get_correlations
Compute pairwise Pearson and Spearman correlations for numeric columns, generate a heatmap, and create scatter plots for correlations above a configurable threshold.
Instructions
Compute pairwise correlations between all numeric columns in the dataset and generate a Spearman correlation heatmap. Scatter plots are generated for column pairs with a Spearman correlation above the threshold.
Returns both Pearson and Spearman correlation matrices, the strongest pairs above the threshold (sorted by absolute Spearman correlation, max 10), highly correlated flags for pairs with |ρ| >= 0.9, and file paths for all generated plots.
Only continuous and discrete columns are included — categorical, binary, temporal, and high_cardinality columns are excluded automatically.
threshold controls which pairs get scatter plots (default 0.5). Set higher e.g. 0.7 for only strong correlations, lower e.g. 0.3 to cast a wider net. Scatter plots are capped at 10 pairs regardless of threshold.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | ||
| output_dir | No | ||
| threshold | No | ||
| table | No |