Skip to content

edsnlp

EDS-NLP

conjugator

conjugate_verb(verb, conjugator)

Conjugates the verb using an instance of mlconjug3, and formats the results in a pandas DataFrame.

PARAMETER DESCRIPTION
verb

Verb to conjugate.

TYPE: str

conjugator

mlconjug3 instance for conjugating.

TYPE: mlconjug3.Conjugator

RETURNS DESCRIPTION
pd.DataFrame

Normalized dataframe containing all conjugated forms for the verb.
Source code in edsnlp/conjugator.py 
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
def conjugate_verb(
    verb: str,
    conjugator: mlconjug3.Conjugator,
) -> pd.DataFrame:
    """
    Conjugates the verb using an instance of mlconjug3,
    and formats the results in a pandas `DataFrame`.

    Parameters
    ----------
    verb : str
        Verb to conjugate.
    conjugator : mlconjug3.Conjugator
        mlconjug3 instance for conjugating.

    Returns
    -------
    pd.DataFrame
        Normalized dataframe containing all conjugated forms
        for the verb.
    """

    df = pd.DataFrame(
        conjugator.conjugate(verb).iterate(),
        columns=["mode", "tense", "person", "term"],
    )

    df.term = df.term.fillna(df.person)
    df.loc[df.person == df.term, "person"] = None

    df.insert(0, "verb", verb)

    return df

conjugate(verbs, language='fr')

Conjugate a list of verbs.

PARAMETER DESCRIPTION
verbs

List of verbs to conjugate

TYPE: Union[str, List[str]]

language

Language to conjugate. Defaults to French (fr).

TYPE: str DEFAULT: 'fr'

RETURNS DESCRIPTION
pd.DataFrame

Dataframe containing the conjugations for the provided verbs. Columns: verb, mode, tense, person, term
Source code in edsnlp/conjugator.py 
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
def conjugate(
    verbs: Union[str, List[str]],
    language: str = "fr",
) -> pd.DataFrame:
    """
    Conjugate a list of verbs.

    Parameters
    ----------
    verbs : Union[str, List[str]]
        List of verbs to conjugate
    language: str
        Language to conjugate. Defaults to French (`fr`).

    Returns
    -------
    pd.DataFrame
        Dataframe containing the conjugations for the provided verbs.
        Columns: `verb`, `mode`, `tense`, `person`, `term`
    """
    if isinstance(verbs, str):
        verbs = [verbs]

    conjugator = mlconjug3.Conjugator(language=language)

    df = pd.concat([conjugate_verb(verb, conjugator=conjugator) for verb in verbs])

    df = df.reset_index(drop=True)

    return df

get_conjugated_verbs(verbs, matches, language='fr')

Get a list of conjugated verbs.

PARAMETER DESCRIPTION
verbs

List of verbs to conjugate.

TYPE: Union[str, List[str]]

matches

List of dictionary describing the mode/tense/persons to keep.

TYPE: Union[List[Dict[str, str]], Dict[str, str]]

language

[description], by default "fr" (French)

TYPE: str, optional DEFAULT: 'fr'

RETURNS DESCRIPTION
List[str]

List of terms to look for.

Examples:

>>> get_conjugated_verbs(
        "aimer",
        dict(mode="Indicatif", tense="Présent", person="1p"),
    )
['aimons']
Source code in edsnlp/conjugator.py 
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
def get_conjugated_verbs(
    verbs: Union[str, List[str]],
    matches: Union[List[Dict[str, str]], Dict[str, str]],
    language: str = "fr",
) -> List[str]:
    """
    Get a list of conjugated verbs.

    Parameters
    ----------
    verbs : Union[str, List[str]]
        List of verbs to conjugate.
    matches : Union[List[Dict[str, str]], Dict[str, str]]
        List of dictionary describing the mode/tense/persons to keep.
    language : str, optional
        [description], by default "fr" (French)

    Returns
    -------
    List[str]
        List of terms to look for.

    Examples
    --------
    >>> get_conjugated_verbs(
            "aimer",
            dict(mode="Indicatif", tense="Présent", person="1p"),
        )
    ['aimons']
    """

    if isinstance(matches, dict):
        matches = [matches]

    terms = []

    df = conjugate(
        verbs=verbs,
        language=language,
    )

    for match in matches:
        q = " & ".join([f'{k} == "{v}"' for k, v in match.items()])
        terms.extend(df.query(q).term.unique())

    return list(set(terms))

components

Back to top