Question

我尝试使用R。

从此站点创建新的子集数据框

#load libraries
library(dplyr)
library(jsonlite)
library(tidyr)

#source file
url = "http://api.us.socrata.com/api/catalog/v1 q=nasa&domains=data.nasa.gov&offset=0&limit=500"

metadata <- fromJSON(url)
#Create a new data frame
nasa_api <- data.frame(id =  metadata$results$resource$id, 
                     title = metadata$results$resource$name,
                     description = metadata$results$resource$description,
                     download_count = metadata$results$resource$download_count,
                     domain_category = metadata$results$classification$domain_category,
                     link = metadata$results$link,
                     permlink = metadata$results$permalink)

我注意到元数据对象包含嵌套列表。我需要为分类创建一个新的数据集，这是一个嵌套在元数据中的数据框。理想情况下，我希望这个新数据框包含＆＃34; id＆＃34;这样我以后就可以加入这两个数据集了。

我认为这将是一项轻松的任务，但我是R的新手。请帮忙吗？

Answer 1

我注意到您的网址存在问题（v1 q=nasa应为v1?q=nasa）。因此，我已经说明了如何使用tidyjson包解决此问题。它可以进行大量的输入，但之后会为您提供一个坚实的整洁的数据框。我推荐来自devtools::install_github('jeremystan/tidyjson')的{{3}} CRAN，其中classification/domain_metadata尚未提供某些功能。

在任何情况下，由于您没有明确表达您感兴趣的嵌套数组，我只选了一个（## devtools::install_github('jeremystan/tidyjson') library(dplyr) library(tidyjson) j <- as.tbl_json("http://api.us.socrata.com/api/catalog/v1?q=nasa&domains=data.nasa.gov&offset=0&limit=500") base <- j %>% enter_object(results) %>% gather_array() nasa_api <- base %>% spread_values(id = jstring(resource, id), title = jstring(resource, name), description = jstring(resource, description), download_count = jstring(resource, download_count), domain_category = jstring(classification, domain_category), link = jstring(link), permlink = jstring(permlink)) print(nasa_api) #> # A tbl_json: 500 x 9 tibble with a "JSON" attribute #> `attr(., "JSON")` document.id array.index id #> <chr> <int> <int> <chr> #> 1 "{\"resource\":{\"d..." 1 1 gvk9-iz74 #> 2 "{\"resource\":{\"d..." 1 2 scmi-np9r #> 3 "{\"resource\":{\"d..." 1 3 gquh-watm #> 4 "{\"resource\":{\"d..." 1 4 dtgb-tk9p #> 5 "{\"resource\":{\"d..." 1 5 j6wr-4xhn #> 6 "{\"resource\":{\"d..." 1 6 357b-ra7j #> 7 "{\"resource\":{\"d..." 1 7 e2ud-kf5m #> 8 "{\"resource\":{\"d..." 1 8 uwnx-gns8 #> 9 "{\"resource\":{\"d..." 1 9 fzmj-dfnj #> 10 "{\"resource\":{\"d..." 1 10 szzb-kefa #> # ... with 490 more rows, and 6 more variables: title <chr>, #> # description <chr>, download_count <chr>, domain_category <chr>, #> # link <chr>, permlink <chr> ## explore the json_types of one of the objects base %>% enter_object("classification") %>% .[1, ] %>% gather_object() %>% json_types() #> # A tbl_json: 5 x 4 tibble with a "JSON" attribute #> `attr(., "JSON")` document.id array.index name #> <chr> <int> <int> <chr> #> 1 [] 1 1 categories #> 2 [] 1 1 tags #> 3 "\"Management/Ope..." 1 1 domain_category #> 4 [] 1 1 domain_tags #> 5 "[{\"value\":\"\",\"k..." 1 1 domain_metadata #> # ... with 1 more variables: type <fctr> ## example of an ancillary table base %>% spread_values(id = jstring(resource, id)) %>% enter_object("classification") %>% enter_object("domain_metadata") %>% gather_array("domain_metadata_id") %>% spread_values(key = jstring(key), value = jstring(value)) %>% select(document.id, array.index, id, key, value) %>% as_data_frame() #> # A tibble: 6,343 x 5 #> document.id array.index id key #> * <int> <int> <chr> <chr> #> 1 1 1 gvk9-iz74 Common-Core_Contact-Email #> 2 1 1 gvk9-iz74 Common-Core_License #> 3 1 1 gvk9-iz74 Common-Core_System-of-Records #> 4 1 1 gvk9-iz74 Common-Core_Program-Code #> 5 1 1 gvk9-iz74 Common-Core_Described-By #> 6 1 1 gvk9-iz74 Common-Core_Public-Access-Level #> 7 1 1 gvk9-iz74 Common-Core_Temporal-Applicability #> 8 1 1 gvk9-iz74 Common-Core_Is-Quality-Data #> 9 1 1 gvk9-iz74 Common-Core_Language #> 10 1 1 gvk9-iz74 Common-Core_References #> # ... with 6,333 more rows, and 1 more variables: value <chr>）。

void signal_handler_wrapper(int x)
{
   myclass::my_handler(x);
}

将API JSON格式转换为数据框

1 个答案: