-
-
Save Studentenfutter/b03a5f03bcee00f721287f627eb95c2c to your computer and use it in GitHub Desktop.
Import SentiWS dictionary for sentiment analysis into R as data.table
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# The get_sentiws function will download the zip-file with the SentiWS dictionary, | |
# unzip it and return a data.table. | |
library(data.table) | |
get_sentiws <- function(){ | |
sentiws_tmp_dir <- file.path(tempdir(), "sentiws") | |
if (!file.exists(sentiws_tmp_dir)) dir.create(sentiws_tmp_dir) | |
sentiws_zipfile <- file.path(sentiws_tmp_dir, "SentiWS_v2.0c.zip") | |
sentiws_url <- "http://pcai056.informatik.uni-leipzig.de/downloads/etc/SentiWS/SentiWS_v2.0.zip" | |
download.file(url = sentiws_url, destfile = sentiws_zipfile) | |
unzip(zipfile = sentiws_zipfile, exdir = sentiws_tmp_dir) | |
.unfold <- function(.SD){ | |
pos <- gsub("^([A-Z]+)\\s+.*$", "\\1", .SD[["data"]][1]) | |
weight <- as.numeric(gsub("^[A-Z]+\\s+(-?\\d\\.\\d+).*$", "\\1", .SD[["data"]][1])) | |
words <- gsub("^[A-Z]+\\s+-?\\d\\.\\d+\\s*(.*?)\\s*$", "\\1", .SD[["data"]][1]) | |
words <- if (!grepl("^\\s*$", words)) strsplit(x = words, split = ",")[[1]] else NULL | |
list( | |
word = c(.SD[["word"]][1], words), | |
base = c(TRUE, rep(FALSE, times = length(words))), | |
lemma = .SD[["word"]][1], | |
pos = pos, | |
weight = weight | |
) | |
} | |
dts <- lapply( | |
c(positive = "SentiWS_v2.0_Positive.txt", negative = "SentiWS_v2.0_Negative.txt"), | |
function(filename){ | |
dt <- fread(file.path(sentiws_tmp_dir, filename), sep = "|", encoding="UTF-8") | |
colnames(dt) <- c("word", "data") | |
dt[, "id" := 1L:nrow(dt)] | |
dt[, .unfold(.SD), by = c("id")] | |
} | |
) | |
rbindlist(dts) | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment