mgaughan/24_deb_pkg_gov
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

expanding matching for data

Browse Source
This commit is contained in:
mjgaughan 2023-11-13 10:52:40 -06:00
parent 9e6c28de9f
commit 7bcf7ac4f8
2 changed files with 9 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
R/EDA.R
View File

@ -36,7 +36,7 @@ t.test(df1$up.fac.mean)
# -0.1961401 -0.1647757 # -0.1961401 -0.1647757
df$mmt <- (df$contributors + (2 * df$collaborators)) / (df$contributors + df$collaborators) df$mmt <- (df$contributors + (2 * df$collaborators)) / (df$contributors + df$collaborators)
df$old_mmt <- (df$contributors) / (df$contributors + df$collaborators) df$old_mmt <- (df$contributors) / (df$contributors + df$collaborators)
t.test(df$mmt) t.test(df$old_mmt)
# 95 percent confidence interval: # 95 percent confidence interval:
# 1.610638 1.684438 # 1.610638 1.684438
# #

13
R/calculatePower.R
View File

@ -24,17 +24,20 @@ data1 <- read_csv('../power_data_111023_mmt.csv',show_col_types = FALSE)
data2 <- read_csv('../inst_all_packages_full_results.csv') data2 <- read_csv('../inst_all_packages_full_results.csv')
#d$nd <- to_logical(d$not.damaging, custom_true=c("Y")) #d$nd <- to_logical(d$not.damaging, custom_true=c("Y"))
#levels(d$source) <- c("IP-based Editors", "New Editors", "Registered Editors", "Tor-based Editors") #levels(d$source) <- c("IP-based Editors", "New Editors", "Registered Editors", "Tor-based Editors")
python_labeled <- as.numeric(data2$up.fac.mean[match(paste('python',tolower(data1$pkg), sep = "-"), data2$pkg)])
data1$up.fac.mean <- as.numeric(data2$up.fac.mean[match(data1$pkg, data2$pkg)]) same_labeled <- as.numeric(data2$up.fac.mean[match(tolower(data1$pkg), data2$pkg)])
data1$milestones <- as.numeric(data1$milestones > 0) + 1 data1$up.fac.mean <- pmin(python_labeled, same_labeled, na.rm=TRUE)
data1$milestones <- as.numeric(data1$milestones > 0)
# (2) - Run the model on the pilot data # (2) - Run the model on the pilot data
data1$formal.score <- data1$mmt / (data1$milestones/data1$age) data1$formal.score <- data1$mmt / (data1$milestones/data1$age)
table(data1$milestones) table(data1$milestones)
hist(data1$mmt) #inequality of participation hist(data1$old_mmt) #inequality of participation
hist(data1$formal.score) hist(data1$formal.score)
hist(data1$age/365) hist(data1$age/365)
kmodel1 <- lm(up.fac.mean ~ mmt, data=data1) kmodel1 <- lm(up.fac.mean ~ mmt, data=data1)
summary(kmodel1) summary(kmodel1)
kmodel1 <- lm(up.fac.mean ~ old_mmt, data=data1)
summary(kmodel1)
kmodel1 <- lm(up.fac.mean ~ formal.score, data=data1) kmodel1 <- lm(up.fac.mean ~ formal.score, data=data1)
summary(kmodel1) summary(kmodel1)
hist(data1$formal.score) hist(data1$formal.score)
@ -48,7 +51,7 @@ g <- ggplot(data1, aes(x=formal.score, y=up.fac.mean)) +
geom_smooth() geom_smooth()
g g
data2 <- subset(data1, (data1$age / 365) < 9 ) data2 <- subset(data1, (data1$age / 365) < 14 )
hist(data2$age) hist(data2$age)
g <- ggplot(data2, aes(x=formal.score, y=up.fac.mean)) + g <- ggplot(data2, aes(x=formal.score, y=up.fac.mean)) +
geom_point() + geom_point() +