Spaces:
Configuration error
Configuration error
File size: 4,383 Bytes
8cbfc52 | 1 2 3 4 5 6 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 40 41 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 72 73 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | import re
from dataclasses import dataclass
from typing import List
import pandas as pd
import config
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Data Model
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
@dataclass
class QARecord:
id: int
question: str
answer: str
content: str
tokens: List[str]
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Arabic Cleaning
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ARABIC_DIACRITICS = re.compile("""
Ω | # Tashdid
Ω | # Fatha
Ω | # Tanwin Fath
Ω | # Damma
Ω | # Tanwin Damm
Ω | # Kasra
Ω | # Tanwin Kasr
Ω | # Sukun
Ω
""", re.VERBOSE)
def normalize_arabic(text):
text = re.sub(
"[Ψ₯Ψ£Ψ’Ψ§]",
"Ψ§",
text,
)
text = re.sub(
"Ω",
"Ω",
text,
)
text = re.sub(
"Ψ€",
"Ω",
text,
)
text = re.sub(
"Ψ¦",
"Ω",
text,
)
text = re.sub(
"Ψ©",
"Ω",
text,
)
return text
def strip_diacritics(text):
return re.sub(
ARABIC_DIACRITICS,
"",
text,
)
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Cleaning
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
def clean_text(text):
text = str(text).strip()
text = strip_diacritics(text)
text = normalize_arabic(text)
text = re.sub(
r"\s+",
" ",
text,
)
return text
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Tokenization
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
def tokenize(text):
text = clean_text(text)
text = re.sub(
r"[^\w\s]",
" ",
text,
)
tokens = text.split()
return tokens
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
# Load Excel
# βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
def load_excel(
path,
question_col=None,
answer_col=None,
):
question_col = (
question_col
or
config.QUESTION_COL
)
answer_col = (
answer_col
or
config.ANSWER_COL
)
df = pd.read_excel(path)
records = []
for idx, row in df.iterrows():
q = clean_text(
row[question_col]
)
a = clean_text(
row[answer_col]
)
# IMPORTANT:
# index question + answer together
content = f"""
Ψ§ΩΨ³Ψ€Ψ§Ω:
{q}
Ψ§ΩΨ¬ΩΨ§Ψ¨:
{a}
"""
tokens = tokenize(content)
records.append(
QARecord(
id=idx,
question=q,
answer=a,
content=content,
tokens=tokens,
)
)
return records |