t.test - test sprawdzenia srednich dwoch grup
jak 0.05 < to hipoteza

t.test:
tabelka:
        |gen    |  p.value|
        |-----------------|
        |cos    |   cos   |







library(dplyr)
library(caret)
library(randomForest)
library(ModelMetrics)
setwd("F:/pajtoon/lab 11")
load('dataLeukemia.RData')

View(data[1:100,1:100])
names(data)[1:10]
unique(data$Leukemia.class)

set.data = data[data$Leukemia.class == "AML with normal karyotype + other abnormalities" |data$Leukemia.class == "CLL", -c(1,3)]
set.data$Leukemia.class = as.numeric(set.data$Leukemia.class)/6-1
View(set.data[,1:100])
rm(data)
v=1:length(set.data$Leukemia.class)

index.test = sample(v,round(length(set.data$Leukemia.class)/3))
index.train = v[-index.test]

data.train = set.data[index.train,]
data.test = set.data[index.test,]

result = randomForest(x=data.train[,-1], y=as.factor(data.train[,1]), importance = TRUE)
var.imp = result$importance  # View(var.imp)
var.imp100 = row.names(var.imp[order(var.imp[,4], decreasing = TRUE),])[1:100]
View(var.imp[order(var.imp[,4], decreasing = TRUE),])
var.pred.test = predict(result, x=data.test[,var.imp100])
print(auc(as.factor(data.test[,1]), var.pred.test))

result2 = randomForest(x=data.train[,var.imp100], y=as.factor(data.train[,1]), importance = TRUE)
var.pred.test = predict(result2, x=data.test[,var.imp100])
print(auc(as.factor(data.test[,1]), var.pred.test))



#####
gene.vac = set.data[,1:2]
View(gene.vac)
geneCLL = gene.vac[gene.vac$Leukemia.class == 0,]
geneAML = gene.vac[gene.vac$Leukemia.class == 1,]
p.value = t.test(geneCLL, geneAML)$p.value
p.value
# t-test dla wszystkich kolumn
Ttest= function(set.data.i){
  gene.vac = set.data[,c(1,i)]
  geneCLL = gene.vac[gene.vac$Leukemia.class ==0,]
  geneAML = gene.vac[gene.vac$Leukemia.class ==1,]
  p.value= t.test(geneCLL, geneAML)$p.value
}

list() ->pvalue
for (i in 2:54676) {
  pvalue[(i)] = Ttest(set.data,i)
}

data.frame.pvalue = cbind(names(set.data)[-1], unlist(pvalue))
data.frame.pvalue.order = as.data.frame(data.frame.pvalue[order(as.numeric(data.frame.pvalue[,2]), decreasing = FALSE),])
names(data.frame.pvalue.order)

p.value.corect = p.adjust(data.frame.pvalue.order[,2], method = "BH")
View(p.value.corect)













table(data$Leukemia.class)

cechy <- filter(data$Leukemia.class == "CLL", data$Leukemia.class == "AML with normal karyotype + other abnormalities")

data.asd <- data[data$Leukemia.class == "CLL" | data$Leukemia.class == "AML with normal karyotype + other abnormalities"]

rows <- sample.int(nrow(data), size = round(nrow(data)/3), replace = F)
data.train <- data[-rows,]
data.test <- data[rows,]

View(data.test[1:100,1:100])

library(randomForest)
model.rf <- randomForest(x = data.train[-2], y = data.train[,2], ntree = 100 , do.trace = 10)

rf.result <- predict(model.rf , newdata = data.test[,-2])
error.rf1 <- sum(data.test[,2] != rf.result)/length(rf.result)


###
gene.vac = set.data[,1:2]
geneCLL = gene.vac[gene.vac$]