from sklearn.feature_extraction.text import CountVectorizer
from sklearn.linear_model import LogisticRegression

train_text = df_train_augmented.text.tolist()
X_train = CountVectorizer(ngram_range=(1, 2)).fit_transform(train_text)

clf = LogisticRegression(solver="lbfgs")
clf.fit(X=X_train, y=df_train_augmented.label.values)