adds method for splitting data into periods

minor

return iterator and adds test

starts to add retime

changes _split

changes LTS

overload Base.split

changes interface of _split to return timestamps

.github/workflows/CI.yml

@@ -15,8 +15,7 @@ jobs:
       fail-fast: false
       matrix:
         version:
-          - "1.6.7" # LTS
-          - "1.6"
+          - "1.10.7" # LTS
           - "1" # Latest Release
         os:
           - ubuntu-latest

docs/src/split.md

@@ -124,3 +124,14 @@ using MarketData
 tail(cl)
 tail(cl, 3)
 ```
+
+## Splitting by period
+
+Splitting data by a given function, e.g. `Dates.day` into periods.
+
+```@repl
+using TimeSeries
+using MarketData
+
+split(cl, Dates.day)
+```

src/TimeSeries.jl

@@ -58,5 +58,6 @@ include("modify.jl")
 include("basemisc.jl")
 include("deprecated.jl")
 include("plotrecipes.jl")
+include("retime.jl")
 
 end  # module TimeSeries

src/retime.jl

@@ -0,0 +1,48 @@
+function retime(ta, new_dt::Dates.Period; kwargs...)
+    new_timestamps = timestamp(ta)[1]:new_dt:timestamp(ta)[end]
+    return retime(ta, new_timestamps; kwargs...)
+end
+
+function retime(ta, period::Function; kwargs...)
+    new_timestamps = map(i -> first(timestamp(ta)[i]), _split(timestamp(ta), period))
+    return retime(ta, new_timestamps; kwargs...)
+end
+
+function retime(
+    ta::TimeSeries{T,N,D,A},
+    new_timestamps::AbstractVector{DN};
+    upsample=:previous,
+    downsample::Union{Symbol,Function}=:mean,
+    extrapolate::Bool=true,
+) where {T,N,D,A,DN}
+    new_values = zeros(T, length(new_timestamps), size(values(ta), 2))
+    old_timestamps = convert(Vector{DN}, timestamp(ta))
+    old_values = values(ta)
+    @views begin
+        for col_i in 1:size(old_values, 2)
+            _retime!(new_values[:, col_i], old_timestamps, old_values[:, col_i], new_timestamps, upsample, downsample, extrapolate)
+        end
+    end
+    return TimeArray(new_timestamps, new_values, colnames(ta), meta(ta))
+end
+
+function _retime!(
+    new_values::AbstractVector{A},
+    old_timestamps::AbstractVector{D},
+    old_values::AbstractVector{A},
+    new_timestamps::AbstractVector{D},
+    upsample,
+    downsample,
+    extrapolate,
+) where {D,A}
+
+    x = Dates.value.(old_timestamps)
+    x_min, x_max = extrema(x)
+    x_new = Dates.value.(new_timestamps)
+
+    # check each interval between i and i+1 if there is no or one sample (upsample), more than one sample (downsample)
+    for i in eachindex(x_new)
+    end
+    return
+end
+

src/split.jl

@@ -70,3 +70,36 @@ end
 Base.first(ta::TimeArray) = head(ta, 1)
 
 Base.last(ta::TimeArray) = tail(ta, 1)
+
+"""
+    split(data::TimeSeries.TimeArray, period::Function)
+
+Split `data` by `period` function, returns a vector of `TimeSeries.TimeArray`.
+
+## Arguments
+
+- `data::TimeSeries.TimeArray`: Data to split
+- `period::Function`: Function, e.g. `Dates.day` that is used to split the `data`.
+"""
+Base.split(data::TimeSeries.TimeArray, period::Function) =
+    Iterators.map(i -> data[i], _split(TimeSeries.timestamp(data), period))
+
+function _split(ts::AbstractVector{D}, period::Function) where {D<:TimeType}
+    m = length(ts)
+    idx = UnitRange{Int}[]
+    isempty(ts) && return idx
+
+    sizehint!(idx, m)
+    t0 = period(ts[1])
+    j = 1
+    for i in 1:(m - 1)
+        t1 = period(ts[i + 1])
+        t0 == t1 && continue
+        push!(idx, j:i)
+        j = i + 1
+        t0 = t1
+    end
+    push!(idx, j:m)
+
+    return Iterators.map(i -> ts[i], idx)
+end

test/split.jl

@@ -1,8 +1,6 @@
 using Dates
 using Test
-
 using MarketData
-
 using TimeSeries
 
 @testset "split" begin
@@ -123,4 +121,19 @@ using TimeSeries
             @test length(last(ohlc)) == 1
         end
     end
+
+    @testset "split period" begin
+        for period in [day, week, month, year]
+            for cl_ in split(cl, period)
+                @test allequal(period.(timestamp(cl_)))
+            end
+        end
+        @test length(split(cl, day)) == 500
+        @test length(split(cl, week)) == 105
+        @test length(split(cl, month)) == 24
+        @test length(split(cl, year)) == 2
+
+        # test empty timearray
+        @test length(split(to(cl, Date(2000)), week)) == 0
+    end
 end  # @testset "split"