def get_transform(nparray):
data_file = "framingham.csv"
numeric_var = [
"age",
"cigsPerDay",
"totChol",
"sysBP",
"diaBP",
"BMI",
"heartRate",
"glucose",
]
level_var = ["education"]
category_var = [
"male",
"currentSmoker",
"BPMeds",
"prevalentStroke",
"prevalentHyp",
"diabetes",
]
target = ["TenYearCHD"]
# Create Data object
data = Datasets(
data_file=data_file,
cat_cols=category_var,
num_cols=numeric_var,
level_cols=level_var,
label_col=target,
train=True,
)
return data.preprocess_newdata(nparray)
