Wire local-only data setup workflow

src/julia/02_enrich_output.jl

@@ -1,20 +1,16 @@
 #!/usr/bin/env julia
 #=
-02_enrich_output.jl - Enrich party positions CSV with metadata
+02_enrich_output.jl - Enrich party positions CSV with model-input-derived metadata
 
-Fast post-processing script that adds party names, union membership status,
-and election results to the model output CSV. Operates purely on CSV files
-(no chain loading). Takes seconds, not minutes.
+Fast post-processing script that adds union membership status from the model-ready
+inputs. Operates purely on CSV files (no chain loading). Takes seconds, not minutes.
 
 Usage:
     julia 02_enrich_output.jl                # enriches latest party_positions_*.csv
     julia 02_enrich_output.jl somefile.csv    # enriches a specific file
 
 Adds columns:
-    party_name_english  - Full English party name (from data/party_names.csv)
-    party_name_short    - Standard abbreviation
     in_union            - 1 if party's union had a joint manifesto that year, 0 otherwise
-    pervote             - Vote share (%) at election years; missing for non-election years
 =#
 
 using CSV
@@ -40,32 +36,7 @@ function enrich(input_file::String)
     output = CSV.read(input_file, DataFrame)
     println("  Rows: $(nrow(output)), Columns: $(ncol(output))")
 
-    # --- Party names ---
-    party_names_file = joinpath("data", "party_names.csv")
-    if isfile(party_names_file)
-        names_df = CSV.read(party_names_file, DataFrame)
-        name_lookup = Dict{Int, Tuple{String, String}}()
-        for row in eachrow(names_df)
-            short = ismissing(row.party_name_short) ? "" : string(row.party_name_short)
-            name_lookup[row.partyfacts_id] = (string(row.party_name_english), short)
-        end
-        output.party_name_english = [
-            haskey(name_lookup, pid) ? name_lookup[pid][1] : ""
-            for pid in output.party_id
-        ]
-        output.party_name_short = [
-            haskey(name_lookup, pid) ? name_lookup[pid][2] : ""
-            for pid in output.party_id
-        ]
-        n_named = count(x -> x != "", output.party_name_english)
-        println("  Party names: $n_named / $(nrow(output)) rows matched")
-    else
-        output.party_name_english = fill("", nrow(output))
-        output.party_name_short = fill("", nrow(output))
-        println("  WARNING: data/party_names.csv not found")
-    end
-
-    # --- Union mapping (for in_union + pervote fallback) ---
+    # --- Union mapping (for in_union) ---
     union_mapping_file = joinpath("data", "union_mapping.csv")
     constituent_to_union = Dict{Int, Int}()
     if isfile(union_mapping_file)
@@ -126,49 +97,6 @@ function enrich(input_file::String)
         println("  WARNING: Could not compute in_union (missing files)")
     end
 
-    # --- Election results (pervote) ---
-    election_file = joinpath("data", "election_data.csv")
-    output.pervote = Vector{Union{Float64, Missing}}(missing, nrow(output))
-
-    if isfile(election_file)
-        election_df = CSV.read(election_file, DataFrame)
-
-        # Build lookup: (party_id, year) -> pervote
-        election_lookup = Dict{Tuple{Int, Int}, Float64}()
-        for row in eachrow(election_df)
-            election_lookup[(row.party, row.year)] = row.pervote
-        end
-
-        n_filled = 0
-        for i in 1:nrow(output)
-            pid = output.party_id[i]
-            yr = output.year[i]
-
-            # Direct match (standalone party)
-            if haskey(election_lookup, (pid, yr))
-                output.pervote[i] = election_lookup[(pid, yr)]
-                n_filled += 1
-            elseif hasproperty(output, :union_party_id) && !ismissing(output.union_party_id[i])
-                # Union constituent: look up by union PF ID
-                uid = output.union_party_id[i]
-                if haskey(election_lookup, (uid, yr))
-                    output.pervote[i] = election_lookup[(uid, yr)]
-                    n_filled += 1
-                end
-            elseif haskey(constituent_to_union, pid)
-                # Fallback: use union mapping even if union_party_id column not populated
-                uid = constituent_to_union[pid]
-                if haskey(election_lookup, (uid, yr))
-                    output.pervote[i] = election_lookup[(uid, yr)]
-                    n_filled += 1
-                end
-            end
-        end
-        println("  pervote: $n_filled / $(nrow(output)) rows filled")
-    else
-        println("  WARNING: election_data.csv not found")
-    end
-
     # --- Reorder columns ---
     estimate_cols = Symbol[]
     for base in ["economic_lr", "galtan", "pro_market", "pro_welfare", "cosmopolitan", "traditional"]
@@ -185,8 +113,7 @@ function enrich(input_file::String)
     output.country = replace(output.country, "MO" => "MK")
 
     col_order = vcat(
-        [:party_id, :party_name_english, :party_name_short, :country, :year, :segment_num,
-         :union_party_id, :in_union, :pervote],
+        [:party_id, :country, :year, :segment_num, :union_party_id, :in_union],
         estimate_cols
     )
     col_order = filter(c -> hasproperty(output, c), col_order)