Census / FRED time series DB

[christophsax]

where we can take out our examples. We should have a list or a nested tibble with a few 1000 series, so we can pick interesting ones.

I guess FRED would be more interesting, because we can include international series: https://fred.stlouisfed.org/categories

Did we had something on that? How could we come up with a list of 1000 or so broadly mixed IDs?

[christophsax]

Perhaps also something for @andreranza?

[christophsax]

There is a ‘popularity’ attribute in fredr, and we can use tags. Here I am getting two ‘pages’, i.e., each 2000 quarterly and monthly series.

library(fredr)
library(tidyverse)

monthly <- 
  fredr_tags_series("nsa;monthly", order_by = "popularity", sort_order = "desc")

monthly_p2 <- 
  fredr_tags_series("nsa;monthly", order_by = "popularity", sort_order = "desc", offset = 1000)

quarterly <- 
  fredr_tags_series("nsa;quarterly", order_by = "popularity", sort_order = "desc")

quarterly_p2 <- 
  fredr_tags_series("nsa;quarterly", order_by = "popularity", sort_order = "desc", offset = 1000)

The most popular series

monthly |> 
  select(id, title, popularity)
#> # A tibble: 1,000 × 3
#>    id                 title                                           popularity
#>    <chr>              <chr>                                                <int>
#>  1 FEDFUNDS           Federal Funds Effective Rate                            98
#>  2 CSUSHPINSA         S&P CoreLogic Case-Shiller U.S. National Home …         88
#>  3 REAINTRATREARAT10Y 10-Year Real Interest Rate                              80
#>  4 AAA                Moody's Seasoned Aaa Corporate Bond Yield               80
#>  5 UMCSENT            University of Michigan: Consumer Sentiment              80
#>  6 TB3MS              3-Month Treasury Bill Secondary Market Rate, D…         79
#>  7 ACTLISCOUUS        Housing Inventory: Active Listing Count in the…         78
#>  8 PPIACO             Producer Price Index by Commodity: All Commodi…         78
#>  9 BOGMBASE           Monetary Base; Total                                    78
#> 10 APU0000708111      Average Price: Eggs, Grade A, Large (Cost per …         76
#> # ℹ 990 more rows

quarterly |> 
  select(id, title, popularity)
#> # A tibble: 1,000 × 3
#>    id            title                                                popularity
#>    <chr>         <chr>                                                     <int>
#>  1 MSPUS         Median Sales Price of Houses Sold for the United St…         90
#>  2 ASPUS         Average Sales Price of Houses Sold for the United S…         84
#>  3 GFDEBTN       Federal Debt: Total Public Debt                              83
#>  4 MMMFFAQ027S   Money Market Funds; Total Financial Assets, Level            76
#>  5 USSTHPI       All-Transactions House Price Index for the United S…         75
#>  6 GDPPOT        Real Potential Gross Domestic Product                        75
#>  7 DRTSCILM      Net Percentage of Domestic Banks Tightening Standar…         73
#>  8 COMREPUSQ159N Commercial Real Estate Prices for United States              71
#>  9 CASTHPI       All-Transactions House Price Index for California            71
#> 10 RHORUSQ156N   Homeownership Rate in the United States                      71
#> # ℹ 990 more rows

As for the less lower part of the table, we have:

monthly_p2 |> 
  select(id, title, popularity) |> 
  tail(10)
#> # A tibble: 10 × 3
#>    id                 title                                           popularity
#>    <chr>              <chr>                                                <int>
#>  1 TWEXMTHY           Trade-Weighted Exchange Value of U.S. Dollar v…         12
#>  2 JTU480099JOR       Job Openings: Transportation, Warehousing, and…         12
#>  3 PCU3315233315231   Producer Price Index by Industry: Nonferrous M…         12
#>  4 APU0000711311      Average Price: Oranges, Navel (Cost per Pound/…         12
#>  5 PCU532111532111221 Producer Price Index by Industry: Passenger Ca…         12
#>  6 GBRCPICORMINMEI    Consumer Price Indices (CPIs, HICPs), COICOP 1…         12
#>  7 IR3TCP01CAM156N    Interest Rates: 3-Month or 90-Day Rates and Yi…         12
#>  8 ACTLISCOU6065      Housing Inventory: Active Listing Count in Riv…         12
#>  9 NYURN              Unemployment Rate in New York                           12
#> 10 PCU327327          Producer Price Index by Industry: Nonmetallic …         12

quarterly_p2 |> 
  select(id, title, popularity) |> 
  tail(10)
#> # A tibble: 10 × 3
#>    id             title                                               popularity
#>    <chr>          <chr>                                                    <int>
#>  1 MNTACAFSS      Total Amortized Cost of Available-For-Sale Securit…          3
#>  2 IATEQC         Total Equity Capital for Commercial Banks in Iowa …          3
#>  3 EQTA26         Total Equity to Total Assets, Banks with Total Ass…          3
#>  4 ENUC180230010  Total Quarterly Wages in Columbus, IN (MSA)                  3
#>  5 ENUC201030010  Total Quarterly Wages in Dover, DE (MSA)                     3
#>  6 EVLNNQ         Total Value of Loans for More than 365 Days, Minim…          3
#>  7 EDSXFBNQ       Weighted-Average Maturity for 2 to 30 Days, U.S. B…          3
#>  8 ERTP365PDXSLNQ Weighted-Average Risk Rating by Time that Pricing …          3
#>  9 ERTSFXFBNQ     Weighted-Average Risk Rating by Time that Pricing …          3
#> 10 ERTSIXSLNQ     Weighted-Average Risk Rating by Time that Pricing …          3

[andreranza]

Perhaps also something for @andreranza?

@christophsax, sorry this week was full and couldn't have a look. Conf is getting closer...

[andreranza]

Is there maybe "mini" task I can take over?

[christophsax]

Thanks, no it's fine, I have something here. Just focus on conf!

[christophsax]

The 4000 series are now included in seasonalbook::fred. ?fred gives an example:

library(seasonalbook)
stopifnot(packageVersion("seasonalbook") >= "0.1.1")

library(dplyr)
library(seasonalbook)
library(seasonal)
library(furrr)

try_na_real <- function(expr) {
  cat(".")
  ans <- try(expr)
  if (inherits(ans, "try-error")) return(NA_real_)
  ans
}
my_stats <- function(x) try_na_real(AIC(seas(x)))
my_stats(AirPassengers)

ans <-
  fred |>
  mutate(aic = purrr::map_dbl(ts, my_stats))

# To speed up, use parallel processing
plan(multisession, workers = parallelly::availableCores())
ans_2 <-
  fred |>
  mutate(aic = furrr::future_map_dbl(ts, my_stats))

ans_2 |>
  arrange(aic)

@jlivsey this can be used to find examples.