Last active
May 2, 2018 17:44
-
-
Save tomastitera/75452e258ee59e7dcace4a24b8255a28 to your computer and use it in GitHub Desktop.
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
| setwd("~/R/snmupdpipe") | |
| library(udpipe) | |
| udmodel_czech <- udpipe_load_model(file = "czech-ud-2.0-170801.udpipe") | |
| page <- read.csv("page_179497582061065_2018_04_25_14_18_33.tab", sep="\t", encoding = "UTF-8") | |
| korpus.raw <- as.vector(page$post_message) | |
| x <- udpipe_annotate(udmodel_czech, x = korpus.raw) | |
| x <- as.data.frame(x) | |
| View(x) | |
| stats <- subset(x, upos %in% "NOUN") | |
| View(stats) | |
| stats <- txt_freq(x = stats$lemma) | |
| library(lattice) | |
| stats$key <- factor(stats$key, levels = rev(stats$key)) | |
| barchart(key ~ freq, data = head(stats, 30), col = "cadetblue", main = "Most occurring nouns", xlab = "Freq") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment