def train(self, dataset_path, features=None, target=None, **kwargs):
# Record features & target
self._features = features
self._target = target
# Load CSV file as pandas dataframe
csv_path = dataset_path
data = pd.read_csv(csv_path)
# Extract X & y from dataframe
(X, y) = self._extract_xy(data)
X = self.prepare_X(X)
self._clf.fit(X, y)
# Compute train accuracy
score = self._clf.score(X, y)
logger.log('Train accuracy: {}'.format(score))
def train(self, dataset_path, features=None, target=None, **kwargs):
# Record features & target
self._features = features
self._target = target
# Load CSV file as pandas dataframe
csv_path = dataset_path
data = pd.read_csv(csv_path)
# Extract X & y from dataframe
(X, y) = self._extract_xy(data)
# Encode categorical features
X = self._encoding_categorical_type(X)
self._clf.fit(X, y)
# Compute train root mean square error
preds = self._clf.predict(X)
rmse = np.sqrt(mean_squared_error(y, preds))
logger.log('Train RMSE: {}'.format(rmse))