# -*- coding: utf-8 -*-
# SPDX-FileCopyrightText: 2016-2024 PyThaiNLP Project.
# SPDX-License-Identifier: Apache-2.0
"""
Thai National Corpus word frequency
"""
__all__ = [
"bigram_word_freqs",
"trigram_word_freqs",
"unigram_word_freqs",
"word_freqs",
]
from collections import defaultdict
from typing import List, Tuple
from pythainlp.corpus import get_corpus, get_corpus_path
_UNIGRAM_FILENAME = "tnc_freq.txt"
_BIGRAM_CORPUS_NAME = "tnc_bigram_word_freqs"
_TRIGRAM_CORPUS_NAME = "tnc_trigram_word_freqs"
[docs]
def word_freqs() -> List[Tuple[str, int]]:
"""
Get word frequency from Thai National Corpus (TNC)
\n(See: `dev/pythainlp/corpus/tnc_freq.txt\
<https://github.com/PyThaiNLP/pythainlp/blob/dev/pythainlp/corpus/tnc_freq.txt>`_)
Credit: Korakot Chaovavanich https://www.facebook.com/groups/thainlp/posts/434330506948445
"""
freqs: list[tuple[str, int]] = []
lines = list(get_corpus(_UNIGRAM_FILENAME))
for line in lines:
word_freq = line.split("\t")
if len(word_freq) >= 2:
freqs.append((word_freq[0], int(word_freq[1])))
return freqs
[docs]
def unigram_word_freqs() -> dict[str, int]:
"""
Get unigram word frequency from Thai National Corpus (TNC)
"""
freqs: dict[str, int] = defaultdict(int)
lines = list(get_corpus(_UNIGRAM_FILENAME))
for i in lines:
_temp = i.strip().split(" ")
if len(_temp) >= 2:
freqs[_temp[0]] = int(_temp[-1])
return freqs
[docs]
def bigram_word_freqs() -> dict[Tuple[str, str], int]:
"""
Get bigram word frequency from Thai National Corpus (TNC)
"""
freqs: dict[tuple[str, str], int] = defaultdict(int)
path = get_corpus_path(_BIGRAM_CORPUS_NAME)
if not path:
return freqs
path = str(path)
with open(path, "r", encoding="utf-8-sig") as fh:
for i in fh.readlines():
temp = i.strip().split(" ")
freqs[(temp[0], temp[1])] = int(temp[-1])
return freqs
[docs]
def trigram_word_freqs() -> dict[Tuple[str, str, str], int]:
"""
Get trigram word frequency from Thai National Corpus (TNC)
"""
freqs: dict[tuple[str, str, str], int] = defaultdict(int)
path = get_corpus_path(_TRIGRAM_CORPUS_NAME)
if not path:
return freqs
path = str(path)
with open(path, "r", encoding="utf-8-sig") as fh:
for i in fh.readlines():
temp = i.strip().split(" ")
freqs[(temp[0], temp[1], temp[2])] = int(temp[-1])
return freqs