appa

Author: libjohn

00_tokenization.Rmd

@@ -15,6 +15,8 @@ library(tidytext)
 
 ## Text
 
+Poem by Emily Dickinson
+
 ```{r}
 text <- c("Because I could not stop for Death -",
           "He kindly stopped for me -",
@@ -33,7 +35,7 @@ text_df
 ```
 
 
-## Todenization
+## Tokenization
 
 ```{r}
 text_df %>%

00_tokenization.nb.html

@@ -265,6 +265,7 @@ <h4 class="date">2021-04-14</h4>
 <!-- rnb-text-begin -->
 <div id="text" class="section level2">
 <h2>Text</h2>
+<p>Poem by Emily Dickinson</p>
 <!-- rnb-text-end -->
 <!-- rnb-chunk-begin -->
 <!-- rnb-source-begin eyJkYXRhIjoiYGBgclxudGV4dCA8LSBjKFwiQmVjYXVzZSBJIGNvdWxkIG5vdCBzdG9wIGZvciBEZWF0aCAtXCIsXG4gICAgICAgICAgXCJIZSBraW5kbHkgc3RvcHBlZCBmb3IgbWUgLVwiLFxuICAgICAgICAgIFwiVGhlIENhcnJpYWdlIGhlbGQgYnV0IGp1c3QgT3Vyc2VsdmVzIC1cIixcbiAgICAgICAgICBcImFuZCBJbW1vcnRhbGl0eVwiKVxuXG50ZXh0XG5gYGAifQ== -->
@@ -301,8 +302,8 @@ <h2>A tidy table</h2>
 <!-- rnb-chunk-end -->
 <!-- rnb-text-begin -->
 </div>
-<div id="todenization" class="section level2">
-<h2>Todenization</h2>
+<div id="tokenization" class="section level2">
+<h2>Tokenization</h2>
 <!-- rnb-text-end -->
 <!-- rnb-chunk-begin -->
 <!-- rnb-source-begin eyJkYXRhIjoiYGBgclxudGV4dF9kZiAlPiVcbiAgdW5uZXN0X3Rva2Vucyh3b3JkLCB0ZXh0KVxuYGBgIn0= -->
@@ -321,7 +322,7 @@ <h2>Todenization</h2>
 <!-- rnb-text-end -->
 </div>
 
-<div id="rmd-source-code">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</div>
+<div id="rmd-source-code">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</div>
 
 
 

01_textmining.Rmd

@@ -3,7 +3,12 @@ title: "Refamiliarize with Silge"
 author: "John Little"
 date: "`r Sys.Date()`"
 abstract: "SA = algorithmically mapping the emotion or opinion of a text.\n\n"
-output: html_notebook
+output:
+  html_notebook: defult
+  rmdformats::html_clean:
+    highlight: kate
+    lightbox: TRUE
+    thumbnails: TRUE
 ---
 
 Find this repository:  https://github.com/libjohn/workshop_textmining
@@ -19,6 +24,17 @@ library(tidytext)
 library(wordcloud2)
 ```
 
+```{r echo=FALSE}
+htmltools::img(src = knitr::image_uri(here::here("images", "Rfun_logo.png")),
+alt = 'Rfun',
+style = 'position:absolute; bottom:15px; left:0; padding:5px; border:0px;')
+
+htmltools::img(src = knitr::image_uri(here::here("images", "CDVS-logo_sm_Spring2020.png")),
+alt = 'Rfun',
+style = 'position:absolute; bottom:0; right:0; padding:5px; border:0px;')
+```
+
+
 ## Data
 
 We'll look at some books by [Jane Austen](https://en.wikipedia.org/wiki/Jane_Austen), an 18th century novelist. Austen explored women and marriage within the British upper class.  The novelist has a unique and well earned following within literature. Her works is consistently discussed and honored. To this day, Austen's novels are the source of many adaptations, written and on-screen.  Through the `janeaustenr` package we can access and mine the text of six Austen novels.  We can call the collection of novels a corpra.  An individual novel is a corpus.
@@ -116,7 +132,7 @@ bind_rows(get_stopwords(), stopwords_custom)    # The default is "snowball"
 
 ### Calculate word frequency
 
-How many Austen countable words are there if we remove _snowball_ stop-words?  There are `r library(magrittr); matchwords_books %>% distinct(word) %>% nrow()` countable words. 
+How many Austen countable words are there if we remove _snowball_ stop-words?  There are `r   nrow(dplyr::distinct(matchwords_books, word))` countable words. 
 
 ```{r}
 matchwords_books %>% 
@@ -289,7 +305,7 @@ head(get_sentiments("nrc"))
 head(get_sentiments("afinn"))
 
 get_sentiments("nrc") %>% 
-  count(sentiment, sort = TRUE)
+  count(sentiment, sort = TRUE) 
 
 ```
 
@@ -374,8 +390,25 @@ emma_afinn %>%
 - Data Visualization with ggplot2: ([video](https://warpwire.duke.edu/w/80YEAA/) | [workshop](https://rfun.library.duke.edu/portfolio/ggplot_workshop/))
 
 
-## License
+---
+
+```{r include=FALSE}
+library(htmltools)
+tagList(rmarkdown::html_dependency_font_awesome())
+```
+
+<center>
+[John Little](https://johnlittle.info/)  
+[Rfun](https://Rfun.library.duke.edu/)  
+[Center for Data & Visualization Sciences](https://library.duke.edu/data/)
+
+<i class="fab fa-creative-commons fa-2x"></i> &nbsp; <i class="fab fa-creative-commons-by fa-2x"></i><i class="fab fa-creative-commons-nc fa-2x"></i> 
+
+CC BY-NC  
+Creative Commons:  Attribution, Non-commercial  
+https://creativecommons.org/licenses/by-nc/4.0/
+</center>
+
+&nbsp;  
 
-CC BY-NC
-Creative Commons:  Attribution, Non-commercial
-https://creativecommons.org/licenses/by-nc/4.0/
+&nbsp;