Explore all the economic data from different providers (national and international statistical institutes, central banks, etc.), for free, following the link db.nomics.world
(N.B.: in the examples, data have already been retrieved on april 6th 2020).
ids
First, let's assume that we know which series we want to download. A series identifier (ids
) is defined by three values, formatted like this: provider_code
/dataset_code
/series_code
.
library <- function(...) { suppressWarnings( suppressPackageStartupMessages(base::library(..., quietly = TRUE)) ) }
library(data.table) library(rdbnomics)
reorder_cols <- function(x) { data.table::setDT(x) cols <- c( "provider_code", "dataset_code", "dataset_name", "series_code", "series_name", "original_period", "period", "original_value", "value", "@frequency" ) if ("unit" %in% colnames(x)) { cols <- c(cols, "unit", "Unit") } if ("geo" %in% colnames(x)) { cols <- c(cols, "geo", "Country") } if ("freq" %in% colnames(x)) { cols <- c(cols, "freq", "Frequency") } cols_add <- setdiff(colnames(x), cols) cols <- c(cols, cols_add) cols <- cols[cols %in% colnames(x)] cols <- match(cols, colnames(x)) x[, .SD, .SDcols = cols] } knitr::opts_chunk$set(dev.args = list(bg = "transparent")) display_table <- function(DT) { DT <- head(DT) DT <- as.data.table( lapply(DT, function(x) { if (is.character(x)) { ifelse( nchar(x) > 16, paste0(substr(x, 1, 16), "..."), x ) } else { x } }) ) DT[] }
df <- rdb(ids = "AMECO/ZUTN/EA19.1.0.0.0.ZUTN") df <- df[!is.na(value)]
df <- rdbnomics:::rdbnomics_df001 data.table::setDT(df)
In such data.table
, you will always find at least ten columns:
provider_code
dataset_code
dataset_name
series_code
series_name
original_period
(character string)period
(date of the first day of original_period
)original_value
(character string)value
@frequency
(harmonized frequency generated by DBnomics)The other columns depend on the provider and on the dataset. They always come in pairs (for the code and the name). In the data.frame df
, you have:
unit
(code) and Unit
(name)geo
(code) and Country
(name)freq
(code) and Frequency
(name)df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 0.5, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) legend( "bottomleft", inset = 0.005, legend = sort(unique(df$series_name)), col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
In the event that you only use the argument ids
, you can drop it and run:
df <- rdb("AMECO/ZUTN/EA19.1.0.0.0.ZUTN")
df <- rdb(ids = c("AMECO/ZUTN/EA19.1.0.0.0.ZUTN", "AMECO/ZUTN/DNK.1.0.0.0.ZUTN")) df <- df[!is.na(value)]
df <- rdbnomics:::rdbnomics_df002 data.table::setDT(df)
df <- df[order(series_code, period)] df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 1.7, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "l") points(x2, y2, col = cols[2], pch = PCH) legend( "bottomleft", inset = 0.005, legend = sort(unique(df$series_name)), col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
df <- rdb(ids = c("AMECO/ZUTN/EA19.1.0.0.0.ZUTN", "Eurostat/une_rt_q/Q.SA.Y15-24.PC_ACT.T.EA19")) df <- df[!is.na(value)]
df <- rdbnomics:::rdbnomics_df003 data.table::setDT(df)
df <- df[order(series_code, period)] df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics(legend.text = element_text(size = 7)) i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 legend_text <- sort(unique(df$series_name)) legend_text[2] <- sapply( legend_text[2], function(y) { paste0( paste0( strsplit(y, "active ")[[1]], collapse = "active\n" ), "\n" ) } ) plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 1.5, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "l") points(x2, y2, col = cols[2], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
mask
The code mask notation is a very concise way to select one or many time series at once.
df <- rdb("IMF", "BOP", mask = "A.FR.BCA_BP6_EUR") df <- df[!is.na(value)]
df <- rdbnomics:::rdbnomics_df004 data.table::setDT(df)
df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_step(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "s", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value), max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
In the event that you only use the arguments provider_code
, dataset_code
and mask
, you can drop the name mask
and run:
df <- rdb("IMF", "BOP", "A.FR.BCA_BP6_EUR")
You just have to add a +
between two different values of a dimension.
df <- rdb("IMF", "BOP", mask = "A.FR+ES.BCA_BP6_EUR") df <- df[!is.na(value)]
df <- rdbnomics:::rdbnomics_df005 data.table::setDT(df)
df <- df[order(series_code, period)] df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_step(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "s", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 2*10^4, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "s") points(x2, y2, col = cols[2], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
df <- rdb("IMF", "BOP", mask = "A..BCA_BP6_EUR") df <- df[!is.na(value)] df <- df[order(-period, REF_AREA)] df <- head(df, 100)
df <- rdbnomics:::rdbnomics_df006 data.table::setDT(df)
df <- reorder_cols(df) display_table(df)
df <- rdb("IMF", "BOP", mask = "A.FR.BCA_BP6_EUR+IA_BP6_EUR") df <- df[!is.na(value)] df <- df[order(period), head(.SD, 50), by = INDICATOR]
df <- rdbnomics:::rdbnomics_df007 data.table::setDT(df)
df <- reorder_cols(df) display_table(df)
dimensions
Searching by dimensions
is a less concise way to select time series than using the code mask
, but it works with all the different providers. You have a "Description of series code" at the bottom of each dataset page on the DBnomics website.
df <- rdb("AMECO", "ZUTN", dimensions = list(geo = "ea19")) df <- df[!is.na(value))] # or # df <- rdb("AMECO", "ZUTN", dimensions = '{"geo": ["ea19"]}') # df <- df[!is.na(value))]
df <- rdbnomics:::rdbnomics_df008 data.table::setDT(df)
df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 0.2, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
df <- rdb("AMECO", "ZUTN", dimensions = list(geo = c("ea19", "dnk"))) df <- df[!is.na(value))] # or # df <- rdb("AMECO", "ZUTN", dimensions = '{"geo": ["ea19", "dnk"]}') # df <- df[!is.na(value))]
df <- rdbnomics:::rdbnomics_df009 data.table::setDT(df)
df <- df[order(series_code, period)] df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 1.2, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "l") points(x2, y2, col = cols[2], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
df <- rdb("WB", "DB", dimensions = list(country = c("DZ", "PE"), indicator = c("ENF.CONT.COEN.COST.ZS", "IC.REG.COST.PC.FE.ZS"))) df <- df[!is.na(value))] # or # df <- rdb("WB", "DB", dimensions = '{"country": ["DZ", "PE"], "indicator": ["ENF.CONT.COEN.COST.ZS", "IC.REG.COST.PC.FE.ZS"]}') # df <- df[!is.na(value))]
df <- rdbnomics:::rdbnomics_df010 data.table::setDT(df)
df <- df[order(series_name, period)] df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value i <- 3 x3 <- df[series_name == sort(unique(series_name))[i]]$period y3 <- df[series_name == sort(unique(series_name))[i]]$value i <- 4 x4 <- df[series_name == sort(unique(series_name))[i]]$period y4 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen", "purple") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 7, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "l") points(x2, y2, col = cols[2], pch = PCH) lines(x3, y3, col = cols[3], type = "l") points(x3, y3, col = cols[3], pch = PCH) lines(x4, y4, col = cols[4], type = "l") points(x4, y4, col = cols[4], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
query
The query is a Google-like search that will filter/select time series from a provider's dataset.
df <- rdb("IMF", "WEO:2019-10", query = "France current account balance percent") df <- df[!is.na(value))]
df <- rdbnomics:::rdbnomics_df014 data.table::setDT(df)
df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen", "purple") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 0.5, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
df <- rdb("IMF", "WEO:2019-10", query = "current account balance percent") df <- df[!is.na(value))]
df <- rdbnomics:::rdbnomics_df015 data.table::setDT(df)
df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = `WEO Country`)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # ggtitle("Current account balance (% GDP)") + # dbnomics(legend.direction = "horizontal") i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value i <- 3 x3 <- df[series_name == sort(unique(series_name))[i]]$period y3 <- df[series_name == sort(unique(series_name))[i]]$value i <- 4 x4 <- df[series_name == sort(unique(series_name))[i]]$period y4 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen", "purple") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value), max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "l") points(x2, y2, col = cols[2], pch = PCH) lines(x3, y3, col = cols[3], type = "l") points(x3, y3, col = cols[3], pch = PCH) lines(x4, y4, col = cols[4], type = "l") points(x4, y4, col = cols[4], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
When you don't know the codes of the dimensions, provider, dataset or series, you can:
go to the page of a dataset on DBnomics website, for example Doing Business,
select some dimensions by using the input widgets of the left column,
click on "Copy API link" in the menu of the "Download" button,
use the rdb(api_link = ...)
function such as below.
df <- rdb(api_link = "https://api.db.nomics.world/v22/series/WB/DB?dimensions=%7B%22country%22%3A%5B%22FR%22%2C%22IT%22%2C%22ES%22%5D%7D&q=IC.REG.PROC.FE.NO&observations=1&format=json&align_periods=1&offset=0&facets=0") df <- df[!is.na(value))]
df <- rdbnomics:::rdbnomics_df011 data.table::setDT(df)
df <- df[order(period, series_name)] df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_step(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value i <- 3 x3 <- df[series_name == sort(unique(series_name))[i]]$period y3 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 plot( x1, y1, col = cols[1], type = "s", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 1.2, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "s") points(x2, y2, col = cols[2], pch = PCH) lines(x3, y3, col = cols[3], type = "s") points(x3, y3, col = cols[3], pch = PCH) legend( "bottomleft", inset = 0.005, legend = sort(unique(df$series_name)), col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
In the event that you only use the argument api_link
, you can drop the name and run:
df <- rdb("https://api.db.nomics.world/v22/series/WB/DB?dimensions=%7B%22country%22%3A%5B%22FR%22%2C%22IT%22%2C%22ES%22%5D%7D&q=IC.REG.PROC.FE.NO&observations=1&format=json&align_periods=1&offset=0&facets=0")
On the cart page of the DBnomics website, click on "Copy API link" and copy-paste it as an argument of the rdb(api_link = ...)
function. Please note that when you update your cart, you have to copy this link again, because the link itself contains the ids of the series in the cart.
df <- rdb(api_link = "https://api.db.nomics.world/v22/series?observations=1&series_ids=BOE/6008/RPMTDDC,BOE/6231/RPMTBVE") df <- df[!is.na(value))]
df <- rdbnomics:::rdbnomics_df012 data.table::setDT(df)
df[ , series_name := sapply( series_name, function(y) { paste0( paste0( strsplit(y, "institutions' ")[[1]], collapse = "institutions'\n" ), "\n" ) } ) ]
df <- df[order(period, series_name)] df <- reorder_cols(df) display_table(df)
# ggplot(df, aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen") PCH <- 18 plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 4*10^3, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "l") points(x2, y2, col = cols[2], pch = PCH) legend( "bottomleft", inset = 0.005, legend = sort(unique(df$series_name)), col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
When fetching series from DBnomics, you need
to give a provider and a dataset before specifying correct dimensions. With
the function rdb_datasets
, you can download the list of the available datasets
for a provider.
For example, to fetch the IMF datasets, you have to use:
rdb_datasets(provider_code = "IMF")
The result is a named list (its name is IMF) with one element which is a
data.table
:
str(rdbnomics:::rdbnomics_df016)
With the same function, if you want to fetch the available datasets for multiple providers, you can give a vector of providers and get a named list.
rdb_datasets(provider_code = c("IMF", "BDF"))
str(rdbnomics:::rdbnomics_df018)
DT <- rdbnomics:::rdbnomics_df018 DT <- sapply(DT, function(y) { paste0(": ", nrow(y)) }) DT <- paste0("Number of datasets for ", names(DT), " ", unname(DT)) cat(DT, sep = "\n")
In the event that you only request the datasets for one provider, if you define
simplify = TRUE
, then the result will be a data.table
not a named list.
rdb_datasets(provider_code = "IMF", simplify = TRUE)
DT <- rdbnomics:::rdbnomics_df017 data.table::setDT(DT) display_table(DT)
The extent of datasets gathered by DBnomics can be
appreciate by using the function with the argument provider_code
set to
NULL
:
options(rdbnomics.progress_bar_datasets = TRUE) rdb_datasets() options(rdbnomics.progress_bar_datasets = FALSE)
DT <- rdbnomics:::rdbnomics_df019 DT <- data.table(Provider = names(DT), `Number of datasets` = sapply(DT, nrow)) DT <- DT[order(Provider)] display_table(DT)
When fetching series from DBnomics, it can be
interesting and especially useful to specify dimensions for a particular
dataset to download only the series you want to analyse. With
the function rdb_dimensions
, you can download these dimensions and their
meanings.
For example, for the dataset WEO:2019-10 of the IMF, you may use:
rdb_dimensions(provider_code = "IMF", dataset_code = "WEO:2019-10")
The result is a nested named list (its names are IMF, WEO:2019-10 and the
dimensions names) with a data.table
at the end of each branch:
DT <- rdbnomics:::rdbnomics_df020 DT <- DT$IMF$`WEO:2019-10` DT <- paste0("Number of dimensions for IMF/WEO:2019-10 : ", length(DT)) cat(DT, sep = "\n")
DT <- rdbnomics:::rdbnomics_df020 DT <- DT$IMF$`WEO:2019-10`[[1]] display_table(DT)
DT <- rdbnomics:::rdbnomics_df020 DT <- DT$IMF$`WEO:2019-10`[[2]] display_table(DT)
DT <- rdbnomics:::rdbnomics_df020 DT <- DT$IMF$`WEO:2019-10`[[3]] display_table(DT)
In the event that you only request the dimensions for one dataset for one
provider, if you define simplify = TRUE
, then the result will be a named list
data.table
not a nested named list.
rdb_dimensions(provider_code = "IMF", dataset_code = "WEO:2019-10", simplify = TRUE)
str(rdbnomics:::rdbnomics_df021)
You can measure the vast extent of datasets gathered by
DBnomics by downloading all the possible
dimensions. To do this, you have to set the arguments
provider_code
and dataset_code
to NULL
.
⚠ It's relatively long to run and heavy to show so we display
the first 100.
options(rdbnomics.progress_bar_datasets = TRUE) rdb_dimensions() options(rdbnomics.progress_bar_datasets = FALSE)
DT <- rdbnomics:::rdbnomics_df022 DT <- DT[order(Provider, Dataset)] DT <- head(DT, 100) display_table(DT) # rdbnomics_df022 %>% # sapply(function(u) { # sapply( # u, # function(x) { # sapply( # x, # function(y) { # nrow(y) # }, # simplify = FALSE # ) %>% # { # data.table(Dimension = names(.), `Number of codes` = unname(.)) # } # }, # simplify = FALSE # ) %>% # rbindlist(idcol = "Dataset") # }, # simplify = FALSE # ) %>% # rbindlist(idcol = "Provider")
You can download the list of series, and especially their codes, of a dataset's
provider by using the function rdb_series
. The result is a nested named list
with a data.table
at the end of each branch. If you define simplify = TRUE
,
then the result will be a data.table
not a nested named list.
For example, for the IMF provider and the dataset WEO:2019-10, the command is (only first 100):
rdb_series(provider_code = "IMF", dataset_code = "WEO:2019-10", simplify = TRUE)
DT <- rdbnomics:::rdbnomics_df023 DT <- head(DT, 100) display_table(DT)
Like the function rdb()
, you can add features to rdb_series()
. You can ask for
the series with specific dimensions
:
rdb_series(provider_code = "IMF", dataset_code = "WEO:2019-10", dimensions = list(`weo-subject` = "NGDP_RPCH"), simplify = TRUE)
or with a query
:
rdb_series(provider_code = "IMF", dataset_code = c("WEO:2019-10", "WEOAGG:2019-10"), query = "NGDP_RPCH")
⚠ We ask the user to use this function parsimoniously because there are a huge amount
of series per dataset. Please only fetch for one dataset if you need it or
visit the website https://db.nomics.world.
For example, for the IMF provider, the number of series is (only first 5):
DT <- rdbnomics:::rdbnomics_df024 DT <- DT[order(-`Number of series`)] DT <- head(DT, 5) display_table(DT)
Could not resolve host
When using the function rdb
, you may come across the following error:
Error in open.connection(con, "rb") : Could not resolve host: api.db.nomics.world
To get round this situation, you have two options:
configure curl to use a specific and authorized proxy.
use the default R internet connection i.e. the Internet Explorer proxy defined in internet2.dll.
In rdbnomics, by default the function curl_fetch_memory
(of the package curl) is used to fetch the data. If a specific proxy must be used, it is possible to define it permanently with the package option rdbnomics.curl_config
or on the fly through the argument curl_config
. Because the object is a named list, its elements are passed to the connection (the curl_handle
object created internally with new_handle()
) with handle_setopt()
before using curl_fetch_memory
.
To see the available parameters, run names(curl_options())
in R or visit the website https://curl.haxx.se/libcurl/c/curl_easy_setopt.html. Once they are chosen, you define the curl object as follows:
h <- list( proxy = "<proxy>", proxyport = <port>, proxyusername = "<username>", proxypassword = "<password>" )
The curl connection can be set up for a session by modifying the following package option:
options(rdbnomics.curl_config = h)
When fetching the data, the following command is executed:
hndl <- curl::new_handle() curl::handle_setopt(hndl, .list = getOption("rdbnomics.curl_config")) curl::curl_fetch_memory(url = <...>, handle = hndl)
After configuration, just use the standard functions of rdbnomics e.g.:
df1 <- rdb(ids = "AMECO/ZUTN/EA19.1.0.0.0.ZUTN")
This option of the package can be disabled with:
options(rdbnomics.curl = NULL)
If a complete configuration is not needed but just an "on the fly" execution, then use the argument curl_config
of the function rdb
:
df1 <- rdb(ids = "AMECO/ZUTN/EA19.1.0.0.0.ZUTN", curl_config = h)
To retrieve the data with the default R internet connection, rdbnomics will use the base function readLines
.
To activate this feature for a session, you need to enable an option of the package:
options(rdbnomics.use_readLines = TRUE)
And then use the standard function as follows:
df1 <- rdb(ids = "AMECO/ZUTN/EA19.1.0.0.0.ZUTN")
This configuration can be disabled with:
options(rdbnomics.use_readLines = FALSE)
If you just want to do it once, you may use the argument use_readLines
of the function rdb
:
df1 <- rdb(ids = "AMECO/ZUTN/EA19.1.0.0.0.ZUTN", use_readLines = TRUE)
The rdbnomics package can interact with the Time Series Editor of DBnomics to transform time series by applying filters to them.
Available filters are listed on the filters page https://editor.nomics.world/filters.
Here is an example of how to proceed to interpolate two annual time series with a monthly frequency, using a spline interpolation:
filters <- list( code = "interpolate", parameters = list(frequency = "monthly", method = "spline") )
The request is then:
df <- rdb( ids = c("AMECO/ZUTN/EA19.1.0.0.0.ZUTN", "AMECO/ZUTN/DNK.1.0.0.0.ZUTN"), filters = filters )
If you want to apply more than one filter, the filters
argument will be a list of valid filters:
filters <- list( list( code = "interpolate", parameters = list(frequency = "monthly", method = "spline") ), list( code = "aggregate", parameters = list(frequency = "bi-annual", method = "end_of_period") ) ) df <- rdb( ids = c("AMECO/ZUTN/EA19.1.0.0.0.ZUTN", "AMECO/ZUTN/DNK.1.0.0.0.ZUTN"), filters = filters )
The data.table
columns change a little bit when filters are used. There are two new columns:
period_middle_day
: the middle day of original_period
(can be useful when you compare graphically interpolated series and original ones).filtered
(boolean): TRUE
if the series is filtered, FALSE
otherwise.The content of two columns are modified:
series_code
: same as before for original series, but the suffix _filtered
is added for filtered series.series_name
: same as before for original series, but the suffix (filtered)
is added for filtered series.df <- rdbnomics:::rdbnomics_df013 data.table::setDT(df)
df <- df[order(filtered, series_name, period)] df <- reorder_cols(df) display_table(df)
# ggplot(df[!is.na(value)], aes(x = period, y = value, color = series_name)) + # geom_line(size = 1.2) + # geom_point(size = 2) + # dbnomics() df <- df[!is.na(value)] i <- 1 x1 <- df[series_name == sort(unique(series_name))[i]]$period y1 <- df[series_name == sort(unique(series_name))[i]]$value i <- 2 x2 <- df[series_name == sort(unique(series_name))[i]]$period y2 <- df[series_name == sort(unique(series_name))[i]]$value i <- 3 x3 <- df[series_name == sort(unique(series_name))[i]]$period y3 <- df[series_name == sort(unique(series_name))[i]]$value i <- 4 x4 <- df[series_name == sort(unique(series_name))[i]]$period y4 <- df[series_name == sort(unique(series_name))[i]]$value cols <- c("red", "blue", "darkgreen", "purple") PCH <- 18 legend_text <- sort(unique(df$series_name)) plot( x1, y1, col = cols[1], type = "l", xlab = "", ylab = "", xlim = c(min(df$period), max(df$period)), ylim = c(min(df$value) - 4, max(df$value)), panel.first = grid(lty = 1) ) points(x1, y1, col = cols[1], pch = PCH) lines(x2, y2, col = cols[2], type = "l") points(x2, y2, col = cols[2], pch = PCH) lines(x3, y3, col = cols[3], type = "l") points(x3, y3, col = cols[3], pch = PCH) lines(x4, y4, col = cols[4], type = "l") points(x4, y4, col = cols[4], pch = PCH) legend( "bottomleft", inset = 0.005, legend = legend_text, col = cols, lty = 1, pch = PCH, box.lty = 0, cex = 0.7 ) mtext( text = "DBnomics <https://db.nomics.world>", side = 3, col = "grey", font = 3, adj = 1 )
Any scripts or data that you put into this service are public.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.