rfc_pipeline.py

from sklearn.ensemble import RandomForestClassifier
from sklearn.pipeline import Pipeline


steps = [
    ("vectorizer", TfidfVectorizer(stop_words=my_stopwords)),
    ("rf", RandomForestClassifier())
]

# instatiating the pipeline
pipe = Pipeline(steps)

# setting the values for the RandomForest model
grid_params = {
    "vectorizer__max_features": [2000, 3000, 4000],
    "vectorizer__ngram_range":[(1,1), (1,2)],
    "rf__n_estimators": [2500, 3000, 3500],
    "rf__max_depth": [17, 18, 19, 20],
    "rf__min_samples_leaf": [1, 2, 3]
}

# grid search
gs = GridSearchCV(pipe, grid_params, verbose=1, n_jobs=2)
results = gs.fit(X_train, y_train)