remove old observations framework

removed unused functionality based on old Observations typo docs example typo
CliMA · Jul 31, 2024 · 69eb4a5 · 69eb4a5
1 parent f2e95cf
commit 69eb4a5
Show file tree

Hide file tree

Showing 8 changed files with 21 additions and 59 deletions.
diff --git a/docs/src/examples/Cloudy_example.md b/docs/src/examples/Cloudy_example.md
@@ -76,7 +76,6 @@ and finally the EKP packages.
 
 ```julia
 using EnsembleKalmanProcesses
-using EnsembleKalmanProcesses.Observations
 using EnsembleKalmanProcesses.ParameterDistributions
 using EnsembleKalmanProcesses.DataContainers
 using EnsembleKalmanProcesses.PlotRecipes
@@ -163,8 +162,13 @@ for i in 1:n_samples
     y_t[:, i] = G_t .+ rand(MvNormal(μ, Γy))
 end
 
-truth = Observations.Observation(y_t, Γy, data_names)
-truth_sample = truth.mean 
+truth = Observation(
+    Dict(
+        "samples" => vec(mean(y_t, dims = 2)),
+        "covariances" => Γy,
+        "names" => data_names,
+    )
+)
 ```
 
 #### Perform ensemble Kalman inversion
@@ -181,8 +185,7 @@ N_iter = 8 # number of EKI iterations
 initial_params = construct_initial_ensemble(rng, priors, N_ens)
 ekiobj = EnsembleKalmanProcess(
     initial_params,
-    truth_sample,
-    truth.obs_noise_cov,
+    truth,
     Inversion(),
     scheduler=DataMisfitController()
 )

diff --git a/docs/src/examples/lorenz_example.md b/docs/src/examples/lorenz_example.md
@@ -68,7 +68,6 @@ using CalibrateEmulateSample.Utilities
 using CalibrateEmulateSample.EnsembleKalmanProcesses
 using CalibrateEmulateSample.ParameterDistributions
 using CalibrateEmulateSample.DataContainers
-using CalibrateEmulateSample.Observations
 ```
 
 The first input settings define which input-output pairs to use for training the emulator. The Calibrate stage (run using `calibrate.jl`) generates parameter-to-data pairs by running the L96 system using an iterative optimization approach (`EnsembleKalmanProcess.jl`). So we first define which iterations we would like to use data from for our emulator training

diff --git a/examples/Cloudy/Cloudy_calibrate.jl b/examples/Cloudy/Cloudy_calibrate.jl
@@ -20,7 +20,6 @@ include(joinpath(@__DIR__, "DynamicalModel.jl"))
 
 # Import Ensemble Kalman Processes modules
 using EnsembleKalmanProcesses
-using EnsembleKalmanProcesses.Observations
 using EnsembleKalmanProcesses.ParameterDistributions
 using EnsembleKalmanProcesses.DataContainers
 using EnsembleKalmanProcesses.PlotRecipes
@@ -100,7 +99,7 @@ savefig(p, output_directory * "cloudy_priors.png")
 ###  Define the data from which we want to learn the parameters
 ###
 
-data_names = ["M0", "M1", "M2"]
+data_names = ["M0_M1_M2"]
 moments = [0.0, 1.0, 2.0]
 n_moments = length(moments)
 
@@ -139,8 +138,7 @@ for i in 1:n_samples
     y_t[:, i] = G_t .+ rand(MvNormal(μ, Γy))
 end
 
-truth = Observations.Observation(y_t, Γy, data_names)
-truth_sample = truth.mean
+truth = Observation(Dict("samples" => vec(mean(y_t, dims = 2)), "covariances" => Γy, "names" => data_names))
 
 
 ###
@@ -153,8 +151,7 @@ N_iter = 15 # number of EKI iterations
 initial_params = construct_initial_ensemble(rng, priors, N_ens)
 ekiobj = EnsembleKalmanProcess(
     initial_params,
-    truth_sample,
-    truth.obs_noise_cov,
+    truth,
     Inversion(),
     scheduler = DataMisfitController(),
 )
@@ -196,9 +193,9 @@ save(
     "eki",
     ekiobj,
     "truth_sample",
-    truth_sample,
-    "truth_sample_mean",
-    truth.mean,
+    get_sample(truth),
+    "truth_sample_mean", 
+    vec(mean(y_t, dims = 2)),
     "truth_input_constrained",
     ϕ_true,
 )

diff --git a/examples/Lorenz/calibrate.jl b/examples/Lorenz/calibrate.jl
@@ -119,7 +119,7 @@ function main()
     ###
     ###  Define the data from which we want to learn the parameters
     ###
-    data_names = ["y0", "y1"]
+    data_names = ["y0_y1"]
 
 
     ###
@@ -254,8 +254,7 @@ function main()
 
 
     # Construct observation object
-    truth = Observations.Observation(yt, Γy, data_names)
-    truth_sample = yt[:, end]
+truth = Observation(Dict("samples" => vec(mean(yt, dims = 2)), "covariances" => Γy, "names" => data_names))
     ###
     ###  Calibrate: Ensemble Kalman Inversion
     ###
@@ -271,8 +270,7 @@ function main()
 
     ekiobj = EKP.EnsembleKalmanProcess(
         initial_params,
-        truth_sample,
-        truth.obs_noise_cov,
+        truth,
         EKP.Inversion(),
         scheduler = EKP.DataMisfitController(),
         verbose = true,
@@ -316,9 +314,9 @@ function main()
         "eki",
         ekiobj,
         "truth_sample",
-        truth_sample,
+        get_sample(truth),
         "truth_sample_mean",
-        truth.mean,
+        vec(mean(yt, dims = 2)),
         "truth_input_constrained",
         params_true, #constrained here, as these are in a physically constrained space (unlike the u inputs),
     )

diff --git a/examples/Lorenz/emulate_sample.jl b/examples/Lorenz/emulate_sample.jl
@@ -17,7 +17,6 @@ using CalibrateEmulateSample.Utilities
 using CalibrateEmulateSample.EnsembleKalmanProcesses
 using CalibrateEmulateSample.ParameterDistributions
 using CalibrateEmulateSample.DataContainers
-using CalibrateEmulateSample.Observations
 
 function get_standardizing_factors(data::Array{FT, 2}) where {FT}
     # Input: data size: N_data x N_ensembles

diff --git a/src/CalibrateEmulateSample.jl b/src/CalibrateEmulateSample.jl
@@ -10,9 +10,9 @@ module CalibrateEmulateSample
 using Distributions, Statistics, LinearAlgebra, DocStringExtensions
 
 # imported modules from EKP.
-import EnsembleKalmanProcesses: EnsembleKalmanProcesses, ParameterDistributions, Observations, DataContainers
+import EnsembleKalmanProcesses: EnsembleKalmanProcesses, ParameterDistributions, DataContainers
 
-export EnsembleKalmanProcesses, ParameterDistributions, Observations, DataContainers
+export EnsembleKalmanProcesses, ParameterDistributions, DataContainers
 
 
 # Internal deps, light external deps

diff --git a/src/Utilities.jl b/src/Utilities.jl
@@ -5,13 +5,11 @@ using LinearAlgebra
 using Statistics
 using StatsBase
 using Random
-using ..Observations
 using ..EnsembleKalmanProcesses
 EnsembleKalmanProcess = EnsembleKalmanProcesses.EnsembleKalmanProcess
 using ..DataContainers
 
 export get_training_points
-export get_obs_sample
 export orig2zscore
 export zscore2orig
 """
@@ -50,33 +48,6 @@ function get_training_points(
     return training_points
 end
 
-
-"""
-$(DocStringExtensions.TYPEDSIGNATURES)
-
-Return a random sample from the observations, for use in the MCMC.
-
- - `rng` - optional RNG object used to pick random sample; defaults to `Random.GLOBAL_RNG`.
- - `obs` - Observation struct with the observations (extract will pick one
-           of the sample observations to train).
- - `rng_seed` - optional kwarg; if provided, used to re-seed `rng` before sampling.
-"""
-function get_obs_sample(
-    rng::Random.AbstractRNG,
-    obs::Observation;
-    rng_seed::Union{IT, Nothing} = nothing,
-) where {IT <: Int}
-    # Ensuring reproducibility of the sampled parameter values: 
-    # re-seed the rng *only* if we're given a seed
-    if rng_seed !== nothing
-        rng = Random.seed!(rng, rng_seed)
-    end
-    row_idxs = StatsBase.sample(rng, axes(obs.samples, 1), 1; replace = false, ordered = false)
-    return obs.samples[row_idxs...]
-end
-# first arg optional; defaults to GLOBAL_RNG (as in Random, StatsBase)
-get_obs_sample(obs::Observation; kwargs...) = get_obs_sample(Random.GLOBAL_RNG, obs; kwargs...)
-
 function orig2zscore(X::AbstractVector{FT}, mean::AbstractVector{FT}, std::AbstractVector{FT}) where {FT}
     # Compute the z scores of a vector X using the given mean
     # and std

diff --git a/test/Utilities/runtests.jl b/test/Utilities/runtests.jl
@@ -4,7 +4,6 @@ using Statistics
 using LinearAlgebra
 
 using CalibrateEmulateSample.Utilities
-using CalibrateEmulateSample.Observations
 using CalibrateEmulateSample.EnsembleKalmanProcesses
 using CalibrateEmulateSample.DataContainers
 
@@ -15,10 +14,6 @@ using CalibrateEmulateSample.DataContainers
 
     arr = vcat([i * ones(3)' for i in 1:5]...)
     arr_t = permutedims(arr, (2, 1))
-    data_names = ["d1", "d2", "d3"]
-    obs = Observation(arr_t, data_names) #data must be columns as default
-    sample = get_obs_sample(rng, obs)
-    @test sample == [5.0, 5.0, 5.0]
 
     mean_arr = dropdims(mean(arr, dims = 1), dims = 1)
     std_arr = dropdims(std(arr, dims = 1), dims = 1)