3. Data, Science & AI

Automates extraction and analysis of financial data from documents, categorizing expenses and generating reports for expense tracking.

Python toolkit for molecular biology analysis including sequence manipulation, file parsing (FASTA, GenBank), and bioinformatics workflows.

Compares document similarity using TF-IDF, cosine similarity, and Jaccard index for plagiarism detection and duplicate content identification.

Performs data analysis using pandas, numpy, and analytics libraries for data manipulation and exploration.

Bioinformatics tool for reading, writing, and manipulating biological sequence files (FASTA, GenBank, FASTQ) with indexed access and sequence operations.

Analyzes datasets to determine schema, quality metrics, and data characteristics via profiling of CSV, JSON, and Parquet files.

Analyzes SQL queries using EXPLAIN plans, provides index recommendations, and rewrites queries to enhance database performance.

Builds RAG systems, semantic search, and document clustering using Google Gemini embeddings API for vector search.

Provides core PyTorch fundamentals including tensor operations, autograd, model architecture, and training loop implementation.

Enables building, training, and optimizing deep learning models with PyTorch, including data pipelines and distributed training.

Optimizes machine learning model inference performance via compression, distillation, and edge deployment strategies.

Provides efficient linear algebra operations in NumPy, including matrix multiplication, SVD, and least squares fitting for data science and AI applications.

Transforms and exports data using DuckDB SQL, supporting multiple formats and complex operations like joins and aggregations for efficient data processing.

High-performance tokenization for NLP research and production, supporting BPE, WordPiece, and Unigram algorithms with Hugging Face Transformers integration.

Provides numerical algorithms and computational techniques specifically for statistical analysis and data processing tasks.

Provides foundational knowledge for writing Stan 2.37 statistical models, covering structure, type system, distributions, and best practices.

High-performance CLI for splitting, merging, and analyzing SQL dump files across databases, with integrity validation, ERD generation, and DuckDB analytics.

Expert guidance for Stan probabilistic programming language development, including modern syntax, cmdstanr/cmdstanpy integration, and testing patterns.

Validates datasets for Unsloth fine-tuning by analyzing tokens, calculating Chinchilla optimality, and preparing data for efficient model training.

Guides construction of probability distributions meeting exact statistical constraints, including KL divergence targets and high-dimensional optimization.

Guides implementation of PyTorch pipeline parallelism for distributed deep learning training, including model partitioning and inter-rank tensor communication.

Provides statistical patterns for hierarchical Bayesian models including random effects, partial pooling, and parameterization techniques.

Extracts text commands and typed input from video recordings using OCR for text-based game and terminal session analysis.

Guides semantic search implementation using sentence transformers for document retrieval, encoding, and cosine similarity ranking in MTEB benchmark workflows.