File size: 3,232 Bytes
0a4a484 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
import pandas as pd
import numpy as np
def data_imp():
feature_descriptions = {
"CustID": "Unique identifier for each customer.",
"FirstPolYear": "Year when the customer first bought an insurance policy.",
"BirthYear": "Birth year of the customer, used to calculate age.",
"EducDeg": "Highest educational degree obtained by the customer.",
"MonthSal": "Monthly salary of the customer. (Numerical, float64)",
"GeoLivArea": "Geographical area where the customer lives.",
"Children": "Number of children the customer has.",
"CustMonVal": "Total monetary value of the customer to the company.",
"ClaimsRate": "Rate at which the customer files insurance claims.",
"PremMotor": "Premium amount for motor insurance.",
"PremHousehold": "Premium amount for household insurance.",
"PremHealth": "Premium amount for health insurance.",
"PremLife": "Premium amount for life insurance.",
"PremWork": "Premium amount for work insurance."
}
insurance_defaults = {
"FirstPolYear": 1999,
"BirthYear": 1980,
"MonthSal": 1000,
"GeoLivArea": 0, # Options: 0, 1, 2, 3
"Children": 0, # Options: 0, 1, 2
"CustMonVal": 100,
"ClaimsRate": 2.33,
"PremMotor": 200,
"PremHousehold": 200,
"PremHealth": 200,
"PremLife": 200,
"PremWork": 200
}
# Define default values for banking dataset features
banking_defaults = {
"BALANCE": 2000,
"BALANCE_FREQUENCY": 0.5,
"PURCHASES": 500,
"ONEOFF_PURCHASES": 0,
"INSTALLMENTS_PURCHASES": 0,
"CASH_ADVANCE": 200,
"PURCHASES_FREQUENCY": 0.1,
"ONEOFF_PURCHASES_FREQUENCY": 0.1,
"PURCHASES_INSTALLMENTS_FREQUENCY": 0.5,
"CASH_ADVANCE_FREQUENCY": 5,
"CASH_ADVANCE_TRX": 5,
"PURCHASES_TRX": 5,
"CREDIT_LIMIT": 10000,
"PAYMENTS": 500,
"MINIMUM_PAYMENTS": 130,
"PRC_FULL_PAYMENT": 0.22,
"TENURE": 10
}
# Define default values for retail dataset features
retail_defaults = {
"Fresh": 6000,
"Milk": 9000,
"Grocery": 9000,
"Frozen": 4000,
"Detergents_Paper": 4000,
"Delicassen": 2000
}
return feature_descriptions,insurance_defaults,banking_defaults,retail_defaults
def preprocess_data(data):
if 'CustID' in data.columns:
data = data.drop(columns=['CustID'])
if 'Channel' in data.columns:
data = data.drop(columns=['Channel'])
if 'Region' in data.columns:
data = data.drop(columns=['Region'])
data = remove_outliers(data)
return data
def remove_outliers(df, threshold=3):
df_numeric = df.select_dtypes(include=[float, int])
z_scores = np.abs((df_numeric - df_numeric.mean()) / df_numeric.std())
df_clean = df[(z_scores < threshold).all(axis=1)]
return df_clean
|