from sklearn.feature_extraction.text import TfidfVectorizer


documents = [
    "reset password token expired",
    "reset account password link",
    "invoice payment receipt delayed",
    "payment reminder invoice sent",
]

vectorizer = TfidfVectorizer(
    lowercase=True,
    stop_words="english",
    ngram_range=(1, 2),
)

matrix = vectorizer.fit_transform(documents)
feature_names = vectorizer.get_feature_names_out()

new_documents = ["password reset link sent"]
new_matrix = vectorizer.transform(new_documents)

print(f"training documents: {matrix.shape[0]}")
print(f"tf-idf matrix shape: {matrix.shape}")
print("first features:", ", ".join(feature_names[:8]))
print("learned vocabulary contains:", "password" in vectorizer.vocabulary_)
print(f"new document shape: {new_matrix.shape}")
print("new document non-zero weights:")

row = new_matrix[0]
for column_index in row.nonzero()[1]:
    print(f"  {feature_names[column_index]}: {row[0, column_index]:.3f}")