Lees de woorden en stopwoorden
setwd("~/Downloads")
#Read the data
data <-read_csv("./text_analysis_wapp.csv")
#Read stopwoorden
stopwoorden <- read_csv("./stopwoorden.csv") %>%
pull()
stopwoorden <- c(stopwoorden, "media", "weggelaten", "nee")
data <- data %>%
unnest_tokens(word, Text) %>%
count(word, sort = T) %>%
mutate(total = sum(n),
rank = row_number(),
`term frequency` = n/total) %>%
filter(!is.element(word, stopwoorden), str_count(word) > 1, is.na(as.numeric(word)))
## Warning in mask$eval_all_filter(dots, env_filter): NAs introduced by coercion
wordcloud(data$word, data$n, max.words = 150)
#Read the data
data <-read_csv("./text_analysis_wapp.csv")
vaag <- c("+31 6 18866181", "16")
data2 <- data %>%
unnest_tokens(word, Text) %>%
group_by(Naam) %>%
count(word, sort = T) %>%
mutate(total = sum(n),
rank = row_number(),
`term frequency` = n/total) %>%
filter(!is.element(word, stopwoorden), str_count(word) > 1, is.na(as.numeric(word))) %>%
filter(!is.element(Naam, vaag))
for(i in 1:length(unique(data2$Naam))){
print(unique(data2$Naam)[i])
df <- data2 %>%
filter(Naam == unique(data2$Naam)[i]) %>%
ungroup() %>%
mutate(freq = n) %>%
select(word, freq)
wordcloud(df$word, df$freq, max.words=150)
}
## [1] "Wim Leferink Op Reinink"
## [1] "Bas Machielsen"
## [1] "Marc De Rode"
## [1] "Thijs Hilberdink"
## [1] "Julius Kuit"
## [1] "Erik Emondt"
## [1] "Jelle Heuver"
## [1] "Mitch"
## [1] "Julian Boer"
## [1] "Yorick Karseboom"
## [1] "Daan van der Zwaag"