DataframeCorrelation / Aggregation Layer

Calculate pairwise correlation coefficients between numeric columns, similar to pandas corr() or numpy corrcoef().

Mathematical forms: Pearson: $r = \frac{\sum ( x - x ˉ ) ( y - y ˉ )}{\sum ( x - x ˉ ) ^{2} \sum ( y - y ˉ ) ^{2}}$ Spearman: Same formula applied to ranks instead of raw values

Interpretation:

+1: Perfect positive correlation
0: No linear correlation
-1: Perfect negative correlation

Common applications:

Feature selection in machine learning
Financial asset analysis
Scientific variable relationships
Quality control correlations
Multi-sensor data analysis

Table

Method

enum

Pearson

Statistical methods for measuring correlation between variables. Different methods capture different aspects of relationships.

Pearson ~

Linear correlation coefficient. Best for:

Linear relationships
Normally distributed data
Continuous variables Sensitive to outliers

Spearman ~

Rank correlation coefficient. Suitable for:

Monotonic relationships
Non-normal distributions
Ordinal data Robust to outliers