bank customer

[qyuanawilliams-commits]

import pandas as pd

Load the CSV file (adjust path if needed)

df = pd.read_csv("BankCustomers (1).csv")

Preview the first few rows

print("First five rows of data:")
print(df.head())

Verify fields

print("\nList of fields (columns):")
print(df.columns)

Completeness check

percent_complete = df.notnull().sum() / len(df) * 100
print("\nPercentage of records with values per field:")
print(percent_complete)

1. Completeness of Customer Income

income_complete_pct = df["Customer Income"].notnull().sum() / len(df) * 100
print(f"\n1) Income data completeness: {income_complete_pct:.1f}% of records have values.")

2. Average income overall and by branch

overall_avg_income = df["Customer Income"].mean()
branch_avg_income = df.groupby("Bank Branch")["Customer Income"].mean()
print(f"\n2) Overall average income: {overall_avg_income:.2f}")
print("Average income by branch:")
print(branch_avg_income)

3. Online-only customers

online_customers = df[df["Bank Branch"] == "Online"]
print(f"\n3) Online-only customers: {len(online_customers)}")

4. Compare online vs physical branch incomes

avg_income_online = online_customers["Customer Income"].mean()
avg_income_physical = df[df["Bank Branch"] != "Online"]["Customer Income"].mean()
print(f"\n4) Average income (Online customers): {avg_income_online:.2f}")
print(f" Average income (Physical branch customers): {avg_income_physical:.2f}")