more cleanup

R/datawrangling/atc_codes_cleanup.rmd

@@ -73,29 +73,73 @@ Both the level5 and the kegg columns may contain IDs that can be useful for conn
 
 Technically, the level1-level4 columns contain potentially redundant information, but it may be useful for grouping in the future. 
 
+
 ```{r}
-unique(atc.codes.c$level1)
 atc.codes.c <- atc.codes.c %>% 
- mutate(code = recode(
+ mutate(level5_code = str_sub(level5, 1, 7)) %>%
+ mutate(level5 = str_sub(level5, 9, -1)) %>% 
+ select(level5_code, everything())
+glimpse(atc.codes.c)
+length(unique(atc.codes.c$level5_code))
+nrow(atc.codes.c)
+# a sign that some trimming needs to be done or drugs are used for multiple indications
+atc.codes.c <- atc.codes.c %>% 
+ mutate(level1_code = recode(
  level1,
- "alimentary tract and metabolism" = "a",
- "blood and blood forming organs" = "b",
- "cardiovascular system" = "c",
- "dermatologicals" = "d",
- "genito urinary system and sex hormones" = "g",
- "systemic hormonal preparations, excl. sex hormones and insulins" = "h",
- "antiinfectives for systemic use" = "j",
- "antineoplastic and immunomodulating agents" = "l",
- "musculo-skeletal system" = "m",
- "nervous system" = "n",
- "antiparasitic products, insecticides and repellents" = "p",
- "respiratory system" = "r",
- "sensory organs" = "s",
- "various" = "v"
+ "alimentary tract and metabolism" = "A",
+ "blood and blood forming organs" = "B",
+ "cardiovascular system" = "C",
+ "dermatologicals" = "D",
+ "genito urinary system and sex hormones" = "G",
+ "systemic hormonal preparations, excl. sex hormones and insulins" = "H",
+ "antiinfectives for systemic use" = "J",
+ "antineoplastic and immunomodulating agents" = "L",
+ "musculo-skeletal system" = "M",
+ "nervous system" = "N",
+ "antiparasitic products, insecticides and repellents" = "P",
+ "respiratory system" = "R",
+ "sensory organs" = "S",
+ "various" = "V"
  )
  ) %>% 
- select(level5:kegg, code, everything())
+ select(level5_code:kegg, level1_code, everything())
+glimpse(atc.codes.c)
+unique(atc.codes.c$level1_code)
+# everything is recoded
+```
+
+Now to split off the second level through the fourth level codes and to convert the remaining strings to lowercase:
+
+```{r}
+atc.codes.c <- atc.codes.c %>% 
+ mutate(level2_code = str_sub(level2, 1, 3),
+ level3_code = str_sub(level3, 1, 4),
+ level4_code = str_sub(level4, 1, 5))
 glimpse(atc.codes.c)
-unique(atc.codes.c$code)
+atc.codes.c <- atc.codes.c %>% 
+ mutate(level2 = str_to_lower(str_sub(level2, 5, -1)),
+ level3 = str_to_lower(str_sub(level3, 6, -1)),
+ level4 = str_to_lower(str_sub(level4, 7, -1))) %>% 
+ select(level5_code:level1, level2_code, level2, level3_code, level3, level4_code, level4)
+glimpse(atc.codes.c)
+```
+
+Happy with the structure of it for now. A bit of sanity checking before uploading the cleaned version to data.world:
+
+```{r}
+sapply(atc.codes.c, function(x) length(unique(x)))
+```
+
+Starting at the third level, there are more codes than descriptions. What's going on?
+
+```{r}
+mult.level3 <- atc.codes.c %>% 
+ select(starts_with("level3")) %>% 
+ unique() %>% 
+ group_by(level3) %>% 
+ summarize(tot = n()) %>% 
+ filter(tot > 1)
+test <- atc.codes.c %>% 
+ filter(level3 %in% mult.level3$level3)
 ```