ccfd-project - Complete Reference¶

Progress¶

  ✅ STEP 1: Load Data
  ✅ STEP 2: Split Train/Test
  ✅ STEP 3: Create Pipeline
  ✅ STEP 4: Train Pipeline
  ✅ STEP 5: Evaluate & Metrics
  ✅ STEP 6: Save Pipeline
  ✅ STEP 7: Save Metrics JSON

All steps complete. This is the final reference version with full docstrings on every function.

What's Different From v7¶

Aspect	v7	ccfd-project
Code	Identical functionality	Identical functionality
Docstrings	Minimal	Full docstrings with Args, Returns, examples
Purpose	Learning (incremental build)	Reference (production-ready)

Project Structure¶

ccfd-project/
├── p1_01_generate_initial_dataset.py    # Generate synthetic dataset
├── p3_01_train_model_baseline.py        # Training script (7 steps)
├── requirements.txt                     # Python dependencies
└── utils/
    ├── __init__.py                      # Package exports
    ├── data_utils.py                    # load_data, split_data, create_preprocessor
    ├── model_utils.py                   # create_pipeline, save_pipeline
    └── metrics_utils.py                 # print_metrics, save_metrics_json

All Functions¶

data_utils.py¶

Function	Purpose
`load_data()`	Load CSV → DataFrame
`get_feature_columns()`	Return categorical + numerical column lists
`split_data()`	Stratified train/test split with feature info
`create_preprocessor()`	ColumnTransformer (OneHotEncoder + StandardScaler)

model_utils.py¶

Function	Purpose
`create_pipeline()`	Build sklearn Pipeline (preprocessor + model)
`save_pipeline()`	Save pipeline pickle + metadata JSON

metrics_utils.py¶

Function	Purpose
`print_metrics()`	Print technical + business metrics
`calculate_business_metrics()`	Compute net benefit, fraud caught/missed
`save_metrics_json()`	Save metrics to results/ as JSON

How to Run¶

cd ccfd-project/

# 1. Generate data
python p1_01_generate_initial_dataset.py

# 2. Train model
python p3_01_train_model_baseline.py

Next Section¶

Next	Topic	What You'll Do
04_02_Inference_API	Serve Predictions	Build FastAPI server, test via browser + scripts

Prefer to learn by watching?

The video course builds this whole project with you on screen, step by step.

Get the Video Course

Back to 04 A - Train Baseline Model