Resultados CTU19_RandomForest

library(ggplot2)
library(dplyr)
library(tidyr)
library(stringr)

Parte Uno

Tt <- Puro_N %>% select(-standard_deviation) %>% mutate(PuroSN = Puro_SN$prom) %>% mutate(DownN = Down_N$prom) %>% mutate(DownSN = Down_SN$prom) %>% 
  mutate(UpN = Up_N$prom) %>% mutate(UpSN = Up_SN$prom) 
colnames(Tt)[2] <- "PuroN"

Tsd <- Puro_N %>% select(-prom) %>% mutate(PuroSN = Puro_SN$standard_deviation) %>% mutate(DownN = Down_N$standard_deviation) %>%
  mutate(DownSN = Down_SN$standard_deviation) %>% mutate(UpN = Up_N$standard_deviation) %>% mutate(UpSN = Up_SN$standard_deviation) 

Tengo mejores resultados luego de aplicar DownSampling. Tambien tengo mejores resultados con los feature vectors sin normalizar, aunque esta mejora es extremadamente minima.

Tt %>% pivot_longer(cols = -X1) %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>%
  ggplot()+
  geom_col(aes(x=name,y=value), fill="skyblue")+
  facet_wrap(~X1)+
  theme_bw()

Como vemos la desviacion nunca es mayor a 0.04.

Tsd %>% pivot_longer(cols = -X1) %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>%
  ggplot()+
  geom_point(aes(x=name,y=value), fill="skyblue")+
  facet_wrap(~X1)+
  theme_bw()

Parte Dos

PuroN <- PuroV_N %>% mutate(test = "PuroN") %>% 
  select(-standard_deviation,-standard_deviation.1,-standard_deviation.2,-standard_deviation.3,
         -standard_deviation.4,-standard_deviation.5,-standard_deviation.6,-standard_deviation.7,-standard_deviation.8)

PuroSN <- PuroV_SN %>% mutate(test = "PuroSN") %>% 
  select(-standard_deviation,-standard_deviation.1,-standard_deviation.2,-standard_deviation.3,
         -standard_deviation.4,-standard_deviation.5,-standard_deviation.6,-standard_deviation.7,-standard_deviation.8)

DownN <- DownV_N %>% mutate(test = "DownN") %>% 
  select(-standard_deviation,-standard_deviation.1,-standard_deviation.2,-standard_deviation.3,
         -standard_deviation.4,-standard_deviation.5,-standard_deviation.6,-standard_deviation.7,-standard_deviation.8)

DownSN <- DownV_SN %>% mutate(test = "DownSN") %>% 
  select(-standard_deviation,-standard_deviation.1,-standard_deviation.2,-standard_deviation.3,
         -standard_deviation.4,-standard_deviation.5,-standard_deviation.6,-standard_deviation.7,-standard_deviation.8)

UpN <- UpV_N %>% mutate(test = "UpN") %>% 
  select(-standard_deviation,-standard_deviation.1,-standard_deviation.2,-standard_deviation.3,
         -standard_deviation.4,-standard_deviation.5,-standard_deviation.6,-standard_deviation.7,-standard_deviation.8)

UpSN <- UpV_SN %>% mutate(test = "UpSN") %>% 
  select(-standard_deviation,-standard_deviation.1,-standard_deviation.2,-standard_deviation.3,
         -standard_deviation.4,-standard_deviation.5,-standard_deviation.6,-standard_deviation.7,-standard_deviation.8)

PuroN <- PuroN %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>% select(-X1) %>% pivot_longer(cols = -test) %>% select(-name)
PuroSN <- PuroSN %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>% select(-X1) %>% pivot_longer(cols = -test) %>% select(-name)
DownN <- DownN %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>% select(-X1) %>% pivot_longer(cols = -test) %>% select(-name)
DownSN <- DownSN %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>% select(-X1) %>% pivot_longer(cols = -test) %>% select(-name)
UpN <- UpN %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>% select(-X1) %>% pivot_longer(cols = -test) %>% select(-name)
UpSN <- UpSN %>% filter(X1 %in% c("Sensitivity","Specificity","F1","Balanced Accuracy")) %>% select(-X1) %>% pivot_longer(cols = -test) %>% select(-name)

name <- c("Sensitivity.0","Sensitivity.1","Sensitivity.2","Sensitivity.3","Sensitivity.4","Sensitivity.5","Sensitivity.6","Sensitivity.7","Sensitivity.8","Specificity.0","Specificity.1","Specificity.2","Specificity.3","Specificity.4","Specificity.5","Specificity.6","Specificity.7","Specificity.8","F1.0","F1.1","F1.2","F1.3","F1.4","F1.5","F1.6","F1.7","F1.8","BAccuracy.0","BAccuracy.1","BAccuracy.2","BAccuracy.3","BAccuracy.4","BAccuracy.5","BAccuracy.6","BAccuracy.7","BAccuracy.8")
PuroN <- PuroN %>% cbind(name)
PuroSN <- PuroSN %>% cbind(name)
DownN <- DownN %>% cbind(name)
DownSN <- DownSN %>% cbind(name)
UpN <- UpN %>% cbind(name)
UpSN <- UpSN %>% cbind(name)

Ahora falta meter todo en un mismo dataset para poder graficar.

Tsec <- PuroN %>% rbind(PuroSN) %>% rbind(DownN) %>% rbind(DownSN) %>% rbind(UpN) %>% rbind(UpSN)
Tsec

Tsec %>%
  ggplot()+
  geom_col(aes(x=test,y=value), fill="skyblue")+
  facet_wrap(~name, ncol = 9)+
  theme_bw()

Analizando Solo Normalizado

Tsecc <- PuroN %>% rbind(DownN) %>% rbind(UpN)
Tsecc

Tsecc %>%
  ggplot()+
  geom_col(aes(x=test,y=value), fill="skyblue")+
  facet_wrap(~name, ncol = 9)+
  theme_bw()

Analizando solo Puro Normalizado

Balanced accuracy

PuroN %>% filter(grepl("BA",name)) %>%
  ggplot()+
  geom_col(aes(x=name,y=value), fill="skyblue")+
  theme_bw()

Specificty

PuroN %>% filter(grepl("Sp",name)) %>%
  ggplot()+
  geom_col(aes(x=name,y=value), fill="skyblue")+
  theme_bw()