Custom record validator function for training a model on UC Irvine's Heart Disease Dataset

customer_validator-uci.py

# Validate each generated record
# Note: This custom validator verifies the record structure matches
# the expected format for UCI healthcare data, and also that 
# generated records are Female (e.g. column 1 is 0)

def validate_record(line):
    rec = line.strip().split(",")
    if not int(rec[1]) == 0:
        raise Exception("record generated must be female")
    if len(rec) == 14:
        int(rec[0])
        int(rec[2])
        int(rec[3])
        int(rec[4])
        int(rec[5])
        int(rec[6])
        int(rec[7])
        int(rec[8])
        float(rec[9])
        int(rec[10])
        int(rec[11])
        int(rec[12])
        int(rec[13])
    else:
        raise Exception('record not 14 parts')