General specifications
NaN handling
Most functions take a parameter nan_policy to specify how to handle nan values in the data. The options are:
warn (default) – Warn on nan values
raise – Raise an error on nan values
omit – Silently drop rows with nan values
- yli.utils.check_nan(df, nan_policy, *, cols=None)
Check df against nan_policy and return cleaned input
- Parameters:
df (DataFrame) – Data to check for NaNs
nan_policy (str) – Policy to apply when encountering NaN values (warn, raise, omit)
cols (List[str]) – Columns to check for NaN, or None for all columns
- Returns:
Data with NaNs removed, which may or may not be copied
- Return type:
DataFrame
dtype conventions
- yli.as_ordinal(data)
Convert the data to an ordered category dtype
- Parameters:
data – Data to convert
- Return type:
Series
General result classes
- class yli.utils.Estimate(point, ci_lower, ci_upper)
A point estimate and surrounding confidence interval
- ci_lower
Lower confidence limit (float)
- ci_upper
Upper confidence limit (float)
- point
Point estimate (float)
- summary()
Return a stringified summary of the estimate and confidence interval
- Return type:
str