2
我已經從google_reverse_code API下載地址列表，但是獲取經緯度信息的地方列表，因爲我在R中很新。我不知道如何提取有用的信息。所有下載數據庫的代碼都在問題的底部。從R嵌套列表中提取數據
列表的結構一般是這樣的。
`$ 60 :List of 1
..$ results:'data.frame': 1 obs. of 5 variables:
.. ..$ address_components:List of 1
.. .. ..$ :'data.frame': 8 obs. of 3 variables:
.. .. .. ..$ long_name : chr [1:8] "119" "Avenida Diego Díaz de Berlanga"
"Jardines de Anahuac 2do Sector" "San Nicolás de los Garza" ...
.. .. .. ..$ short_name: chr [1:8] "119" "Avenida Diego Díaz de Berlanga"
"Jardines de Anahuac 2do Sector" "San Nicolás de los Garza" ...
.. .. .. ..$ types :List of 8
.. .. .. .. ..$ : chr "street_number"
.. .. .. .. ..$ : chr "route"
.. .. .. .. ..$ : chr [1:3] "political" "sublocality" "sublocality_level_1"
.. .. .. .. ..$ : chr [1:2] "locality" "political"
.. .. .. .. ..$ : chr [1:2] "administrative_area_level_2" "political"
.. .. .. .. ..$ : chr [1:2] "administrative_area_level_1" "political"
.. .. .. .. ..$ : chr [1:2] "country" "political"
.. .. .. .. ..$ : chr "postal_code"
.. ..$ formatted_address : chr "Avenida Diego Díaz de Berlanga 119, Jardines
de Anahuac 2do Sector, 66444 San Nicolás de los Garza, N.L., Mexico"
.. ..$ geometry :'data.frame': 1 obs. of 3 variables:
.. .. ..$ location :'data.frame': 1 obs. of 2 variables:
.. .. .. ..$ lat: num 25.7
.. .. .. ..$ lng: num -100
.. .. ..$ location_type: chr "ROOFTOP"
.. .. ..$ viewport :'data.frame': 1 obs. of 2 variables:
.. .. .. ..$ northeast:'data.frame': 1 obs. of 2 variables:
.. .. .. .. ..$ lat: num 25.7
.. .. .. .. ..$ lng: num -100
.. .. .. ..$ southwest:'data.frame': 1 obs. of 2 variables:
.. .. .. .. ..$ lat: num 25.7
.. .. .. .. ..$ lng: num -100
.. ..$ place_id : chr "ChIJRY_wPdqUYoYRTJetT6AJETA"
.. ..$ types :List of 1
.. .. ..$ : chr "street_address"
我需要這些信息作爲數據框來執行我的分析。該信息具體爲C（緯度，經度，的formatted_address，place_id）
我寫的代碼是這樣的：
prueba <- sapply(direccion1, function(x){
uno <- unlist(x[[1]])
})
pureba2 < - data.frame（prueba）
我得到的以下錯誤：Error in (function (..., row.names = NULL, check.rows = FALSE, check.names = TRUE, : arguments imply differing number of rows: 40, 32, 37, 44, 36, 0, 41, 28, 39, 47, 43, 35, 48 其他代碼不起作用。
用於下載包含經度和緯度的數據的代碼如下。
# CRE FILES
library(easypackages)
my_packages <- c("ggmap","maps","mapdata","rlist","readr", "tidyverse",
"lubridate", "stringr", "rebus", "stringi", "purrr", "geosphere", "XML",
"RCurl", "xml2")
libraries(my_packages)
# Set link to website
link1 <-
("https://publicacionexterna.azurewebsites.net/publicaciones/prices")
# Get data from webpage
data_prices <- getURL(link1)
# Parse XML data
xmlfile <- xmlParse(data_prices)
# Get place nodes
places <- getNodeSet(xmlfile, "//place")
# Get values for each place
values <- lapply(places, function(x){
# Get current place id
p_id <- xmlAttrs(x)
# Get values for each gas type for current place
newrows <- lapply(xmlChildren(x), function(y){
# Get type and update time
attrs <- xmlAttrs(y)
# Get price value
price <- xmlValue(y)
names(price) <- "price"
# Return values
return(c(p_id, attrs, price)
)
})
# Combine rows to single list
newrows <- do.call(rbind, newrows)
# Return rows
return(newrows)
})
# Combine all values into a single dataframe
datosDePrecios <- as.data.frame(do.call(rbind, values), stringsAsFactors =
FALSE)
# Re-set row names for dataframe
row.names(datosDePrecios) <- c(1:nrow(datosDePrecios))
# Set link to website to the places file
link2 <-
("https://publicacionexterna.azurewebsites.net/publicaciones/places")
data_places <- read_xml(link2)
datos_id <- data_places %>%
xml_find_all("//place") %>%
xml_attr("place_id")
datos_name <- data_places %>%
xml_find_all("//name") %>%
xml_text("name")
datos_brand <- data_places %>%
xml_find_all("//brand") %>%
xml_text("brand")
datos_cre_id <- data_places %>%
xml_find_all("//cre_id") %>%
xml_text("cre_id")
datos_category <- data_places %>%
xml_find_all("//category") %>%
xml_text("category")
datos_adress_street <- data_places %>%
xml_find_all("//address_street") %>%
xml_text("adress_street")
datos_longitud <- data_places %>%
xml_find_all("//x") %>%
xml_text("x")
datos_latitud <- data_places %>%
xml_find_all("//y") %>%
xml_text("y")
datosDeLugares <- data.frame(datos_id, datos_name,
datos_brand, datos_cre_id,
datos_category, datos_adress_street,
datos_latitud, datos_longitud)
colnames(datosDeLugares) <- c("place_id", "name", "brand","cre_id",
"category", "adress_street", "Latitude", "Longitude")
rm(data_prices,places,values,xmlfile,data_places, datos_adress_street,
datos_brand, datos_category, datos_cre_id, datos_id, datos_name,
datos_longitud, datos_latitud)
rm(results, results2)
獲取地址信息的代碼如下。
datosDePrecios <- datosDePrecios %>%
data.frame(datosDePrecios) %>%
mutate(place_id = as.numeric(place_id))
datosDeLugares <- datosDeLugares %>%
data.frame(datosDeLugares) %>%
mutate(place_id = as.numeric(place_id))
baseGeneral <- inner_join(datosDeLugares, datosDePrecios, by = "place_id")
baseGeneral <- baseGeneral %>%
select(Latitude, Longitude, place_id) %>%
mutate(Latitude = as.numeric(as.character(Latitude))) %>%
mutate(Longitude = as.numeric(as.character(Longitude)))
baseGeneral <- baseGeneral[1:100,]
baseGeneral <- apply(baseGeneral,1 ,function(x) {
google_reverse_geocode(location = c(x["Latitude"],x["Longitude"]), key =
key, result_type = "street_address")
})
謝謝你的幫忙。 :)
你可能想嘗試tidyr :: UNNEST（）https://rdrr.io/cran/tidyr/man/unnest.html –
我認爲tidyr只適用於數據框類數據。我擁有的是一個列表。你知道一些使用列表格式工作的方法嗎？謝謝您的回答。 –
您是否可以包含下載該數據的代碼，以便其他人可以複製您擁有的對象？ – moman822