MCA.Rmd

---
title: "MCA"
author: "Dalmas Otieno"
date: "February 12, 2018"
output: github_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```
```{r}
library(FactoMineR)
library(ggplot2)
data(tea)
View(tea)
```

```{r}
newtea=tea[,c("Tea","How","how","sugar","where","always")]
head(newtea)
```


```{r}
g<-function(x){
  nlevels(as.factor(x))
}
cuts<-apply(newtea,2,g)
#cuts function(x) nlevels(as.factor(x))
cuts
```


##mca
```{r}
mca1<-MCA(newtea,graph = FALSE)
mca1
```



```{r}
# data frame with variable coordinates
mca1_vars_df = data.frame(mca1$var$coord, Variable = rep(names(cuts), cuts))
#rep(names(cuts), cuts)
#View(mca1_vars_df)
# data frame with observation coordinates
mca1_obs_df = data.frame(mca1$ind$coord)
#View(mca1_obs_df)
# plot of variable categories
ggplot(data=mca1_vars_df, 
       aes(x = Dim.1, y = Dim.2, label = rownames(mca1_vars_df))) +
 geom_hline(yintercept = 0, colour = "gray70") +
 geom_vline(xintercept = 0, colour = "gray70") +
 geom_text(aes(colour=Variable)) +
 ggtitle("MCA plot of variables using R package FactoMineR")
```

```{r}
# MCA plot of observations and categories
ggplot(data = mca1_obs_df, aes(x = Dim.1, y = Dim.2)) +
  geom_hline(yintercept = 0, colour = "gray70") +
  geom_vline(xintercept = 0, colour = "gray70") +
  geom_point(colour = "gray50", alpha = 0.7) +
  geom_density2d(colour = "gray80") +
  geom_text(data = mca1_vars_df, 
            aes(x = Dim.1, y = Dim.2, 
                label = rownames(mca1_vars_df), colour = Variable)) +
  ggtitle("MCA plot of variables using R package FactoMineR") +
  scale_colour_discrete(name = "Variable")

```