import unittest
import re
import nltk
from gensim.models import Word2Vec
import pandas as pd
from scipy.sparse import csr_matrix


# 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, "pd"), 
            "`pd` is not declared"
        )
        _require_success(
            self,
            user_code.pd == pd,
            "`pd` is declared, but it's not `pandas` library"
        )
        _require_success(
            self, 
            hasattr(user_code, "Word2Vec"), 
            "`Word2Vec` is not declared"
        )
        _require_success(
            self,
            user_code.Word2Vec == Word2Vec,
            "`Word2Vec` is declared, but it's not `gensim.models.Word2Vec`"
        )
        self._testMethodName = "imports are correct"

    # Test original corpus
    def test_corpus(self):
        import user_code
        expected = pd.read_csv(
    'https://content-media-cdn.codefinity.com/courses/c68c1f2e-2c90-4d5d-8db9-1e97ca89d15e/section_3/chapter_4/example_corpus.csv')
        _require_success(
            self, 
            hasattr(user_code, "corpus"), 
            "`corpus` is not declared"
        )
        _check_success(
            self,
            expected.equals(user_code.corpus),
            "`corpus` contains correct value",
            "`corpus` shouldn't be modified"
        )

    # Test that sentences are correctly computed
    def test_sentences(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "corpus"), 
            "`corpus` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.corpus, pd.DataFrame), 
            "`corpus` is not a DataFrame"
        )
        _require_success(
            self, 
            "Document" in user_code.corpus.columns, 
            "`corpus` doesn't contain `'Document'` column"
        )
        _require_success(
            self, 
            hasattr(user_code, "sentences"), 
            "`sentences` is not declared"
        )
        sentences = user_code.corpus['Document'].str.split()
        _check_success(
            self,
            sentences.equals(user_code.sentences),
            "`sentences` is computed correctly",
            "`sentences` is not computed correctly"
        )
  
    # Test that model is declared correctly
    def test_model(self):
        import user_code
        _require_success(
            self, 
            hasattr(user_code, "sentences"), 
            "`sentences` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.sentences, pd.Series), 
            "`sentences` is not a `Series` object"
        )
        model = Word2Vec(user_code.sentences, vector_size=50, window=2, min_count=1, sg=1)
        _require_success(
            self, 
            hasattr(user_code, "model"), 
            "`model` is not declared"
        )
        _require_success(
            self, 
            isinstance(user_code.model, Word2Vec), 
            "`model` is not an instance of `Word2Vec`"
        )
        _require_success(
            self, 
            user_code.model.corpus_count == model.corpus_count and user_code.model.corpus_total_words == model.corpus_total_words, 
            "`model` should be initialized with `sentences`"
        )
        _require_success(
            self, 
            user_code.model.vector_size == model.vector_size, 
            "`model` should be initialized with `vector_size=50`"
        )
        _require_success(
            self, 
            user_code.model.window == model.window, 
            "`model` should be initialized with `window=2`"
        )
        _require_success(
            self, 
            user_code.model.min_count == model.min_count, 
            "`model` should be initialized with `min_count=1`"
        )
        _require_success(
            self, 
            user_code.model.sg == model.sg, 
            "`model` should be initialized with `sg=1`"
        )
        self._testMethodName = "`model` is defined correctly"

    # 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 *\( *model *\. *wv *\. *most_similar *\( *(?P<quote>[\\"'])bowl(?P=quote) *, *topn *= *3 *\) *\)", user_code_text),
            "print statement is correct",
            "print statement is not correct"
        )


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

test_main.py

Behersk praktiske NLP-pipelines ved hjælp af TensorFlow og NLTK. Fokus på avanceret tekstforbehandling, tokenisering og implementering af word embeddings, herunder Word2Vec. Dette kursus er målrettet deep learning-ingeniører, der søger praktisk erfaring med at opbygge robuste NLP-fundamenter til AI-applikationer.

Udfordring: Oprettelse af Word Embeddings

Løsning