modelpipe.py

# MODEL Pipeline

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix, accuracy_score
import matplotlib.pyplot as plt

# random forest classifier
rf_classifier = RandomForestClassifier(n_estimators = 11, criterion='entropy', random_state=0)

rf_model_pipeline = Pipeline(steps=[
    ('preprocessing', columns_transformer),
    ('rf_model', rf_classifier),
])

rf_model_pipeline.fit(X_train, y_train)

# predict on test set
y_pred = rf_model_pipeline.predict(X_test)

# calculate accuracy
ac = accuracy_score(y_test, y_pred)
print(f"Accuracy= {ac}")