@@ -33,7 +33,7 @@ def __init__(
3333 - (low, high, "geometric"): Geometric spacing (doubling)
3434 - (low, high, "logarithmic"): Logarithmic spacing (powers of 10)
3535 - [value1, value2, ...]: Custom list of specific levels to sample from
36- - {'levels': [value1, value2, ...], 'biases': [weight1, weight2, ...]}:
36+ - {'levels': [value1, value2, ...], 'biases': [weight1, weight2, ...]}:
3737 Custom levels with optional biases/weights for non-uniform sampling.
3838 Biases will be normalized to sum to 1.0 if they don't already.
3939 :param conditional_subparameters: A dictionary containing the conditional subparameters for the design.
@@ -303,7 +303,7 @@ def sample_continuous_lhs(continuous_params, n_samples, seed):
303303 # Use biased sampling with inverse transform method
304304 biases = np .array (biases )
305305 if len (biases ) != len (possible ):
306- raise ValueError (f"Length of biases ({ len (biases )} ) must match length of levels ({ len (possible )} ) for parameter '{ key } '" )
306+ raise ValueError (f"Bias length ({ len (biases )} ) must match levels length ({ len (possible )} ) for parameter '{ key } '" )
307307 if not np .isclose (sum (biases ), 1.0 ):
308308 biases = biases / np .sum (biases )
309309
@@ -797,7 +797,7 @@ def calculate_max_mixed_correlation(design, continuous_keys, categorical_keys, s
797797
798798 :param design: The design DataFrame
799799 :param continuous_keys: List of continuous parameter names
800- :param categorical_keys: List of categorical parameter names
800+ :param categorical_keys: List of categorical parameter names
801801 :param subparam_mapping: Dictionary mapping categorical variables to their subparameters
802802 :return: Maximum absolute mixed correlation value
803803 """
0 commit comments