import unittest
import importlib
import re
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
import nltk


# 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 imported correctly
    def test_imports(self):
        import user_code
        _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, "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, "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 that text is declared and unmodified
    def test_text(self):
        import user_code
        expected = """
The Natural Language Toolkit, or NLTK for short, provides a suite of libraries and programs for symbolic and statistical natural language processing in Python. It includes  a diverse set of linguistic data and tools to work with, making it easier for developers and researchers to build 
NLP applications without having to worry about data gathering and preprocessing.
"""
        _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 that text_lower is declared and lowercase
    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 that stop_words variable is declared and correct
    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 that tokens is declared and tokenized correctly
    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 that tokens_clean is declared and filtered correctly
    def test_tokens_clean(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, "tokens_clean"),
            "`tokens_clean` is not declared"
        )
        expected = [tok for tok in user_code.tokens if tok not in user_code.stop_words]
        _check_success(
            self,
            user_code.tokens_clean == expected,
            "`tokens_clean` is computed correctly",
            "stop words in `tokens` are not correctly filtered out"
        )

    # 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 *\( *\\"Filtered Tokens:\\" *, *tokens_clean *\)", user_code_text) is not None,
                "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

Tutustu luonnollisen kielen käsittelyn (NLP) perusteisiin oppimalla keskeiset tekstin esikäsittelytekniikat ja menetelmät tekstiaineiston esittämiseen. Saat käytännön kokemusta työkaluista, joilla puhdistetaan, analysoidaan ja tulkitaan tekstimuotoista tietoa. Kehitä taidot, joilla muutat raakakielen jäsennellyiksi havainnoiksi ja luot vahvan pohjan tekoälyn ja koneoppimisen edistyneille sovelluksille.

Perehdy tekstin esikäsittelyn perusteisiin raakatekstin valmistelussa analyysia varten. Opiskele tekstin tokenisointia, stop-sanojen suodatusta sekä tokenisoinnin mukauttamista säännöllisten lausekkeiden avulla.

Opi, miten sanoja voidaan palauttaa perusmuotoonsa stemmauksen ja lemmatisaation avulla. Hallitse sanaluokkien tunnistus tekstin kieliopillisen kontekstin rikastamiseksi ja sovella sanaluokkatietoista lemmatisaatiota.

Opi, miten teksti voidaan esittää numeroina vektoriavaruusmallien avulla. Saat käytännön kokemusta toteuttamalla ja mukauttamalla kahta suosittua vektoriavaruusmallia: sanapussimalli ja TF-IDF.

Hanki vankka ymmärrys sanaesityksistä ja siitä, miten ne tallentavat semanttista merkitystä. Tutustu Word2Vecin CBoW- ja Skip-gram-arkkitehtuureihin ja toteuta ne itse.

Haaste: Stop-Sanat

Ratkaisu

Haaste: Stop-Sanat

Ratkaisu