Utils

The utils module provides a number of different methods that are useful for training and working with synthetic data.

Some of these methods carry heavy dependencies such as scikit-learn. To prevent adding unnecessary requirements to the main gretel-synthetics package, util dependencies are shipped under an extra called, utils. To install the utils extra, you may run

pip install -U gretel-synthetics[utils]

• Stats
  • calculate_correlation()
  • calculate_correlation_ratio()
  • calculate_pearsons_r()
  • calculate_theils_u()
  • compute_distribution_distance()
  • compute_pca()
  • count_memorized_lines()
  • get_categorical_field_distribution()
  • get_numeric_distribution_bins()
  • get_numeric_field_distribution()
  • normalize_dataset()
• Header Clusters
  • cluster()