Credit History & Utilization EDA

[RigelAlgebar]

Issue 3 – Credit History & Utilization EDA with OOP + Functional Report

Goal
Explore how credit history, balances, utilization, and inquiries relate to loan_status.

You must use:

• OOP: create a class that encapsulates credit-history EDA.
• Functional programming: build a report function that stores and runs multiple EDA steps via functions/lambdas.

---

Columns in scope

You are responsible for the following columns:

Ratios

• dti
• dti_joint
• revol_util
• il_util
• all_util

Delinquency / history

• delinq_2yrs
• earliest_cr_line
• mths_since_last_delinq
• mths_since_last_record
• mths_since_last_major_derog

Accounts & public records

• open_acc
• total_acc
• pub_rec
• acc_now_delinq

Balances & limits

• revol_bal
• total_rev_hi_lim
• tot_coll_amt
• tot_cur_bal
• total_bal_il
• max_bal_bc

Recent account activity

• open_acc_6m
• open_il_6m
• open_il_12m
• open_il_24m
• mths_since_rcnt_il
• open_rv_12m
• open_rv_24m

Inquiries / pulls

• inq_last_6mths
• inq_last_12m
• inq_fi
• last_credit_pull_d

Collections

• collections_12_mths_ex_med

Shared target

• loan_status (used for default-rate and correlation analyses)

---

Files to edit

• src/eda_credit_history.py
• notebooks/eda_credit_history_demo.ipynb

---

1. Implement the CreditHistoryEDA class

In src/eda_credit_history.py, create and implement:

"""
import pandas as pd
from typing import Dict, Any, Callable

CREDIT_NUMERIC_COLS = [
"dti", "dti_joint",
"delinq_2yrs",
"mths_since_last_delinq", "mths_since_last_record", "mths_since_last_major_derog",
"open_acc", "total_acc", "pub_rec", "acc_now_delinq",
"revol_bal", "revol_util", "total_rev_hi_lim",
"tot_coll_amt", "tot_cur_bal", "total_bal_il",
"open_acc_6m", "open_il_6m", "open_il_12m", "open_il_24m",
"mths_since_rcnt_il",
"open_rv_12m", "open_rv_24m",
"max_bal_bc",
"all_util",
"inq_last_6mths", "inq_last_12m", "inq_fi",
"collections_12_mths_ex_med",
]

class CreditHistoryEDA:
def init(self, df: pd.DataFrame, target_col: str = "loan_status"):
"""
Store the full DataFrame and the name of the target column.
"""
self.df = df
self.target_col = target_col

def credit_structure_summary(self) -> pd.DataFrame:
    """
    One row per CREDIT_NUMERIC_COLS column with:
    - column
    - dtype
    - n_missing
    - missing_pct
    - mean (if numeric)
    - std (if numeric)
    """
    ...

def default_rate_by_bucket(self, col: str, bins: int = 4) -> pd.DataFrame:
    """
    For a numeric credit column (e.g., dti, revol_util),
    create `bins` buckets and compute default rate per bucket.

    Return a DataFrame with columns:
    - bucket (interval)
    - n_loans
    - default_rate
    """
    ...

def correlation_with_default(self) -> pd.Series:
    """
    Compute correlation of each numeric credit column with the target
    (assuming loan_status is encoded as 0/1).
    Return a Series indexed by column name.
    """
    ...

"""

---

2. Functional credit-history report

Add a functional report generator that coordinates several EDA steps:

"""
def credit_history_report(eda: CreditHistoryEDA) -> Dict[str, Any]:
"""
Build a dict of step_name -> callable and run them to produce
a combined report.

Example steps:
  - "structure_summary": eda.credit_structure_summary
  - "dti_buckets": lambda: eda.default_rate_by_bucket("dti", bins=5)
  - "revol_util_buckets": lambda: eda.default_rate_by_bucket("revol_util", bins=5)
  - "correlation_with_default": eda.correlation_with_default

Iterate over this dict, call each function, and return
a result dict: step_name -> output.
"""
...

"""

Example idea:

"""
def credit_history_report(eda: CreditHistoryEDA) -> Dict[str, Any]:
steps: Dict[str, Callable[[], Any]] = {
"structure_summary": eda.credit_structure_summary,
"dti_buckets": lambda: eda.default_rate_by_bucket("dti", bins=5),
"revol_util_buckets": lambda: eda.default_rate_by_bucket("revol_util", bins=5),
"correlation_with_default": eda.correlation_with_default,
}

report: Dict[str, Any] = {}
for name, func in steps.items():
    report[name] = func()
return report

"""

This should clearly show higher-order functions (functions stored and called later).

---

3. Create the demo notebook

In notebooks/eda_credit_history_demo.ipynb:

1. Load the dataset:

"""
import pandas as pd
from src.eda_credit_history import CreditHistoryEDA, credit_history_report

df = pd.read_csv("data/loan_sample.csv") # or correct path
"""

2. Instantiate the EDA class:

"""
eda = CreditHistoryEDA(df, target_col="loan_status")
"""

3. Run the report:

"""
report = credit_history_report(eda)
"""

4. Display at least:

"""
report["structure_summary"] # structure of all credit-history columns
report["dti_buckets"] # default rate by DTI bucket
report["revol_util_buckets"] # default rate by revol_util bucket
report["correlation_with_default"] # correlation of each credit feature with default
"""

Optionally add one bar plot (e.g., default rate by DTI bucket), but stay within EDA (no modeling).

---

Acceptance Criteria ✅

• CreditHistoryEDA:

  • Initializes correctly with a DataFrame.
  • credit_structure_summary() returns a DataFrame with one row per credit-history numeric column and basic stats.
  • default_rate_by_bucket(col, bins) returns a DataFrame with bucket, n_loans, and default_rate.
  • correlation_with_default() returns a Series of correlations.

• Functional report:

  • credit_history_report(eda) uses a dict of callables or similar FP construct.
  • It iterates over steps, calls each function, and returns a dict of results.

• Notebook:

  • Runs top-to-bottom without errors.
  • Shows structure summary, bucketed default-rate tables, and correlations.
  • Contains only EDA (no model training).