2024-06-10 21:05:31 +00:00
|
|
|
library(tidyverse)
|
|
|
|
|
library(plyr)
|
|
|
|
|
# script for the analysis of document readability metrics
|
|
|
|
|
# readability metrics will be studied controlled by their length
|
|
|
|
|
# gaughan@u.northwestern.edu
|
|
|
|
|
# loading in the data
|
|
|
|
|
try(setwd(dirname(rstudioapi::getActiveDocumentContext()$path)))
|
|
|
|
|
readme_df <- read_csv("../text_analysis/draft_readability_readme.csv")
|
|
|
|
|
contributing_df <- read_csv("../text_analysis/draft_readability_contributing.csv")
|
|
|
|
|
head(readme_df)
|
2024-06-19 23:40:22 +00:00
|
|
|
aggregate(readme_df[, 3:10], list(readme_df$subdir), median)
|
2024-06-10 21:05:31 +00:00
|
|
|
#readme_df <- readme_df |>
|
|
|
|
|
# mutate(coef_grouping <- as.factor(subdir))
|
|
|
|
|
#test_lm <- lm(mcalpine_eflaw ~ word_count + as.factor(subdir),data=readme_df)
|
|
|
|
|
#summary(test_lm)
|
2024-06-19 23:40:22 +00:00
|
|
|
aggregate(contributing_df[, 3:10], list(contributing_df$subdir), median)
|
