+Vanbergen2013_backhill+Vanbergen2013_corntulloch+Vanbergen2013_allancreich
Fragoso_RA2+Fragoso_RA3+Fragoso_RD1+Fragoso_RD3
Pornon2017
Orford_B6+Orford_B7+Orford_B8+Orford_B9
Blumel2016
Kantsa2018
Grass2013_1+Grass2013_2+Grass2013_3+Grass2013_4+Grass2013_5+Grass2013_6+Grass2013_7+Grass2013_8+Grass2013_9+Grass2013_10+Grass2013_11+Grass2013_12+Grass2013_13+Grass2013_14+Grass2013_15+Grass2013_16+Grass2013_17
CordenizPicanco2018_NatVeg
Hackett2019_UK_sand_dune+Hackett2019_UK_grassland+Hackett2019_UK_heathland+Hackett2019_UK_woodland+Hackett2019_UK_salt_marsh+Hackett2019_UK_scrub
Traveset2013_Pinta
Traveset2013_SanCristobal
Simanonok2014
Baldock2019_Edinburgh
-

Pour la collection 11

-
-Collection 11 - pirho -

-Collection 11 - pirho -

-
- - - - - - - - - - - - - - - - - -
Networks
kato1990
ramirez1989
Kato1993
-

Pour la collection 12

-
-Collection 12 - pirho -

-Collection 12 - pirho -

-
- - - - - - - - - - - - - - - - - -
Networks
Chamberlain_cr1+Chamberlain_cr2+Chamberlain_fs1+Chamberlain_fs2+Chamberlain_go1+Chamberlain_go2+Chamberlain_mm1+Chamberlain_mm2+Chamberlain_mz1+Chamberlain_mz2+Chamberlain_sm1+Chamberlain_sm2
Dattilo2016
KatoMiura1996
-

Pour la collection 13

-
-Collection 13 - pirho -

-Collection 13 - pirho -

-
- - - - - - - - - - - -
Networks
olensen2002aig
-

Pour la collection 14

-
-Collection 14 - pirho -

-Collection 14 - pirho -

-
- - - - - - - - - - - -
Networks
Trojelsgaard2015_El Hierro
-

Pour la collection 15

-
-Collection 15 - pirho -

-Collection 15 - pirho -

-
- - - - - - - - - - - -
Networks
Gibson2006_GA2
-

Et voici donc les valeurs numériques pour les \(\alpha\) (paramètres de connectivité).

-

Pour la collection 1 : \[\begin{bmatrix} 0.52 &0.6 &0.34 &0.1 &0.15 &0 &0.36 \\0.12 &0.93 &0.01 &0.01 &0 &0.61 &0.16 \\0.05 &0.31 &0.02 &0.08 &0.37 &0.27 &0.12 \\0.04 &0.05 &0.01 &0.38 &0.03 &0.01 &0.17 \\0 &0.03 &0.16 &0.11 &0.04 &0.01 &0.01 \\0.01 &0.22 &0.02 &0.01 &0.05 &0 &0.01 \\ \end{bmatrix}\] Pour la collection 2 : \[\begin{bmatrix} 0.66 &0.23 \\0.2 &0.05 \\ \end{bmatrix}\] Pour la collection 3 : \[\begin{bmatrix} 0.64 &0.32 &0.11 &0.53 &0.19 &0.05 \\0.47 &0.21 &0.02 &0.19 &0.07 &0.03 \\0.16 &0.05 &0.01 &0.07 &0.01 &0 \\ \end{bmatrix}\] Pour la collection 4 : \[\begin{bmatrix} 0.45 &0.07 \\0.22 &0.62 \\0.23 &0.04 \\ \end{bmatrix}\] Pour la collection 5 : \[\begin{bmatrix} 0.78 &0.43 &0.16 &0.56 \\0.29 &0.04 &0.22 &0.08 \\0.02 &0.12 &0.03 &0 \\ \end{bmatrix}\] Pour la collection 6 : \[\begin{bmatrix} 0.82 &0.63 &0.2 &0.74 \\0.34 &0.07 &0.41 &0.13 \\0.02 &0.16 &0.03 &0 \\ \end{bmatrix}\] Pour la collection 7 : \[\begin{bmatrix} 0.9 &0.46 &0.72 \\0.17 &0.37 &0.03 \\ \end{bmatrix}\] Pour la collection 8 : \[\begin{bmatrix} 0.66 &0.97 &0.72 &1 &0.13 &0.71 &0 \\0.99 &0.93 &0.84 &0.64 &0.5 &0.11 &0.17 \\0.71 &0.7 &0.28 &0.32 &0.13 &0.07 &0.05 \\0.96 &0.46 &0.75 &0.14 &0.39 &0.01 &0.07 \\0.62 &0.36 &0.09 &0.11 &0.04 &0.02 &0.01 \\0.62 &0.12 &0.43 &0.02 &0.17 &0 &0.02 \\0.33 &0.03 &0.14 &0 &0.03 &0 &0 \\ \end{bmatrix}\] Pour la collection 9 : \[\begin{bmatrix} 0.59 &0.17 &0.32 \\0.06 &0.15 &0.02 \\ \end{bmatrix}\] Pour la collection 10 : \[\begin{bmatrix} 0.91 &0.62 &0.3 &0.79 &0.44 \\0.15 &0.7 &0.32 &0.07 &0.36 \\0.15 &0.03 &0.16 &0.05 &0.01 \\ \end{bmatrix}\] Pour la collection 11 : \[\begin{bmatrix} 0.09 &0.36 &1 &0.12 &0.41 \\0.33 &0 &0.07 &0.46 &0.09 \\0 &0.01 &0.07 &0.14 &0 \\0.03 &0.16 &0.02 &0 &0 \\ \end{bmatrix}\] Pour la collection 12 : \[\begin{bmatrix} 0.68 &0.37 &0.12 \\0.41 &0.17 &0.04 \\0.19 &0.05 &0.01 \\ \end{bmatrix}\] Pour la collection 13 : \[\begin{bmatrix} 0.78 \\0.19 \\ \end{bmatrix}\] Pour la collection 14 : \[\begin{bmatrix} 0.44 &0.08 \\ \end{bmatrix}\] Pour la collection 15 : \[\begin{bmatrix} 0.42 &1 \\0.35 &0.01 \\ \end{bmatrix}\]

-
-

Répartition dans les clusters selon la taxonomie

-
-Pollinators repartition for the pirho model regarding taxonomy -

-Pollinators repartition for the pirho model regarding taxonomy -

-
-
-Pollinators repartition for the pirho model regarding taxonomy -

-Pollinators repartition for the pirho model regarding taxonomy -

-
-
-Plants repartition for the pirho model regarding taxonomy -

-Plants repartition for the pirho model regarding taxonomy -

-
-
-Plants repartition for the pirho model regarding taxonomy -

-Plants repartition for the pirho model regarding taxonomy -

-
-
-
- - - - -
- - - - - - - - - - - - - - - diff --git a/Rcodes/real_data/presentation_dore.pdf b/Rcodes/real_data/presentation_dore.pdf deleted file mode 100644 index a72696a..0000000 Binary files a/Rcodes/real_data/presentation_dore.pdf and /dev/null differ diff --git a/Rcodes/simulation/NA_robustness_analyse.html b/Rcodes/simulation/NA_robustness_analyse.html deleted file mode 100644 index 6af0a38..0000000 --- a/Rcodes/simulation/NA_robustness_analyse.html +++ /dev/null @@ -1,475 +0,0 @@ - - - - - - - - - - - - - -Analyzing the capacity of the colBiSBM to recover structure for missing data from other networks - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
- - - - - - -
- -
- -
-

Simulation context

-

The idea is to benchmark the capacity of the models when NAs are in the data.

-

To do this, we chose the below structure:

-

\[M = 3, n_r = 100, n_c = 150 \\ \alpha = \begin{bmatrix}0.7&0.4&0.3 \\0.4&0.2&0.05 \\0.3&0.05&0.05 \\\end{bmatrix} - \\ \pi = \begin{bmatrix}0.5 \\0.3 \\0.2 \\\end{bmatrix} \rho = \begin{bmatrix}0.5 \\0.3 \\0.2 \\\end{bmatrix}\]

-

With \(M\) the number of networks, \(n_r\) the number of nodes in row of the incidence matrix, \(n_c\) the number of nodes in column, \(\alpha\) the connectivity parameters between the row and column clusters. \(\pi\) and \(\rho\) are the proportion of nodes in the row and columns clusters.

-

And set some randomly chosen interactions to NA. The below plots will show the different quality indicators in function of proportion of NAs in the first of the 3 networks.

-
-
-

AUC in function of the proportion of NAs

-

-

-
-
-

ARI in function of the proportion of NAs

-
-Difference of ARI for the row clusterings -

-Difference of ARI for the row clusterings -

-
-
-Difference of ARI for the columns clusterings -

-Difference of ARI for the columns clusterings -

-
-
- - - - -
- - - - - - - - - - - - - - - diff --git a/Rcodes/simulation/NA_robustness_analyse.pdf b/Rcodes/simulation/NA_robustness_analyse.pdf deleted file mode 100644 index b6b7bbe..0000000 Binary files a/Rcodes/simulation/NA_robustness_analyse.pdf and /dev/null differ diff --git a/Rcodes/simulation/data/simulated_collection_data_clustering_iid_08-07-23-16:51:52.Rds b/Rcodes/simulation/data/simulated_collection_data_clustering_iid_08-07-23-16:51:52.Rds deleted file mode 100644 index 38c4c63..0000000 Binary files a/Rcodes/simulation/data/simulated_collection_data_clustering_iid_08-07-23-16:51:52.Rds and /dev/null differ diff --git a/Rcodes/simulation/data/simulated_collection_data_clustering_iid_10-07-23-10:08:21.Rds b/Rcodes/simulation/data/simulated_collection_data_clustering_iid_10-07-23-10:08:21.Rds new file mode 100644 index 0000000..9e38ed6 Binary files /dev/null and b/Rcodes/simulation/data/simulated_collection_data_clustering_iid_10-07-23-10:08:21.Rds differ diff --git a/Rcodes/simulation/data/simulated_collection_data_clustering_pi_10-07-23-10:39:58.Rds b/Rcodes/simulation/data/simulated_collection_data_clustering_pi_10-07-23-10:39:58.Rds new file mode 100644 index 0000000..a6f5841 Binary files /dev/null and b/Rcodes/simulation/data/simulated_collection_data_clustering_pi_10-07-23-10:39:58.Rds differ diff --git a/Rcodes/simulation/data/simulated_collection_data_clustering_pirho_08-07-23-17:04:36.Rds b/Rcodes/simulation/data/simulated_collection_data_clustering_pirho_08-07-23-17:04:36.Rds deleted file mode 100644 index 8e91546..0000000 Binary files a/Rcodes/simulation/data/simulated_collection_data_clustering_pirho_08-07-23-17:04:36.Rds and /dev/null differ diff --git a/Rcodes/simulation/data/simulated_collection_data_clustering_pirho_10-07-23-10:34:17.Rds b/Rcodes/simulation/data/simulated_collection_data_clustering_pirho_10-07-23-10:34:17.Rds new file mode 100644 index 0000000..c1d7e59 Binary files /dev/null and b/Rcodes/simulation/data/simulated_collection_data_clustering_pirho_10-07-23-10:34:17.Rds differ diff --git a/Rcodes/simulation/data/simulated_collection_data_clustering_rho_08-07-23-16:58:41.Rds b/Rcodes/simulation/data/simulated_collection_data_clustering_rho_08-07-23-16:58:41.Rds deleted file mode 100644 index 4a94c99..0000000 Binary files a/Rcodes/simulation/data/simulated_collection_data_clustering_rho_08-07-23-16:58:41.Rds and /dev/null differ diff --git a/Rcodes/simulation/data/simulated_collection_data_clustering_rho_10-07-23-10:45:16.Rds b/Rcodes/simulation/data/simulated_collection_data_clustering_rho_10-07-23-10:45:16.Rds new file mode 100644 index 0000000..7ce0cca Binary files /dev/null and b/Rcodes/simulation/data/simulated_collection_data_clustering_rho_10-07-23-10:45:16.Rds differ diff --git a/Rcodes/simulation/inference_analyze.Rmd b/Rcodes/simulation/inference_analyze.Rmd index 32190b7..69cf13b 100644 --- a/Rcodes/simulation/inference_analyze.Rmd +++ b/Rcodes/simulation/inference_analyze.Rmd @@ -227,7 +227,7 @@ kable(proportion_preferred_table, #| fig.height = 4, #| dpi=300 -proportion_preferred_data %>% ggplot() + +plot <- proportion_preferred_data %>% ggplot() + aes( x = epsilon_alpha, y = prop_model, color = preferred_model, fill = preferred_model @@ -237,12 +237,12 @@ proportion_preferred_data %>% ggplot() + color = guide_legend(title = "Preferred Model") ) + scale_x_continuous(breaks = seq(from = 0.0, to = 0.24, by = 0.03)) + - scale_color_okabe_ito() + - scale_fill_okabe_ito() + - xlab(TeX("$\\epsilon_{\\alpha}$")) + + scale_color_okabe_ito() + + scale_fill_okabe_ito() + + xlab(TeX("$\\epsilon_{\\alpha}$")) + ylab("Model proportions") + geom_col(position = "stack") - +print(plot) ``` \paragraph{Results} For the model comparison, when $\eps[\alpha]$ is small diff --git a/Rcodes/simulation/netclustering_analyze.Rmd b/Rcodes/simulation/netclustering_analyze.Rmd index ba0c0be..3fc62c3 100644 --- a/Rcodes/simulation/netclustering_analyze.Rmd +++ b/Rcodes/simulation/netclustering_analyze.Rmd @@ -18,8 +18,62 @@ filenames <- list.files( # data_list <- lapply(filenames, function(file) lapply(readRDS(file), function(model) model$list_clustering)) df_netclust <- do.call("rbind", lapply(filenames, readRDS)) +df_netclust$model <- factor(df_netclust$model, levels = c( + "iid", "pi", + "rho", "pirho" +)) ``` +\paragraph{Simulation settings} For all models we simulate $M = 9$ networks with +$\forall m \in \{ 1 \dots M \} , n^m_1 = n^m_2 = 75$ with $Q_1 = Q_2 = 3$. For +the simulations the proportions are the following: + +\begin{align*} +\bm{\pi}^1 = \left( 0.2, 0.3, 0.5 \right) & & \bm{\rho}^1 = \left( 0.2, 0.3, 0.5 \right) +\end{align*} +and for all $m = 2,\dots,9$ +\begin{align*} +\bm{\pi}^m = \begin{cases} + \bm{\pi}^1 & \text{for } iid\text{-}colBiSBM \\ + \sigma^1_m(\bm{\pi}^1) & \text{for } \pi\text{-}colBiSBM \text{ and } \pi\rho\text{-}colBiSBM +\end{cases}\\ +\bm{\rho}^m = +\begin{cases} + \bm{\rho}^1 & \text{for } iid\text{-}colBiSBM \\ + \sigma^2_m(\bm{\rho}^1) & \text{for } \rho\text{-}colBiSBM \text{ and } \pi\rho\text{-}colBiSBM +\end{cases} +\end{align*} +where $\sigma^1_m$ and $\sigma^2_m$ are permutations of {1, 2, 3} proper to network $m$ and +$\sigma^1 (\pi)= {(\pi_{\sigma^1 (i)})}_{i=\{1,\dots,3\}}$ +and $\sigma^2 (\rho)= {(\rho_{\sigma^2 (i)})}_{i=\{1,\dots,3\}}$. +The networks are divided into 3 sub-collections of 3 +networks with connectivity parameters as follows: + +\begin{align*} +\bm{\alpha}^{as} = .3 + \begin{pmatrix} + \epsilon & - \frac{\epsilon}{2} & - \frac{\epsilon}{2}\\ + - \frac{\epsilon}{2} & \epsilon & - \frac{\epsilon}{2}\\ + - \frac{\epsilon}{2} & - \frac{\epsilon}{2} & \epsilon +\end{pmatrix}, && +\bm{\alpha}^{cp} = .3 + \begin{pmatrix} + \frac{3 \epsilon}{2} & \epsilon & \frac{\epsilon}{2}\\ + \epsilon & \frac{\epsilon}{2} & 0\\ + \frac{\epsilon}{2} & 0 & - \frac{\epsilon}{2} +\end{pmatrix}, && +\bm{\alpha}^{dis} = .3 + \begin{pmatrix} + - \frac{\epsilon}{2} & \epsilon & \epsilon\\ + \epsilon & - \frac{\epsilon}{2} & \epsilon\\ + \epsilon & \epsilon & - \frac{\epsilon}{2} +\end{pmatrix}, +\end{align*} +with $\epsilon \in [.1, .4]$. $\bm{\alpha}^{as}$ represents a classical +assortative community structure, +while $\bm{\alpha}^{cp}$ is a layered core-periphery structure with block 2 +acting as a semi-core. Finally, $\bm{\alpha}^{dis}$ is a disassortative +community structure with stronger +connections between blocks than within blocks. If $\epsilon = 0$, the three +matrices are equal and the 9 networks have the same connection structure. +Increasing $\epsilon$ differentiates the 3 sub-collections of networks. ```{r netclustering-ARI-boxplot, echo = FALSE} #| dpi = 300, @@ -34,4 +88,10 @@ df_netclust %>% guides(fill = guide_legend(title = "Model")) + ylab("ARI of obtained netclustering") + geom_boxplot(aes(fill = model)) -``` \ No newline at end of file +``` + +\paragraph{Results} The evaluation of our method involves a comparison between +the resulting partition of the network collection and the simulated partition +using the ARI index. As the value of $\epsilon$ increases, our ability to +distinguish between the networks improves, and this distinction becomes nearly +perfect in all setups of the $colBiSBM$. \ No newline at end of file diff --git a/Rcodes/simulation/netclustering_analyze.tex b/Rcodes/simulation/netclustering_analyze.tex index 2c690d6..8a368ba 100644 --- a/Rcodes/simulation/netclustering_analyze.tex +++ b/Rcodes/simulation/netclustering_analyze.tex @@ -1,8 +1,67 @@ \section{Network clustering of simulated networks}\label{sec:network-clustering-of-simulated-networks} +\paragraph{Simulation settings} + +For all models we simulate \(M = 9\) networks with +\(\forall m \in \{ 1 \dots M \} , n^m_1 = n^m_2 = 75\) with +\(Q_1 = Q_2 = 3\). For the simulations the proportions are the +following: + +\begin{align*} +\bm{\pi}^1 = \left( 0.2, 0.3, 0.5 \right) & & \bm{\rho}^1 = \left( 0.2, 0.3, 0.5 \right) +\end{align*} and for all \(m = 2,\dots,9\) \begin{align*} +\bm{\pi}^m = \begin{cases} + \bm{\pi}^1 & \text{for } iid\text{-}colBiSBM \\ + \sigma^1_m(\bm{\pi}^1) & \text{for } \pi\text{-}colBiSBM \text{ and } \pi\rho\text{-}colBiSBM +\end{cases}\\ +\bm{\rho}^m = +\begin{cases} + \bm{\rho}^1 & \text{for } iid\text{-}colBiSBM \\ + \sigma^2_m(\bm{\rho}^1) & \text{for } \rho\text{-}colBiSBM \text{ and } \pi\rho\text{-}colBiSBM +\end{cases} +\end{align*} where \(\sigma^1_m\) and \(\sigma^2_m\) are permutations of +\{1, 2, 3\} proper to network \(m\) and +\(\sigma^1 (\pi)= {(\pi_{\sigma^1 (i)})}_{i=\{1,\dots,3\}}\) and +\(\sigma^2 (\rho)= {(\rho_{\sigma^2 (i)})}_{i=\{1,\dots,3\}}\). The +networks are divided into 3 sub-collections of 3 networks with +connectivity parameters as follows: + +\begin{align*} +\bm{\alpha}^{as} = .3 + \begin{pmatrix} + \epsilon & - \frac{\epsilon}{2} & - \frac{\epsilon}{2}\\ + - \frac{\epsilon}{2} & \epsilon & - \frac{\epsilon}{2}\\ + - \frac{\epsilon}{2} & - \frac{\epsilon}{2} & \epsilon +\end{pmatrix}, && +\bm{\alpha}^{cp} = .3 + \begin{pmatrix} + \frac{3 \epsilon}{2} & \epsilon & \frac{\epsilon}{2}\\ + \epsilon & \frac{\epsilon}{2} & 0\\ + \frac{\epsilon}{2} & 0 & - \frac{\epsilon}{2} +\end{pmatrix}, && +\bm{\alpha}^{dis} = .3 + \begin{pmatrix} + - \frac{\epsilon}{2} & \epsilon & \epsilon\\ + \epsilon & - \frac{\epsilon}{2} & \epsilon\\ + \epsilon & \epsilon & - \frac{\epsilon}{2} +\end{pmatrix}, +\end{align*} with \(\epsilon \in [.1, .4]\). \(\bm{\alpha}^{as}\) +represents a classical assortative community structure, while +\(\bm{\alpha}^{cp}\) is a layered core-periphery structure with block 2 +acting as a semi-core. Finally, \(\bm{\alpha}^{dis}\) is a +disassortative community structure with stronger connections between +blocks than within blocks. If \(\epsilon = 0\), the three matrices are +equal and the 9 networks have the same connection structure. Increasing +\(\epsilon\) differentiates the 3 sub-collections of networks. + \begin{figure} \centering -\includegraphics{./img/99d363f6aa43bf0eba413cb994dc00b130709107.png} +\includegraphics{./img/ca0adc96e26b9b41eb8dec4c472696309ebcf0fe.png} \caption{\label{}ARI of the partition obtained by clustering in function of \(\eps\)} \end{figure} + +\paragraph{Results} + +The evaluation of our method involves a comparison between the resulting +partition of the network collection and the simulated partition using +the ARI index. As the value of \(\epsilon\) increases, our ability to +distinguish between the networks improves, and this distinction becomes +nearly perfect in all setups of the \(colBiSBM\). diff --git a/Rcodes/simulation/netclustering_check.R b/Rcodes/simulation/netclustering_check.R index 1b027bc..b4987a1 100644 --- a/Rcodes/simulation/netclustering_check.R +++ b/Rcodes/simulation/netclustering_check.R @@ -10,7 +10,7 @@ if (!exists("model_to_test")) { } if (!exists("repetitions")) { - repetitions <- seq.int(3) + repetitions <- seq.int(30) } nr <- 75 @@ -32,7 +32,7 @@ if (identical(arg, character(0))) { conditions <- tidyr::crossing(epsilons, pi, rho, repetitions) -results <- lapply(seq_len(nrow(conditions)), function(s) { +results <- bettermc::mclapply(seq_len(nrow(conditions)), function(s) { eps <- conditions[s, ]$epsilons current_pi <- conditions[s, ]$pi current_rho <- conditions[s, ]$rho @@ -195,6 +195,9 @@ results <- lapply(seq_len(nrow(conditions)), function(s) { ) best_partitions <- unlist(extract_best_bipartite_partition(list_collection)) + if (!is(best_partitions, "list")) { + best_partitions <- list(best_partitions) + } clustering <- unlist(lapply(seq_along(best_partitions), function(col_idx) { setNames( rep(col_idx, best_partitions[[col_idx]]$M), @@ -206,15 +209,13 @@ results <- lapply(seq_len(nrow(conditions)), function(s) { ari <- aricode::ARI(rep(c(1, 2, 3), each = 3), clustering) toc() - cat(paste("Finished", s)) return( data.frame(epsilon = eps, model = model_to_test, ARI = ari) ) -} -# , -# mc.cores = parallel::detectCores() - 1, -# mc.progress = TRUE, -# mc.retry = -1 +}, +mc.cores = parallel::detectCores() - 1, +mc.progress = TRUE, +mc.retry = -1 ) data_frame_result <- do.call("rbind", results) diff --git a/figure/netclustering-ARI-boxplot-1.png b/figure/netclustering-ARI-boxplot-1.png index 3709395..0212412 100644 Binary files a/figure/netclustering-ARI-boxplot-1.png and b/figure/netclustering-ARI-boxplot-1.png differ diff --git a/img/6a5c3c2748922aace8a2034349434383ce4a9f11.png b/img/6a5c3c2748922aace8a2034349434383ce4a9f11.png new file mode 100644 index 0000000..0c776e0 Binary files /dev/null and b/img/6a5c3c2748922aace8a2034349434383ce4a9f11.png differ diff --git a/img/ca0adc96e26b9b41eb8dec4c472696309ebcf0fe.png b/img/ca0adc96e26b9b41eb8dec4c472696309ebcf0fe.png new file mode 100644 index 0000000..0212412 Binary files /dev/null and b/img/ca0adc96e26b9b41eb8dec4c472696309ebcf0fe.png differ diff --git a/img/d424b38c3b69ae646295e877eee9ae4e8602ec6c.png b/img/d424b38c3b69ae646295e877eee9ae4e8602ec6c.png new file mode 100644 index 0000000..fc8f70c Binary files /dev/null and b/img/d424b38c3b69ae646295e877eee9ae4e8602ec6c.png differ diff --git a/rapport.pdf b/rapport.pdf index 0afcc03..b772ab3 100644 Binary files a/rapport.pdf and b/rapport.pdf differ