Turkish Deasciifier

This tool is used to turn Turkish text written in ASCII characters, which do not include some letters of the Turkish alphabet, into correctly written text with the appropriate Turkish characters (such as ı, ş, and so forth). It can also do the opposite, turning Turkish input into ASCII text, for the purpose of processing.

Simple Web Interface

Asciifier Link 1 Asciifier Link 2

Deasciifier Link 1 Deasciifier Link 2

Video Lectures

For Developers

You can also see Cython, Java, C++, C, Swift, Js, Php, or C# repository.

Requirements

• Python 3.7 or higher
• Git

Python

To check if you have a compatible version of Python installed, use the following command:

python -V

You can find the latest version of Python here.

Git

Install the latest version of Git.

Pip Install

pip3 install NlpToolkit-Deasciifier

Download Code

In order to work on code, create a fork from GitHub page. Use Git for cloning the code to your local or below line for Ubuntu:

git clone <your-fork-git-link>

A directory called Deasciifier will be created. Or you can use below link for exploring the code:

git clone https://github.com/starlangsoftware/TurkishDeasciifier-Py.git

Open project with Pycharm IDE

Steps for opening the cloned project:

• Start IDE
• Select File | Open from main menu
• Choose TurkishDeasciifier-PY file
• Select open as project option
• Couple of seconds, dependencies will be downloaded.

Detailed Description

• Asciifier
• Deasciifier

Using Asciifier

Asciifier converts text to a format containing only ASCII letters. This can be instantiated and used as follows:

  asciifier = SimpleAsciifier()
  sentence = Sentence("çocuk")
  asciified = asciifier.asciify(sentence)
  print(asciified)

Output:

cocuk      

Using Deasciifier

Deasciifier converts text written with only ASCII letters to its correct form using corresponding letters in Turkish alphabet. There are two types of Deasciifier:

• SimpleDeasciifier

  The instantiation can be done as follows:

    fsm = FsmMorphologicalAnalyzer()
    deasciifier = SimpleDeasciifier(fsm)
  

• NGramDeasciifier

  • To create an instance of this, both a FsmMorphologicalAnalyzer and a NGram is required.

  • FsmMorphologicalAnalyzer can be instantiated as follows:

      fsm = FsmMorphologicalAnalyzer()
    

  • NGram can be either trained from scratch or loaded from an existing model.

    • Training from scratch:

        corpus = Corpus("corpus.txt")
        ngram = NGram(corpus.getAllWordsAsArrayList(), 1)
        ngram.calculateNGramProbabilities(LaplaceSmoothing())
      

    There are many smoothing methods available. For other smoothing methods, check here.

    • Loading from an existing model:

            ngram = NGram("ngram.txt")
      

  For further details, please check here.

  • Afterwards, NGramDeasciifier can be created as below:

      deasciifier = NGramDeasciifier(fsm, ngram)
    

A text can be deasciified as follows:

sentence = Sentence("cocuk")
deasciified = deasciifier.deasciify(sentence)
print(deasciified)

Output:

çocuk

For Contibutors

Setup.py file

1. Do not forget to set package list. All subfolders should be added to the package list.

    packages=['Classification', 'Classification.Model', 'Classification.Model.DecisionTree',
              'Classification.Model.Ensemble', 'Classification.Model.NeuralNetwork',
              'Classification.Model.NonParametric', 'Classification.Model.Parametric',
              'Classification.Filter', 'Classification.DataSet', 'Classification.Instance', 'Classification.Attribute',
              'Classification.Parameter', 'Classification.Experiment',
              'Classification.Performance', 'Classification.InstanceList', 'Classification.DistanceMetric',
              'Classification.StatisticalTest', 'Classification.FeatureSelection'],

2. Package name should be lowercase and only may include _ character.

    name='nlptoolkit_math',

Python files

1. Do not forget to comment each function.

    def __broadcast_shape(self, shape1: Tuple[int, ...], shape2: Tuple[int, ...]) -> Tuple[int, ...]:
        """
        Determines the broadcasted shape of two tensors.

        :param shape1: Tuple representing the first tensor shape.
        :param shape2: Tuple representing the second tensor shape.
        :return: Tuple representing the broadcasted shape.
        """

2. Function names should follow caml case.

    def addItem(self, item: str):

3. Local variables should follow snake case.

	det = 1.0
	copy_of_matrix = copy.deepcopy(self)

4. Class variables should be declared in each file.

class Eigenvector(Vector):
    eigenvalue: float

5. Variable types should be defined for function parameters and class variables.

    def getIndex(self, item: str) -> int:

6. For abstract methods, use ABC package and declare them with @abstractmethod.

    @abstractmethod
    def train(self, train_set: list[Tensor]):
        pass

7. For private methods, use __ as prefix in their names.

    def __infer_shape(self, data: Union[List, List[List], List[List[List]]]) -> Tuple[int, ...]:

8. For private class variables, use __ as prefix in their names.

class Matrix(object):
    __row: int
    __col: int
    __values: list[list[float]]

9. Write __repr__ class methods as toString methods
10. Write getter and setter class methods.

    def getOptimizer(self) -> Optimizer:
        return self.optimizer
    def setValue(self, value: Optional[Tensor]) -> None:
        self._value = value

11. If there are multiple constructors for a class, define them as constructor1, constructor2, ..., then from the original constructor call these methods.

    def constructor1(self):
        self.__values = []
        self.__size = 0

    def constructor2(self, values: list):
        self.__values = values.copy()
        self.__size = len(values)

    def __init__(self,
                 valuesOrSize=None,
                 initial=None):
        if valuesOrSize is None:
            self.constructor1()
        elif isinstance(valuesOrSize, list):
            self.constructor2(valuesOrSize)

12. Extend test classes from unittest and use separate unit test methods.

class TensorTest(unittest.TestCase):

    def test_inferred_shape(self):
        a = Tensor([[1.0, 2.0], [3.0, 4.0]])
        self.assertEqual((2, 2), a.getShape())

    def test_shape(self):
        a = Tensor([1.0, 2.0, 3.0])
        self.assertEqual((3, ), a.getShape())

13. Enumerated types should be used when necessary as enum classes.

class AttributeType(Enum):
    """
    Continuous Attribute
    """
    CONTINUOUS = auto()
    """
    Discrete Attribute
    """
    DISCRETE = auto()