PCA and Clustering
Objective
PCA is a dimension reduction technique. The data is represented in the form of components
where each component is a linear combination of original variables.It can be used for
correlated data.
Clustering or grouping is the detection of similarities.The goal of clustering is to identify
pattern or groups of similar objects within a data set of interest. It is a method of unsupervised
learning method.
PCA in conjunction with k-means is a powerful method for visualizing high dimensional data.
This dataset is originally from the National Institute of Diabetes and Digestive and Kidney
Diseases. It includes diabetes outcome and measurements of Glucose, Insulin, BMI et al.)I will
apply PCA and Clustering machine learning on presented measurements to detect the similarity
of data and group then into optimal clusters. The data download link
https://www.kaggle.com/mathchi/diabetes-data-set
Data Descriptions
• Pregnancies: Number of times pregnant
• Glucose: Plasma glucose concentration a 2 hours in an oral glucose tolerance test
• BP: Diastolic blood pressure (mm Hg)
• SkinThickness: Triceps skin fold thickness (mm)
• Insulin: 2-Hour serum insulin (mu U/ml)
• BMI: Body mass index (weight in kg/(height in m)^2)
• Pedigree : Diabetes pedigree function
• Age: Age (years)
• Outcome: Class variable (0 = No ; 1 = Yes)
Exploring the data uing PCA
•STEP 1: Load the Libraries
•STEP 2: Load the data set
• Examine the structure of the Dmdata frame
• from the results we notice the unusual scenario of zero in Glucose, BP, SkinTHickness,
Insulin and BMI; presumably those are NA
•
