Skip to main content

Documentation Index

Fetch the complete documentation index at: https://sourcetable.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

Sourcetable gives you a complete data science environment inside your spreadsheet. Ask the AI to run analyses in plain English and it executes Python code with pandas, scikit-learn, StatsModels, and more — no installs, no notebooks, no configuration.

How it works

1

Prepare your data

Import data via file upload, connector, or paste. Sourcetable handles CSV, XLSX, Parquet, JSON, and 15+ other formats.
2

Ask the AI

Describe what you want in the chat: “Run a correlation analysis on columns A through F” or “Build a classification model to predict churn.”
3

Review results

The AI writes and executes Python code, then writes results back to your spreadsheet. You can view, modify, and re-run the generated code.

Available libraries

LibraryCapabilities
pandasData manipulation, cleaning, aggregation, merging, time series
NumPyNumerical computing, linear algebra, random sampling
SciPyStatistical tests, optimization, signal processing, interpolation
StatsModelsRegression, ANOVA, time series (ARIMA/SARIMAX), hypothesis tests
scikit-learnClassification, regression, clustering, dimensionality reduction, feature selection
TabPFNZero-shot predictions and classifications without training
plotlyInteractive charts and visualizations
matplotlibStatic plots, histograms, heatmaps
seabornStatistical visualizations, distribution plots, pair plots
bokehInteractive browser-based visualizations
transformersNLP, text classification, sentiment analysis
BeautifulSoupWeb scraping and HTML parsing
SQLAlchemyDatabase queries from Python

What you can do

Exploratory data analysis

Profile datasets, find distributions, and surface patterns automatically.

Statistical analysis

Hypothesis tests, regression, ANOVA, and correlation analysis.

Machine learning

Classification, regression, clustering, and zero-shot predictions with TabPFN.

Forecasting

ARIMA, exponential smoothing, and ML-based time series forecasting.

Anomaly detection

Statistical and ML methods to find outliers, fraud, and quality issues.

Feature engineering

Transform raw data into model-ready features with encoding, scaling, and creation.

Who it’s for

  • Analysts — Run statistical tests and build models without leaving your spreadsheet
  • Data scientists — Prototype faster with instant Python execution and visualization
  • Researchers — Process experimental data with proper statistical methods
  • Business users — Get data science results through natural language, no coding required