From a2fe06a31c2bfc8e518d77f6d32f58fc6fd25dbb Mon Sep 17 00:00:00 2001
From: Kaylea Champion <khascall@gmail.com>
Date: Thu, 9 Nov 2023 10:10:40 -0800
Subject: [PATCH] adds this to git

'EDA' is Exploratory Data Analysis
---
 R/EDA.R | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
 create mode 100644 R/EDA.R

diff --git a/R/EDA.R b/R/EDA.R
new file mode 100644
index 0000000..67fd2ce
--- /dev/null
+++ b/R/EDA.R
@@ -0,0 +1,20 @@
+
+library(dplyr)
+df<-read.csv('~/Research/kkex_repo/power_data_110923.csv')
+
+hist(df$age/365) #there's a big bump at 9 years, why?
+hist(df$contributors) #skewed
+hist(log(df$contributors)) #better
+hist(df$collaborators) #skewed
+hist(log(df$collaborators)) #better
+hist(df$milestones)
+
+#one of many ways to generate a dichotomous variable
+df$uses_milestones <- case_when(df$milestones != 0 ~ TRUE, 
+                                .default = FALSE)
+
+table(df$uses_milestones)
+
+#playing around
+cor.test(df$contributors, as.numeric(df$uses_milestones))
+cor.test(df$collaborators, as.numeric(df$uses_milestones))