Trusted by +2 million users,
1000+ happy students everyday
1000+ happy students everyday
Showing pages 1 to 4 of 18 pages
Visual AnalyticsRed Wine and White Wine Quality Analysis ConsideringInternal CompositionsStudent Name:Student ID:Course Name:Course ID:Faculty Name:University Name:
IntroductionThe paper is concerned with the study of white wine and red wine quality in relation to thepresence of various components in them such as alcohol, sulphur, residual sugar, and other.The major focus is to understand the quality ratings of the wines. The first chapter discussesthe motivation behind conducting this study and the type of data being used. Moreover, someresearch questions have been developed which is likely to be answered at the end of thisresearch. The next chapter is concerned with understanding the approach of the research. Thechapter of analytical steps discusses the ways considered for reaching the results. The chapteron finding discusses the important findings and answers the research questions. The finalchapter critically analyses the implications of the findings and the other aspects.Motivation, Data, Research QuestionsThe wine quality is an important aspect in attracting the customers to make the purchase(Charters and Pettigrew, 2007). There are various chemicals aspects within the wine thatimpacts the rating of the wines by the customers. The presence of one aspect and the absenceof another change the way wines taste. These chemical components are integral part to thewine quality (Bell et al, 1979). This research paper is focused towards assessing thecomponents that plays major role in quality ratings of the wines. This paper has selected twotypes of wine for the study, one is red wine and another is white wine.Motivation for the StudyThe benefits of understanding what components lead to better ratings of the wine are wide.The companies involved in the development of wines must be curious to know the reasonswhy particular wine category is rated good by the customers and other is not (O’Neill andCharters, 2000). The study will be demystifying the factors that are important to be kept inconsideration while manufacturing wines. The two major wine categories are normallymanufactured by the companies, red wine, and white wine. The comparative study ofelements within the red and white wine will help companies in deciding which one toproduce and with what composition.Data and its SuitabilityThere are two types of data that has been collected for analysis of the wine quality. The datahas been brought from the secondary sources. The UCI Machine Learning Repository whichcollects data in association with National Science Foundation and Rexa.info(Archive.ics.uci.edu, 2009). The two data sets taken for the analyses are related to thePortuguese “Vinho Verde” wine. It is a wine company situated in Portuguese. As per the datasource, the data variables are related only to the physiochemical (input) and sensory (output).The reason is cited is privacy and logistic challenges. The input variables that are present inthe data are given below:1 - fixed acidity2 - volatile acidity
3 - citric acid4 - residual sugar5 - chlorides6 - free sulfur dioxide7 - total sulfur dioxide8 - density9 - pH10 - sulphates11 - alcoholThe output variable of the data is:12 – Quality (score between 0 and 10)In total, there are 12 attributes within the data set and the total number of instances is 4898(Archive.ics.uci.edu, 2009). The data set and attribute characteristics are multivariate and realrespectively. All these data are from particular Portugal region only.Research Questions to InvestigateThe research questions have been prepared concerning the topic of the research. The researchquestions are:-What are the major and important factors that impact the wine quality preferences?-How understanding components behind wine quality is beneficial in wine production?These are the questions that will be answered through the investigation. However, it cannotbe stated at this point that the research will lead to understanding all the questions that putforward for the study.Tasks and ApproachThis chapter discusses the visual and computational techniques that have been used in theconduction of this research. The paper has considered the utilization of R as the softwaretools to analyse the data. The statistical tools that have been used to analyse the data aredistribution analysis for the data of red and white wine, scatter plot matrix, correlationanalysis, and analysis plot. The data were passed through these statistical tests and the visualpresentation of each analysis has been presented in the next chapter. The R software has beenused which is a free statistical computing software which is capable enough to carry outnecessary statistical tasks. The distribution analysis was the first step through which all thedata was passed. The distribution analysis helps make the data readable and understandablefor human eye and mind (Dixon and Massey, 1957). The visual analysis method has beenused in this paper (Van and Jewitt, 2001).
Analytical StepsThis chapter is concerned with the analysis of the data brought in from the secondaryresource. The analysis has been conducted considering the below mentioned parameters:coho:It is the important aspect for the wine quality and therefore it has been considered tounderstand the quality (Darias-Martin et al, 2002).SO2values:The analysis will focus on the effect this chemical has on the qualitydetermination of the wine (Bakker et al, 1998).Alcohol content:It is also an important variable that determines the quality of the wine. Wineis an alcoholic product and the customers’ prefer its quantity.The further analysis is focused on analysing these three parameters together and tries tounderstand the effect it has on the wine quality.Distribution Analysis for Red WineFrom the plot given below for the red wine, it can be stated that the pH value is normallydistributed as the major portion of the collected data is from 3.0 to 3.5. The free SO2isbetween 1 and 100 and more inclined around 50. The similar is with total SO2; however it’sspreading is from 0 to 300 and collects around 150. The alcohol is from 8 to 15 andconcentrates around 10.