USP Drug Classification data dictionary + tidying

.gitignore

@@ -97,3 +97,4 @@ ENV/
 # Mac OS files
 .DS_Store
 .Rproj.user
+

R/README.md

@@ -0,0 +1,10 @@
+## R
+
+All R scripts and notebooks are here! Organizational structure:
+
+- `analysis-vis`: Analyses and visualizations
+- `apps`: Shiny app files (subfolder for each)
+- `d4ddrugspending`: Anything that could be put in an R package - for example, functions to join specific datasets in our project
+- `datawrangling`: Dataset-specific scripts to collect and clean
+
+Note that data.world has an [R client](https://github.com/datadotworld/data.world-r)! This makes it easy to import data directly from our repo there.

R/analysis-vis/README.md

@@ -0,0 +1,5 @@
+## analysis-vis
+
+Analysis and visualization scripts/Rmd files.
+
+Note that data.world has a [R client](https://github.com/datadotworld/data.world-r)! Great for importing datasets directly from our repo there.

explore_drugspending.Rmd → R/analysis-vis/explore_drugspending.Rmd

@@ -16,9 +16,6 @@ library(jsonlite)
 
 ```{r load_spending_data}
 ## -- Spending data --------------------------------------------------------------------------------
-## Read in drug names (brand + generic)
-drugnames <- read_feather('data/drugnames.feather')
-
 ## Function to add a column with spending year to a data frame
 add_drug_year <- function(df, yr){
   mutate(df, drug_year = yr)
@@ -27,9 +24,8 @@ add_drug_year <- function(df, yr){
 drug.years <- 2011:2015
 
 ## Read in each year's data set, add year and drug names, and combine into a single data.frame
-spending.data <- map(paste0('data/spending-', drug.years, '.feather'), read_feather) %>%
+spending.data <- map(paste0('dataworld/spending-', drug.years, '.feather'), read_feather) %>%
   map2(drug.years, add_drug_year) %>%
-  map(bind_cols, drugnames) %>%
   bind_rows()
 
 ```
@@ -39,6 +35,24 @@ head(spending.data)
 
 ```
 
+```{r load_atc}
+atc.data <- read.csv('dataworld/atc-codes.csv')
+head(atc.data)
+```
+
+```{r check_drug_uses}
+matt.drug.uses <- read_feather('dataworld/drug_uses.feather')
+
+matt.drug.uses
+
+```
+
+```{r dig}
+length(intersect())
+
+```
+
+
 ```{r combine_generics}
 ## -- Combine data by year for all brand names for the same generic --------------------------------
 spending.data.bygeneric <- spending.data %>%
@@ -95,6 +109,18 @@ head(therapeutic.areas)
 
 ```
 
+# Try to merge therapeutic classes with drug names
+```{r join_class_names}
+library(fuzzyjoin)
+
+## Need to extract generic names from name column
+
+# ## -- Separate generic and brand names in therapeutic.areas ----------------------------------------
+# therapeutic.areas <- therapeutic.areas %>%
+#   separate(name, into = c('brand', 'generic'), sep = ' \\(', remove = FALSE, fill = )
+
+```
+
 # Out-of-pocket cost over time for low-income vs non-low-income users of aripiprazole (Aricept)
 ```{r plot_aripiprazole}
 plotdata <- spending.data.bygeneric %>%

R/apps/README.md

@@ -0,0 +1,5 @@
+## apps
+
+Scripts for R Shiny apps. Store each app in a separate subdirectory.
+
+Note that data.world has a [R client](https://github.com/datadotworld/data.world-r)! Great for importing datasets directly from our repo there.