CH1 The tidy text format

load library

library(data.table)
library(dplyr) #data manipulation
library(ggplot2) #visualizations
library(gridExtra) #viewing multiple plots together
library(tidytext) #text mining
#library(wordcloud2) #creative visualizations

load data

lyric_data=fread('../data/prince_raw_data.csv')

1.1 Contrasting tidy text with other data structures

1.2 The unnest_tokens function

把以下4個句子轉成tidy data

text <- c("Because I could not stop for Death -",
          "He kindly stopped for me -",
          "The Carriage held but just Ourselves -",
          "and Immortality")
text

[1] "Because I could not stop for Death -"  
[2] "He kindly stopped for me -"            
[3] "The Carriage held but just Ourselves -"
[4] "and Immortality"                       

轉成tidy data前先轉成dataframe

text_df <- data_frame(line = 1:4, text = text)
text_df

library(tidytext)

one-token-per-row format:

text_df %>%
  unnest_tokens(word, text)

1.3 Tidying the words of lyric data

library(janeaustenr)
library(dplyr)
library(stringr)

original_songs <- lyric_data[,1:6] %>%
  group_by(album) %>%
  mutate(linenumber = row_number()) %>% 
  ungroup()
original_songs

one-token-per-row format:

library(tidytext)
tidy_songs <- original_songs %>%
  unnest_tokens(word, text)
tidy_songs

data(stop_words)
tidy_songs <- tidy_songs %>%
  anti_join(stop_words)

Joining, by = "word"

tidy_songs %>%
  count(word, sort = TRUE) 

tidy_songs %>%
  count(word, sort = TRUE) %>%
  filter(n > 600) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n)) +
  geom_col() +
  xlab(NULL) +
  coord_flip()