Tech Stack

Core Framework

• – Primary language (99.3% of repository)
• – Distributed processing engine
• – Real-time streaming platform
• – Web server framework

Big Data & Streaming

• – Python API for Spark 3.5.1
• – Structured data processing
• – Real-time data streams
• – Python Kafka client
• – Columnar storage format

Machine Learning

• – Distributed ML library
• – Primary model
• – Ensemble learning
• – Baseline model
• – Preprocessing automation

Data Processing & Analysis

• – Data manipulation & analysis
• – Numerical computing
• – Spark initialization

Data Visualization

• – Core plotting library
• – Statistical visualizations
• – Feature relationships
• – Model evaluation

Frontend Technologies

• – Web interface structure
• – Styling & layout
• – Interactive visualizations
• – Responsive layout

Database

• – NoSQL database (attempted)
• – Production storage (used)

Development Tools

• – Interactive notebooks
• – Code editor
• – Local web hosting
• – Version control
• – Repository hosting

Cloud Platform

• – VM deployment
• – Virtual machines

Python Libraries

• – CLI argument parsing
• – Data serialization
• – CSV file handling
• – File pattern matching

Data Formats

• – Input dataset
• – Kafka messages
• – Streaming output

---

Data Processing vs. Web Interface

Backend (Data Processing)	Frontend (Web Interface)
Distributed Engine	Structure
Streaming	Styling
Python API	Interactivity
ML Framework	Web Server
Data Analysis	Templating
Numerical Ops	Responsive Layout
Visualization	Local Hosting
Heatmaps	Pre-rendered
Storage
Database (attempted)
Producer
CLI

---

ML Pipeline Components

Component	Technology
Classification Models
Feature Engineering
Feature Transformation
Model Evaluation
Metrics