Skip to content
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

Refactor SurveyDesign and add in-place constructor #320

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open
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
73 changes: 43 additions & 30 deletions src/SurveyDesign.jl
Original file line number Diff line number Diff line change
Expand Up @@ -54,10 +54,22 @@ struct SurveyDesign <: AbstractSurveyDesign
# Single stage clusters sample, like apiclus1
function SurveyDesign(
data::AbstractDataFrame;
clusters::Union{Nothing,Symbol,Vector{Symbol}} = nothing,
strata::Union{Nothing,Symbol} = nothing,
popsize::Union{Nothing,Symbol} = nothing,
weights::Union{Nothing,Symbol} = nothing,
clusters::Union{Nothing,Symbol,Vector{Symbol}}=nothing,
strata::Union{Nothing,Symbol}=nothing,
popsize::Union{Nothing,Symbol}=nothing,
weights::Union{Nothing,Symbol}=nothing,
)
# call SurveyDesign!
SurveyDesign!(data; clusters=clusters, strata=strata, popsize=popsize, weights=weights)
end

# Function to manipulate the dataframe in place with ! added to its name
function SurveyDesign!(
data::AbstractDataFrame;
clusters::Union{Nothing,Symbol,Vector{Symbol}}=nothing,
strata::Union{Nothing,Symbol}=nothing,
popsize::Union{Nothing,Symbol}=nothing,
weights::Union{Nothing,Symbol}=nothing,
)
# sampsize here is number of clusters completely sampled, popsize is total clusters in population
if typeof(strata) <: Nothing
Expand Down Expand Up @@ -99,8 +111,8 @@ struct SurveyDesign <: AbstractSurveyDesign
data[!, popsize] = data[!, sampsize_labels] .* data[!, weights_labels]
end
elseif isa(popsize, Symbol)
weights_labels = :_weights
data[!, weights_labels] = data[!, popsize] ./ data[!, sampsize_labels]
weights_labels = :_weights
data[!, weights_labels] = data[!, popsize] ./ data[!, sampsize_labels]
else
# neither popsize nor weights given
weights_labels = :_weights
Expand All @@ -122,6 +134,7 @@ struct SurveyDesign <: AbstractSurveyDesign
pps,
)
end

end

"""
Expand Down Expand Up @@ -305,31 +318,31 @@ struct ReplicateDesign{ReplicateType} <: AbstractSurveyDesign
type::String,
replicates::UInt,
replicate_weights::Vector{Symbol},
) where {ReplicateType <: InferenceMethod}
) where {ReplicateType<:InferenceMethod}
new{ReplicateType}(data, cluster, popsize, sampsize, strata, weights, allprobs,
pps, type, replicates, replicate_weights, ReplicateType(replicates))
pps, type, replicates, replicate_weights, ReplicateType(replicates))
end

# constructor with given replicate_weights
function ReplicateDesign{ReplicateType}(
data::AbstractDataFrame,
replicate_weights::Vector{Symbol};
clusters::Union{Nothing,Symbol,Vector{Symbol}} = nothing,
strata::Union{Nothing,Symbol} = nothing,
popsize::Union{Nothing,Symbol} = nothing,
weights::Union{Nothing,Symbol} = nothing
) where {ReplicateType <: InferenceMethod}
clusters::Union{Nothing,Symbol,Vector{Symbol}}=nothing,
strata::Union{Nothing,Symbol}=nothing,
popsize::Union{Nothing,Symbol}=nothing,
weights::Union{Nothing,Symbol}=nothing
) where {ReplicateType<:InferenceMethod}
# rename the replicate weights if needed
rename!(data, [replicate_weights[index] => "replicate_"*string(index) for index in 1:length(replicate_weights)])
rename!(data, [replicate_weights[index] => "replicate_" * string(index) for index in 1:length(replicate_weights)])

# call the SurveyDesign constructor
base_design = SurveyDesign(
data;
clusters=clusters,
strata=strata,
popsize=popsize,
weights=weights
)
data;
clusters=clusters,
strata=strata,
popsize=popsize,
weights=weights
)
new{ReplicateType}(
base_design.data,
base_design.cluster,
Expand All @@ -350,11 +363,11 @@ struct ReplicateDesign{ReplicateType} <: AbstractSurveyDesign
ReplicateDesign{ReplicateType}(
data::AbstractDataFrame,
replicate_weights::UnitRange{Int};
clusters::Union{Nothing,Symbol,Vector{Symbol}} = nothing,
strata::Union{Nothing,Symbol} = nothing,
popsize::Union{Nothing,Symbol} = nothing,
weights::Union{Nothing,Symbol} = nothing
) where {ReplicateType <: InferenceMethod} =
clusters::Union{Nothing,Symbol,Vector{Symbol}}=nothing,
strata::Union{Nothing,Symbol}=nothing,
popsize::Union{Nothing,Symbol}=nothing,
weights::Union{Nothing,Symbol}=nothing
) where {ReplicateType<:InferenceMethod} =
ReplicateDesign{ReplicateType}(
data,
Symbol.(names(data)[replicate_weights]);
Expand All @@ -368,11 +381,11 @@ struct ReplicateDesign{ReplicateType} <: AbstractSurveyDesign
ReplicateDesign{ReplicateType}(
data::AbstractDataFrame,
replicate_weights::Regex;
clusters::Union{Nothing,Symbol,Vector{Symbol}} = nothing,
strata::Union{Nothing,Symbol} = nothing,
popsize::Union{Nothing,Symbol} = nothing,
weights::Union{Nothing,Symbol} = nothing
) where {ReplicateType <: InferenceMethod} =
clusters::Union{Nothing,Symbol,Vector{Symbol}}=nothing,
strata::Union{Nothing,Symbol}=nothing,
popsize::Union{Nothing,Symbol}=nothing,
weights::Union{Nothing,Symbol}=nothing
) where {ReplicateType<:InferenceMethod} =
ReplicateDesign{ReplicateType}(
data,
Symbol.(names(data)[findall(name -> occursin(replicate_weights, name), names(data))]);
Expand Down
Loading