Skip to content

possible summarize benchmark improvement #151

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.

Sign up for GitHub

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

possible summarize benchmark improvement #151

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
55 changes: 21 additions & 34 deletions src/TidierData.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -338,52 +338,39 @@ macro summarize(df, exprs...)

tidy_exprs = parse_tidy.(tidy_exprs; autovec=true) # use auto-vectorization inside `@summarize()`
df_expr = quote
if $any_found_n || $any_found_row_number
if $(esc(df)) isa GroupedDataFrame
local df_copy = transform($(esc(df)); ungroup=false)
else
local df_copy = copy($(esc(df)))
end
else
local df_copy = $(esc(df)) # not a copy

local orig_df = $(esc(df))
local is_grouped = orig_df isa GroupedDataFrame
local needs_temp = $any_found_n || $any_found_row_number

local df_copy = needs_temp ? (is_grouped ? transform(orig_df; ungroup=false) : copy(orig_df)) : orig_df

if $any_found_n
transform!(df_copy, nrow => :TidierData_n; ungroup=false)
end
if $any_found_row_number
transform!(df_copy, eachindex => :TidierData_row_number; ungroup=false)
end

if $(esc(df)) isa GroupedDataFrame
local col_names = groupcols($(esc(df)))
if $any_found_n
transform!(df_copy, nrow => :TidierData_n; ungroup=false)
end
if $any_found_row_number
transform!(df_copy, eachindex => :TidierData_row_number; ungroup=false)
local df_output
if is_grouped
local col_names = groupcols(orig_df)
df_output = combine(df_copy, $(tidy_exprs...); ungroup=true)
if $any_found_n || $any_found_row_number
select!(df_output, Cols(Not(r"^(TidierData_n|TidierData_row_number)$")))
end

if length(col_names) == 1
local df_output = combine(df_copy, $(tidy_exprs...); ungroup=true)
if $any_found_n || $any_found_row_number
select!(df_output, Cols(Not(r"^(TidierData_n|TidierData_row_number)$")))
end
else
local df_output = combine(df_copy, $(tidy_exprs...); ungroup=true)
if $any_found_n || $any_found_row_number
select!(df_output, Cols(Not(r"^(TidierData_n|TidierData_row_number)$")))
end
# Re-group if there is more than one grouping column.
if length(col_names) > 1
df_output = groupby(df_output, col_names[1:end-1]; sort=false)
end
else
if $any_found_n
transform!(df_copy, nrow => :TidierData_n; ungroup=false)
end
if $any_found_row_number
transform!(df_copy, eachindex => :TidierData_row_number; ungroup=false)
end
local df_output = combine(df_copy, $(tidy_exprs...))
df_output = combine(df_copy, $(tidy_exprs...))
if $any_found_n || $any_found_row_number
select!(df_output, Cols(Not(r"^(TidierData_n|TidierData_row_number)$")))
end
end

log[] && @info generate_log(df_copy, df_output, "@summarize", [:newsize])

df_output
end
if code[]
Expand Down
Loading