Text vectorization with TF-IDF for strong classical baselines

                  from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.metrics import classification_report

pipeline = Pipeline([
    ('vectorizer', TfidfVectorizer(max_features=30_000, ngram_range=(1, 2), min_df=3)),
    ('model', LogisticRegression(max_iter=2000, class_weight='balanced')),
])

pipeline.fit(train_texts, train_labels)
predictions = pipeline.predict(valid_texts)
print(classification_report(valid_labels, predictions, digits=3))