# javencp/diabetes_readmission_project architecture

> Architecture diagram of the GitHub repository javencp/diabetes_readmission_project, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-07). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/javencp/diabetes_readmission_project
- Repository: https://github.com/javencp/diabetes_readmission_project

## Overview

This repository is a diabetes 30-day readmission prediction project combining SQLite data preparation with Python machine learning. Its main workflow builds a database and feature table from included hospital encounter CSVs, loads and cleans those features, splits by patient to reduce leakage, encodes categorical variables, fits three classifiers, and evaluates them. Separate notebooks document exploratory analysis, tuning, and model comparison; SQL analysis is another product capability. SQL relationships are based on the README, since those files were not sampled.

Main entry points: [`python/run_pipeline.py`](https://github.com/javencp/diabetes_readmission_project/blob/main/python/run_pipeline.py) (Pipeline Runner), [`db`](https://github.com/javencp/diabetes_readmission_project/tree/main/db) (SQLite Database), [`sql/schema.sql`](https://github.com/javencp/diabetes_readmission_project/blob/main/sql/schema.sql) (Database Schema), [`sql/load_data.sql`](https://github.com/javencp/diabetes_readmission_project/blob/main/sql/load_data.sql) (Load and Clean)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_sql["SQL Data Preparation"]
  node_rawdata["Encounter CSVs<br/>[diabetic_data.csv]"]
  node_schema["Database Schema<br/>[schema.sql]"]
  node_loadsql["Load and Clean<br/>[load_data.sql]"]
  node_featuresql["Feature Builder<br/>[features.sql]"]
  node_db[("SQLite Database")]
end

subgraph group_ml["ML Pipeline"]
  node_pipeline["Pipeline Runner<br/>[run_pipeline.py]"]
  node_loader["Feature Loader<br/>[data_loader.py]"]
  node_preprocess["Clean and Encode<br/>[preprocessing.py]"]
  node_split["Patient Split<br/>[split.py]"]
  node_models["Three Classifiers<br/>[run_pipeline.py]"]
  node_evaluate["Metric Evaluation<br/>[evaluate.py]"]
  node_artifacts["Saved Models<br/>[run_pipeline.py]"]
end

subgraph group_research["Analysis and Tuning"]
  node_sqlanalysis["SQL Analysis<br/>[data_analysis.sql]"]
  node_notebooks["EDA and Tuning"]
end

node_analyst(("Project User"))

node_analyst -->|"creates schema"| node_schema
node_rawdata -->|"imports records"| node_loadsql
node_loadsql -->|"loads cleaned data"| node_db
node_schema -->|"defines tables"| node_db
node_db -->|"supplies records"| node_featuresql
node_featuresql -->|"builds features"| node_db
node_db -->|"reads feature table"| node_loader
node_pipeline -->|"loads features"| node_loader
node_pipeline -->|"cleans and encodes"| node_preprocess
node_pipeline -->|"splits and selects"| node_split
node_pipeline -->|"fits classifiers"| node_models
node_pipeline -->|"computes metrics"| node_evaluate
node_pipeline -->|"saves models"| node_artifacts
node_analyst -->|"runs pipeline"| node_pipeline
node_notebooks -.->|"tunes model families"| node_models
node_analyst -->|"explores and compares"| node_notebooks
node_analyst -.->|"runs analysis"| node_sqlanalysis
node_sqlanalysis -.->|"queries"| node_db

click node_rawdata "https://github.com/javencp/diabetes_readmission_project/blob/main/data/diabetic_data.csv"
click node_schema "https://github.com/javencp/diabetes_readmission_project/blob/main/sql/schema.sql"
click node_loadsql "https://github.com/javencp/diabetes_readmission_project/blob/main/sql/load_data.sql"
click node_featuresql "https://github.com/javencp/diabetes_readmission_project/blob/main/sql/features.sql"
click node_db "https://github.com/javencp/diabetes_readmission_project/tree/main/db"
click node_sqlanalysis "https://github.com/javencp/diabetes_readmission_project/blob/main/sql/data_analysis.sql"
click node_pipeline "https://github.com/javencp/diabetes_readmission_project/blob/main/python/run_pipeline.py"
click node_loader "https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/data_loader.py"
click node_preprocess "https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/preprocessing.py"
click node_split "https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/split.py"
click node_models "https://github.com/javencp/diabetes_readmission_project/blob/main/python/run_pipeline.py"
click node_evaluate "https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/evaluate.py"
click node_artifacts "https://github.com/javencp/diabetes_readmission_project/blob/main/python/run_pipeline.py"
click node_notebooks "https://github.com/javencp/diabetes_readmission_project/tree/main/python/notebooks"

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_rawdata,node_schema,node_loadsql,node_featuresql,node_db,node_analyst toneBlue
class node_pipeline,node_loader,node_preprocess,node_split,node_models,node_evaluate,node_artifacts toneAmber
class node_sqlanalysis,node_notebooks toneMint
```

## Components

### SQL Data Preparation

- [Encounter CSVs](https://github.com/javencp/diabetes_readmission_project/blob/main/data/diabetic_data.csv): `data/diabetic_data.csv`
- [Database Schema](https://github.com/javencp/diabetes_readmission_project/blob/main/sql/schema.sql): `sql/schema.sql`
- [Load and Clean](https://github.com/javencp/diabetes_readmission_project/blob/main/sql/load_data.sql): `sql/load_data.sql`
- [Feature Builder](https://github.com/javencp/diabetes_readmission_project/blob/main/sql/features.sql): `sql/features.sql`
- [SQLite Database](https://github.com/javencp/diabetes_readmission_project/tree/main/db): `db`

### ML Pipeline

- [Pipeline Runner](https://github.com/javencp/diabetes_readmission_project/blob/main/python/run_pipeline.py): `python/run_pipeline.py`
- [Feature Loader](https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/data_loader.py): `python/src/data_loader.py`
- [Clean and Encode](https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/preprocessing.py): `python/src/preprocessing.py`
- [Patient Split](https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/split.py): `python/src/split.py`
- [Three Classifiers](https://github.com/javencp/diabetes_readmission_project/blob/main/python/run_pipeline.py): `python/run_pipeline.py`
- [Metric Evaluation](https://github.com/javencp/diabetes_readmission_project/blob/main/python/src/evaluate.py): `python/src/evaluate.py`
- [Saved Models](https://github.com/javencp/diabetes_readmission_project/blob/main/python/run_pipeline.py): `python/run_pipeline.py`

### Analysis and Tuning

- [SQL Analysis](https://github.com/javencp/diabetes_readmission_project/blob/main/sql/data_analysis.sql): `sql/data_analysis.sql`
- [EDA and Tuning](https://github.com/javencp/diabetes_readmission_project/tree/main/python/notebooks): `python/notebooks`

### Other components

- **Project User**

## Connections

- Project User → Database Schema: creates schema (evidence: `README.md`)
- Encounter CSVs → Load and Clean: imports records (evidence: `README.md`)
- Load and Clean → SQLite Database: loads cleaned data (evidence: `README.md`)
- Database Schema → SQLite Database: defines tables (evidence: `README.md`)
- SQLite Database → Feature Builder: supplies records (evidence: `README.md`)
- Feature Builder → SQLite Database: builds features (evidence: `README.md`)
- SQLite Database → Feature Loader: reads feature table (evidence: `python/src/data_loader.py`)
- Pipeline Runner → Feature Loader: loads features (evidence: `python/run_pipeline.py`)
- Pipeline Runner → Clean and Encode: cleans and encodes (evidence: `python/run_pipeline.py`)
- Pipeline Runner → Patient Split: splits and selects (evidence: `python/run_pipeline.py`)
- Pipeline Runner → Three Classifiers: fits classifiers (evidence: `python/run_pipeline.py`)
- Pipeline Runner → Metric Evaluation: computes metrics (evidence: `python/run_pipeline.py`)
- Pipeline Runner → Saved Models: saves models (evidence: `python/run_pipeline.py`)
- Project User → Pipeline Runner: runs pipeline (evidence: `README.md`)
- EDA and Tuning → Three Classifiers: tunes model families (evidence: `README.md`)
- Project User → EDA and Tuning: explores and compares (evidence: `README.md`)
- Project User → SQL Analysis: runs analysis
- SQL Analysis → SQLite Database: queries
