import unittest
import re
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import PorterStemmer


# Helper functions
def _require_success(test_case, condition, failure_message):
    if not condition:
        test_case._testMethodName = failure_message
        test_case.fail()

def _check_success(test_case, condition, success_message, failure_message):
    if condition:
        test_case._testMethodName = success_message
    else:
        test_case._testMethodName = failure_message
        test_case.fail()


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

    # Test that required NLTK resources are downloaded
    def test_nltk_downloads(self):
        import user_code
        _require_success(
            self,
            hasattr(user_code, "nltk"),
            "`nltk` is not declared"
        )
        _require_success(
            self,
            user_code.nltk == nltk,
            "`nltk` is declared, but it's not `nltk` library"
        )
        with open("user_code.py", "r") as f:
            user_code_text = f.read()
            _require_success(
                self,
                re.search(r"nltk *\. *download *\( *'punkt_tab' *\)", user_code_text),
                "Code for downloading `'punkt_tab'` tokenizer shouldn't be modified"
            )
            _require_success(
                self,
                re.search(r"nltk *\. *download *\( *'stopwords' *\)", user_code_text),
                "Code for downloading `'stopwords'` shouldn't be modified"
            )
        self._testMethodName = "NLTK resources are downloaded"

    # Test original text
    def test_text(self):
        import user_code
        expected = "Despite the pouring rain, the overwhelming sense of joy and accomplishment made the day unforgettable!"
        _require_success(
            self, 
            hasattr(user_code, "text"), 
            "`text` is not declared"
        )
        _check_success(
            self,
            user_code.text == expected,
            "`text` contains correct value",
            "`text` shouldn't be modified"
        )

    # Test lowercase conversion
    def test_text_lower(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "text"), 
            "`text` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.text, str), 
            "`text` is not a string"
        )
        _require_success(
            self, 
            hasattr(user_code, "text_lower"), 
            "`text_lower` is not declared"
        )
        _check_success(
            self,
            user_code.text_lower == user_code.text.lower(),
            "`text_lower` is computed correctly",
            "`text_lower` is not the lowercase of `text`"
        )

    # Test tokenization of text_lower
    def test_tokens(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "text_lower"), 
            "`text_lower` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.text_lower, str), 
            "`text_lower` is not a string"
        )
        _require_success(
            self, 
            hasattr(user_code, "tokens"), 
            "`tokens` is not declared"
        )
        _check_success(
            self,
            user_code.tokens == word_tokenize(user_code.text_lower),
            "`tokens` is computed correctly",
            "`text_lower` is not correctly tokenized into words"
        )

    # Test stop_words set
    def test_stop_words(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "stop_words"), 
            "`stop_words` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.stop_words, set), 
            "`stop_words` is not a set"
        )
        _check_success(
            self,
            user_code.stop_words == set(stopwords.words('english')),
            "`stop_words` contains correct English stopwords set",
            "`stop_words` doesn't contain English stopwords"
        )

    # Test filtered_tokens filtering
    def test_filtered_tokens(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "tokens"), 
            "`tokens` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.tokens, list), 
            "`tokens` is not a list"
        )
        _require_success(
            self, 
            hasattr(user_code, "stop_words"), 
            "`stop_words` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.stop_words, set), 
            "`stop_words` is not a set"
        )
        _require_success(
            self, 
            hasattr(user_code, "filtered_tokens"), 
            "`filtered_tokens` is not declared"
        )
        expected = [tok for tok in user_code.tokens if tok not in user_code.stop_words]
        _check_success(
            self,
            user_code.filtered_tokens == expected,
            "`filtered_tokens` is computed correctly",
            "stop words in `tokens` are not correctly filtered out"
        )

    # Test stemmer instance
    def test_stemmer(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "stemmer"), 
            "`stemmer` is not declared"
        )
        _check_success(
            self,
            isinstance(user_code.stemmer, PorterStemmer),
            "`stemmer` is defined correctly",
            "`stemmer` is not an instance of `PorterStemmer`"
        )

    # Test stemming results
    def test_stemmed_tokens(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "stemmer"), 
            "`stemmer` is not declared"
        )
        _require_success(
            self,
            isinstance(user_code.stemmer, PorterStemmer),
            "`stemmer` is not an instance of `PorterStemmer`"
        )
        _require_success(
            self, 
            hasattr(user_code, "filtered_tokens"), 
            "`filtered_tokens` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.filtered_tokens, list), 
            "`filtered_tokens` is not a list"
        )
        _require_success(
            self, 
            hasattr(user_code, "stemmed_tokens"), 
            "`stemmed_tokens` is not declared"
        )
        expected = [user_code.stemmer.stem(tok) for tok in user_code.filtered_tokens]
        _check_success(
            self,
            user_code.stemmed_tokens == expected,
            "`stemmed_tokens` is computed correctly",
            "`filtered_tokens` are not correctly stemmed"
        )

    # Test print statement
    def test_print(self):
        with open("user_code.py", "r") as f:
            user_code_text = f.read()
        _check_success(
            self,
            re.search(r"print *\( *\\"Stemmed tokens:\\" *, *stemmed_tokens *\)", user_code_text),
            "print statement is correct",
            "print statement shouldn't be modified"
        )


if __name__ == '__main__':
    nltk.download('punkt_tab')
    nltk.download('stopwords')
    unittest.main()

test_main.py

Erkunden Sie die Grundlagen der Verarbeitung natürlicher Sprache (NLP), indem Sie wesentliche Techniken zur Textvorverarbeitung und Methoden zur Repräsentation von Textdaten erlernen. Sammeln Sie praktische Erfahrungen mit Werkzeugen zur Bereinigung, Analyse und Interpretation von Textinformationen. Entwickeln Sie die Fähigkeiten, rohe Sprache in strukturierte Erkenntnisse umzuwandeln und schaffen Sie so eine solide Grundlage für fortgeschrittene Anwendungen in künstlicher Intelligenz und maschinellem Lernen.

Tauchen Sie in die Grundlagen der Textvorverarbeitung ein, um Rohtext für die Analyse vorzubereiten. Erfahren Sie, wie Text tokenisiert, Stoppwörter entfernt und die Tokenisierung mit regulären Ausdrücken angepasst wird.

Erfahren Sie, wie Wörter mithilfe von Stemming und Lemmatisierung auf ihre Grundformen reduziert werden können. Beherrschen Sie die Part-of-Speech-Tagging-Technik, um Texte mit grammatischem Kontext anzureichern, und wenden Sie POS-basierte Lemmatisierung an.

Erfahren Sie, wie Text mithilfe von Vektorraum-Modellen in Zahlen dargestellt werden kann. Sammeln Sie praktische Erfahrungen durch die Implementierung und Anpassung zweier gängiger Vektorraum-Modelle: Bag-of-Words und TF-IDF.

Fundiertes Verständnis von Wort-Einbettungen und deren Erfassung semantischer Bedeutungen. Untersuchung der CBoW- und Skip-gram-Architekturen, die in Word2Vec verwendet werden, sowie deren eigenständige Implementierung.

Herausforderung: Stemming

Lösung

Herausforderung: Stemming

Lösung