Download data sets from Eurostat database and put in a standardized format.
get_eurostat_bulk(
id,
cache = TRUE,
update_cache = FALSE,
cache_dir = NULL,
compress_file = TRUE,
stringsAsFactors = TRUE,
select_freq = NULL,
keep_flags = FALSE,
cflags = FALSE,
check_toc = FALSE,
verbose = FALSE,
...
)a code name for the dataset of interest.
See search_eurostat_toc for details how to get an id.
a logical value whether to do caching. Default is TRUE.
a logical value with a default value FALSE, whether to update cache. Can be set also with
options(restatapi_update=TRUE).
a path to a cache directory. The NULL (default) uses the memory as cache.
If the folder cache_dir directory does not exist it saves in the 'restatapi' directory
under the temporary directory from tempdir(). Directory can also be set with
option(restatapi_cache_dir=...).
a logical value whether to compress the
RDS-file in caching. Default is TRUE.
a logical value with the default TRUE. In this case the columns are converted to factors. If FALSE,
the strings are returned as characters.
a character symbol for a time frequency when a dataset has multiple time
frequencies. Possible values are:
A = annual, S = semi-annual, H = half-year, Q = quarterly, M = monthly, W = weekly, D = daily.
The default is NULL as most datasets have only one time frequency.
In case if there are multiple frequencies and select_freq=NULL, then only the most common frequency kept.
If all the frequencies needed the get_eurostat_raw function can be used.
a logical value whether the observation status (flags) - e.g. "confidential",
"provisional", etc. - should be kept in a separate column or if they
can be removed. Default is FALSE. For flag values see:
https://ec.europa.eu/eurostat/api/dissemination/sdmx/2.1/codelist/ESTAT/OBS_STATUS/?compressed=false&format=TSV&lang=en.
a logical value whether the missing observations with flag 'c' - "confidential"
should be kept or not. Default is FALSE, in this case these observations dropped from the dataset. If this parameter
TRUE then all the flags and the suppressed observations with missing values are kept. In this case the parameter provided in keep_flags is set to TRUE.
a logical value whether to check the provided id in the Table of Contents (TOC) or not. The default value
FALSE, in this case the base URL for the download link is retrieved from the configuration file.
If the value is TRUE then the TOC is downloaded and the id is checked in it. If it found there then the download link
is retrieved form the TOC.
a logical value with default FALSE, so detailed messages (for debugging) will not printed.
Can be set also with options(restatapi_verbose=TRUE).
other parameter(s) to pass on the load_cfg function
a data.table with the following columns:
| dimension names | One column for each dimension in the data |
time | A column for the time dimension |
values | A column for numerical values |
flags | A column for flags if the keep_flags=TRUE or cflags=TRUE otherwise this column
is not included in the data table |
The data.table does not include all missing values. The missing values are dropped if both the value and the flag is missing on a particular time.
Data sets are downloaded from the Eurostat bulk download facility in TSV format as in this case smaller file has to be downloaded and processed. If there is more then one frequency then the dataset is filtered for a unique time frequency. If no frequency is selected and there are multiple frequencies in the dataset, then the most common value is used used for frequency.
Compared to the ouptut of the get_eurostat_raw function, the frequency (FREQ) and time format (TIME_FORMAT) columns are not included in the bulk data
and the column names for the time period, observation values and status have standardised names: "time", "values" and "flags"
independently if the data was downloaded previously in SDMX or TSV format.
By default all datasets cached as they are often rather large.
The datasets cached in memory (default) or can be stored in a temporary directory if cache_dir or option(restatpi_cache_dir) is defined.
The cache can be emptied with clean_restatapi_cache.
The id, is a value from the code column of the table of contents (get_eurostat_toc), and can be searched for it with the search_eurostat_toc function. The id value can be retrieved from the Eurostat database
as well. The Eurostat database gives codes in the Data Navigation Tree after every dataset
in parenthesis.
# \donttest{
if (!(grepl("amzn|-aws|-azure ",Sys.info()['release']))) options(timeout=2)
head(get_eurostat_bulk("agr_r_milkpr",keep_flags=TRUE))
#> milkitem dairyprod geo time values flags
#> <fctr> <fctr> <fctr> <fctr> <num> <fctr>
#> 1: PRO D1110A CY 1995 139.0
#> 2: PRO D1110A CY0 1995 139.0
#> 3: PRO D1110A CY00 1995 139.0
#> 4: PRO D1110A EE 1995 706.6
#> 5: PRO D1110A EE0 1995 706.6
#> 6: PRO D1110A EE00 1995 706.6
options(restatapi_update=TRUE)
head(get_eurostat_bulk("avia_par_ee",check_toc=TRUE))
#> There are multiple frequencies in the dataset. The 'M' is selected as it is the most common frequency.
#> unit tra_meas airp_pr time values
#> <fctr> <fctr> <fctr> <fctr> <num>
#> 1: FLIGHT CAF_PAS EE_EETN_BE_EBBR 2005-01 34
#> 2: FLIGHT CAF_PAS EE_EETN_CZ_LKPR 2005-01 85
#> 3: FLIGHT CAF_PAS EE_EETN_DE_EDDB 2005-01 62
#> 4: FLIGHT CAF_PAS EE_EETN_DE_EDDF 2005-01 114
#> 5: FLIGHT CAF_PAS EE_EETN_DE_EDDH 2005-01 26
#> 6: FLIGHT CAF_PAS EE_EETN_DE_EDDT 2005-01 26
head(get_eurostat_bulk("avia_par_ee",select_freq="A",verbose=TRUE))
#>
#> get_eurostat_bulk - API version:2
#> get_eurostat_bulk - class of id, cache, update_cache, cache_dir, compress_file, stringsAsFactors, keep_flags, check_toc, melt, verbose:
#> character - logical -logical - NULL - logical - logical - logical - logical - logical - logical
#>
#> get_eurostat_raw - API version:2
#> get_eurostat_raw - bulk url: https://ec.europa.eu/eurostat/api/dissemination/sdmx/2.1/data/avia_par_ee?format=TSV&compressed=true
#> get_eurostat_raw - class(raw): data.tabledata.frame
#> get_eurostat_raw - caching in raw: FALSE
#> get_eurostat_raw - local filter: FALSE
#> get_eurostat_raw - called from: restatapi::get_eurostat_rawidtxtcacheupdate_cachecache_dircompress_filestringsAsFactorskeep_flagscheck_tocTRUEverbose
#> get_eurostat_raw - get_eurostat_raw in sys.call(): FALSE
#> unit tra_meas airp_pr time values
#> <fctr> <fctr> <fctr> <fctr> <num>
#> 1: FLIGHT CAF_PAS EE_EETN_AT_LOWW 2001 540
#> 2: FLIGHT CAF_PAS EE_EETN_DE_EDDF 2001 415
#> 3: FLIGHT CAF_PAS EE_EETN_DK_EKCH 2001 1829
#> 4: FLIGHT CAF_PAS EE_EETN_FI_EFHK 2001 4464
#> 5: FLIGHT CAF_PAS EE_EETN_LT_EYVI 2001 1083
#> 6: FLIGHT CAF_PAS EE_EETN_RU_UUEE 2001 869
options(restatapi_update=FALSE)
head(get_eurostat_bulk("agr_r_milkpr",cache_dir=tempdir(),compress_file=FALSE,verbose=TRUE))
#>
#> get_eurostat_bulk - API version:2
#> get_eurostat_bulk - class of id, cache, update_cache, cache_dir, compress_file, stringsAsFactors, keep_flags, check_toc, melt, verbose:
#> character - logical -logical - character - logical - logical - logical - logical - logical - logical
#>
#> get_eurostat_raw - API version:2
#> get_eurostat_raw - bulk url: https://ec.europa.eu/eurostat/api/dissemination/sdmx/2.1/data/agr_r_milkpr?format=TSV&compressed=true
#> get_eurostat_raw - class(raw): data.tabledata.frame
#> get_eurostat_raw - caching in raw: FALSE
#> get_eurostat_raw - local filter: FALSE
#> get_eurostat_raw - called from: restatapi::get_eurostat_rawidtxtcacheupdate_cachecache_dircompress_filestringsAsFactorskeep_flagscheck_tocTRUEverbose
#> get_eurostat_raw - get_eurostat_raw in sys.call(): FALSE
#> milkitem dairyprod geo time values
#> <fctr> <fctr> <fctr> <fctr> <num>
#> 1: PRO D1110A CY 1995 139.0
#> 2: PRO D1110A CY0 1995 139.0
#> 3: PRO D1110A CY00 1995 139.0
#> 4: PRO D1110A EE 1995 706.6
#> 5: PRO D1110A EE0 1995 706.6
#> 6: PRO D1110A EE00 1995 706.6
clean_restatapi_cache(cache_dir=tempdir(),verbose=TRUE)
#>
#> clean_restatapi_cache - All objects (outside of 'cfg', 'rav', 'cc' and 'dmethod') are removed from '.restatapi_env'.
#> clean_restatapi_cache - The cache folder /tmp/Rtmp7EeCja/restatapi is empty.
options(timeout=60)
# }