surya8522/adult-income-prediction

How surya8522/adult-income-prediction works

This repository is an Adult Income binary-classification project with a conventional ML workflow and an MLOps extension for tracking, registry, and lifecycle management. The main production-oriented path validates and preprocesses the dataset, trains and evaluates a model, then records model artifacts and registry state. The README documents broader capabilities, including EDA, model comparison, tuning, and prediction; those are represented without inferring unshown calls. Source excerpts show the production preprocessing outputs and MLflow training behavior, but not all downstream wiring.

Main entry points: run_lab3_baseline.py Baseline runner · run_lab5_pipeline.py Production runner · run_lab6_registry.py Registry runner · preprocess_pipeline.py Production preprocessing

Components 21

Data preparation

Adult dataset data/raw/adult.csv
Data validation src/validate_data.py
Production preprocessing src/preprocess_pipeline.py
Train/test features data/processed/X_train_final.npy
Fitted preprocessor models/preprocessor.pkl
Output validation src/validate_outputs.py
Baseline preprocessing src/preprocess.py

Modeling and evaluation

EDA and baseline src/income_prediction.py
Baseline training src/train.py
Model evaluation src/evaluate.py
Income prediction src/income_prediction.py

MLOps lifecycle

Tracked training src/train_mlflow.py
Registry training src/train_registry.py
Version promotion src/automate_lifecycle.py
Registry report src/generate_registry_report.py
MLflow service

Workflow automation

Baseline runner pipelines/run_lab3_baseline.py
Tracking runner pipelines/run_lab4_tracking.py
Production runner pipelines/run_lab5_pipeline.py
Registry runner pipelines/run_lab6_registry.py

Other components

Project user

Connections 25

Project user → Production runner: runs pipeline README.md
Production runner → Data validation: executes pipelines/run_lab5_pipeline.py
Production runner → Production preprocessing: executes pipelines/run_lab5_pipeline.py
Production runner → Output validation: executes pipelines/run_lab5_pipeline.py
Adult dataset → Production preprocessing: loads data src/preprocess_pipeline.py
Production preprocessing → Train/test features: writes arrays src/preprocess_pipeline.py
Production preprocessing → Fitted preprocessor: saves transform src/preprocess_pipeline.py
Project user → Baseline runner: runs pipeline README.md
Baseline runner → Baseline preprocessing: executes pipelines/run_lab3_baseline.py
Baseline runner → Baseline training: executes pipelines/run_lab3_baseline.py
Baseline runner → Model evaluation: executes pipelines/run_lab3_baseline.py
Project user → Tracking runner: runs pipeline README.md
Tracking runner → Baseline preprocessing: executes pipelines/run_lab4_tracking.py
Tracking runner → Tracked training: executes pipelines/run_lab4_tracking.py
Project user → Registry runner: runs pipeline README.md
Registry runner → Registry training: executes pipelines/run_lab6_registry.py
Registry runner → Version promotion: executes pipelines/run_lab6_registry.py
Registry runner → Registry report: executes pipelines/run_lab6_registry.py
Train/test features → Tracked training: loads arrays src/train_mlflow.py
Tracked training → MLflow service: logs run and model src/train_mlflow.py
Train/test features → Registry training: loads arrays src/train_registry.py
Registry training → MLflow service: registers model src/train_registry.py
Adult dataset → EDA and baseline: analyzes dataset README.md
EDA and baseline → Income prediction: demonstrates prediction src/income_prediction.py
Project user → Income prediction: requests estimate

More Python diagrams: lightonai/lightonocr · littlek0i/snowkill · markos-diomataris/wandr · mattjmorrison/reportlab · mobilise-d/mobgap

Drawn by GitDiagram on October 1, 2026 from the repository's file tree, README and source files. Read as Markdown ·