Metrics

tmplot.entropy(phi: ndarray, max_probs: bool = False)

Renyi entropy calculation routine [1].

Renyi entropy can be used to estimate the optimal number of topics: fit several models varying the number of topics and choose the model for which Renyi entropy is minimal.

Parameters:

phi (np.ndarray) – Topics vs words probabilities matrix (T x W).

Returns:

• renyi (double) – Renyi entropy value.

• max_probs (bool) – Use maximum probabilities of terms per topics instead of all probability values.

References

[1]

Koltcov, S. (2018). Application of Rényi and Tsallis entropies to topic modeling optimization. Physica A: Statistical Mechanics and its Applications, 512, 1192-1204.

Example

>>> import tmplot as tmp
>>> # Preprocessing step
>>> # ...
>>> # Model fitting step
>>> # model = ...
>>> # phi = ...
>>> # Entropy calculation
>>> entropy = tmp.entropy(phi)