import unittest
import re
import nltk
from nltk.tokenize import word_tokenize
from nltk import pos_tag
import pandas as pd


# 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, "pos_tag"), 
            "`pos_tag` is not declared"
        )
        _require_success(
            self,
            user_code.pos_tag == pos_tag,
            "`pos_tag` is declared, but it's not `nltk.pos_tag`"
        )
        _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 *\( *'averaged_perceptron_tagger_eng' *\)", user_code_text),
                "Code for downloading `'averaged_perceptron_tagger_eng'` is not provided"
            )
        self._testMethodName = "NLTK resources are downloaded"

    # Test original text
    def test_text(self):
        import user_code
        expected = "The central bank raised interest rates by 0.5 percentage points yesterday."
        _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 pos tagging results
    def test_tagged_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, "tagged_tokens"), 
            "`tagged_tokens` is not declared"
        )
        _check_success(
            self,
            user_code.tagged_tokens == pos_tag(user_code.tokens),
            "`tagged_tokens` is computed correctly",
            "`tokens` are not correctly pos tagged"
        )

    # Test print statement
    def test_dataframe_print(self):
        import user_code
        _require_success(
            self,
            hasattr(user_code, "pd"),
            "`pd` is not declared"
        )
        _require_success(
            self,
            user_code.pd == pd,
            "`pd` is declared, but it's not `pandas` library"
        )
        with open("user_code.py", "r") as f:
            user_code_text = f.read()
        _check_success(
            self,
            re.search(r"print *\( *pd *. *DataFrame *\( *tagged_tokens *, *columns *= *\[ *'Token', *'POS tag' *\] *\) *\)", user_code_text),
            "print statement is correct",
            "print statement is either incorrect, or original parts were modified"
        )


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

test_main.py

Explorez les principes fondamentaux du traitement automatique du langage naturel (TALN) en apprenant les techniques essentielles de prétraitement du texte et les méthodes de représentation des données textuelles. Acquérez une expérience pratique avec les outils utilisés pour nettoyer, analyser et interpréter les informations textuelles. Développez les compétences nécessaires pour transformer le langage brut en informations structurées, posant ainsi une base solide pour des applications avancées en intelligence artificielle et en apprentissage automatique.

Explorez les fondamentaux du prétraitement de texte afin de préparer le texte brut pour l'analyse. Découvrez la tokenisation du texte, l'élimination des mots vides et la personnalisation de la tokenisation à l'aide d'expressions régulières.

Découvrez comment les mots peuvent être réduits à leur forme de base grâce à la racinisation et à la lemmatisation.
Maîtrise de l'étiquetage des parties du discours pour enrichir le texte avec un contexte grammatical et application de la lemmatisation sensible au POS.

Découvrez comment le texte peut être représenté par des nombres à l'aide de modèles d'espace vectoriel. Expérimentez concrètement en implémentant et en personnalisant deux modèles d'espace vectoriel populaires : sac de mots et TF-IDF.

Acquérir une compréhension approfondie des représentations vectorielles de mots et de leur capacité à capturer la signification sémantique. Explorer les architectures CBoW et Skip-gram utilisées dans Word2Vec, et les mettre en œuvre soi-même.

Défi : Étiquetage des Parties du Discours

Solution

Awesome!

Défi : Étiquetage des Parties du Discours

Solution