From 9e504d574414089feb3fa7f88b63454332a06723 Mon Sep 17 00:00:00 2001
From: Daniel Rizk <rizkytennis@gmail.com>
Date: Wed, 13 Nov 2024 17:59:04 -0500
Subject: [PATCH] fixes `@summary`

---
 NEWS.md           |  3 +++
 Project.toml      |  2 +-
 src/docstrings.jl |  3 ++-
 src/summary.jl    | 26 ++++++++++++++------------
 4 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/NEWS.md b/NEWS.md
index f221043c..43fe1b3c 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,5 +1,8 @@
 # TidierData.jl updates
 
+## v16.3
+- Bugfix: `@summary` will only act on numeric/integer columns, instead of throwing an error
+
 ## v0.16.2 - 2024-09-03
 - Bugfix: `@slice_min` and `@slice_max` respect the `n` argument
 - Adds `@head`
diff --git a/Project.toml b/Project.toml
index d7d9e33a..bd366a21 100644
--- a/Project.toml
+++ b/Project.toml
@@ -1,7 +1,7 @@
 name = "TidierData"
 uuid = "fe2206b3-d496-4ee9-a338-6a095c4ece80"
 authors = ["Karandeep Singh"]
-version = "0.16.2"
+version = "0.16.3"
 
 [deps]
 Chain = "8be319e6-bccf-4806-a6f7-6fae938471bc"
diff --git a/src/docstrings.jl b/src/docstrings.jl
index ae20886f..bf18730a 100644
--- a/src/docstrings.jl
+++ b/src/docstrings.jl
@@ -2415,7 +2415,8 @@ For numerical columns, returns a dataframe with the Q1,Q3, min, max, mean, media
 julia> df = DataFrame(a = [1, 2, 3, 4, 5],
                       b = [missing, 7, 8, 9, 10],
                       c = [11, missing, 13, 14, missing],
-                      d = [16, 17, 18, 19, 20]);
+                      d = [16.1, 17.2, 18.3, 19.4, 20.5],
+                      e = ["a", "a", "a", "a", "a"]);
 
 julia> @summary(df);
 
diff --git a/src/summary.jl b/src/summary.jl
index 68e0f295..126ba36f 100644
--- a/src/summary.jl
+++ b/src/summary.jl
@@ -3,18 +3,20 @@ function summary_stats(df::DataFrame)
     summary_data = []
     for column in colnames
         col = df[:, column]
-        col_nonmissing = collect(skipmissing(col))
-        push!(summary_data, (
-            Column = column,
-            Min = minimum(col_nonmissing),
-            Q1 = quantile(col_nonmissing, 0.25),
-            Median = median(col_nonmissing),
-            Mean = mean(col_nonmissing),
-            Q3 = quantile(col_nonmissing, 0.75),
-            Max = maximum(col_nonmissing),
-            Count = length(col_nonmissing),
-            Missing_Count = count(ismissing, col)
-        ))
+        if eltype(col) <: Union{Number, Missing}
+            col_nonmissing = collect(skipmissing(col))
+            push!(summary_data, (
+                Column = column,
+                Min = minimum(col_nonmissing),
+                Q1 = quantile(col_nonmissing, 0.25),
+                Median = median(col_nonmissing),
+                Mean = mean(col_nonmissing),
+                Q3 = quantile(col_nonmissing, 0.75),
+                Max = maximum(col_nonmissing),
+                Count = length(col_nonmissing),
+                Missing_Count = count(ismissing, col)
+            ))
+        end
     end
     return DataFrame(summary_data)
 end