home << dhlab reference

Collocations

from dhlab import Collocations

class Collocations(corpus=None, words=None, before=10, after=10, reference=None, samplesize=20000, alpha=False, ignore_caps=False)

Bases: DhlabObj

Create collocations object

Parameters:

• corpus (dh.Corpus, optional) – target corpus, defaults to None

• words (str or list, optional) – target words(s), defaults to None

• before (int, optional) – words to include before, defaults to 10

• after (int, optional) – words to include after, defaults to 10

• reference (pd.DataFrame, optional) – reference frequency list, defaults to None

• samplesize (int, optional) – _description_, defaults to 20000

• alpha (bool, optional) – Only include alphabetical tokens, defaults to False

• ignore_caps (bool, optional) – Ignore capitalized letters, defaults to False

classmethod from_df(df)

Typecast DataFrame to Collocation

Parameters:

df – DataFrame

Returns:

Collocation