def test_fit(self, example_dataset):
"""Tests fitting the model."""
X, y = example_dataset
model = TitanicModel()
model.fit(X, y)
assert len(y_pred) > 0
def test_fit(self, example_dataset):
"""Tests fitting the model."""
X, y = example_dataset
model = TitanicModel()
model.fit(X, y)
# pylint: disable=protected-access
assert model._estimator is not None
def test_predict(self, example_dataset):
"""Tests predicting with the model."""
X, y = example_dataset
model = TitanicModel()
model.fit(X, y)
y_pred = model.predict(X)
assert len(y_pred) > 0
def __init__(self):
self._m = TitanicModel()
self._context = './data/'
self._train = self.create_train()
def train(input_path, model_path, n_estimators):
"""Trains a model on the given dataset."""
logger = logging.getLogger(__name__)
logger.info("Loading input dataset")
train_dataset = pd.read_csv(input_path)
X_train = train_dataset.drop(["Survived"], axis=1)
y_train = train_dataset["Survived"]
logger.info(f"Training model with n_estimators = {n_estimators}")
model = TitanicModel(n_estimators=n_estimators)
model.fit(X_train, y=y_train)
logger.info(f"Writing output to {model_path}")
model_dir = Path(model_path).parent
model_dir.mkdir(parents=True, exist_ok=True)
joblib.dump(model, model_path)
def main(input_dir, input_file, model_dir, model_file, n_trees):
# Fetch our dataset.
dataset = pd.read_csv(input_dir / input_file)
X = dataset.drop("Survived", axis=1)
y = dataset["Survived"]
# Train our model.
model = TitanicModel(n_trees=n_trees)
model.fit(X, y=y)
# Save our model output.
model_dir.mkdir(parents=True, exist_ok=True)
model.save(model_dir / model_file)
def __init__(self):
self._m = TitanicModel()
self._context = './data/'
def __init__(self):
self._m = TitanicModel()
print('***********************************')
print(self._m.test_id)
##self._context = './data/'
self._train = self.create_train()
def __init__(self):
self._m = TitanicModel()
self._context = '/Temp/'
