---
tags: Tartu_Texts101_R
---

# Jagatud märkmed - (HVEE.01.006)

Püsilink: https://hackmd.io/@OGZFb2mRSA65ybyn4hSfkQ/BJFwvc4li/edit


Pildi jagamiseks paremklõps pildi peal (all paremal nurgas) -> copy image.

Ja CTRL+V (CMD+V) siin tekstikastis. Hackmd laeb faili üles ja siis kuvab lingi markdown formaadis. Joonise järgi saab kirjutada oma nime.

Joonis 1. Näitepilt

## 03.04.2023

edetabel %>% 
  filter(language=="en") %>% 
  filter(year <2000 &year >1989)

Proovi ka teada saada, mitu lugu oli mis keeles 1994 aastal ja 2014 aastal.

edetabel %>% 
  filter(year == 1994 | year == 2014) %>% 
  count(year, language)

## 10.04.2023

laulusonad %>%
  left_join(stopsonad2,by="word") %>%
  group_by(artist,song) %>%
  filter(onstopsona==TRUE) %>%
  count(word) %>%
  mutate(proportsioon=n/sum(n)) %>% 
  arrange(desc(proportsioon)) %>% 
  filter(artist=="Winny Puhh")

laulusonad %>% 
  filter(artist=="Winny Puhh") %>% 
  left_join(stopsonad2,by="word") %>% 
  filter(onstopsona==T) %>% 
  count(word,sort=T)


laulusonad %>% 
  filter(artist=="Winny Puhh") %>% 
  inner_join(stopsonad,by="word") %>% 
  count(word,sort=T)

laulusonad %>%
  left_join(stopsonad2,by="word") %>%
  filter(is.na(onstopsona))


laulusonad %>%
  left_join(stopsonad2,by="word") %>%
  filter(onstopsona==NA)

## 17.04.2023

Näidisgraafik

## 08.05.2023

peatykid_sonad2 %>% 
  filter(chapter<11) %>% 
  anti_join(stopwords,by="word") %>% 
  filter(!str_detect(word,"[A-ZÕÄÖÜ]")) %>% 
  ungroup() %>% 
  mutate(row_number=row_number()) %>% 
  filter(row_number<11)


raamat1_sonad2 %>% 
  filter(chapter<11) %>% 
  anti_join(stopwords,by="word") %>% 
  filter(!str_detect(word,"[A-ZÕÄÖÜ]")) %>% 
  count(word,sort=T) %>% 
  mutate(row_number=row_number()) %>% 
  filter(row_number<11)

## 15.05.2023

 Sys.setenv(VROOM_CONNECTION_SIZE = "500000000")

filelist <- list.files("data/uiboaed_ilukirjandus/soned",full.names=T)[1:29]
texts <- map_df(filelist, ~ tibble(txt = read_lines(.x)) %>%
                  mutate(filename = .x)) %>%
                  mutate(filename= basename(filename))

words %>% 
  count(word,sort=T) %>% 
  mutate(rank=row_number()) %>% 
  filter(rank<11) %>% 
  ggplot(aes(y=word,x=n))+
  geom_col()



words %>% 
  group_by(filename) %>% 
  count(word,sort=T)

words %>% 
  filter(filename=="Andres_Saal_Vambola.utf8") %>% 
  count(word,sort=T) %>% 
  mutate(rank=row_number()) %>% 
  filter(rank<11)




words %>% 
  group_by(filename) %>% 
  count(word,sort=T) %>% 
  mutate(rank=row_number()) %>% 
  filter(rank<11)


words %>% 
  group_by(filename) %>% 
  count(word,sort=T) %>% 
  mutate(freq=n/sum(n)) %>% 
  filter(word=="töö") %>% 
  #filter(row_number()<10) %>%  #sort pani need juba õigessejärjekorda
  ggplot(aes(y=filename,x=freq,color=filename))+
  geom_point()+
  guides(color=F)

keywords <- texts %>% 
  unnest_tokens(word,txt,to_lower=F) %>% 
  mutate(word=str_replace_all(word,"w","v")) %>% 
  #anti_join(stopwords,"word") %>% 
  group_by(filename) %>% 
  filter(!str_detect(word,"[A-ZÕÄÖÜ]")) %>% 
  count(word,sort=T) %>% 
  bind_tf_idf(word,filename,n) %>% 
  arrange(desc(tf_idf)) %>% 
  head(100)