Random forest classification
Classification of clades using song level attributes
Patagona and Topazes were excluded
Classification accuracy at the element level:
Classification accuracy at the song level:
Relative importance (contribution) of song attributes to classification
Sequence complexity (corrected.complx): a composite measure of sequence complexity. The index uses the number of transitions in the sequence as a measure of the complexity induced by the state ordering and the longitudinal entropy as a measure of the complexity induced by the state distribution in the sequence
Aggregated importance by parameter type
Clade song structure
Complexity measures
Correlation between complexity parameters
Phylogenetic PCA on complexity measures:
Variance explained:
## Importance of components:
## PC1 PC2 PC3 PC4
## Standard deviation 1.60041 1.00019 0.598789 0.282414
## Proportion of Variance 0.64033 0.25010 0.089637 0.019939
## Cumulative Proportion 0.64033 0.89042 0.980061 1.000000
Loadings:
Map complexity on tree
Distribution of PC1 on complexity and category intervals with equal number of species per category
Correlation of PC1 and individual complexity variables
Phylogenetic signal complexity
## $lambda
## [1] 0.32767
##
## $logL
## [1] -904.76
##
## $logL0
## [1] -911.15
##
## $P
## [1] 0.00035004Complexity-PC1 mapped on phylogeny
Phylogram
Fan phylogeny
Discrete trait evolution model (transitions) “equal number of species” complexity
| model | AICc | DeltaAICc |
|---|---|---|
| ER | 584.28 | 0.00 |
| SYM | 584.28 | 0.00 |
| ARD | 586.29 | 2.01 |
| meristic | 586.31 | 2.03 |
| cstm | 586.89 | 2.61 |
| cstm2 | 593.09 | 8.81 |
| cstm3 | 763.64 | 179.36 |
Discrete trait evolution model (transitions) “equal length” complexity
| model | AICc | DeltaAICc |
|---|---|---|
| ER | 363.33 | 0.00 |
| SYM | 397.97 | 34.65 |
| ARD | 415.38 | 52.05 |
| meristic | 415.54 | 52.22 |
| cstm | 450.01 | 86.69 |
| cstm2 | 508.04 | 144.71 |
| cstm3 | 545.94 | 182.61 |
MCMC SIMMAP
Equal rates & “equal number of species”" complexity:
## 100 trees with a mapped discrete character with states:
## 1, 2, 3
##
## trees have 4924.03 changes between states on average
##
## changes are of the following types:
## 1,2 1,3 2,1 2,3 3,1 3,2
## x->y 817.06 824.21 818.77 819.49 823.27 821.23
##
## mean total time spent in each state is:
## 1 2 3 total
## raw 458.54139 457.11421 463.22740 1378.9
## prop 0.33255 0.33151 0.33594 1.0
Different rates “equal number of species” complexity:
## 100 trees with a mapped discrete character with states:
## 1, 2, 3
##
## trees have 3370.42 changes between states on average
##
## changes are of the following types:
## 1,2 1,3 2,1 2,3 3,1 3,2
## x->y 592.2 584.36 525.84 541.48 651.62 474.92
##
## mean total time spent in each state is:
## 1 2 3 total
## raw 456.77804 456.37835 465.72661 1378.9
## prop 0.33127 0.33098 0.33776 1.0
Different rates “equal length” complexity:
## 100 trees with a mapped discrete character with states:
## 1, 2, 3
##
## trees have 1786.99 changes between states on average
##
## changes are of the following types:
## 1,2 1,3 2,1 2,3 3,1 3,2
## x->y 806.89 50.43 809.09 33.81 53.16 33.61
##
## mean total time spent in each state is:
## 1 2 3 total
## raw 949.0814 405.64793 24.153710 1378.9
## prop 0.6883 0.29419 0.017517 1.0
Session information
## R version 3.4.4 (2018-03-15)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.1 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/openblas/libblas.so.3
## LAPACK: /usr/lib/x86_64-linux-gnu/libopenblasp-r0.2.20.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_US.UTF-8 LC_COLLATE=en_US.UTF-8
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## attached base packages:
## [1] parallel stats graphics grDevices utils datasets methods
## [8] base
##
## other attached packages:
## [1] pbmcapply_1.2.5 future_1.9.0 taxize_0.9.4
## [4] knitr_1.20 kableExtra_0.9.0 geiger_2.0.6
## [7] randomForest_4.6-14 smacof_1.10-8 plotrix_3.7-4
## [10] viridis_0.5.1 viridisLite_0.3.0 corrplot_0.84
## [13] TraMineR_2.0-9 caret_6.0-80 lattice_0.20-35
## [16] pbapply_1.3-4 phytools_0.6-60 ape_5.2
## [19] warbleR_1.1.16 NatureSounds_1.0.0 seewave_2.1.0
## [22] tuneR_1.3.3 stringdist_0.9.5.1 fossil_0.3.7
## [25] shapefiles_0.7 foreign_0.8-69 maps_3.3.0
## [28] sp_1.3-1 RColorBrewer_1.1-2 ggplot2_3.1.0
##
## loaded via a namespace (and not attached):
## [1] tidyselect_0.2.5 lme4_1.1-18-1
## [3] fftw_1.0-4 htmlwidgets_1.2
## [5] grid_3.4.4 combinat_0.0-8
## [7] munsell_0.5.0 animation_2.5
## [9] codetools_0.2-15 withr_2.1.2
## [11] colorspace_1.3-2 highr_0.7
## [13] rstudioapi_0.7 geometry_0.3-6
## [15] stats4_3.4.4 robustbase_0.93-2
## [17] dtw_1.20-1 dimRed_0.1.0
## [19] listenv_0.7.0 labeling_0.3
## [21] mnormt_1.5-5 rprojroot_1.3-2
## [23] coda_0.19-2 clusterGeneration_1.3.4
## [25] ipred_0.9-7 R6_2.3.0
## [27] DRR_0.0.3 reshape_0.8.7
## [29] bitops_1.0-6 assertthat_0.2.0
## [31] scales_1.0.0 nnet_7.3-12
## [33] gtable_0.2.0 globals_0.12.2
## [35] ddalpha_1.3.4 bold_0.5.0
## [37] phangorn_2.4.0 weights_0.90
## [39] timeDate_3043.102 rlang_0.3.0.1
## [41] CVST_0.2-2 scatterplot3d_0.3-41
## [43] RcppRoll_0.3.0 splines_3.4.4
## [45] lazyeval_0.2.1 ModelMetrics_1.2.0
## [47] acepack_1.4.1 wordcloud_2.6
## [49] broom_0.5.0 checkmate_1.8.5
## [51] yaml_2.2.0 reshape2_1.4.3
## [53] abind_1.4-5 backports_1.1.2
## [55] Hmisc_4.1-1 tools_3.4.4
## [57] lava_1.6.3 proxy_0.4-22
## [59] polynom_1.3-9 Rcpp_1.0.0
## [61] plyr_1.8.4 base64enc_0.1-3
## [63] purrr_0.2.5 RCurl_1.95-4.11
## [65] rpart_4.1-13 zoo_1.8-4
## [67] deSolve_1.21 sfsmisc_1.1-2
## [69] haven_1.1.2 cluster_2.0.6
## [71] crul_0.6.0 magrittr_1.5
## [73] data.table_1.11.4 openxlsx_4.1.0
## [75] mvtnorm_1.0-8 mitml_0.3-6
## [77] hms_0.4.2 evaluate_0.11
## [79] rio_0.5.10 jpeg_0.1-8
## [81] soundgen_1.3.1 readxl_1.1.0
## [83] gridExtra_2.3 compiler_3.4.4
## [85] ellipse_0.4.1 tibble_1.4.2
## [87] mice_3.3.0 crayon_1.3.4
## [89] minqa_1.2.4 htmltools_0.3.6
## [91] Formula_1.2-3 tidyr_0.8.1
## [93] expm_0.999-3 lubridate_1.7.4
## [95] magic_1.5-8 subplex_1.5-4
## [97] MASS_7.3-49 boot_1.3-20
## [99] Matrix_1.2-12 car_3.0-2
## [101] readr_1.1.1 heplots_1.3-5
## [103] quadprog_1.5-5 gdata_2.18.0
## [105] bindr_0.1.1 pan_1.6
## [107] gower_0.1.2 igraph_1.2.2
## [109] forcats_0.3.0 pkgconfig_2.0.2
## [111] numDeriv_2016.8-1 signal_0.7-6
## [113] recipes_0.1.3 xml2_1.2.0
## [115] foreach_1.4.4 prodlim_2018.04.18
## [117] rvest_0.3.2 stringr_1.3.1
## [119] digest_0.6.18 pracma_2.2.2
## [121] pls_2.7-0 httpcode_0.2.0
## [123] rmarkdown_1.10 cellranger_1.1.0
## [125] fastmatch_1.1-0 htmlTable_1.12
## [127] Deriv_3.8.5 curl_3.2
## [129] kernlab_0.9-27 gtools_3.8.1
## [131] jomo_2.6-4 rjson_0.2.20
## [133] nloptr_1.0.4 jsonlite_1.5
## [135] nlme_3.1-131 bindrcpp_0.2.2
## [137] carData_3.0-1 Sim.DiffProc_4.3
## [139] pillar_1.3.0 httr_1.3.1
## [141] DEoptimR_1.0-8 survival_2.41-3
## [143] glue_1.3.0 zip_1.0.0
## [145] iterators_1.0.10 candisc_0.8-0
## [147] class_7.3-14 stringi_1.2.4
## [149] nnls_1.4 latticeExtra_0.6-28
## [151] dplyr_0.7.8