File size: 1,233 Bytes
d840583
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""Text cleaning / normalization for Arabic sentiment analysis."""

from preprocessing.arabic_normalizer import Arabic_Light_Stemmer, normalizeArabic
from preprocessing.emoji_handler import (
    emoji_counter,
    extract_emoji,
    remove_emoji,
    replace_emojis_with_text,
    replace_emoticon_with_emojis,
    space_between_emojis,
)
from preprocessing.pipeline import (
    CLEANING_STEPS,
    EMOJI_STEPS,
    clean_text,
    preprocess_dataframe,
)
from preprocessing.text_cleaning import (
    Removing_non_arabic,
    Removing_numbers,
    Removing_punctuations,
    Removing_urls,
    remove_extra_Space,
    remove_hashtags_and_mentions,
    remove_small_sentences,
    remove_stop_words,
)

__all__ = [
    "Arabic_Light_Stemmer",
    "CLEANING_STEPS",
    "EMOJI_STEPS",
    "Removing_non_arabic",
    "Removing_numbers",
    "Removing_punctuations",
    "Removing_urls",
    "clean_text",
    "emoji_counter",
    "extract_emoji",
    "normalizeArabic",
    "preprocess_dataframe",
    "remove_emoji",
    "remove_extra_Space",
    "remove_hashtags_and_mentions",
    "remove_small_sentences",
    "remove_stop_words",
    "replace_emojis_with_text",
    "replace_emoticon_with_emojis",
    "space_between_emojis",
]