A decorator is a callable Python construct placed above a function definition with @. It wraps the function to extend or alter its behavior without changing the function’s source code. This makes a repeated behavior—such as a timeout or profiling hook—portable across functions. section 5.3.4
Limit model-training time
The stopit package provides a timeoutable decorator. Applying @timeoutable() to train_model lets the call supply a timeout alongside the function’s normal arguments: train_model(timeout=180, features=train_features, labels=train_labels). If training does not finish, the function returns None, allowing the code to raise an error. section 5.3.4
Listing 5.14 This listing’s code uses a timeout limit whenever the train_model function is called. Try the code out for yourself in the ch5/stopit_with_decorator.py file.
from stopit import threading_timeoutable as timeoutable #1
from sklearn.ensemble import RandomForestClassifier #1
from ch4.dataset_class_final import DataSet #1
@timeoutable() #2
def train_model(features, labels): #2
forest_model = RandomForestClassifier( #2
n_estimators = 500).\ #2
fit(features, labels) #2
return forest_model #2
customer_obj = DataSet( #3
feature_list = [ #3
"total_day_minutes", #3
"total_day_calls", #3
"number_customer_service_calls"], #3
file_name = "data/customer_churn_data.csv", #3
label_col = "churn", #3
pos_category = "yes" #3
)
forest_model = train_model(timeout = 180, #4
features = train_features, #4
labels = train_labels) #4
# Did code finish running in under
# 180 seconds (3 minutes)?
if forest_model: #5
print("FINISHED TRAINING MODEL...") #5
# Did code timeout?
else: #6
raise AssertionError("""DID NOT FINISH
MODEL TRAINING WITHIN TIME LIMIT""") #6
# [Additional code block...] #7
See the complete decorator example, including imports, a decorated train_model function, model training, and a timeout-enabled call. section 5.3.4
Decorators support practical data-science workflows:
- Add execution time limits to model training or other functions without placing the main code inside a with block. section 5.3.4
- Apply @profile to a function so line-profiler can measure compute time line by line through terminal commands. section 6.1.2








