Update minor version (#334)

* Update minor version

* fix tests

* bump actions

* update jldoctest

* Update .github/workflows/documentation.yml

Co-authored-by: Raphael Saavedra <raphael.saavedra93@gmail.com>

* fix more docs

* fix another output from doctest

* fix docs

* fix exports

* update

* fix cross referencing

---------

Co-authored-by: Raphael Saavedra <raphael.saavedra93@gmail.com>

Author: guilhermebodin

.github/workflows/ci.yml

@@ -22,12 +22,12 @@ jobs:
             os: ubuntu-latest
             arch: x86
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - uses: julia-actions/setup-julia@v1
         with:
           version: ${{ matrix.version }}
           arch: ${{ matrix.arch }}
-      - uses: actions/cache@v1
+      - uses: actions/cache@v4
         env:
           cache-name: cache-artifacts
         with:
@@ -40,6 +40,6 @@ jobs:
       - uses: julia-actions/julia-buildpkg@v1
       - uses: julia-actions/julia-runtest@v1
       - uses: julia-actions/julia-processcoverage@v1
-      - uses: codecov/codecov-action@v1
+      - uses: codecov/codecov-action@v5
         with:
           file: lcov.info

.github/workflows/doc_cleanup.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout gh-pages branch
-        uses: actions/checkout@v2
+        uses: actions/checkout@v4
         with:
           ref: gh-pages
       - name: Delete preview and history + push changes

.github/workflows/documentation.yml

@@ -9,11 +9,10 @@ jobs:
   build:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
+      - uses: actions/checkout@v4
       - uses: julia-actions/setup-julia@latest
         with:
-          # Build documentation on Julia 1.0
-          version: '1.0'
+          version: '1'
       - name: Install dependencies
         run: julia --project=docs/ -e 'using Pkg; Pkg.develop(PackageSpec(path=pwd())); Pkg.instantiate()'
       - name: Build and deploy

Project.toml

@@ -1,7 +1,7 @@
 name = "StateSpaceModels"
 uuid = "99342f36-827c-5390-97c9-d7f9ee765c78"
 authors = ["raphaelsaavedra <raphael.saavedra93@gmail.com>, guilhermebodin <guilherme.b.moraes@gmail.com>, mariohsouto"]
-version = "0.6.9"
+version = "0.7.0"
 
 [deps]
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
@@ -19,16 +19,16 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 
 [compat]
-Distributions = "0.16, 0.17, 0.18, 0.19, 0.20, 0.21, 0.22, 0.23, 0.24, 0.25"
-MatrixEquations = "1, 2"
-Optim = "0.17, 0.18, 0.19, 0.20, 0.21, 0.22, 1.2"
+Distributions = "0.25"
+MatrixEquations = "2"
+Optim = "1"
 OrderedCollections = "1"
-Polynomials = "1, 2"
+Polynomials = "4"
 RecipesBase = "1"
 SeasonalTrendLoess = "0.1"
-ShiftedArrays = "1"
-StatsBase = "0.27, 0.28, 0.29, 0.30, 0.31, 0.32, 0.33, 0.34"
-julia = "1"
+ShiftedArrays = "2"
+StatsBase = "0.34"
+julia = "1.6"
 
 [extras]
 CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"

docs/src/examples.md

@@ -197,7 +197,7 @@ plot(df.date, get_smoothed_state(smoother_output)[:, 2], label = "slope")
 
 This example illustrates how to perform vehicle tracking from noisy data.
 
-```@setup bt
+```@setup vehicle_tracking
 using StateSpaceModels, Random
 using Plots
 ```

docs/src/manual.md

@@ -100,6 +100,10 @@ LinearMultivariateTimeVariant
 
 The model hyperparameters are constant (non-time-varying) parameters that are optimized when [`fit!`](@ref) is called. The package provides some useful functions to accelerate experimentation and custom model development.
 
+```@docs
+StateSpaceModels.HyperParameters
+```
+
 The getters are:
 ```@docs
 get_names
@@ -124,14 +128,17 @@ unconstrain_identity!
 
 ## Filters and smoothers
 
-StateSpaceModels.jl lets users define tailor-made filters in an easy manner. TODO docs here
+StateSpaceModels.jl lets users define tailor-made filters in an easy manner.
 
 ```@docs
 UnivariateKalmanFilter
 ScalarKalmanFilter
 SparseUnivariateKalmanFilter
+MultivariateKalmanFilter
 FilterOutput
 SmootherOutput
+kalman_filter
+kalman_smoother
 get_innovations
 get_innovations_variance
 get_filtered_state
@@ -149,7 +156,7 @@ StateSpaceModels.jl has an interface for [Optim.jl](https://github.com/JuliaNLSo
 ```@docs
 fit!
 Optimizer
-results
+print_results
 has_fit_methods
 isfitted
 ```
@@ -198,8 +205,8 @@ plot(model, ks)
 ```@example
 using StateSpaceModels, CSV, DataFrames, Plots
 
-finland_fatalities = CSV.File(StateSpaceModels.NILE) |> DataFrame
-model = UnobservedComponents(nile; trend = "local level", cycle = "stochastic")
+nile = CSV.File(StateSpaceModels.NILE) |> DataFrame
+model = UnobservedComponents(nile.flow; trend = "local level", cycle = "stochastic")
 fit!(model)
 kf = kalman_filter(model)
 
@@ -219,4 +226,5 @@ StateSpaceModels.RJ_TEMPERATURE
 StateSpaceModels.VEHICLE_FATALITIES
 StateSpaceModels.WHOLESALE_PRICE_INDEX
 StateSpaceModels.US_CHANGE
+StateSpaceModels.SUNSPOTS_YEAR
 ```

src/StateSpaceModels.jl

@@ -78,6 +78,7 @@ export LocalLevelCycle
 export LocalLevelExplanatory
 export LocalLinearTrend
 export MultivariateBasicStructural
+export MultivariateKalmanFilter
 export Naive
 export Optimizer
 export SARIMA

src/cross_validation.jl

@@ -41,7 +41,7 @@ end
 
 Makes rolling window estimating and forecasting to benchmark the forecasting skill of the model
 in for different time periods and different lead times. The function returns a struct with the MAE
-and mean CRPS per lead time. See more on [CrossValidation the forecasts of a model](@ref)
+and mean CRPS per lead time. See more on [Cross validation of the forecasts of a model](@ref)
 
 # References
  * DTU course "31761 - Renewables in electricity markets" available on youtube https://www.youtube.com/watch?v=Ffo8XilZAZw&t=556s

src/filters/multivariate_kalman_filter.jl

@@ -1,8 +1,3 @@
-"""
-    MultivariateKalmanState{Fl <: AbstractFloat}
-
-A Kalman filter that is tailored to multivariate systems.
-"""
 mutable struct MultivariateKalmanState{Fl<:AbstractFloat}
     v::Vector{Fl}
     F::Matrix{Fl}
@@ -320,7 +315,7 @@ function filter_recursions!(
             )
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return kalman_state.llk
@@ -350,7 +345,7 @@ function filter_recursions!(
             )
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return kalman_state.llk
@@ -383,7 +378,7 @@ function filter_recursions!(
             save_kalman_state_in_filter_output!(filter_output, kalman_state, t)
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return filter_output
@@ -415,7 +410,7 @@ function filter_recursions!(
             save_kalman_state_in_filter_output!(filter_output, kalman_state, t)
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return filter_output

src/filters/regression_kalman_filter.jl

@@ -1,10 +1,8 @@
-"""
-    RegressionKalmanState{Fl <: AbstractFloat}
+#     RegressionKalmanState{Fl <: AbstractFloat}
 
-Similar to the univariate Kalman filter, but exploits the structure of the regression system
-matrices - in particular, the fact that the variance of the state (`P`) is always zero, as
-well as `R` and `Q`.
-"""
+# Similar to the univariate Kalman filter, but exploits the structure of the regression system
+# matrices - in particular, the fact that the variance of the state (`P`) is always zero, as
+# well as `R` and `Q`.
 mutable struct RegressionKalmanState{Fl<:AbstractFloat}
     v::Fl
     F::Fl

src/filters/scalar_kalman_filter.jl

@@ -209,7 +209,7 @@ function filter_recursions!(
             )
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return kalman_state.llk
@@ -242,7 +242,7 @@ function filter_recursions!(
             save_kalman_state_in_filter_output!(filter_output, kalman_state, t)
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return filter_output

src/filters/sparse_univariate_kalman_filter.jl

@@ -275,7 +275,7 @@ function filter_recursions!(
             )
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return kalman_state.llk
@@ -310,7 +310,7 @@ function filter_recursions!(
             save_kalman_state_in_filter_output!(filter_output, kalman_state, t)
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return filter_output

src/filters/univariate_kalman_filter.jl

@@ -327,7 +327,7 @@ function filter_recursions!(
             )
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations.")
         rethrow()
     end
     return kalman_state.llk
@@ -357,7 +357,7 @@ function filter_recursions!(
             )
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return kalman_state.llk
@@ -390,7 +390,7 @@ function filter_recursions!(
             save_kalman_state_in_filter_output!(filter_output, kalman_state, t)
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return filter_output
@@ -423,7 +423,7 @@ function filter_recursions!(
             save_kalman_state_in_filter_output!(filter_output, kalman_state, t)
         end
     catch
-        @error("Numerical error when applying Kalman filter euqations, the current state is: $kalman_state")
+        @error("Numerical error when applying Kalman filter equations")
         rethrow()
     end
     return filter_output

src/fit.jl

@@ -14,16 +14,16 @@ the [Optim.jl](https://github.com/JuliaNLSolvers/Optim.jl) optimization algortih
 # Example
 ```jldoctest
 julia> model = LocalLevel(rand(100))
-LocalLevel model
+LocalLevel
 
 julia> fit!(model)
-LocalLevel model
+LocalLevel
 
 julia> model = LocalLinearTrend(LinRange(1, 100, 100) + rand(100))
-LocalLinearTrend model
+LocalLinearTrend
 
 julia> fit!(model; optimizer = Optimizer(StateSpaceModels.Optim.NelderMead()))
-LocalLinearTrend model
+LocalLinearTrend
 ```
 """
 function fit!(
@@ -57,9 +57,9 @@ function fit!(
             @warn(
                 "The optimization process converged but the Hessian matrix is not positive definite. " *
                 "This means that StateSpaceModels.jl cannot estimate the distribution of the hyperparameters " *
-                "If you are interested in estimates of the distribution of ther hyperparameters we advise you to" *
+                "If you are interested in estimates of the distribution of ther hyperparameters we advise you to " *
                 "change the optimization algorithm by using the kwarg fit(...; optimizer = "*
-                "Optimizer(StateSpaceModels.Optim.THE_METHOD_OF_YOUR_CHOICE()))" * 
+                "Optimizer(StateSpaceModels.Optim.THE_METHOD_OF_YOUR_CHOICE())) " * 
                 "The list of possible algorithms can be found on this link https://julianlsolvers.github.io/Optim.jl/stable/# " * 
                 "otherwise you can simply skip this proccess by using fit(...; save_hyperparameter_distribution=false) "
             )

src/hyperparameters.jl

@@ -195,18 +195,18 @@ Fill a model with user inputed initial points for hyperparameter optimzation.
 # Example
 ```jldoctest
 julia> model = LocalLevel(rand(100))
-LocalLevel model
+LocalLevel
 
 julia> get_names(model)
-2-element Array{String,1}:
+2-element Vector{String}:
  "sigma2_ε"
  "sigma2_η"
 
 julia> set_initial_hyperparameters!(model, Dict("sigma2_η" => 100.0))
-LocalLevel model
+LocalLevel
 
 julia> model.hyperparameters.constrained_values
-2-element Array{Float64,1}:
+2-element Vector{Float64}:
  NaN  
  100.0
 ```
@@ -257,18 +257,18 @@ the model estimation.
 # Example
 ```jldoctest
 julia> model = LocalLevel(rand(100))
-LocalLevel model
+LocalLevel
 
 julia> get_names(model)
-2-element Array{String,1}:
+2-element Vector{String}:
  "sigma2_ε"
  "sigma2_η"
 
 julia> fix_hyperparameters!(model, Dict("sigma2_ε" => 100.0))
-LocalLevel model
+LocalLevel
 
 julia> model.hyperparameters.fixed_constrained_values
-Dict{String,Float64} with 1 entry:
+Dict{String, Float64} with 1 entry:
   "sigma2_ε" => 100.0
 ```
 """

src/models/common.jl

@@ -10,7 +10,7 @@ observations(model::StateSpaceModel) = model.system.y
 function lagmat(y::Vector{Fl}, k::Int) where Fl
     X = Matrix{Fl}(undef, length(y) - k, k)
     for i in 1:k
-        X[:, i] = lag(y, i)[k + 1:end]
+        X[:, i] = ShiftedArrays.lag(y, i)[k + 1:end]
     end
     return X
 end

src/models/sarima.jl

@@ -89,7 +89,7 @@ In terms of a univariate structural model, this can be represented as
 # Example
 ```jldoctest
 julia> model = SARIMA(rand(100); order=(1,1,1), seasonal_order=(1,2,3,12))
-SARIMA(1, 1, 1)x(1, 2, 3, 12) model
+SARIMA(1, 1, 1)x(1, 2, 3, 12) with zero mean
 ```
 
 See more on [Airline passengers](@ref)