nlp14.py

# feature selection
label = "is_bad_review"
ignore_cols = [label, "review", "review_clean"]
features = [c for c in reviews_df.columns if c not in ignore_cols]

# split the data into train and test
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(reviews_df[features], reviews_df[label], test_size = 0.20, random_state = 42)