27th January 2018

Overview

Data

Uses the Wine Reviews dataset provided by the Kaggle: https://www.kaggle.com/zynicide/wine-reviews The dataset contains 130k wine reviews with variety, location, winery, price, and description.

The data consists of 10 fields, which following will be used:

  • Points: the number of points WineEnthusiast rated the wine on a scale of 1-100.
  • Description: a few sentences from a sommelier describing the wine's taste, smell, look, feel, etc.
  • Country: the country that the wine is from.
  • Price: the cost for a bottle of the wine.
  • Taster Name: name of the person who tasted and reviewed the wine.

Instructions

The wine recommendation app will pick top10 wines for you based on your selections. You can specify:

  1. Country
  2. Price

Results will be shown in a table.

How does it work?

The wine dataset is filtered based on selections given by a user. Please find an example below (with harcoded values Chile and max price 20 $)

    # Filter the data by country and price
    filtered <- wine_DT %>% 
                filter(country %in% 'Chile') %>% 
                filter(price <= 20)  %>% arrange(desc(points))
    
    filtered <- head(filtered, 5)
    filtered
##   country points price       taster_name
## 1   Chile     92    20 Michael Schachner
## 2   Chile     92    20 Michael Schachner
## 3   Chile     92    20 Michael Schachner
## 4   Chile     92    20 Michael Schachner
## 5   Chile     92    20 Michael Schachner