R: tidy text dataset - tibble - Revision history

Onnowpurbo: /* Tidy Text gutenbergr */

2018-10-31T03:52:16Z

Tidy Text gutenbergr

← Older revision		Revision as of 03:52, 31 October 2018
Line 111:		Line 111:
	theme(legend.position="none") +		theme(legend.position="none") +
	labs(y = "Jane Austen", x = NULL)		labs(y = "Jane Austen", x = NULL)


			Correlation

			cor.test(data = frequency[frequency$author == "Brontë Sisters",],
			~ proportion + `Jane Austen`)


			cor.test(data = frequency[frequency$author == "H.G. Wells",],
			~ proportion + `Jane Austen`)

	==Pranala Menarik==		==Pranala Menarik==

	* [[R]]		* [[R]]

2018-10-31T03:48:50Z

Tidy Text gutenbergr

@@ Line 94: / Line 94: @@
      spread(author, proportion) %>%
      gather(author, proportion, `Brontë Sisters`:`H.G. Wells`)
 ==Pranala Menarik==
 * [[R]]

2018-10-31T03:45:45Z

Tidy Text gutenbergr

← Older revision		Revision as of 03:45, 31 October 2018
Line 64:		Line 64:
	install.packages("gutenbergr")		install.packages("gutenbergr")
	library(gutenbergr)		library(gutenbergr)


	hgwells <- gutenberg_download(c(35, 36, 5230, 159))		hgwells <- gutenberg_download(c(35, 36, 5230, 159))
	tidy_hgwells <- hgwells %>%		tidy_hgwells <- hgwells %>%
	unnest_tokens(word, text) %>%		unnest_tokens(word, text) %>%
	anti_join(stop_words)		anti_join(stop_words)
			tidy_hgwells %>%
			count(word, sort = TRUE)

	~~tidy_hgwells~~ %>%
			bronte <- gutenberg_download(c(1260, 768, 969, 9182, 767))
			tidy_bronte <- bronte %>%
			unnest_tokens(word, text) %>%
			anti_join(stop_words)
			tidy_bronte %>%
	count(word, sort = TRUE)		count(word, sort = TRUE)

			Compare 3 text

			library(tidyr)
			frequency <- bind_rows(mutate(tidy_bronte, author = "Brontë Sisters"),
			mutate(tidy_hgwells, author = "H.G. Wells"),
			mutate(tidy_books, author = "Jane Austen")) %>%
			mutate(word = str_extract(word, "[a-z']+")) %>%
			count(author, word) %>%
			group_by(author) %>%
			mutate(proportion = n / sum(n)) %>%
			select(-n) %>%
			spread(author, proportion) %>%
			gather(author, proportion, `Brontë Sisters`:`H.G. Wells`)

	==Pranala Menarik==		==Pranala Menarik==

	* [[R]]		* [[R]]

2018-10-31T03:39:50Z

Tidy Text gutenbergr

← Older revision		Revision as of 03:39, 31 October 2018
Line 62:		Line 62:
	==Tidy Text gutenbergr==		==Tidy Text gutenbergr==

	~~Kayanya ada masalah dengan~~ gutenbergr~~, karena di R versi terakhir sudah tidak ada ...~~		install.packages("gutenbergr")

	library(gutenbergr)		library(gutenbergr)
	hgwells <- gutenberg_download(c(35, 36, 5230, 159))		hgwells <- gutenberg_download(c(35, 36, 5230, 159))
Line 70:		Line 69:
	anti_join(stop_words)		anti_join(stop_words)

	~~kegiatan di atas tidak bisa di lakukan~~		tidy_hgwells %>%
			count(word, sort = TRUE)

	==Pranala Menarik==		==Pranala Menarik==

	* [[R]]		* [[R]]

2018-10-31T03:36:32Z

Tidy Text Novel

← Older revision		Revision as of 03:36, 31 October 2018
Line 58:		Line 58:
	xlab(NULL) +		xlab(NULL) +
	coord_flip()		coord_flip()


			==Tidy Text gutenbergr==

			Kayanya ada masalah dengan gutenbergr, karena di R versi terakhir sudah tidak ada ...

			library(gutenbergr)
			hgwells <- gutenberg_download(c(35, 36, 5230, 159))
			tidy_hgwells <- hgwells %>%
			unnest_tokens(word, text) %>%
			anti_join(stop_words)

			kegiatan di atas tidak bisa di lakukan

	==Pranala Menarik==		==Pranala Menarik==

	* [[R]]		* [[R]]

2018-10-31T02:21:34Z

Tidy Text Novel

@@ Line 35: / Line 35: @@
                 unnest_tokens(word, text)
   tidy_books
 ==Pranala Menarik==
 * [[R]]

2018-10-31T02:17:33Z

Tidy Text Novel

← Older revision		Revision as of 02:17, 31 October 2018
Line 29:		Line 29:
	original_books		original_books

			Buat menjadi one-token-per-row

			library(tidytext)
			tidy_books <- original_books %>%
			unnest_tokens(word, text)
			tidy_books

	==Pranala Menarik==		==Pranala Menarik==

	* [[R]]		* [[R]]

2018-10-31T02:14:24Z

← Older revision		Revision as of 02:14, 31 October 2018
Line 14:		Line 14:
	text_df <- data_frame(line = 1:4, text = text)		text_df <- data_frame(line = 1:4, text = text)
	text_df		text_df


			==Tidy Text Novel==

			library(janeaustenr)
			library(dplyr)
			library(stringr)
			original_books <- austen_books() %>%
			group_by(book) %>%
			mutate(linenumber = row_number(),
			chapter = cumsum(str_detect(text, regex("^chapter [\\divxlc]",
			ignore_case = TRUE)))) %>%
			ungroup()
			original_books

2018-10-31T01:36:36Z

← Older revision		Revision as of 01:36, 31 October 2018
Line 14:		Line 14:
	text_df <- data_frame(line = 1:4, text = text)		text_df <- data_frame(line = 1:4, text = text)
	text_df		text_df






			==Pranala Menarik==

			* [[R]]

2018-10-31T01:36:03Z

Tidy Text Dataset

← Older revision		Revision as of 01:36, 31 October 2018
Line 10:		Line 10:
	==Tidy Text Dataset==		==Tidy Text Dataset==

			install.packages("dplyr")
	library(dplyr)		library(dplyr)
	text_df <- data_frame(line = 1:4, text = text)		text_df <- data_frame(line = 1:4, text = text)
	text_df		text_df