first_observations.Rmd

---
title: "Trials Population VEF"
output:
  html_document:
    toc: true
    toc_float: true
    df_print: paged
---

## Description

Below is a description of the VEF population (Vivero equipo frijol), which has information from 2013 to 2014.

----


## Dataset Global




```{r , echo=FALSE, warning=FALSE,message=FALSE}
library(plotly)
library(ggplot2)
library(dplyr)
library(RColorBrewer)
```


```{r rows.print=5,echo=FALSE}
file <- "D:/APARICIO JOHAN/CGIAR/Ariza, Daniel (CIAT) - Johan/VEF_raw_data/all_merged_to_send.csv"
#file <- "C:/Users/johan/CGIAR/Ariza, Daniel (CIAT) - Johan_Aparicio/VEF_raw_data/all_merged_to_send.csv"
Data <- read.csv(file)
head(Data)
```

<br>

The notation used for each trial is given by:

$$Pal14C\_drt$$

1. the location where the trial was conducted
1. the year in which it took place
1. the quarter of the year
1. the conditions or stress to which the test was submitted


<br>

<br>

<center>
```{r , echo=FALSE, warning=FALSE,message=FALSE, rows.print=12}
Data %>% group_by(dataset) %>% 
  summarise(Number_Gen=n_distinct(line),
            Number_Rep=n_distinct(rep),
            Number_Block=n_distinct(block)) -> Gen
Gen
```
</center>

<br>

<center>
```{r, echo=FALSE, warning=FALSE,message=FALSE}
library(dplyr)
library(reshape)
introduced <- function(datosVEF){
k <- list()
for (i in 1:nlevels(datosVEF$dataset)) {
  k[[i]] <-  droplevels(datosVEF$line[datosVEF$dataset==levels(datosVEF$dataset)[i]])
  names(k)[i] <- levels(datosVEF$dataset)[i]
}

Datasets <- nlevels(datosVEF$dataset)
Line_GL <- levels(datosVEF$line)
Binary <- matrix(NA,nrow = length(Line_GL), ncol = Datasets )


# Matriz Binaria 
for (i in 1:Datasets) {
  Binary[,i] <- ifelse(Line_GL%in%k[[i]], 1 , 0)
}
colnames(Binary) <- names(k)
rownames(Binary) <- Line_GL

# Ordenar por a?o
Binary <- Binary[,c(4:9,1,3,10,11,12)]
Trials <- 11
# Nuevo Orden
Order_K <- c(k[4:9],k[1],k[3],k[10:12])

# Codigo-----------------------------------
w <- matrix(NA,Trials,Trials)

for (i in 1:(Trials-1)) {
  for (j in 1:(Trials-1)) {
    w[i+1,j] <- length(Reduce(intersect, Order_K[j:(i+1)]))
  }
}
diag(w) <- colSums(Binary)[1:Trials]
for (i in Trials:2) {
 w[,i] <- w[,i]-w[,i-1]
}
for (i in 1:(Trials-1)) {
  for (j in 1:(Trials-1)) {
    if (j>i) {
      w[i,j] <- 0
    }
  }
}
#----------------------------------------

# Matriz
rownames(w) <- colnames(Binary)
colnames(w) <- colnames(Binary)
w <- melt(w)
w$value <- ifelse(w$value==0,NA,w$value)
w$X2 <- factor(w$X2, levels = rev(levels(w$X2)) )
names(w) <- c("Trial", "Introduced","Freq")

w %>% filter(Freq > 3) -> w

# GGPLOT
library(RColorBrewer)
library(ggplot2)
p <- ggplot(w, aes(x = Trial, y = Freq,fill=Introduced, label = Freq)) +
  geom_bar(stat = "identity", colour="black") +
  guides(fill=guide_legend(reverse = TRUE))+
  geom_text(size = 3, position = position_stack(vjust = 0.5))+theme_bw(base_size = 13)+
  theme(legend.position="top",axis.text.x = element_text(angle = 90, hjust = 1))+ ylab("Number of Lines")+
  scale_fill_manual(values = rev(brewer.pal(7,"Pastel1")))+
  scale_x_discrete(limits=c("Pal13C_drt", "Pal14A_irr", "Pal14C_drt", "Pal15C_drt", "Pal15C_irr",
                            "Pal16C_drt","Dar16C_hiP" ,"Dar16C_mdP", "Pal17C_drt", "Pal18A_irr" ,
                            "Pal18C_drt"))
return(p)
}
datosVEF <- read.csv(file = file)
ggplotly(introduced(datosVEF))
```
</center>



<br>

<center>
```{r , echo=FALSE, warning=FALSE,message=FALSE  }
k <- brewer.pal(12,"Set3")
k[9] <- "#CD534CFF" ;  k[12] <- "#CD534CFF"

Data %>% 
  group_by(dataset) %>% 
  summarise(Total=n()) -> conteo 

g <- ggplot(conteo, aes(dataset,y=Total, fill=dataset,label=Total))+
     geom_bar(stat = "identity", colour="black") +
     guides(fill=guide_legend(reverse = TRUE))+
     geom_text(size = 3, position = position_stack(vjust = 0.5))+theme_bw(base_size = 13)+
     scale_x_discrete(limits=c("Pal13C_drt", "Pal14A_irr", "Pal14C_drt", "Pal15C_drt", "Pal15C_irr",
                               "Pal16C_drt","Dar16C_hiP" ,"Dar16C_mdP", "Dar16C_loP"  , "Pal17C_drt",                                           "Pal18A_irr" ,"Pal18C_drt"))+ 
     scale_fill_manual(values = k )+ 
  theme(legend.position="top",axis.text.x = element_text(angle = 90, hjust = 1))
  
ggplotly(g)
```
</center>

## End


----