#load in libraries and data
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.4
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(plotly)
## 
## Attaching package: 'plotly'
## 
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## 
## The following object is masked from 'package:stats':
## 
##     filter
## 
## The following object is masked from 'package:graphics':
## 
##     layout
wines <- read.csv("/Users/jamesflaumenhaft/STAT218/Homeworks/Wine_Training.csv")
#lets get an idea of the data by looking at the distribution of qualities
wines |>
  ggplot(aes(x = quality))+
  geom_bar()+ 
  geom_text(stat='count', aes(label=..count..), vjust= 0)
## Warning: The dot-dot notation (`..count..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(count)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

Interesting, so most wines fall between a quality 5 and 6. So, we want to be careful when selecting a variable to be sure it is predictive of these rarer qualities. That is to say, a simple regression maybe misleading because it could be really good at differentiating a 4 from 6 but not a 6 from an 8.

With this in mind, lets graph the variables that have the strongest regressions

First, volatile acidity a predictor of poor quality according to the regression

#volatile acidity and quality

wines|>
  ggplot()+
  geom_boxplot(aes(y = volatile.acidity, x = factor(quality)))+
   geom_point(aes(y = volatile.acidity, x = factor(quality)), fill=NA, shape=21)

This looks great!

#Next, lets look at chlorides

wines|>
  ggplot()+
  geom_boxplot(aes(y = chlorides, x = factor(quality)))+
   geom_point(aes(y = chlorides, x = factor(quality)), fill=NA, shape=21)

Does not look very promising. While these is a notable trend the differences between the means seem to subtle.

#Next, lets look at total sulfur dioxide

wines|>
  ggplot()+
  geom_boxplot(aes(y = total.sulfur.dioxide, x = factor(quality)))+
   geom_point(aes(y = total.sulfur.dioxide, x = factor(quality)), fill=NA, shape=21)

The mean differences betweeen the two extremes seem to similar.

#Next, sulphates (a positive predictor)
wines|>
  ggplot()+
  geom_boxplot(aes(y = sulphates, x = factor(quality)))+
   geom_point(aes(y = sulphates, x = factor(quality)), fill=NA, shape=21)

The jump from 6 to 7 looks pretty good and so does the over all trend, but the high outliers in the middle groups worry me.

#Next, alcohol (a positive predictor)
wines|>
  ggplot()+
  geom_boxplot(aes(y = alcohol, x = factor(quality)))+
   geom_point(aes(y = alcohol, x = factor(quality)), fill=NA, shape=21)

I worry about the differences between the two extremes, but there is definitely a strong trend.

Lets look at are seemingly best three variable graphed together.

#3d graph of volatile acidity, sulphates, and alcohol

wines|>
  plot_ly(x = ~volatile.acidity, y = ~sulphates, z = ~alcohol, color = ~factor(quality)) |> 
  add_markers() |> 
  layout(scene = list(xaxis = list(title = 'volatile.acidity'),
                      yaxis = list(title = 'sulphates'),
                      zaxis = list(title = 'alcohol')))

Does not look great but doesnt look bad. My worry is that we need to make a model that distinguish particularly accurately at the extremes and I think this could have trouble distinguishing between a 6 and a 7 for example.