From 7ce256e541ce5d0051c3be32fbb3ae6410d31928 Mon Sep 17 00:00:00 2001
From: Kyle Belanger <kyleb44@hotmail.com>
Date: Mon, 5 Aug 2024 16:53:16 -0400
Subject: [PATCH] updates to Chap 4

---
 LearnJulia/src/Chapter4.jl | 41 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 39 insertions(+), 2 deletions(-)

diff --git a/LearnJulia/src/Chapter4.jl b/LearnJulia/src/Chapter4.jl
index 161a546..b22ea43 100644
--- a/LearnJulia/src/Chapter4.jl
+++ b/LearnJulia/src/Chapter4.jl
@@ -1,7 +1,10 @@
 using DataFrames
 using CSV
+using Dates
+using CategoricalArrays
+using DataFramesMeta
 
-# Julid for Data Sciences makes use of functions to keep variable scooping under control
+# Julia for Data Sciences makes use of functions to keep variable scooping under control
 
 function grades_2020()
   name = ["Sally", "Bob", "Alice", "Hank"]
@@ -14,6 +17,7 @@ function write_grades()
   CSV.write(path, grades_2020())
 end
 
+# Chapter 4.3
 
 filter(:name => ==("Alice"), grades_2020())
 
@@ -31,4 +35,37 @@ function salaries()
   DataFrame(; names, salary)
 end
 
-subset(salaries(), :salary => ByRow(>(2_000)); skipmissing = true)
\ No newline at end of file
+subset(salaries(), :salary => ByRow(>(2_000)); skipmissing = true)
+
+# Chapter 4.4
+function responses()
+  id = [1, 2]
+  q1 = [28, 61]
+  q2 = [:us, :fr]
+  q3 = ["F", "B"]
+  q4 = ["B", "C"]
+  q5 = ["A", "E"]
+  DataFrame(; id, q1, q2, q3, q4, q5)
+end
+
+renames = (1 => "particiapant", :q1 =>"age", :q2 => "nationality")
+select(responses(), renames...)
+
+# Chapter 4.5
+function wrong_types()
+  id = 1:4
+  date = ["28-01-2018", "03-04-2019", "01-08-2018", "22-11-2020"]
+  age = ["adolescent", "adult", "infant", "adult"]
+  DataFrame(; id, date, age)
+end
+
+# Trying out DataFramesMeta
+df = wrong_types()
+ages_levels = ["infant", "adolescent", "adult"]
+strings2dates(dates::Vector) = Date.(dates, dateformat"dd-mm-yyyy")
+
+
+@transform df begin
+  :date = strings2dates(:date)
+  :age = categorical(:age; levels = ages_levels, ordered = true)
+end