diff --git a/.DS_Store b/.DS_Store index e12d4f5..db27f7c 100644 Binary files a/.DS_Store and b/.DS_Store differ diff --git a/src/TidierText.jl b/src/TidierText.jl index 2a75fe0..589d937 100644 --- a/src/TidierText.jl +++ b/src/TidierText.jl @@ -1,11 +1,11 @@ module TidierText + using MacroTools using StatsBase using Languages using DataFrames using Reexport - include("docstrings.jl") diff --git a/src/docstrings.jl b/src/docstrings.jl index 5097398..7b6e3c9 100644 --- a/src/docstrings.jl +++ b/src/docstrings.jl @@ -261,12 +261,12 @@ Creates character shingles of size `n` from the text in `input_col` of `df`, out # Examples ```jldoctest -julia> df = DataFrame( - text = [ - "The fox runs.", - "The sun rises."], doc = [1, 2]); +julia> df = DataFrame( + text = [ + "The fox runs.", + "The sun rises."], doc = [1, 2]); -julia> @unnest_character_shingles(df, term, text, 10, to_lower = false, strip_non_alphanum = true) +julia> @unnest_character_shingles(df, term, text, 10, to_lower = false, strip_non_alphanum = true) 7×2 DataFrame Row │ doc term │ Int64 String @@ -279,7 +279,7 @@ julia> @unnest_character_shingles(df, term, text, 10, to_lower = false, strip_n 6 │ 2 esunrise 7 │ 2 sunrises -julia> @unnest_character_shingles(df, term, text, 10, to_lower = true, strip_non_alphanum = false) +julia> @unnest_character_shingles(df, term, text, 10, to_lower = true, strip_non_alphanum = false) 9×2 DataFrame Row │ doc term │ Int64 String @@ -314,12 +314,12 @@ Splits the text in `input_col` of `df` into separate characters, outputting the # Examples ```jldoctest -julia> julia> df = DataFrame( +julia> df = DataFrame( text = [ "The quick.", "Nice."], doc = [1, 2]); -julia> @unnest_characters(df, term, text, to_lower = false) +julia> @unnest_characters(df, term, text, to_lower = false) Row │ doc term │ Int64 Char ─────┼─────────────