def test_regression():
df_boston_train, df_boston_test = utils.get_boston_regression_dataset()
ml_predictor = utils.train_basic_regressor(df_boston_train)
test_score = ml_predictor.score(df_boston_test,
df_boston_test.MEDV,
verbose=0)
# Currently, we expect to get a score of -3.09
# Make sure our score is good, but not unreasonably good
assert -3.2 < test_score < -2.8
def test_getting_single_predictions_regression():
np.random.seed(0)
df_boston_train, df_boston_test = utils.get_boston_regression_dataset()
ml_predictor = utils.train_basic_regressor(df_boston_train)
file_name = ml_predictor.save(str(random.random()))
with open(file_name, 'rb') as read_file:
saved_ml_pipeline = dill.load(read_file)
os.remove(file_name)
df_boston_test_dictionaries = df_boston_test.to_dict('records')
# 1. make sure the accuracy is the same
predictions = []
for row in df_boston_test_dictionaries:
predictions.append(saved_ml_pipeline.predict(row))
first_score = utils.calculate_rmse(df_boston_test.MEDV, predictions)
print('first_score')
print(first_score)
# Make sure our score is good, but not unreasonably good
assert -3.2 < first_score < -2.8
# 2. make sure the speed is reasonable (do it a few extra times)
data_length = len(df_boston_test_dictionaries)
start_time = datetime.datetime.now()
for idx in range(1000):
row_num = idx % data_length
saved_ml_pipeline.predict(df_boston_test_dictionaries[row_num])
end_time = datetime.datetime.now()
duration = end_time - start_time
print('duration.total_seconds()')
print(duration.total_seconds())
# It's very difficult to set a benchmark for speed that will work across all machines.
# On my 2013 bottom of the line 15" MacBook Pro, this runs in about 0.8 seconds for 1000 predictions
# That's about 1 millisecond per prediction
# Assuming we might be running on a test box that's pretty weak, multiply by 3
# Also make sure we're not running unreasonably quickly
assert 0.2 < duration.total_seconds() / 1.0 < 3
# 3. make sure we're not modifying the dictionaries (the score is the same after running a few experiments as it is the first time)
predictions = []
for row in df_boston_test_dictionaries:
predictions.append(saved_ml_pipeline.predict(row))
second_score = utils.calculate_rmse(df_boston_test.MEDV, predictions)
print('second_score')
print(second_score)
# Make sure our score is good, but not unreasonably good
assert -3.2 < second_score < -2.8
def test_saving_trained_pipeline_regression():
df_boston_train, df_boston_test = utils.get_boston_regression_dataset()
ml_predictor = utils.train_basic_regressor(df_boston_train)
file_name = ml_predictor.save()
with open(file_name, 'rb') as read_file:
saved_ml_pipeline = dill.load(read_file)
test_score = saved_ml_pipeline.score(df_boston_test, df_boston_test.MEDV)
# Make sure our score is good, but not unreasonably good
assert -3.2 < test_score < -2.8