3. Data, Science & AI

Comprehensive guide to Apache Spark data processing, covering RDDs, DataFrames, Spark SQL, streaming, MLlib, and production deployment.

Comprehensive guide for database management patterns including schema design, indexing, transactions, replication, and performance tuning for PostgreSQL and MongoDB.

Guides production-ready LLM application development using LangChain's chains, agents, memory systems, and RAG patterns.

Provides end-to-end MLOps workflows for the machine learning lifecycle, including experiment tracking, model registry, deployment, monitoring, and A/B testing with MLflow.

Performs data analysis and manipulation on customer support datasets using the pandas library for insights and reporting.

Enables creation and deployment of AI agents using Google's Agent Development Kit (ADK), including Gemini agents and multi-agent systems.

Provides a guide for data preprocessing tasks including loading, cleaning, missing value handling, outlier detection, and feature engineering in mathematical modeling contexts.

Comprehensive guide for using PostgreSQL's psql terminal client to manage databases, execute SQL queries, and perform administrative tasks.

Statistical validator for trading systems, performing backtests, Monte Carlo simulations, and Apex compliance checks.

Guides mathematical model selection, implementation, and matplotlib visualization for prediction, classification, regression, and research paper figures.

Provides persistent memory management for Claude Code sessions, storing context, decisions, and solutions to enhance coding assistance.

Filters card blueprint database subsets by side (LIGHT/DARK) and excludes defensive shields via jq, resolving slug collisions for card mapping.

Analyzes spending patterns, provides category breakdowns, and summarizes monthly expenses to help users understand financial habits.

Predicts future account balance and simulates purchase impacts for financial forecasting and affordability scenarios.

Invokes Google Gemini models for structured JSON outputs, multi-modal tasks, and Google API integrations, enabling efficient AI-driven applications.

Analyzes AI/ML technical papers and articles, extracting actionable insights for enterprise AI engineering contexts including RAG, embeddings, and LLM deployment.

Advanced reference for AI memory operations: versioning, session scoping, and retention management in conversational systems.

Extracts keywords from documents using YAKE algorithm, supporting 34 languages and domain-specific stopwords for AI/ML and life sciences.

Analyzes Bluesky firehose data to identify real-time trending topics and content clusters for user queries about Bluesky trends.

Creates optimized instructions for Claude.ai, covering project setups, prompt engineering, and Skill development guidance.

Generates interactive EDA reports with statistics, visualizations, and quality insights from uploaded datasets using ydata-profiling.

Generates interactive data visualizations via Vega-Lite, supporting multiple chart types and producing portable JSON specifications for seamless integration.

Generates searchable indexes from GitHub repositories for use as project knowledge in Claude, enabling efficient reference to external documentation and multiple codebases.

Analyzes and categorizes Bluesky accounts by topic using keyword extraction for topic discovery and account curation.