data-analysis

To get descriptive statistics from a CSV dataset, the Skill analyzes tabular data to calculate mean, median, and standard deviation, while identifying time-series trends, correlations, and anomalies. It processes CSV, Excel, or in-memory datasets and outputs a structured report with optional chart recommendations.

Anomaly detection in tabular data identifies missing values and statistical outliers across your dataset columns. The Skill performs diagnostic and comparative analyses using Python with pandas and numpy, running isolated calculations to spot structural anomalies and output a structured overview of the irregularities found.

Yes, you can analyze large Excel datasets using Python with pandas, numpy, and matplotlib. The Skill applies code-assisted analysis via isolated code execution calls, handling small to large scale datasets to perform precise calculations, generate charts, and extract comparative insights without persisting state between runs.

Yes, this data analysis approach supports year-over-year and month-over-month comparisons. It applies comparative analysis methods to tabular data, calculating time-series trends and correlations across your dataset, and delivers a structured report detailing the relative changes and diagnostic insights.

The best way to generate a structured report and visualizations from in-memory data is using this Skill's code-assisted analysis. It loads in-memory datasets into an isolated Python environment with pandas and matplotlib, performs descriptive and diagnostic analysis, and outputs the structured report alongside optional chart recommendations.

Data analysis does not retain variables or state between code executions because each call runs in strict isolation. This design requires loading data fresh for every analysis run, preventing state persistence but ensuring stable, reproducible calculations when generating statistics, charts, or CSVs.