Created
June 12, 2019 12:49
-
-
Save khufkens/7283e3fc6f83881f11b659672c81e6e8 to your computer and use it in GitHub Desktop.
Ghent air quality study VMM rehash
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Ghent air pollution analysis | |
# parametric t-tests | |
# non-parametric Mann-Whitney U test | |
# download and collate the data | |
pdf_data <- paste0(pdftools::pdf_text("https://klimaat.stad.gent/sites/default/files/nota_circulatieplangent_3.pdf")[2], | |
collapse = " ") | |
# some regular expression moving about | |
subset <- gsub(',', ".", pdf_data) | |
subset <- gsub('\n', " ", subset) | |
subset <- unlist(strsplit(subset, "\\s{2,}"))[10:129] | |
# recast into a data frame | |
df <- data.frame(matrix(subset, 20,6, byrow = TRUE), | |
stringsAsFactors = FALSE) | |
# assign column names | |
names(df) <- c("meetplaatscode", | |
"straat", | |
"voor", | |
"na", | |
"verschil", | |
"verschil_perc") | |
# convert to numeric | |
df$voor <- as.numeric(df$voor) | |
df$na <- as.numeric(df$na) | |
df$verschil <- as.numeric(df$verschil) | |
# test for normality | |
s_test <- shapiro.test(df$verschil) | |
# t-test on the difference | |
t.test(df$voor, df$na) | |
t.test(df$voor, df$na + 3.7) | |
# non-parametric t-test | |
wilcox.test(df$voor, df$na) | |
wilcox.test(df$voor, df$na + 3.7) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment