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

Udforsk grundlæggende principper inden for Natural Language Processing (NLP) ved at lære essentielle teknikker til tekstforbehandling og metoder til repræsentation af tekstdata. Opnå praktisk erfaring med værktøjer til at rense, analysere og fortolke tekstuel information. Udvikl færdigheder til at omdanne råt sprog til strukturerede indsigter og skab et solidt fundament for avancerede anvendelser inden for kunstig intelligens og maskinlæring.

Dyk ned i de grundlæggende principper for tekstforbehandling for at klargøre rå tekst til analyse. Lær hvordan man opdeler tekst i tokens, filtrerer stopord fra og tilpasser tokenisering med regulære udtryk.

Opdag, hvordan ord kan reduceres til deres grundformer ved hjælp af stamme- og lemmatisering. Behersk ordklassemærkning for at berige tekst med grammatisk kontekst og anvend ordklassebevidst lemmatisering.

Lær, hvordan tekst kan repræsenteres med tal ved hjælp af vektorrumsmodeller. Få praktisk erfaring med at implementere og tilpasse to populære vektorrumsmodeller: bag of words og TF-IDF.

Opnå en solid forståelse af ordindlejringer og hvordan de indfanger semantisk betydning. Udforsk CBoW- og Skip-gram-arkitekturer anvendt i Word2Vec, og implementer dem selv.

Udfordring: Tokenisering med Regex

Løsning

Awesome!

Udfordring: Tokenisering med Regex

Løsning