pythainlp.generate

The pythainlp.generate module provides classes and functions for generating Thai text using n-gram language models.

N-gram generators

class pythainlp.generate.Unigram(name: str = 'tnc')

Generate text using the unigram model.

Parameters:

name (str) –

corpus name

• tnc - Thai National Corpus (default)

• ttc - Thai Textbook Corpus (TTC)

• oscar - OSCAR Corpus

__init__(name: str = 'tnc') → None

Initialize the unigram model.

counts: dict[str, int]

word: list[str]

n: int

prob: dict[str, float]

gen_sentence(start_seq: str = '', N: int = 3, prob: float = 0.001, output_str: bool = True, duplicate: bool = False) → list[str] | str

Generate a sentence using the unigram model.

Parameters:

• start_seq (str) – word to begin the sentence with

• N (int) – number of words

• prob (float) – minimum word probability

• output_str (bool) – return a string instead of a list of words

• duplicate (bool) – allow duplicate words in the sentence

Returns:

generated sentence as a string or a list of words

Return type:

Union[list[str], str]

Example:

>>> from pythainlp.generate import Unigram

>>> gen = Unigram()

>>> gen.gen_sentence("แมว")
'แมวเวลานะนั้น'

class pythainlp.generate.Bigram(name: str = 'tnc')

Generate text using the bigram model.

Parameters:

name (str) –

corpus name

• tnc - Thai National Corpus (default)

__init__(name: str = 'tnc') → None

Initialize the bigram model.

uni: dict[str, int]

bi: dict[tuple[str, str], int]

uni_keys: list[str]

bi_keys: list[tuple[str, str]]

words: list[str]

prob(t1: str, t2: str) → float

Compute bigram probability P(t2 | t1).

Parameters:

• t1 (str) – first word

• t2 (str) – second word

Returns:

probability value

Return type:

float

gen_sentence(start_seq: str = '', N: int = 4, prob: float = 0.001, output_str: bool = True, duplicate: bool = False) → list[str] | str

Generate a sentence using the bigram model.

Parameters:

• start_seq (str) – word to begin the sentence with

• N (int) – number of words

• prob (float) – minimum word probability

• output_str (bool) – return a string instead of a list of words

• duplicate (bool) – allow duplicate words in the sentence

Returns:

generated sentence as a string or a list of words

Return type:

Union[list[str], str]

Example:

>>> from pythainlp.generate import Bigram

>>> gen = Bigram()

>>> gen.gen_sentence("แมว")
'แมวไม่ได้รับเชื้อมัน'

class pythainlp.generate.Trigram(name: str = 'tnc')

Generate text using the trigram model.

Parameters:

name (str) –

corpus name

• tnc - Thai National Corpus (default)

__init__(name: str = 'tnc') → None

Initialize the trigram model.

uni: dict[str, int]

bi: dict[tuple[str, str], int]

ti: dict[tuple[str, str, str], int]

uni_keys: list[str]

bi_keys: list[tuple[str, str]]

ti_keys: list[tuple[str, str, str]]

words: list[str]

prob(t1: str, t2: str, t3: str) → float

Compute trigram probability P(t3 | t1, t2).

Parameters:

• t1 (str) – first word

• t2 (str) – second word

• t3 (str) – third word

Returns:

probability value

Return type:

float

gen_sentence(start_seq: str | tuple[str, str] = '', N: int = 4, prob: float = 0.001, output_str: bool = True, duplicate: bool = False) → list[str] | str

Generate a sentence using the trigram model.

Parameters:

• start_seq (Union[str, tuple[str, str]]) – word or bigram to begin the sentence with

• N (int) – number of words

• prob (float) – minimum word probability

• output_str (bool) – return a string instead of a list of words

• duplicate (bool) – allow duplicate words in the sentence

Returns:

generated sentence as a string or a list of words

Return type:

Union[list[str], str]

Example:

>>> from pythainlp.generate import Trigram

>>> gen = Trigram()

>>> gen.gen_sentence()
'ยังทำตัวเป็นเซิร์ฟเวอร์คือ'

Usage

Choose the generator class or function for the model you want, initialize it with appropriate parameters, and call its generation methods. Generated text can be used for chatbots, content generation, or data augmentation.

Example

::

from pythainlp.generate import Unigram

unigram = Unigram() sentence = unigram.gen_sentence(“สวัสดีครับ”) print(sentence)