Tashaphyne

https://tashaphyne.readthedocs.io/en/latest/
Admin
Tashaphyne is an Arabic light stemmer and segmentor that removes prefixes and suffixes while...
Tokens:1,465
Snippets:18
Trust Score:9.6
Update:5 months ago
Show doc for...
Tokens:
Raw
### Install Tashaphyne

Source: https://tashaphyne.readthedocs.io/en/latest/README.html

Install the Tashaphyne library using pip. This command downloads and installs the latest version of the package.

```bash
pip install tashaphyne

```

--------------------------------

### Customize Affixes List for Stemming

Source: https://tashaphyne.readthedocs.io/en/latest/README.html

Demonstrates how to customize the prefix and suffix lists for the ArabicLightStemmer to achieve different stemming results. This is useful for tailoring the stemmer to specific contexts or linguistic variations.

```python
import tashaphyne.stemming

CUSTOM_PREFIX_LIST = [u'كال', u'أفبال', u'أفك', u'فك', u'أولل', u'', u'أف', u'ول', u'أوال', u'ف', u'و', u'أو', u'ولل', u'فب', u'أول', u'ألل', u'لل', u'ب', u'وكال', u'أوب', u'بال', u'أكال', u'ال', u'أب', u'وب', u'أوبال', u'أ', u'وبال', u'أك', u'فكال', u'أوك', u'فلل', u'وك', u'ك', u'أل', u'فال', u'وال', u'أوكال', u'أفلل', u'أفل', u'فل', u'أال', u'أفكال', u'ل', u'أبال', u'أفال', u'أفب', u'فبال']
CUSTOM_SUFFIX_LIST = [u'كما', u'ك', u'هن', u'ي', u'ها', u'', u'ه', u'كم', u'كن', u'هم', u'هما', u'نا']

# simple stemmer with default affixes list
simple_stemmer = tashaphyne.stemming.ArabicLightStemmer()

# create a cعstomized stemmer object for stemming enclitics and procletics
custom_stemmer = tashaphyne.stemming.ArabicLightStemmer()
# configure the stemmer object
custom_stemmer.set_prefix_list(CUSTOM_PREFIX_LIST)
custom_stemmer.set_suffix_list(CUSTOM_SUFFIX_LIST)

word = u"بالمدرستين"
# segment word as
simple_stemmer.segment(word)
print  repr(simple_stemmer.get_affix_list())

custom_stemmer.segment(word)

print  repr(custom_stemmer.get_affix_list())

```

--------------------------------

### Stemming Text with Tokenization

Source: https://tashaphyne.readthedocs.io/en/latest/README.html

This snippet shows how to stem all words in a given Arabic text by first tokenizing the text using `pyarabic.araby.tokenize` and then applying the `ArabicLightStemmer` to each token.

```python
import pyarabic.araby as araby
from tashaphyne.stemming import ArabicLightStemmer
stemmer  = ArabicLightStemmer()
text = "الأطفال يستريحون في المكتبة للمطالعة"
tokens = araby.tokenize(text)
for tok in tokens:
    stem = stemmer.light_stem(tok)
    print(tok, stem)

```

--------------------------------

### Tashaphyne Citation (BibTeX)

Source: https://tashaphyne.readthedocs.io/en/latest/README.html

BibTeX format for citing the Tashaphyne library in academic work.

```bibtex
@misc{zerrouki2012tashaphyne,
title={Tashaphyne, Arabic light stemmer},
author={Zerrouki, Taha},
url={https://pypi.python.org/pypi/Tashaphyne/0.2},
year={2012}
}

```

--------------------------------

### Citation for Tashaphyne

Source: https://tashaphyne.readthedocs.io/en/latest/README.html

Use this citation in academic work when referencing Tashaphyne. Both a standard format and BibTeX format are provided.

```misc
T. Zerrouki‏, Tashaphyne, Arabic light stemmer‏,  https://pypi.org/pypi/Tashaphyne/0.2

```

```bibtex
@misc{zerrouki2012tashaphyne,
  title={Tashaphyne, Arabic light stemmer},
  author={Zerrouki, Taha},
  url={https://pypi.org/pypi/Tashaphyne/0.2},
  year={2012}
}

```
Tokens:
Raw