Skip to content

Random sample data #93

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Jan 6, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 20 additions & 9 deletions docs/src/test_data.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,23 @@ Test data `const` objects are smaller datasets designed to be used in
tests for other packages. They include both `Date` and `DateTime`
objects. All but one of the objects has an empty TimeArray `meta` field.

| `const` | Description | First timestamp | Number of rows
|-----------|--------------------------------------|---------------------|-----------------
| op | single column `Date` data | 2000-01-03 | 500
| cl | single column `Date` data | 2000-01-03 | 500
| ohlc | four-column `Date` data | 2000-01-03 | 500
| ohlcv | five-column `Date` data | 2000-01-03 | 500
| mdata | 1-column `Date` data with meta field | 2000-01-03 | 500
| datetime1 | 1-column `DateTime` data | 2013-12-31T00:00:00 | 5
| datetime2 | 1-column `DateTim`e data | 1961-12-31 00:00:00 | 5
| `const` | Description | First timestamp | Number of rows
|-------------|--------------------------------------|---------------------|-----------------
| `op` | single column `Date` data | 2000-01-03 | 500
| `cl` | single column `Date` data | 2000-01-03 | 500
| `ohlc` | four-column `Date` data | 2000-01-03 | 500
| `ohlcv` | five-column `Date` data | 2000-01-03 | 500
| `mdata` | 1-column `Date` data with meta field | 2000-01-03 | 500
| `datetime1` | 1-column `DateTime` data | 2013-12-31T00:00:00 | 5
| `datetime2` | 1-column `DateTim`e data | 1961-12-31 00:00:00 | 5

## Random

| `Function` | Description | First timestamp(*) | Number of rows(*)
|----------------|--------------------------------------------------|---------------------|-----------------
| `random_cl` | random `Close` price | 2020-01-01 | 500
| `random_vol` | random `Volume` | 2020-01-01 | 500
| `random_ohlc` | random `Open`/`High`/`Low`/`Close` price data | 2020-01-01 | 500
| `random_ohlcv` | random `Open`/`High`/`Low`/`Close`/`Volume` data | 2020-01-01 | 500

(*) these values are default values but can be changed passing a keyword argument such as `start=Dates.DateTime(2024, 1, 1)` and `length=1000`.
2 changes: 2 additions & 0 deletions src/MarketData.jl
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,7 @@ using JSON3
export AAPL, BA, CAT, DELL, EBAY, F, GE, TX,
cl, op, ohlc, ohlcv, datetime1, datetime2, mdata,
o, h, l, c, v
export random_cl, random_vol, random_ohlc, random_ohlcv
# downloads.jl
export AbstractQueryOpt,
YahooOpt,
Expand All @@ -23,6 +24,7 @@ export AbstractQueryOpt,

include("utils.jl")
include("const.jl")
include("random.jl")
include("helpers.jl")
include("downloads.jl")

Expand Down
116 changes: 116 additions & 0 deletions src/random.jl
Original file line number Diff line number Diff line change
@@ -0,0 +1,116 @@
using Random


function random_cl(rng::AbstractRNG = Random.GLOBAL_RNG;
start = Dates.DateTime(2020, 1, 1),
step = Dates.Minute(1),
length = 500,
price_init = nothing,
price_init_min = 1.00,
price_init_step = 0.01,
price_init_max = 1000.00,
price_var_min = -1.0,
price_var_step = 0.01,
price_var_max = 1.0,
)
idx = range(start, length = length, step = step)
if isnothing(price_init)
price_init = rand(rng, price_init_min:price_init_step:price_init_max)
end
return TimeArray(
collect(idx),
price_init .+ cumsum(rand(rng, price_var_min:price_var_step:price_var_max, length)),
[:Close],
)
end

function random_vol(rng::AbstractRNG = Random.GLOBAL_RNG;
start = Dates.DateTime(2020, 1, 1),
step = Dates.Minute(1),
length = 500,
vol_init_min = 0.0,
vol_init_step = 0.1,
vol_init_max = 100.0,
)
idx = range(start, length = length, step = step)
return TimeArray(
collect(idx),
rand(rng, vol_init_min:vol_init_step:vol_init_max, length),
[:Volume],
)
end

function random_ohlc(rng::AbstractRNG = Random.GLOBAL_RNG;
start = Dates.DateTime(2020, 1, 1),
step = Dates.Hour(1),
sub_step = Dates.Minute(1),
length = 500,
price_init = nothing,
price_init_min = 1.00,
price_init_step = 0.01,
price_init_max = 1000.00,
price_var_min = -1.0,
price_var_step = 0.01,
price_var_max = 1.0
)
nsub = ceil(Int, step / sub_step)
price = random_cl(rng,
start = start,
step = sub_step,
length = length * nsub,
price_init = price_init,
price_init_min = price_init_min,
price_init_step = price_init_step,
price_init_max = price_init_max,
price_var_min = price_var_min,
price_var_step = price_var_step,
price_var_max = price_var_max,
)
ta_o = collapse(price, step, first, first)
ta_h = collapse(price, step, first, maximum)
ta_l = collapse(price, step, first, minimum)
ta_c = collapse(price, step, first, last)
a_ohlc = hcat(values(ta_o), values(ta_h), values(ta_l), values(ta_c))
return TimeArray(timestamp(ta_o), a_ohlc, [:Open, :High, :Low, :Close])
end


function random_ohlcv(rng::AbstractRNG = Random.GLOBAL_RNG;
start = Dates.DateTime(2020, 1, 1),
step = Dates.Hour(1),
sub_step = Dates.Minute(1),
length = 500,
price_init = nothing,
price_init_min = 1.00,
price_init_step = 0.01,
price_init_max = 1000.00,
price_var_min = -1.0,
price_var_step = 0.01,
price_var_max = 1.0,
vol_init_min = 0.0,
vol_init_step = 0.1,
vol_init_max = 100.0,
)
ta_ohlc = random_ohlc(rng;
start = start,
step = step,
sub_step = sub_step,
length = length,
price_init = price_init,
price_init_min = price_init_min,
price_init_step = price_init_step,
price_init_max = price_init_max,
price_var_min = price_var_min,
price_var_step = price_var_step,
price_var_max = price_var_max
)
ta_vol = random_vol(rng;
start = start,
step = step,
length = Base.length(ta_ohlc),
vol_init_min = vol_init_min,
vol_init_step = vol_init_step,
vol_init_max = vol_init_max,
)
hcat(ta_ohlc, ta_vol)
end
29 changes: 29 additions & 0 deletions test/const.jl
Original file line number Diff line number Diff line change
Expand Up @@ -50,3 +50,32 @@ end
@test length(GE) == 13090
end
end


@testset "random data have expected length" begin

@testset "test random_cl" begin
data = random_cl()
@test length(data) == 500
@test colnames(data) == [:Close]
end

@testset "test random_vol" begin
data = random_vol()
@test length(data) == 500
@test colnames(data) == [:Volume]
end

@testset "test random_ohlc" begin
data = random_ohlc()
@test length(data) == 500
@test colnames(data) == [:Open, :High, :Low, :Close]
end

@testset "test random_ohlcv" begin
data = random_ohlcv()
@test length(data) == 500
@test colnames(data) == [:Open, :High, :Low, :Close, :Volume]
end

end