Add code and results for the various metrics

notebooks/Synthetic_Data_Evaluation.Rmd

@@ -0,0 +1,120 @@
+---
+title: "R Notebook"
+output: html_notebook
+---
+```{r}
+source("../scripts/Equity_metrics.R")
+source("../scripts/sunburst_process.R")
+source("../scripts/table_process.R")
+library(plotly)
+library(formattable)
+```
+
+
+Read in the datasets
+```{r}
+ATUSreference<-read.csv(file = "../data/Atus/atus_train.csv")
+ATUSsynthetic<-read.csv(file = "../data/Atus/atus_train_synthetic.csv")
+
+MIMICRacereference<-read.csv(file = "../data/Mimic/mimic_3.csv")
+MIMICRacesynthetic<-read.csv(file = "../data/Mimic/mimic_3_synthetic.csv")
+```
+
+
+Preprocess the ATUS data
+```{r}
+ATUSreference_processed<-ATUSreference %>% 
+  group_by(TESEX, TEAGE) %>% 
+  summarise(background_n = n())
+colnames(ATUSreference_processed)<-c("Gender","Age","background_n")
+
+ATUSsynthetic_processed<-ATUSsynthetic %>% 
+  group_by(TESEX, TEAGE) %>% 
+  summarise(background_n = n())
+colnames(ATUSsynthetic_processed)<-c("Gender","Age","user_n")
+  
+
+ATUSreference_processed<-ATUSreference_processed %>% mutate(Gender=recode(Gender, 
+                         `1`="Male",
+                         `2`="Female"),
+                         Age=recode(Age, 
+                         `0`="15-24",
+                         `1`="25-34",
+                         `2`="35-44",
+                         `3`="45-54",
+                         `4`="55-64",
+                         `5`="65-74",
+                         `6`="75+"))
+
+ATUSsynthetic_processed<-ATUSsynthetic_processed %>% mutate(Gender=recode(Gender, 
+                         `1`="Male",
+                         `2`="Female"),
+                         Age=recode(Age, 
+                         `0`="15-24",
+                         `1`="25-34",
+                         `2`="35-44",
+                         `3`="45-54",
+                         `4`="55-64",
+                         `5`="65-74",
+                         `6`="75+"))
+
+```
+
+Preprocess the MIMIC data
+```{r}
+MIMICRacereference_processed<-MIMICRacereference %>%
+  group_by(GENDER,AGE,ETHNICITY,mortality_withinthirtydays) %>%
+  summarise(background_n = n())
+colnames(MIMICRacereference_processed)<-c("Gender","Age","Ethnicity","Mortality","background_n")
+
+MIMICRacesynthetic_processed<-MIMICRacesynthetic %>%
+  group_by(GENDER,AGE, ETHNICITY, mortality_withinthirtydays) %>%
+  summarise(background_n = n())
+colnames(MIMICRacesynthetic_processed)<-c("Gender","Age","Ethnicity","Mortality","user_n")
+
+
+MIMICRacereference_processed$Mortality<-as.factor(MIMICRacereference_processed$Mortality)
+MIMICRacesynthetic_processed$Mortality<-as.factor(MIMICRacesynthetic_processed$Mortality)
+
+
+MIMICRacereference_processed<-MIMICRacereference_processed %>% mutate(Gender=recode(Gender, 
+                         `M`="Male",
+                         `F`="Female"),
+            Mortality =recode(Mortality, 
+                         `0`="Alive",
+                         `1`="Died"))
+
+MIMICRacesynthetic_processed<-MIMICRacesynthetic_processed %>% mutate(Gender=recode(Gender, 
+                         `M`="Male",
+                         `F`="Female"),
+            Mortality =recode(Mortality, 
+                         `0`="Alive",
+                         `1`="Died"))
+```
+
+
+Evaluation on ATUS data 
+```{r}
+test_sunburst2(ATUSreference_processed,c("Gender","Age"),ATUSsynthetic_processed, "ATUSEquity1.csv", sig_t = 0.05,lower_t = -log(0.9), upper_t = -log(0.8) )
+```
+
+Evaluation on MIMIC data
+```{r}
+test_sunburst2(MIMICRacereference_processed,c("Mortality","Ethnicity","Age","Gender"),MIMICRacesynthetic_processed,"MIMICRaceEquity1.csv", sig_t = 0.05,lower_t = -log(0.9), upper_t = -log(0.8))
+```
+
+Tables for ATUS and MIMIC with significance threshold =0.05, lower metric threshold = -log(0.9), upper metric threshold = -log(0.8), metric = log disparity
+```{r}
+generate_table(0.05,-log(0.9),-log(0.8), "LDI", "ATUS")
+generate_table(0.05,-log(0.9),-log(0.8), "LDI", "MIMIC")
+```
+
+
+
+
+
+
+
+
+
+

results/ATUSEquity1.csv

@@ -0,0 +1,17 @@
+"","ids","labels","parents","Observed_Rate","Ideal_Rate","EquityColors","EquityLable","EquityValue","Observed_Number","Trial_Number"
+"1","Female - 15-24","15-24","Female",0.066,0.0637,"#d4e6e8","Equitable(p)",0.0382,1980,30000
+"2","Female - 25-34","25-34","Female",0.1,0.0986,"#d4e6e8","Equitable(p)",0.0189,3010,30000
+"3","Female - 35-44","35-44","Female",0.131,0.123,"#d4e6e8","Equitable",0.0659,3916,30000
+"4","Female - 45-54","45-54","Female",0.101,0.103,"#d4e6e8","Equitable(p)",-0.0175,3029,30000
+"5","Female - 55-64","55-64","Female",0.0743,0.0766,"#d4e6e8","Equitable(p)",-0.0319,2230,30000
+"6","Female - 65-74","65-74","Female",0.0565,0.0546,"#d4e6e8","Equitable(p)",0.0348,1694,30000
+"7","Female - 75+","75+","Female",0.0445,0.0504,"#eabcad","Underrepresented",-0.13,1335,30000
+"8","Female","Female","",0.573,0.57,"#d4e6e8","Equitable(p)",0.014,17194,30000
+"9","Male - 15-24","15-24","Male",0.0514,0.0554,"#d4e6e8","Equitable(p)",-0.0784,1543,30000
+"10","Male - 25-34","25-34","Male",0.0782,0.0688,"#a5b0cb","Overrepresented",0.138,2346,30000
+"11","Male - 35-44","35-44","Male",0.0995,0.099,"#d4e6e8","Equitable(p)",0.00525,2985,30000
+"12","Male - 45-54","45-54","Male",0.0788,0.0816,"#d4e6e8","Equitable(p)",-0.0389,2363,30000
+"13","Male - 55-64","55-64","Male",0.0559,0.0584,"#d4e6e8","Equitable(p)",-0.0478,1676,30000
+"14","Male - 65-74","65-74","Male",0.0373,0.0399,"#d4e6e8","Equitable(p)",-0.0692,1119,30000
+"15","Male - 75+","75+","Male",0.0258,0.0271,"#d4e6e8","Equitable(p)",-0.0502,774,30000
+"16","Male","Male","",0.427,0.43,"#d4e6e8","Equitable(p)",-0.014,12806,30000