#Import the data set labeled as cocowater-1 (note that your data set has headers). Assign to the vector= df1
df2<-read.table("TIME.txt", header=TRUE)

#The data needs to be converted into a single vector.  Use the as.matrix function on the vector, then transpose by using the “t” function as you concatenate and assign to r
r<-c(t(as.matrix(df2)))

# Assign to f the treatment levels to f
f<-c("T1", "T2", "T3", "T4", "T5")

#Assign to k the number of treatment levels
k<- 5

#Assign to n the number of observations per treatments
n<-12

#Generate levels using the gl function on the basis of:
#Number of treatment levels
#Number of primary factors
#n*k
#factors as the treatment levels
tm<-gl(k, 1, n*k, factor(f))

#Subject to anova using the aov function the data set you have established (r) to the treatment factors (tm)
av2<- aov(r~tm)

summary(av2)
##             Df Sum Sq Mean Sq F value Pr(>F)    
## tm           4  77980   19495   57.35 <2e-16 ***
## Residuals   55  18697     340                   
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
TukeyHSD(av2)
##   Tukey multiple comparisons of means
##     95% family-wise confidence level
## 
## Fit: aov(formula = r ~ tm)
## 
## $tm
##           diff        lwr       upr     p adj
## T2-T1 -1.25000 -22.478999  19.97900 0.9998239
## T3-T1 52.50000  31.271001  73.72900 0.0000000
## T4-T1 64.91667  43.687668  86.14567 0.0000000
## T5-T1 89.25000  68.021001 110.47900 0.0000000
## T3-T2 53.75000  32.521001  74.97900 0.0000000
## T4-T2 66.16667  44.937668  87.39567 0.0000000
## T5-T2 90.50000  69.271001 111.72900 0.0000000
## T4-T3 12.41667  -8.812332  33.64567 0.4730601
## T5-T3 36.75000  15.521001  57.97900 0.0000895
## T5-T4 24.33333   3.104335  45.56233 0.0170039