Update vignette, README (+ typo)

Author: juliasilge

R/bind_log_odds.R

@@ -77,7 +77,7 @@
 #' unregularized <- gear_counts %>%
 #'   bind_log_odds(vs, gear, n, uninformative = TRUE, unweighted = TRUE)
 #'
-#' # these logs odd will be farther from zero
+#' # these log odds will be farther from zero
 #' # than the regularized estimates
 #' unregularized
 #'

README.md

@@ -85,19 +85,19 @@ bigram_log_odds <- bigram_counts %>%
 
 bigram_log_odds %>%
   arrange(-log_odds_weighted)
-#> # A tibble: 328,495 x 5
-#>    book                bigram                n alpha log_odds_weighted
-#>    <fct>               <chr>             <int> <int>             <dbl>
-#>  1 Mansfield Park      sir thomas          287   287              28.3
-#>  2 Pride & Prejudice   mr darcy            243   243              27.7
-#>  3 Emma                mr knightley        269   269              27.5
-#>  4 Emma                mrs weston          229   229              25.4
-#>  5 Sense & Sensibility mrs jennings        199   199              25.2
-#>  6 Persuasion          captain wentworth   170   170              25.1
-#>  7 Mansfield Park      miss crawford       215   215              24.5
-#>  8 Persuasion          mr elliot           147   147              23.3
-#>  9 Emma                mr elton            190   190              23.1
-#> 10 Emma                miss woodhouse      162   162              21.3
+#> # A tibble: 328,495 x 4
+#>    book                bigram                n log_odds_weighted
+#>    <fct>               <chr>             <int>             <dbl>
+#>  1 Mansfield Park      sir thomas          287              28.3
+#>  2 Pride & Prejudice   mr darcy            243              27.7
+#>  3 Emma                mr knightley        269              27.5
+#>  4 Emma                mrs weston          229              25.4
+#>  5 Sense & Sensibility mrs jennings        199              25.2
+#>  6 Persuasion          captain wentworth   170              25.1
+#>  7 Mansfield Park      miss crawford       215              24.5
+#>  8 Persuasion          mr elliot           147              23.3
+#>  9 Emma                mr elton            190              23.1
+#> 10 Emma                miss woodhouse      162              21.3
 #> # … with 328,485 more rows
 ```
 

man/bind_log_odds.Rd

@@ -101,12 +101,24 @@ gear_counts <- mtcars %>%
 gear_counts
 ```
 
-Now we can use `bind_log_odds()` to find the weighted log odds for each number of gears and engine shape.
+Now we can use `bind_log_odds()` to find the weighted log odds for each number of gears and engine shape. First, let's use the default empirical Bayes prior. It regularizes the values.
 
 ```{r dependson="gear_counts"}
-gear_counts %>%
+regularized <- gear_counts %>%
   bind_log_odds(vs, gear, n)
+
+regularized
 ```
 
 For engine shape `vs = 0`, having three gears has the highest weighted log odds while for engine shape `vs = 1`, having four gears has the highest weighted log odds. This dataset is small enough that you can look at the count data and see how this is working. 
-More importantly, you can notice that this approach is useful both in the initial motivating example of text data but also more generally whenever you have counts in some kind of groups or sets and you want to find what feature is more likely to come from a group, compared to the other groups.
+
+Now, let's use the uninformative prior, and compare to the unweighted log odds. These log odds will be farther from zero than the regularized estimates.
+
+```{r dependson="gear_counts"}
+unregularized <- gear_counts %>%
+  bind_log_odds(vs, gear, n, uninformative = TRUE, unweighted = TRUE)
+
+unregularized
+```
+
+Most importantly, you can notice that this approach is useful both in the initial motivating example of text data but also more generally whenever you have counts in some kind of groups or sets and you want to find what feature is more likely to come from a group, compared to the other groups.