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 supports two ML approaches: TabPFN for instant zero-shot predictions, and scikit-learn for full model training pipelines.
TabPFN — zero-shot predictions
TabPFN is a pre-trained neural network that makes predictions on tabular data without any training step. It works immediately on your data.
"Predict which customers will churn based on their usage data using TabPFN"
When to use TabPFN
- Small to medium datasets (under 10,000 rows works best)
- Quick prototyping — get results in seconds
- No hyperparameter tuning needed
- Classification and regression tasks
Available modes
| Mode | Chat mode | Description |
|---|
| Classification | Classify | Predict categorical outcomes (churn/no churn, fraud/legitimate) |
| Regression | Predict | Predict continuous values (price, score, duration) |
scikit-learn — full ML pipeline
For larger datasets or when you need more control, Sourcetable uses scikit-learn under the hood.
Classification
"Build a random forest classifier to predict loan default from the applicant data"
| Algorithm | Best for |
|---|
| Random Forest | General purpose, handles mixed features well |
| Gradient Boosting | High accuracy, handles non-linear relationships |
| Logistic Regression | Interpretable, good baseline |
| SVM | High-dimensional data, clear margin of separation |
| k-Nearest Neighbors | Simple, non-parametric |
| Decision Tree | Interpretable, visual output |
| Naive Bayes | Text classification, very fast |
Regression
"Train a gradient boosting model to predict house prices"
Clustering
"Cluster customers into segments based on purchase behavior"
| Algorithm | Best for |
|---|
| K-Means | Spherical clusters, known number of groups |
| DBSCAN | Arbitrary shapes, automatic cluster count |
| Hierarchical | Dendrogram visualization, nested groups |
| Gaussian Mixture | Overlapping clusters, soft assignments |
Dimensionality reduction
"Reduce the dataset to 2 dimensions with PCA and plot the clusters"
End-to-end ML pipeline
When you ask the AI to build a model, it automatically handles:
- Data splitting — train/test split (default 80/20)
- Feature preprocessing — encoding categoricals, scaling numerics, handling missing values
- Model training — fits the chosen algorithm
- Evaluation — generates metrics and visualizations
- Results — writes predictions back to your spreadsheet
Model evaluation
The AI reports relevant metrics based on the task:
Classification metrics:
- Accuracy, Precision, Recall, F1 Score
- ROC curve and AUC
- Confusion matrix
- Classification report by class
Regression metrics:
- R-squared and Adjusted R-squared
- MAE (Mean Absolute Error)
- RMSE (Root Mean Squared Error)
- Residual plots
Clustering metrics:
- Silhouette score
- Calinski-Harabasz index
- Inertia (for K-Means)
Hyperparameter tuning
"Tune the random forest hyperparameters using cross-validation"
