pratmo / wine-pca-clustering Goto Github PK

Checking the number of clusters formed and the effect of PCA on the wine dataset by performing hierarchical and k-means clustering with and w/o PCA technique for dimentionality reduction.

Information about the Wine Dataset- There are 178 observations and 15 features. Input variables which includes 15 chemical and physical features of wine.

Below is brief description of each feature: Input variables (based on physicochemical tests):

Chemical and Physical Properties:

Alcohol: The percent alcohol content of the wine (% by volume)

Malic Acid : It is one of the principal organic acids found in wine grapes (g/l)

Ash : Ash content is one of the important indicators in wine quality determination (mS/cm)

Alcalinity : Several different types of acids found in wine affect how acidic a wine tastes. (pH)

Magnesium : Magnesium content in wines (gm per 1kg)

Total phenols : These are flavonoids that contribute to the construction of various tannins and contribute to the perception of bitterness in wine. (mg/L)

Flavanoid : Flavonoids are the most abundant polyphenols in the wine. (mg/L)

Non Flavanoid Phenols : Phenolic compounds in wine contribute specific characteristics to wine while also creating specific flavors and aromas when the complex interactions take place in wine during fermentation and wine-making. (mg/L)

Proanthocyanidins : A class of Phenol . (mg/L)

Color intensity : A simple measure of how dark the wine is.

Hue : It is one of the main properties of color.

OD280/ OD315 of Diluted Wine .

Proline : An amino-acid . (mg/L)