# ferozewaris/fraud-credit-card-transaction-detection architecture

> Architecture diagram of the GitHub repository ferozewaris/fraud-credit-card-transaction-detection, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/ferozewaris/fraud-credit-card-transaction-detection
- Repository: https://github.com/ferozewaris/fraud-credit-card-transaction-detection

## Overview

This repository implements a PySpark fraud-detection workflow: it loads transaction data, cleans and engineers features, trains and compares classification models, and saves transformed test results. Its documented product is a Spark ML pipeline intended to run on Spark clusters. The source also includes time-feature transforms and a deployment pipeline, but deployment is a stub and time featurization is not shown in the sampled workflow. Pipeline entry points and external invocation are not documented, so those connections are omitted.

Main entry points: [`fraud_transaction_detection/pipeline/training.py`](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/training.py) (Training pipeline), [`fraud_transaction_detection/pipeline/feature.py`](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/feature.py) (Preprocessing pipeline), [`fraud_transaction_detection/utils/database.py`](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/utils/database.py) (Data file I/O), [`fraud_transaction_detection/pipeline/base.py`](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/base.py) (Pipeline interface)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_prep["Data preparation"]
  node_prep_pipeline["Preprocessing pipeline<br/>[feature.py]"]
  node_data_transforms["Data transformers<br/>[transformers.py]"]
end

subgraph group_features["Feature engineering"]
  node_feature_pipeline["Feature pipeline<br/>[feature.py]"]
  node_feature_transforms["Feature transforms<br/>[transformers.py]"]
  node_time_features["Time featurizer<br/>[transformers.py]"]
  node_feature_constants["Time strategies<br/>[constants.py]"]
end

subgraph group_train["Model training"]
  node_training_pipeline["Training pipeline<br/>[training.py]"]
  node_model_tuning["Model tuning<br/>[training.py]"]
  node_model_selection["Model selection<br/>[training.py]"]
  node_result_manager["Training results<br/>[training.py]"]
  node_result_base["Result interface<br/>[base.py]"]
end

subgraph group_runtime["Pipeline runtime"]
  node_file_io["Data file I/O<br/>[database.py]"]
  node_pipeline_base["Pipeline interface<br/>[base.py]"]
  node_deployment["Deployment pipeline<br/>[deployment.py]"]
end

node_user(("Pipeline initiator"))

node_user -.->|"invokes"| node_prep_pipeline
node_prep_pipeline -->|"configures"| node_data_transforms
node_prep_pipeline -->|"loads data"| node_file_io
node_prep_pipeline -->|"builds and runs"| node_feature_pipeline
node_feature_pipeline -->|"configures"| node_data_transforms
node_feature_pipeline -->|"configures"| node_feature_transforms
node_feature_pipeline -->|"saves features"| node_file_io
node_feature_transforms -->|"checks strategies"| node_feature_constants
node_user -.->|"invokes"| node_training_pipeline
node_training_pipeline -->|"loads features"| node_file_io
node_training_pipeline -->|"tunes models"| node_model_tuning
node_training_pipeline -->|"selects model"| node_model_selection
node_training_pipeline -->|"processes results"| node_result_manager
node_training_pipeline -->|"saves test data"| node_file_io
node_result_manager -->|"implements"| node_result_base
node_prep_pipeline -->|"inherits"| node_pipeline_base
node_training_pipeline -->|"inherits"| node_pipeline_base
node_deployment -->|"inherits"| node_pipeline_base

click node_prep_pipeline "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/feature.py"
click node_data_transforms "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/data_processing/transformers.py"
click node_feature_pipeline "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/feature.py"
click node_feature_transforms "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/features/transformers.py"
click node_time_features "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/features/transformers.py"
click node_feature_constants "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/features/constants.py"
click node_file_io "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/utils/database.py"
click node_pipeline_base "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/base.py"
click node_training_pipeline "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/training.py"
click node_model_tuning "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/training.py"
click node_model_selection "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/training.py"
click node_result_manager "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/result_engine/training.py"
click node_result_base "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/result_engine/base.py"
click node_deployment "https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/deployment.py"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_prep_pipeline,node_data_transforms toneBlue
class node_feature_pipeline,node_feature_transforms,node_time_features,node_feature_constants toneAmber
class node_training_pipeline,node_model_tuning,node_model_selection,node_result_manager,node_result_base toneMint
class node_file_io,node_pipeline_base,node_deployment toneRose
class node_user toneIndigo
```

## Components

### Data preparation

- [Preprocessing pipeline](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/feature.py): `fraud_transaction_detection/pipeline/feature.py`
- [Data transformers](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/data_processing/transformers.py): `fraud_transaction_detection/data_processing/transformers.py`

### Feature engineering

- [Feature pipeline](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/feature.py): `fraud_transaction_detection/pipeline/feature.py`
- [Feature transforms](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/features/transformers.py): `fraud_transaction_detection/features/transformers.py`
- [Time featurizer](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/features/transformers.py): `fraud_transaction_detection/features/transformers.py`
- [Time strategies](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/features/constants.py): `fraud_transaction_detection/features/constants.py`

### Model training

- [Training pipeline](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/training.py): `fraud_transaction_detection/pipeline/training.py`
- [Model tuning](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/training.py): `fraud_transaction_detection/pipeline/training.py`
- [Model selection](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/training.py): `fraud_transaction_detection/pipeline/training.py`
- [Training results](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/result_engine/training.py): `fraud_transaction_detection/result_engine/training.py`
- [Result interface](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/result_engine/base.py): `fraud_transaction_detection/result_engine/base.py`

### Pipeline runtime

- [Data file I/O](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/utils/database.py): `fraud_transaction_detection/utils/database.py`
- [Pipeline interface](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/base.py): `fraud_transaction_detection/pipeline/base.py`
- [Deployment pipeline](https://github.com/ferozewaris/fraud-credit-card-transaction-detection/blob/main/fraud_transaction_detection/pipeline/deployment.py): `fraud_transaction_detection/pipeline/deployment.py`

### Other components

- **Pipeline initiator**

## Connections

- Pipeline initiator → Preprocessing pipeline: invokes
- Preprocessing pipeline → Data transformers: configures (evidence: `fraud_transaction_detection/pipeline/feature.py`)
- Preprocessing pipeline → Data file I/O: loads data (evidence: `fraud_transaction_detection/pipeline/feature.py`)
- Preprocessing pipeline → Feature pipeline: builds and runs (evidence: `fraud_transaction_detection/pipeline/feature.py`)
- Feature pipeline → Data transformers: configures (evidence: `fraud_transaction_detection/pipeline/feature.py`)
- Feature pipeline → Feature transforms: configures (evidence: `fraud_transaction_detection/pipeline/feature.py`)
- Feature pipeline → Data file I/O: saves features (evidence: `fraud_transaction_detection/pipeline/feature.py`)
- Feature transforms → Time strategies: checks strategies (evidence: `fraud_transaction_detection/features/transformers.py`)
- Pipeline initiator → Training pipeline: invokes
- Training pipeline → Data file I/O: loads features (evidence: `fraud_transaction_detection/pipeline/training.py`)
- Training pipeline → Model tuning: tunes models (evidence: `fraud_transaction_detection/pipeline/training.py`)
- Training pipeline → Model selection: selects model (evidence: `fraud_transaction_detection/pipeline/training.py`)
- Training pipeline → Training results: processes results (evidence: `fraud_transaction_detection/pipeline/training.py`)
- Training pipeline → Data file I/O: saves test data (evidence: `fraud_transaction_detection/pipeline/training.py`)
- Training results → Result interface: implements (evidence: `fraud_transaction_detection/result_engine/training.py`)
- Preprocessing pipeline → Pipeline interface: inherits (evidence: `fraud_transaction_detection/pipeline/feature.py`)
- Training pipeline → Pipeline interface: inherits (evidence: `fraud_transaction_detection/pipeline/training.py`)
- Deployment pipeline → Pipeline interface: inherits (evidence: `fraud_transaction_detection/pipeline/deployment.py`)
