Data Science

NumPy library for numerical computing in Python. Use for array operations, linear algebra, statistical calculations, curve fitting, and mathematical transformations.

NumPy library for numerical computing in Python. Use for array operations, statistical calculations, mathematical transformations, and numerical analysis of financial data.

Analyze and transform tabular data using pandas DataFrames. Use when loading report data from CSV/Excel, performing data aggregations, calculating statistics, filtering datasets, or preparing data for visualization in reports.

Data manipulation and analysis library. Use when working with tabular data, CSVs, DataFrames, or performing data transformations.

Matplotlib library for creating scientific visualizations. Use for plotting data, creating Arrhenius plots, adding legends, labels, and saving figures to files.

Analyze port scan results to identify services, vulnerabilities, and attack vectors. Use this skill when interpreting scan data, prioritizing targets, or mapping network services.

GPU-accelerated NumPy-compatible array operations with CuPy. Use when performing numerical computations on GPU, transferring data between CPU/GPU, or optimizing array operations with CUDA.

Analyze supply chain performance and identify optimization opportunities. Use this skill when measuring supply chain KPIs, performing cost analysis, evaluating network efficiency, or generating insights from logistics data.

Analyze biological pathways using KEGG, Reactome, and other pathway databases.

Analyze and transform tabular CRM data using pandas DataFrames. Use when processing contact records, merging customer datasets, performing data aggregations, cleaning CRM exports, or preparing data for sync operations.

Pandas library for data manipulation and analysis. Use for loading CSV files, data transformation, aggregation, filtering, and creating output reports.

Parse, analyze, and manipulate VCF (Variant Call Format) files for variant interpretation. Use when programmatically accessing variant data, calculating statistics, or filtering by quality.

High-performance numerical computing with multi-dimensional arrays, broadcasting, and vectorized operations. Use when performing matrix operations, statistical calculations, linear algebra (eigenvalues, matrix inversion), or array transformations. Essential for portfolio covariance matrices, returns calculations, and mathematical optimizations.

Numerical computing library for arrays and matrices. Use for mathematical operations, linear algebra, and scientific computing.

Plotting and visualization library. Use when creating charts, graphs, or visual representations of data.

Pandas library for data manipulation and time series analysis. Use for loading CSV files, data transformation, time series operations, merging datasets, and creating financial reports.

Pandas library for data manipulation and analysis. Use for loading CSV files, data filtering, sorting, grouping, and creating DataFrames for tabular data.

Graph analysis techniques for network data. Use for network metrics calculation, community detection, hub identification, and analyzing drug interaction patterns.

Use edgeR for differential expression analysis of RNA-seq data with empirical Bayes methods.

Clean and prepare data for analysis. Use when handling missing values, duplicates, or invalid data.