import unittest
import importlib
import re
import types
from nltk.tokenize import RegexpTokenizer


# Helper function to require a successful test
def _require_success(test_case, condition, failure_message):
    if not condition:
        test_case._testMethodName = failure_message  # Rename the test with a failure description
        test_case.fail()  # Fail the test with a failure message


# Helper function to check if test is successful
def _check_success(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message  # Rename the test for better readability in test reports
    else:
        test_case._testMethodName = failure_message  # Rename the test with a failure description
        test_case.fail()  # Fail the test with a failure message

class TestUserCode(unittest.TestCase):
    # Test that everything is imported correctly
    def test_imports(self):
        import user_code
        _require_success(
            self,
            hasattr(user_code, "RegexpTokenizer"),
            "`RegexpTokenizer` is not declared"
        )
        _require_success(
            self,
            user_code.RegexpTokenizer == RegexpTokenizer,
            "`RegexpTokenizer` is declared, but it's not `nltk.tokenize.RegexpTokenizer`"
        )
        self._testMethodName = "imports are correct"

    # Test that message is declared and has the correct value
    def test_message(self):
        import user_code
        _require_success(
            self,
            hasattr(user_code, "message"),
            "`message` is not declared"
        )
        expected = "Amazing event at #NLPConference_20! Over 1000 attendees from 20+ countries. #Networking #Tech"
        _check_success(
            self,
            user_code.message == expected,
            "`message` contains correct value",
            "`message` shouldn't be modified"
        )

    # Test that message_lower is declared and is lowercase
    def test_message_lower(self):
        import user_code
        _require_success(
            self,
            hasattr(user_code, "message"),
            "`message` is not declared"
        )
        _require_success(
            self,
            isinstance(user_code.message, str),
            "`message` is not a string"
        )
        _require_success(
            self,
            hasattr(user_code, "message_lower"),
            "`message_lower` is not declared"
        )
        _check_success(
            self,
            user_code.message_lower == user_code.message.lower(),
            "`message_lower` is computed correctly",
            "`message_lower` is not the lowercase of `message`"
        )

    # Test that word_tokenizer is declared correctly with the right pattern
    def test_word_tokenizer(self):
        import user_code
        _require_success(
            self,
            hasattr(user_code, "word_tokenizer"),
            "`word_tokenizer` is not declared"
        )
        _require_success(
            self,
            isinstance(user_code.word_tokenizer, RegexpTokenizer),
            "`word_tokenizer` is not an instance of `RegexpTokenizer`"
        )
        _check_success(
            self,
            user_code.word_tokenizer._pattern == r"\w+",
            "`word_tokenizer` is defined correctly",
            "`word_tokenizer`'s pattern is incorrect'"
        )

    # Test that words is declared and correctly tokenizes the lowercase message
    def test_words(self):
        import user_code
        _require_success(
            self,
            hasattr(user_code, "message_lower"),
            "`message_lower` is not declared"
        )
        _require_success(
            self,
            isinstance(user_code.message_lower, str),
            "`message_lower` is not a string"
        )
        _require_success(
            self,
            hasattr(user_code, "word_tokenizer"),
            "`word_tokenizer` is not declared"
        )
        _require_success(
            self,
            isinstance(user_code.word_tokenizer, RegexpTokenizer),
            "`word_tokenizer` is not an instance of `RegexpTokenizer`"
        )
        _require_success(
            self,
            hasattr(user_code, "words"),
            "`words` is not declared"
        )
        _check_success(
            self,
            user_code.words == user_code.word_tokenizer.tokenize(user_code.message_lower),
            "`words` is computed correctly",
            "`message_lower` is not correctly tokenized into words"
        )

    # Test that the print statement is present and unmodified
    def test_print(self):
        with open("user_code.py", "r") as f:
            user_code_text = f.read()
            _check_success(
                self,
                re.search(r"print *\( *words *\)", user_code_text),
                "print statement is correct",
                "print statement shouldn't be modified"
            )


if __name__ == '__main__':
    unittest.main()

test_main.py

Verken de basisprincipes van Natural Language Processing (NLP) door essentiële technieken voor tekstvoorbewerking en methoden voor het representeren van tekstgegevens te leren. Doe praktische ervaring op met de tools die worden gebruikt om tekstuele informatie te reinigen, analyseren en interpreteren. Ontwikkel de vaardigheden die nodig zijn om ruwe taal om te zetten in gestructureerde inzichten, waarmee een solide basis wordt gelegd voor geavanceerde toepassingen in kunstmatige intelligentie en machine learning.

Verdiep u in de grondbeginselen van tekstvoorbewerking om ruwe tekst voor analyse voor te bereiden. Leer hoe u tekst segmenteert, stopwoorden verwijdert en tokenisatie aanpast met reguliere expressies.

Ontdek hoe woorden kunnen worden teruggebracht tot hun basisvormen met behulp van stemming en lemmatizatie. Beheers het toekennen van woordsoorten om tekst te verrijken met grammaticale context en pas lemmatizatie toe met kennis van woordsoorten.

Leer hoe tekst kan worden weergegeven met getallen door middel van vectorruimte modellen. Doe praktische ervaring op met het implementeren en aanpassen van twee populaire vectorruimte modellen: bag-of-words en TF-IDF.

Verkrijg een grondig begrip van woordembeddings en hoe deze semantische betekenis vastleggen. Verken CBoW- en Skip-gram-architecturen die worden gebruikt in Word2Vec, en implementeer deze zelfstandig.

Uitdaging: Tokenisatie met Regex

Oplossing

Awesome!

Uitdaging: Tokenisatie met Regex

Oplossing