Changes to data_medstar_epcr_02_variable_management.Rmd

- Part of #27
- Replaced spaces with underscores in address street name.
- Deleted data_medstar_epcr_02_variable_management.nb.html. It's unnecissary and just takes up extra space.
- Saved medstar_epcr_02_variable_management.rds as RDS instead of Feather. It doesn't seem like Feather ever really caught on.

.gitignore

@@ -12,3 +12,5 @@ markdown/pairs_possible_matches.rds
 markdown/rpairs_epiwt.rds
 
 markdown/rpairs_jar.rds
+
+NOTES.txt

markdown/data_medstar_epcr_02_variable_management.Rmd

@@ -1,11 +1,6 @@
 ---
 title: "Manage Variables in MedStar EPCR Data"
 date: "Created: 2018-12-26 <br> Updated: `r Sys.Date()`"
-output: 
-  html_notebook:
-    toc: true
-    toc_float: true
-    css: custom-css.css
 ---
 
 # Overview
@@ -24,28 +19,21 @@ Sys.setenv(TZ = "US/Central")
 
 ```{r message=FALSE}
 library(tidyverse)
-library(bfuncs)
 ```
 
 medstar_epcr.feather was created in data_medstar_epcr_01_import.Rmd
 
-```{r}
-medstar_epcr <- feather::read_feather("/Volumes/sph_research/DETECT/one_year_data/medstar_epcr_01_import.feather")
+```{bash}
+open 'smb://uctnascifs.uthouston.edu/sph_research/DETECT'
 ```
 
 ```{r}
-about_data(medstar_epcr) # 35,557 observations and 32 variables
+medstar_epcr <- feather::read_feather("/Volumes/DETECT/one_year_data/medstar_epcr_01_import.feather")
 ```
 
-[top](#top)
-
-
-
-
-
-
-
-
+```{r}
+dim(medstar_epcr) # 35,557    32
+```
 
 
 # Standardize character strings
@@ -72,14 +60,6 @@ rm(vars)
 [top](#top)
 
 
-
-
-
-
-
-
-
-
 # Remove "city of" from address_city value 
 
 ```{r}
@@ -90,14 +70,6 @@ medstar_epcr <- medstar_epcr %>%
 [top](#top)
 
 
-
-
-
-
-
-
-
-
 # Separate names, dob's, and street addresses
 
 * Some names have three parts (e.g., Mary Jo Blake). Here, we split up full name into first name and last name. For now, we ignore middle name(s). We may need to change this later.
@@ -119,19 +91,18 @@ medstar_epcr <- medstar_epcr %>%
   )
 ```
 
+Replaces spaces with underscores in address street name.
+
 ```{r}
-about_data(medstar_epcr) # 35,557 observations and 39 variables
+medstar_epcr <- medstar_epcr %>% 
+  mutate(
+    address_street_name = stringr::str_replace_all(address_street_name, "\\s", "_")
+  )
 ```
 
-[top](#top)
-
-
-
-
-
-
-
-
+```{r}
+dim(medstar_epcr) # 35,557    39
+```
 
 
 # Recode categories
@@ -158,9 +129,7 @@ medstar_epcr <- medstar_epcr %>%
   ) %>% 
   mutate_at(
     vars(starts_with("detect")),
-    funs(
-      if_else(. == "N/A", NA_character_, .)
-    )
+    ~ if_else(. == "N/A", NA_character_, .)
   )
 ```
 
@@ -185,19 +154,9 @@ medstar_epcr <- medstar_epcr %>%
 ```
 
 ```{r}
-about_data(medstar_epcr) # 35,557 observations and 40 variables
+dim(medstar_epcr) # 35,557    40
 ```
 
-[top](#top)
-
-
-
-
-
-
-
-
-
 
 # Create indicator for completed DETECT screening
 
@@ -216,19 +175,9 @@ medstar_epcr <- medstar_epcr %>%
 ```
 
 ```{r}
-about_data(medstar_epcr) # 35,557 observations and 56 variables
+dim(medstar_epcr) # 35,557    56
 ```
 
-[top](#top)
-
-
-
-
-
-
-
-
-
 
 # Process numeric variables
 
@@ -240,19 +189,9 @@ medstar_epcr <- medstar_epcr %>%
 ```
 
 ```{r}
-about_data(medstar_epcr) # 35,557 observations and 56 variables
+dim(medstar_epcr) # 35,557    56
 ```
 
-[top](#top)
-
-
-
-
-
-
-
-
-
 
 # Duplicate (almost) rows
 
@@ -282,7 +221,7 @@ medstar_epcr <- medstar_epcr %>%
 ```
 
 ```{r}
-about_data(medstar_epcr) # 35,557 observations and 57 variables
+dim(medstar_epcr) # 35,557    57
 ```
 
 How many pairs of duplicate pcr numbers are there?
@@ -302,14 +241,14 @@ For each of those pcr numbers, if the only thing that differs between the two ro
 So, for each variable of interest, create a dummy variable that indicates if if values are different within incident pcr number
 
 ```{r}
-medstar_epcr <- medstar_epcr %>% 
+medstar_epcr <- medstar_epcr %>%
   mutate_at(
     .vars = vars(
       arrival_time, response_num, incident_pcr, incident_complaint, age, 
       name_full, dob, address_street, address_city, address_state,
       address_zip, gender, race, symptoms, crew_sig, disposition
     ),
-    .funs = funs(diff = as.numeric(length(unique(.)) > 1))
+    .funs = list(diff = ~ as.numeric(length(unique(.)) > 1))
   ) %>% 
   ungroup()
 ```
@@ -325,8 +264,8 @@ medstar_epcr <- medstar_epcr %>%
 
 ```{r}
 # Data checking
-# medstar_epcr %>% 
-#   filter(pcr_dup) %>% 
+# medstar_epcr %>%
+#   filter(pcr_dup) %>%
 #   select(incident_pcr, pcr_dup, ends_with("_diff"), aps_report, answered_count, diff_count)
 ```
 
@@ -365,7 +304,7 @@ medstar_epcr <- medstar_epcr %>%
 ```
 
 ```{r}
-about_data(medstar_epcr) # 35,556 observations and 58 variables
+dim(medstar_epcr) # 35,556    58
 ```
 
 
@@ -389,7 +328,7 @@ medstar_epcr <- medstar_epcr %>%
 ```
 
 ```{r}
-about_data(medstar_epcr) # 35,555 observations and 58 variables
+dim(medstar_epcr) # 35,555    58
 ```
 
 
@@ -449,39 +388,19 @@ medstar_epcr <- medstar_epcr %>%
 ```
 
 ```{r}
-about_data(medstar_epcr) # 28,228 observations and 56 variables
+dim(medstar_epcr) # 28,228    56
 ```
 
-[top](#top)
-
-
-
-
-
-
-
-
-
 
 # Save data
 
 ```{r}
-feather::write_feather(
+readr::write_rds(
   medstar_epcr, 
-  "/Volumes/sph_research/Detect/one_year_data/medstar_epcr_02_variable_management.feather"
+  "/Volumes/DETECT/one_year_data/medstar_epcr_02_variable_management.rds"
 )
 ```
 
-[top](#top)
-
-
-
-
-
-
-
-
-
 
 # Session information