Skip to contents

Statistics computed within each calendar month across the whole record, mirroring the C# MonthlySummaryStatistics, MonthlyPercentiles and MonthlyFrequency.

Usage

ts_monthly_statistics(ts)

ts_monthly_percentiles(ts, probabilities = c(0.05, 0.25, 0.5, 0.75, 0.95))

ts_monthly_frequency(ts)

Arguments

ts

a corehydro_ts.

probabilities

the probabilities to report, in [0, 1].

Value

a 12-row matrix (one row per calendar month), or a length-12 vector for ts_monthly_frequency().

Details

A month with no observation keeps an all-zero row rather than a missing one, following the library. The two functions differ in how they treat missing values, also following the library: ts_monthly_statistics() filters them out, while ts_monthly_percentiles() does not, so one missing value gives that month missing percentiles.

Examples

ts <- time_series(seq(as.Date("2000-01-01"), by = "month", length.out = 24), 1:24)
ts_monthly_statistics(ts)[1:3, ]
#>     minimum p05 p25 p50 p75  p95 maximum mean
#> Jan       1 1.6   4   7  10 12.4      13    7
#> Feb       2 2.6   5   8  11 13.4      14    8
#> Mar       3 3.6   6   9  12 14.4      15    9