def main(input_train, input_test, output_train, output_test):
""" Runs data processing scripts to turn raw data from (../raw) into
cleaned data ready to be analyzed (saved in ../processed).
"""
logger = logging.getLogger(__name__)
logger.info('making final data set from raw data')
raw_data = DataSet(input_train, input_test)
df_train = raw_data.get_train_set()
df_test = raw_data.get_test_set()
TitanicPreProcessing(df_train, output_train)
TitanicPreProcessing(df_test, output_test)
def main(input_data, output_model):
""" Runs modeling scripts using processed data (../raw) to
create model. Model is saved as pickle (saved in ../models).
"""
logger = logging.getLogger(__name__)
logger.info('training model')
data = DataSet(train_dir=input_data)
train = data.get_train_set()
X_train = data.get_features(train)
y = data.get_label(train)
clf = models[4]
param_grid = params[4]
model = Model.tune(clf, X_train, y, param_grid)
model.save(output_model + model.name)
def main(input_filepath, output_filepath):
""" Runs data processing scripts to turn raw data from (../raw) into
cleaned data ready to be analyzed (saved in ../processed).
"""
logger = logging.getLogger(__name__)
logger.info('making final data set from raw data')
raw_data = DataSet(train_dir=input_filepath + '/train.csv',
test_dir=input_filepath + '/test.csv')
cleaning = DataWrangling(train_dir=output_filepath + '/train_clean.csv',
test_dir=output_filepath + '/test_clean.csv')
df_train = raw_data.get_train_set()
df_test = raw_data.get_test_set()
df_train_clean = cleaning.apply_preprocessing(df_train, target='Survived')
df_test_clean = cleaning.apply_preprocessing(df_test, target='Survived')
cleaning.processed_train_data(df_train_clean)
cleaning.processed_test_data(df_test_clean)