Assess topic model fits in newsgroups data
Peter Carbonetto
Last updated: 2021-04-09
Checks: 7 0
Knit directory: fastTopics-experiments/analysis/
This reproducible R Markdown analysis was created with workflowr (version 1.6.2.9000). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.
Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.
Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.
The command set.seed(1) was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.
Great job! Recording the operating system, R version, and package versions is critical for reproducibility.
Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.
Great job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.
Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility.
The results in this page were generated with repository version 0ab6c04. See the Past versions tab to see a history of the changes made to the R Markdown and HTML files.
Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated:
Ignored files:
Ignored: data/20news-bydate/
Ignored: data/droplet.RData
Ignored: data/nips_1-17.mat
Ignored: data/pbmc_68k.RData
Ignored: output/droplet/fits-droplet.RData
Ignored: output/newsgroups/fits-newsgroups.RData
Ignored: output/nips/fits-nips.RData
Ignored: output/pbmc68k/fits-pbmc68k.RData
Untracked files:
Untracked: .DS_Store
Untracked: plots/
Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.
These are the previous versions of the repository in which changes were made to the R Markdown (analysis/assess_fits_newsgroups.Rmd) and HTML (docs/assess_fits_newsgroups.html) files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view the files as they were in that past version.
| File | Version | Author | Date | Message |
|---|---|---|---|---|
| Rmd | 0ab6c04 | Peter Carbonetto | 2021-04-09 | workflowr::wflow_publish(“assess_fits_newsgroups.Rmd”) |
| html | 42cb17e | Peter Carbonetto | 2021-04-09 | Adjusted scatterplots in assess_fits_newsgroups analysis. |
| Rmd | 8f157b4 | Peter Carbonetto | 2021-04-09 | workflowr::wflow_publish(“assess_fits_newsgroups.Rmd”) |
| html | d1dadf8 | Peter Carbonetto | 2021-04-09 | Added loadings scatterplots to aassess_fits_newsgroups analysis. |
| Rmd | b37146b | Peter Carbonetto | 2021-04-09 | workflowr::wflow_publish(“assess_fits_newsgroups.Rmd”) |
| html | c679bdc | Peter Carbonetto | 2021-04-07 | Small fix to assess_fits_newsgroups output. |
| Rmd | db4870b | Peter Carbonetto | 2021-04-07 | workflowr::wflow_publish(“assess_fits_newsgroups.Rmd”) |
| html | ca4f229 | Peter Carbonetto | 2021-04-07 | Added max KKT residual progress plots to assess_fits_newsgroups |
| Rmd | b916251 | Peter Carbonetto | 2021-04-07 | workflowr::wflow_publish(“assess_fits_newsgroups.Rmd”) |
| Rmd | 7827775 | Peter Carbonetto | 2021-04-06 | Added plots-for-paper-1 code chunk to assess_fits_newsgroups.Rmd. |
| Rmd | 0f88216 | Peter Carbonetto | 2021-04-06 | A couple of small changes. |
| html | cb0de01 | Peter Carbonetto | 2021-04-06 | Added loglik progress plots to assess_fits_newsgroups analysis. |
| Rmd | 720e225 | Peter Carbonetto | 2021-04-06 | workflowr::wflow_publish(“assess_fits_newsgroups.Rmd”) |
| html | 51a6dd3 | Peter Carbonetto | 2021-04-06 | First build of the assess_fits_newsgroups analysis. |
| Rmd | b57553c | Peter Carbonetto | 2021-04-06 | workflowr::wflow_publish(“assess_fits_newsgroups.Rmd”) |
Here we compare the quality of the fits obtained from the different updates (EM and SCD, with and without extrapolation), and with different numbers of topics, \(K\).
Load the packages used in the analysis below, as well as some additional functions for creating the plots.
library(fastTopics)
library(ggplot2)
library(cowplot)
set.seed(1)Load the results of running fit_poisson_nmf on the “20 newsgroups” data, with different algorithms, and for various settings of \(K\).
load("../output/newsgroups/fits-newsgroups.RData")
fits <- lapply(fits,poisson2multinom)This plot shows the improvement in the log-likelihood as the rank, \(K\), is increased. The log-likelihoods are shown relative to the log-likelihood at \(K = 2\).
plot_loglik_vs_rank(fits) +
theme_cowplot(font_size = 12)
The next set of plots shows the improvement in the fit over time, for \(K\) from 2 to 12, using EM or SCD, with and without extrapolation. The quality of the fit is measured by the log-likelihood relative to the best log-likelihood that was identified among all methods compared.
prune_prefit_iters <- function (fit) {
n <- nrow(fit$progress)
fit$progress <- fit$progress[1000:n,]
fit$progress <- transform(fit$progress,timing = timing/60^2)
return(fit)
}
create_progress_plot <- function (fits, k, y = "loglik")
plot_progress(fits,y = y,add.point.every = 100,shapes = 21,
colors = c("dodgerblue","red","dodgerblue","red"),
fills = c("dodgerblue","red","white","white")) +
scale_y_continuous(trans = "log10",breaks = 10^seq(-8,8)) +
guides(color = "none",fill = "none",size = "none",
shape = "none",linetype = "none") +
labs(x = "runtime (h)",title = paste("K =",k)) +
theme_cowplot(font_size = 10) +
theme(plot.title = element_text(size = 10,face = "plain"))
fits <- lapply(fits,prune_prefit_iters)
p <- vector("list",12)
for (i in 2:12)
p[[i]] <- create_progress_plot(fits[dat$k == i],i)
plot_grid(p[[2]],p[[3]],p[[4]],p[[5]],
p[[6]],p[[7]],p[[8]],p[[9]],
p[[10]],p[[11]],p[[12]],
nrow = 3,ncol = 4)
| Version | Author | Date |
|---|---|---|
| cb0de01 | Peter Carbonetto | 2021-04-06 |
These plots shows the evolution of the KKT residuals over time.
for (i in 2:12)
p[[i]] <- create_progress_plot(fits[dat$k == i],i,y = "res")
plot_grid(p[[2]],p[[3]],p[[4]],p[[5]],
p[[6]],p[[7]],p[[8]],p[[9]],
p[[10]],p[[11]],p[[12]],
nrow = 3,ncol = 4)
| Version | Author | Date |
|---|---|---|
| ca4f229 | Peter Carbonetto | 2021-04-07 |
An example in which the EM and (extrapolated) CD estimates largely agree:
topic_colors <- c("#a6cee3","#1f78b4","#b2df8a","#33a02c","#fb9a99",
"#e31a1c","#fdbf6f","#ff7f00","#cab2d6","#6a3d9a")
fit1 <- fits[["fit-newsgroups-em-k=9"]]
fit2 <- fits[["fit-newsgroups-scd-ex-k=9"]]
n <- nrow(fit1$L)
pdat <- data.frame(x = as.vector(fit1$L),
y = as.vector(fit2$L),
k = factor(rep(1:9,each = n)))
pdat <- pdat[sample(9*n),]
p1 <- ggplot(pdat,aes(x = x,y = y,fill = k)) +
geom_point(color = "white",shape = 21,size = 2) +
geom_abline(color = "black",linetype = "dotted") +
scale_fill_manual(values = topic_colors) +
labs(x = "EM estimate",y = "extrapolated CD estimate") +
theme_cowplot(font_size = 12)
print(p1)
An example in which the EM and (extrapolated) CD estimates greatly differ:
fit1 <- fits[["fit-newsgroups-em-k=10"]]
fit2 <- fits[["fit-newsgroups-scd-ex-k=10"]]
n <- nrow(fit1$L)
pdat <- data.frame(x = as.vector(fit1$L),
y = as.vector(fit2$L),
k = factor(rep(1:10,each = n)))
pdat <- pdat[sample(10*n),]
p2 <- ggplot(pdat,aes(x = x,y = y,fill = k)) +
geom_point(color = "white",shape = 21,size = 2) +
geom_abline(color = "black",linetype = "dotted") +
scale_fill_manual(values = topic_colors) +
labs(x = "EM estimate",y = "extrapolated CD estimate") +
theme_cowplot(font_size = 12)
print(p2)
sessionInfo()
# R version 3.6.2 (2019-12-12)
# Platform: x86_64-apple-darwin15.6.0 (64-bit)
# Running under: macOS Catalina 10.15.7
#
# Matrix products: default
# BLAS: /Library/Frameworks/R.framework/Versions/3.6/Resources/lib/libRblas.0.dylib
# LAPACK: /Library/Frameworks/R.framework/Versions/3.6/Resources/lib/libRlapack.dylib
#
# locale:
# [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#
# attached base packages:
# [1] stats graphics grDevices utils datasets methods base
#
# other attached packages:
# [1] cowplot_1.0.0 ggplot2_3.3.0 fastTopics_0.5-24
#
# loaded via a namespace (and not attached):
# [1] ggrepel_0.9.0 Rcpp_1.0.5 invgamma_1.1
# [4] lattice_0.20-38 tidyr_1.0.0 prettyunits_1.1.1
# [7] assertthat_0.2.1 zeallot_0.1.0 rprojroot_1.3-2
# [10] digest_0.6.23 truncnorm_1.0-8 R6_2.4.1
# [13] backports_1.1.5 MatrixModels_0.4-1 evaluate_0.14
# [16] coda_0.19-3 httr_1.4.2 pillar_1.4.3
# [19] progress_1.2.2 rlang_0.4.5 lazyeval_0.2.2
# [22] data.table_1.12.8 irlba_2.3.3 SparseM_1.78
# [25] whisker_0.4 Matrix_1.2-18 rmarkdown_2.3
# [28] labeling_0.3 Rtsne_0.15 stringr_1.4.0
# [31] htmlwidgets_1.5.1 munsell_0.5.0 mixsqp_0.3-44
# [34] compiler_3.6.2 httpuv_1.5.2 xfun_0.11
# [37] pkgconfig_2.0.3 SQUAREM_2017.10-1 mcmc_0.9-6
# [40] htmltools_0.4.0 tidyselect_0.2.5 tibble_2.1.3
# [43] workflowr_1.6.2.9000 quadprog_1.5-8 viridisLite_0.3.0
# [46] withr_2.1.2 crayon_1.3.4 dplyr_0.8.3
# [49] later_1.0.0 MASS_7.3-51.4 grid_3.6.2
# [52] jsonlite_1.6 gtable_0.3.0 lifecycle_0.1.0
# [55] git2r_0.26.1 magrittr_1.5 scales_1.1.0
# [58] RcppParallel_4.4.2 stringi_1.4.3 farver_2.0.1
# [61] fs_1.3.1 promises_1.1.0 vctrs_0.2.1
# [64] tools_3.6.2 glue_1.3.1 purrr_0.3.3
# [67] hms_0.5.2 yaml_2.2.0 colorspace_1.4-1
# [70] ashr_2.2-51 plotly_4.9.2 knitr_1.26
# [73] quantreg_5.54 MCMCpack_1.4-5