This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. The objective is to predict based on diagnostic measurements whether a patient has diabetes.

Several constraints were placed on the selection of these instances from a larger database. In particular, all patients here are females at least 21 years old of Pima Indian heritage.

Diabetes files consist of 8 fields per record.  Each field is
separated by a comma and each record is separated by a newline.

CSV Columns and format:
(1) Pregnancies (Integer) : Number of times pregnant
(2) Glucose (Integer) : Plasma glucose concentration a 2 hours in an oral glucose tolerance test
(3) Blood Pressure (Integer) : Diastolic blood pressure (mm Hg)
(4) Skin Thickness (Integer) : Triceps skin fold thickness (mm)
(5) Insulin (Integer) : 2-Hour serum insulin (mu U/ml)
(6) BMI (Float) : Body mass index (weight in kg/(height in m)^2)
(6) Diabetes Pedigree (Float) : Diabetes Pedigree Function
(7) Age (Integer): Patient's age (years)
(8) Outcome (Integer): Class variable (0 or 1)
