Alpha¶

evalica.alpha(data, distance='nominal', solver='pyo3')[source]¶

Compute Krippendorff’s alpha.

Note

Krippendorff, K.: Content Analysis: An Introduction to Its Methodology. Sage Publications, Thousand Oaks, CA (2018).

Parameters:

data (DataFrame) – Ratings by observer (rows) and unit (columns).
distance (DistanceFunc[T_distance_contra] | Literal['interval', 'nominal', 'ordinal', 'ratio']) – Distance metric (nominal, ordinal, interval, ratio) or a custom function.
solver (Literal['naive', 'pyo3']) – The solver to use (naive or pyo3).

Returns:

The alpha result.

Return type:

AlphaResult

class evalica.AlphaResult(alpha, observed, expected, solver)[source]¶

The result of Krippendorff’s alpha.

Parameters:

alpha (float)
observed (float)
expected (float)
solver (Literal['naive', 'pyo3'])

alpha¶

The alpha value.

Type:: float

observed¶

The observed disagreement.

Type:: float

expected¶

The expected disagreement.

Type:: float

solver¶

The solver used.

Type:: Literal[‘naive’, ‘pyo3’]

evalica.alpha_bootstrap(data, distance='nominal', solver='pyo3', *, n_resamples=5000, confidence_level=0.95, random_state=None)[source]¶

Compute confidence intervals for Krippendorff’s alpha using KALPHA-style bootstrap.

Note

Krippendorff, K.: Bootstrapping Distributions for Krippendorff’s Alpha. (2006). <https://www.asc.upenn.edu/sites/default/files/2021-03/Algorithm%20for%20Bootstrapping%20a%20Distribution%20of%20Alpha.pdf>.

Note

Hayes, A.F.: Statistical Methods and Macros for SPSS, SAS, and R. <https://afhayes.com/spss-sas-and-r-macros-and-code.html>.

Parameters:

data (DataFrame) – Ratings by observer (rows) and unit (columns).
distance (DistanceFunc[T_distance_contra] | Literal['interval', 'nominal', 'ordinal', 'ratio']) – Distance metric (nominal, ordinal, interval, ratio) or a custom function.
solver (Literal['naive', 'pyo3']) – The solver to use (naive or pyo3).
n_resamples (int) – Number of bootstrap samples.
confidence_level (float) – The confidence level.
random_state (int | None) – The random seed (non-negative integer or None).

Returns:

The alpha bootstrap result.

Return type:

AlphaBootstrapResult

class evalica.AlphaBootstrapResult(alpha, observed, expected, solver, low, high, distribution, n_resamples, confidence_level)[source]¶

The bootstrap result of Krippendorff’s alpha.

Parameters:

alpha (float)
observed (float)
expected (float)
solver (Literal['naive', 'pyo3'])
low (float)
high (float)
distribution (Series)
n_resamples (int)
confidence_level (float)

alpha¶

The alpha value.

Type:: float

observed¶

The observed disagreement.

Type:: float

expected¶

The expected disagreement.

Type:: float

low¶

The lower bound of the confidence interval.

Type:: float

high¶

The upper bound of the confidence interval.

Type:: float

distribution¶

The bootstrap alpha distribution.

Type:: pandas.Series

n_resamples¶

The number of bootstrap samples used.

Type:: int

confidence_level¶

The confidence level.

Type:: float

solver¶

The solver used.

Type:: Literal[‘naive’, ‘pyo3’]

evalica.DistanceName¶: alias of Literal[‘interval’, ‘nominal’, ‘ordinal’, ‘ratio’]

class evalica.DistanceFunc(*args, **kwargs)[source]¶

The distance function protocol.

__call__(left, right, /)[source]¶

Compute the distance between the values.

Parameters:

left (T_distance_contra) – The left-hand side value.
right (T_distance_contra) – The right-hand side value.

Returns:

The non-negative distance between the values.

Return type:

float