From 7bcf7ac4f8a24ec2c5b85b442293ee8c1d0f7d25 Mon Sep 17 00:00:00 2001
From: mjgaughan <mgaughan@proton.me>
Date: Mon, 13 Nov 2023 10:52:40 -0600
Subject: [PATCH] expanding matching for data

---
 R/EDA.R            |  2 +-
 R/calculatePower.R | 13 ++++++++-----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/R/EDA.R b/R/EDA.R
index 667dca3..0c018c3 100644
--- a/R/EDA.R
+++ b/R/EDA.R
@@ -36,7 +36,7 @@ t.test(df1$up.fac.mean)
 # -0.1961401 -0.1647757
 df$mmt <- (df$contributors + (2 * df$collaborators)) / (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:
 # 1.610638 1.684438
 #
\ No newline at end of file
diff --git a/R/calculatePower.R b/R/calculatePower.R
index 81dbd8d..29d3487 100644
--- a/R/calculatePower.R
+++ b/R/calculatePower.R
@@ -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')
 #d$nd <- to_logical(d$not.damaging, custom_true=c("Y")) 
 #levels(d$source) <- c("IP-based Editors", "New Editors", "Registered Editors", "Tor-based Editors")
-
-data1$up.fac.mean <- as.numeric(data2$up.fac.mean[match(data1$pkg, data2$pkg)])
-data1$milestones <- as.numeric(data1$milestones > 0) + 1
+python_labeled <- as.numeric(data2$up.fac.mean[match(paste('python',tolower(data1$pkg), sep = "-"), data2$pkg)])
+same_labeled <- as.numeric(data2$up.fac.mean[match(tolower(data1$pkg), data2$pkg)])
+data1$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
 data1$formal.score <- data1$mmt / (data1$milestones/data1$age)
 table(data1$milestones)
-hist(data1$mmt) #inequality of participation
+hist(data1$old_mmt) #inequality of participation
 hist(data1$formal.score)
 hist(data1$age/365)
 kmodel1 <- lm(up.fac.mean ~ mmt, data=data1)
 summary(kmodel1)
+kmodel1 <- lm(up.fac.mean ~ old_mmt, data=data1)
+summary(kmodel1)
 kmodel1 <- lm(up.fac.mean ~ formal.score, data=data1)
 summary(kmodel1)
 hist(data1$formal.score)
@@ -48,7 +51,7 @@ g <- ggplot(data1, aes(x=formal.score, y=up.fac.mean)) +
   geom_smooth()
 g
 
-data2 <- subset(data1, (data1$age / 365) < 9 )
+data2 <- subset(data1, (data1$age / 365) < 14 )
 hist(data2$age)
 g <- ggplot(data2, aes(x=formal.score, y=up.fac.mean)) +
   geom_point() +