Last updated: 2021-03-10
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 e06246c. 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/nips_1-17.mat
Ignored: output/newsgroups/fits-newsgroups.RData
Ignored: output/nips/fits-nips.RData
Untracked files:
Untracked: analysis/newsgroups.RData
Untracked: data/newsgroups.RData
Unstaged changes:
Modified: .gitignore
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/prepare_newsgroups.Rmd) and HTML (docs/prepare_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 | e06246c | Peter Carbonetto | 2021-03-10 | workflowr::wflow_publish(“prepare_newsgroups.Rmd”) |
| html | 8f6a910 | Peter Carbonetto | 2021-03-10 | Prepared newsgroups data. |
| Rmd | 6e47a78 | Peter Carbonetto | 2021-03-10 | workflowr::wflow_publish(“prepare_newsgroups.Rmd”) |
Here we prepare the “20 Newsgroups” data for subsequent topic modeling analyses. To run these data preparation steps, download the data from here then copy the downloaded files to a directory called 20news-bydate inside the data subdirectory.
The Matrix package is used to create a sparse matrix.
library(Matrix)
library(readr)
library(tools)The data were split into a “training” and “test” set. Here we combine them into one large data set.
data.dir <- "../data/20news-bydate"
topic.names <- read.table(file.path(data.dir,"train.map"),sep = " ",
stringsAsFactors = FALSE)[[1]]
words <- read.table(file.path(data.dir,"vocabulary.txt"),
stringsAsFactors = FALSE)[[1]]
topics <- c(read.table(file.path(data.dir,"train.label"))[[1]],
read.table(file.path(data.dir,"test.label"))[[1]])
train <- read.table(file.path(data.dir,"train.data"),sep = " ")
test <- read.table(file.path(data.dir,"test.data"),sep = " ")
names(train) <- c("document","word","count")
names(test) <- c("document","word","count")
test$document <- test$document + max(train$document)
dat <- rbind(train,test)Create the (sparse) counts matrix.
counts <- sparseMatrix(i = dat$document,j = dat$word,x = dat$count)
colnames(counts) <- wordsRemove all words that appear in fewer than 2 documents.
cols <- which(colSums(counts > 0) >= 2)
counts <- counts[,cols]Get the “topics” assigned to the documents.
topics <- factor(topics)
levels(topics) <- topic.namesThe word counts should be stored as a 18,774 x 55,911 matrix, in which only a small proportion of the word counts (0.2%) are nonzero.
n <- nrow(counts)
m <- ncol(counts)
cat(sprintf("Number of documents: %d\n",n))
cat(sprintf("Number of terms in vocabulary: %d\n",m))
cat(sprintf("Rate of nonzero counts: %0.2f%%\n",100*nnzero(counts)/(n*m)))
# Number of documents: 18774
# Number of terms in vocabulary: 55911
# Rate of nonzero counts: 0.23%Among the counts that are positive, the vast majority are small.
cat("The word counts are mostly small, with a small number of large counts:\n")
print(quantile(summary(counts)$x,c(0,0.5,0.9,0.99,0.999,1)))
# The word counts are mostly small, with a small number of large counts:
# 0% 50% 90% 99% 99.9% 100%
# 1 1 3 13 48 716Write the counts in an RData file.
save(list = c("counts","topics"),file = "newsgroups.RData")
resaveRdaFiles("newsgroups.RData")
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] tools stats graphics grDevices utils datasets methods
# [8] base
#
# other attached packages:
# [1] readr_1.3.1 Matrix_1.2-18
#
# loaded via a namespace (and not attached):
# [1] Rcpp_1.0.5 knitr_1.26 whisker_0.4
# [4] magrittr_1.5 workflowr_1.6.2.9000 hms_0.5.2
# [7] lattice_0.20-38 R6_2.4.1 rlang_0.4.5
# [10] stringr_1.4.0 grid_3.6.2 xfun_0.11
# [13] git2r_0.26.1 htmltools_0.4.0 yaml_2.2.0
# [16] digest_0.6.23 rprojroot_1.3-2 tibble_2.1.3
# [19] crayon_1.3.4 later_1.0.0 vctrs_0.2.1
# [22] promises_1.1.0 fs_1.3.1 zeallot_0.1.0
# [25] glue_1.3.1 evaluate_0.14 rmarkdown_2.3
# [28] stringi_1.4.3 pillar_1.4.3 compiler_3.6.2
# [31] backports_1.1.5 httpuv_1.5.2 pkgconfig_2.0.3