Scalable_Pipeline_Article

modeling.py

X,y = df.drop(columns=['Transported']), df.loc[:, ['Transported']] #Target Variable

#  Replacing the predicted true/false from a string to a boolean
y.replace({True:'True', False:'False'}, inplace=True) 

X_train, X_test, y_train, y_test = train_test_split(X,y, test_size=0.33)

# Using ravel to silence a user warning. No big deal though. Doesn't change anything.
full_pipe.fit(X_train, y_train.values.ravel());
y_pred = full_pipe.predict(X_test)

from sklearn.metrics import accuracy_score # Should have been in libraries but oops
# Get about 76-78% which isn't too bad considering I chose SVC without any reason (just for the demo)
accuracy_score(y_test, y_pred)