I have a data.frame (df) which contains another data.frame called url_variables.
url_variables = df$url_variables
url_variables contains many other data.frames such as source, campaign, page and many others. Each of these data frames has the 3 columns key, value and type. I'm using bind_cols to combine all the individual data frames into one flat data frame.
flat_url_variables = bind_cols(as.list(url_variables))
The problem is the column names for flat_url_variables are the non-descriptive key, value, type, key, value, type etc. How can I name the columns of flat_url_variables from the name of each individual url variable data.frame (source_key, source_value, source_type, campaign_key etc)?
EDIT
Here is a small sample of url_variables
as an image:
Here is the output of dput(head(url_variables))
:
structure(list(`_privatedomain` = structure(list(key = c("_privatedomain",
"_privatedomain", "_privatedomain", "_privatedomain", "_privatedomain",
"_privatedomain"), value = c("t", "t", "t", "t", "t", "t"), type = c("url",
"url", "url", "url", "url", "url")), .Names = c("key", "value",
"type"), row.names = c(NA, 6L), class = "data.frame"), p = structure(list(
key = c("p", NA, NA, "p", "p", "p"), value = c("2", NA, NA,
"2", "2", "2"), type = c("url", NA, NA, "url", "url", "url"
)), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), s = structure(list(key = c("s", NA,
NA, "s", "s", "s"), value = c("incomplete", NA, NA, "incomplete",
"incomplete", "incomplete"), type = c("url", NA, NA, "url", "url",
"url")), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), first_name = structure(list(key = c("first_name",
NA, NA, "first_name", "first_name", "first_name"), value = c("Allan",
NA, NA, "james", "Sheryl", "Yara"), type = c("url", NA, NA,
"url", "url", "url")), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), last_name = structure(list(key = c("last_name",
NA, NA, "last_name", "last_name", "last_name"), value = c("Smith",
NA, NA, "jones", "Smith", "Keating"), type = c("url", NA,
NA, "url", "url", "url")), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), email = structure(list(key = c("email",
NA, NA, "email", "email", "email"), value = c("[email protected]",
NA, NA, "[email protected]", "sheryl@email", "[email protected]"
), type = c("url", NA, NA, "url", "url", "url")), .Names = c("key",
"value", "type"), row.names = c(NA, 6L), class = "data.frame"),
phone_number = structure(list(key = c("phone_number", NA,
NA, "phone_number", "phone_number", "phone_number"), value = c("0401234567",
NA, NA, "0401234567", "0401234567", "0401234567"), type = c("url",
NA, NA, "url", "url", "url")), .Names = c("key", "value",
"type"), row.names = c(NA, 6L), class = "data.frame"), from = structure(list(
key = c("from", NA, NA, "from", "from", "from"), value = c("landing_page",
NA, NA, "landing_page", "landing_page", "landing_page"
), type = c("url", NA, NA, "url", "url", "url")), .Names = c("key",
"value", "type"), row.names = c(NA, 6L), class = "data.frame"),
snc = structure(list(key = c(NA, NA, "snc", NA, NA, NA),
value = c(NA, NA, "1495606827_5925262b571d70.64387871",
NA, NA, NA), type = c(NA, NA, "url", NA, NA, NA)), .Names = c("key",
"value", "type"), row.names = c(NA, 6L), class = "data.frame"),
`__sgtarget` = structure(list(key = c(NA, NA, "__sgtarget",
NA, NA, NA), value = c(NA, NA, "10", NA, NA, NA), type = c(NA,
NA, "url", NA, NA, NA)), .Names = c("key", "value", "type"
), row.names = c(NA, 6L), class = "data.frame"), customertime = structure(list(
key = c(NA_character_, NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_), value = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_), type = c(NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_
)), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), sotime = structure(list(key = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_), value = c(NA_character_, NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_), type = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_)), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), cancelreschedulelink = structure(list(
key = c(NA_character_, NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_), value = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_), type = c(NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_
)), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), params = structure(list(key = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_), value = c(NA_character_, NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_), type = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_)), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), icslink = structure(list(key = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_), value = c(NA_character_, NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_), type = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_)), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame"), type = structure(list(key = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_), value = c(NA_character_, NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_), type = c(NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_,
NA_character_)), .Names = c("key", "value", "type"), row.names = c(NA,
6L), class = "data.frame")), .Names = c("_privatedomain",
"p", "s", "first_name", "last_name", "email", "phone_number",
"from", "snc", "__sgtarget", "customertime", "sotime", "cancelreschedulelink",
"params", "icslink", "type"), row.names = c(NA, 6L), class = "data.frame")
The most straightforward way if probably to just set the names yourself. Here, I am using lapply
to move through each column of url_variables
, setting the names directly, then binding the results:
flat <-
names(url_variables) %>%
lapply(function(thisVar){
url_variables[[thisVar]] %>%
setNames(paste0(thisVar, "_", names(.)))
}) %>%
bind_cols()
We can see part of the result as flat[ , 1:6]
gives:
_privatedomain_key _privatedomain_value _privatedomain_type p_key p_value p_type
1 _privatedomain t url p 2 url
2 _privatedomain t url <NA> <NA> <NA>
3 _privatedomain t url <NA> <NA> <NA>
4 _privatedomain t url p 2 url
5 _privatedomain t url p 2 url
6 _privatedomain t url p 2 url
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With