我正在尝试清理R中的列名。我正在使用JSON数据集，我使用名为“stream_in”的 jsonlite 函数导入到R.
首先，我尝试了“gsub”命令和“粘贴”命令，但两者都没有用。
我觉得这个问题是这样的：当我使用命令 head 来检查数据时，它会向我读取所有列名，甚至包含“。”的列名。奇怪的是，“空格”，但如果我使用名称命令，它只会读取没有“点”或“空格”的那些。有什么建议？ 我的列名称为
hours.Monday.open attributes.Alcohol
我想删除“。”
我试过这样的事情
姓名（restaurant.data）[3]＆lt; - paste（“HoursMondayOpen”）
但是只删除了第一个“。”之前的单词。并且新列名称为“HoursMondayOpen.Monday.Open”
我也试过
姓名（restaurant.data）＆lt; - gsub（“\。”，“”，姓名（restaurant.data））
但这根本没有改变任何东西，也没有给我一个错误。
这有帮助吗？
这是dput（）
的输出> dput(head(restaurant.data))
structure(list(business_id = c("5UmKMjUEUNdYWqANhGckJw", "UsFtqoBl7naz8AVUBZMjQQ",
"3eu6MEFlq2Dg7bQh8QbdOg", "cE27W9VPgO88Qxe4ol6y_g", "HZdLhv6COCleJMo7nPl-RA",
"mVHrayjG3uZ_RLHkLj-AMg"), FullAddress = c("4734 Lebanon Church Rd\nDravosburg, PA 15034",
"202 McClure St\nDravosburg, PA 15034", "1 Ravine St\nDravosburg, PA 15034",
"1530 Hamilton Rd\nBethel Park, PA 15234", "301 South Hills Village\nPittsburgh, PA 15241",
"414 Hawkins Ave\nrankin, PA 15104"), HoursFridayClose = structure(list(
Friday = structure(list(close = c("21:00", NA, NA, NA, "17:00",
"20:00"), open = c("11:00", NA, NA, NA, "10:00", "10:00")), .Names = c("close",
"open"), row.names = c(NA, 6L), class = "data.frame"), Tuesday = structure(list(
close = c("21:00", NA, NA, NA, "21:00", "19:00"), open = c("11:00",
NA, NA, NA, "10:00", "10:00")), .Names = c("close", "open"
), row.names = c(NA, 6L), class = "data.frame"), Thursday = structure(list(
close = c("21:00", NA, NA, NA, "17:00", "19:00"), open = c("11:00",
NA, NA, NA, "10:00", "10:00")), .Names = c("close", "open"
), row.names = c(NA, 6L), class = "data.frame"), Wednesday = structure(list(
close = c("21:00", NA, NA, NA, "21:00", "19:00"), open = c("11:00",
NA, NA, NA, "10:00", "10:00")), .Names = c("close", "open"
), row.names = c(NA, 6L), class = "data.frame"), Monday = structure(list(
close = c("21:00", NA, NA, NA, "21:00", NA), open = c("11:00",
NA, NA, NA, "10:00", NA)), .Names = c("close", "open"
), row.names = c(NA, 6L), class = "data.frame"), Sunday = structure(list(
close = c(NA, NA, NA, NA, "18:00", NA), open = c(NA,
NA, NA, NA, "11:00", NA)), .Names = c("close", "open"
), row.names = c(NA, 6L), class = "data.frame"), Saturday = structure(list(
close = c(NA, NA, NA, NA, "21:00", "16:00"), open = c(NA,
NA, NA, NA, "10:00", "10:00")), .Names = c("close", "open"
), row.names = c(NA, 6L), class = "data.frame")), .Names = c("Friday",
"Tuesday", "Thursday", "Wednesday", "Monday", "Sunday", "Saturday"
), row.names = c(NA, 6L), class = "data.frame"), open = c(TRUE,
TRUE, TRUE, FALSE, TRUE, TRUE), categories = list(c("Fast Food",
"Restaurants"), "Nightlife", c("Auto Repair", "Automotive"),
c("Active Life", "Mini Golf", "Golf"), c("Shopping", "Home Services",
"Internet Service Providers", "Mobile Phones", "Professional Services",
"Electronics"), c("Bars", "American (New)", "Nightlife",
"Lounges", "Restaurants")), city = c("Dravosburg", "Dravosburg",
"Dravosburg", "Bethel Park", "Pittsburgh", "rankin"), review_count = c(4L,
4L, 3L, 5L, 5L, 20L), name = c("Mr Hoagie", "Clancy's Pub", "Joe Cislo's Auto",
"Cool Springs Golf Center", "Verizon", "Emil's Lounge"), neighborhoods = list(
character(0), character(0), character(0), character(0), character(0),
character(0)), longitude = c(-79.9007057, -79.8868138, -79.889059,
-80.0146597, -80.05998, -79.8802474), state = c("PA", "PA", "PA",
"PA", "PA", "PA"), stars = c(4.5, 3.5, 5, 2.5, 2.5, 5), latitude = c(40.3543266,
40.3505527, 40.3509559, 40.3541155, 40.35762, 40.4134643), attributes = structure(list(
`Take-out` = c(TRUE, NA, NA, NA, NA, TRUE), `Drive-Thru` = c(FALSE,
NA, NA, NA, NA, NA), `Good For` = structure(list(dessert = c(FALSE,
NA, NA, NA, NA, FALSE), latenight = c(FALSE, NA, NA, NA,
NA, FALSE), lunch = c(FALSE, NA, NA, NA, NA, TRUE), dinner = c(FALSE,
NA, NA, NA, NA, FALSE), brunch = c(FALSE, NA, NA, NA, NA,
FALSE), breakfast = c(FALSE, NA, NA, NA, NA, FALSE)), .Names = c("dessert",
"latenight", "lunch", "dinner", "brunch", "breakfast"), row.names = c(NA,
6L), class = "data.frame"), Caters = c(FALSE, NA, NA, NA,
NA, TRUE), `Noise Level` = c("average", NA, NA, NA, NA, "average"
), `Takes Reservations` = c(FALSE, NA, NA, NA, NA, FALSE),
Delivery = c(FALSE, NA, NA, NA, NA, FALSE), Ambience = structure(list(
romantic = c(FALSE, NA, NA, NA, NA, FALSE), intimate = c(FALSE,
NA, NA, NA, NA, FALSE), classy = c(FALSE, NA, NA, NA,
NA, FALSE), hipster = c(FALSE, NA, NA, NA, NA, FALSE),
divey = c(FALSE, NA, NA, NA, NA, FALSE), touristy = c(FALSE,
NA, NA, NA, NA, FALSE), trendy = c(FALSE, NA, NA, NA,
NA, FALSE), upscale = c(FALSE, NA, NA, NA, NA, FALSE),
casual = c(FALSE, NA, NA, NA, NA, FALSE)), .Names = c("romantic",
"intimate", "classy", "hipster", "divey", "touristy", "trendy",
"upscale", "casual"), row.names = c(NA, 6L), class = "data.frame"),
Parking = structure(list(garage = c(FALSE, NA, NA, NA, FALSE,
FALSE), street = c(FALSE, NA, NA, NA, FALSE, FALSE), validated = c(FALSE,
NA, NA, NA, FALSE, FALSE), lot = c(FALSE, NA, NA, NA, FALSE,
FALSE), valet = c(FALSE, NA, NA, NA, FALSE, FALSE)), .Names = c("garage",
"street", "validated", "lot", "valet"), row.names = c(NA,
6L), class = "data.frame"), `Has TV` = c(FALSE, NA, NA, NA,
NA, TRUE), `Outdoor Seating` = c(FALSE, FALSE, NA, NA, NA,
FALSE), Attire = c("casual", NA, NA, NA, NA, "casual"), Alcohol = c("none",
NA, NA, NA, NA, "full_bar"), `Waiter Service` = c(FALSE,
NA, NA, NA, NA, TRUE), `Accepts Credit Cards` = c(TRUE, TRUE,
NA, NA, FALSE, TRUE), `Good for Kids` = c(TRUE, NA, NA, TRUE,
NA, TRUE), `Good For Groups` = c(TRUE, TRUE, NA, NA, NA,
TRUE), `Price Range` = c(1L, 1L, NA, NA, 2L, 1L), `Happy Hour` = c(NA,
TRUE, NA, NA, NA, FALSE), `Good For Dancing` = c(NA, NA,
NA, NA, NA, FALSE), `Coat Check` = c(NA, NA, NA, NA, NA,
FALSE), Smoking = c(NA, NA, NA, NA, NA, "no"), `Wi-Fi` = c(NA,
NA, NA, NA, NA, "no"), Music = structure(list(dj = c(NA,
NA, NA, NA, NA, FALSE), background_music = c(NA, NA, NA,
NA, NA, NA), jukebox = c(NA, NA, NA, NA, NA, NA), live = c(NA,
NA, NA, NA, NA, NA), video = c(NA, NA, NA, NA, NA, NA), karaoke = c(NA,
NA, NA, NA, NA, NA)), .Names = c("dj", "background_music",
"jukebox", "live", "video", "karaoke"), row.names = c(NA,
6L), class = "data.frame"), `Wheelchair Accessible` = c(NA,
NA, NA, NA, NA, NA), `Dogs Allowed` = c(NA, NA, NA, NA, NA,
NA), BYOB = c(NA, NA, NA, NA, NA, NA), Corkage = c(NA, NA,
NA, NA, NA, NA), `BYOB/Corkage` = c(NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_
), `Order at Counter` = c(NA, NA, NA, NA, NA, NA), `By Appointment Only` = c(NA,
NA, NA, NA, NA, NA), `Open 24 Hours` = c(NA, NA, NA, NA,
NA, NA), `Hair Types Specialized In` = structure(list(coloring = c(NA,
NA, NA, NA, NA, NA), africanamerican = c(NA, NA, NA, NA,
NA, NA), curly = c(NA, NA, NA, NA, NA, NA), perms = c(NA,
NA, NA, NA, NA, NA), kids = c(NA, NA, NA, NA, NA, NA), extensions = c(NA,
NA, NA, NA, NA, NA), asian = c(NA, NA, NA, NA, NA, NA), straightperms = c(NA,
NA, NA, NA, NA, NA)), .Names = c("coloring", "africanamerican",
"curly", "perms", "kids", "extensions", "asian", "straightperms"
), row.names = c(NA, 6L), class = "data.frame"), `Accepts Insurance` = c(NA,
NA, NA, NA, NA, NA), `Ages Allowed` = c(NA_character_, NA_character_,
NA_character_, NA_character_, NA_character_, NA_character_
), `Dietary Restrictions` = structure(list(`dairy-free` = c(NA,
NA, NA, NA, NA, NA), `gluten-free` = c(NA, NA, NA, NA, NA,
NA), vegan = c(NA, NA, NA, NA, NA, NA), kosher = c(NA, NA,
NA, NA, NA, NA), halal = c(NA, NA, NA, NA, NA, NA), `soy-free` = c(NA,
NA, NA, NA, NA, NA), vegetarian = c(NA, NA, NA, NA, NA, NA
)), .Names = c("dairy-free", "gluten-free", "vegan", "kosher",
"halal", "soy-free", "vegetarian"), row.names = c(NA, 6L), class = "data.frame")), .Names = c("Take-out",
"Drive-Thru", "Good For", "Caters", "Noise Level", "Takes Reservations",
"Delivery", "Ambience", "Parking", "Has TV", "Outdoor Seating",
"Attire", "Alcohol", "Waiter Service", "Accepts Credit Cards",
"Good for Kids", "Good For Groups", "Price Range", "Happy Hour",
"Good For Dancing", "Coat Check", "Smoking", "Wi-Fi", "Music",
"Wheelchair Accessible", "Dogs Allowed", "BYOB", "Corkage", "BYOB/Corkage",
"Order at Counter", "By Appointment Only", "Open 24 Hours", "Hair Types Specialized In",
"Accepts Insurance", "Ages Allowed", "Dietary Restrictions"), row.names = c(NA,
6L), class = "data.frame"), type = c("business", "business",
"business", "business", "business", "business")), .Names = c("business_id",
"FullAddress", "HoursFridayClose", "open", "categories", "city",
"review_count", "name", "neighborhoods", "longitude", "state",
"stars", "latitude", "attributes", "type"), row.names = c(NA,
6L), class = "data.frame")
>
所有这一切都在它的所有荣耀中！
答案 0 :(得分：0)
您的数据非常令人费解（我会说凌乱......）因为您有一个data.frame，其中某些列又是data.frame，其列再次为data.frame＆＃39 ; s ...也有些列只是列表中包含不同长度的元素（即列"neighborhoods"和"categories"）
所以，我会尽可能使用这个自定义函数展平：
poormansUnnest <- function(nestedDF){
toBind <- list()
for(col in names(nestedDF)){
if(is.data.frame(nestedDF[[col]])){
df <- poormansUnnest(nestedDF[[col]])
names(df) <- paste0(col,'.',names(df))
toBind[[length(toBind)+1]] <- df
}else{
toBind[[length(toBind)+1]] <- nestedDF[col]
}
}
final <- do.call(cbind.data.frame,toBind)
return(final)
}
res <- poormansUnnest(restaurant.data)
# store list columns in separate object (then you would do whatever you need with them...)
categories <- res$categories
neighborhoods<- res$neighborhoods
# remove the list columns from the data.frame
res$categories <- NULL
res$neighborhoods <- NULL
现在，您应该可以使用res重命名gsub的列