class DatabaseTest(unittest.TestCase):
engine = create_engine("sqlite:///python_models.db", echo=True)
meta = MetaData()
def setUp(self):
self.df = pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]),
columns=['a', 'b', 'c'])
self._data = Data("unittest")
self._data.add_test_table('unittest')
def test_csv_to_df(self):
self.df.to_csv('./tests/unittest.csv')
self._data.csv_to_df()
self.assertEqual(type(pd.DataFrame()), type(self._data.df))
def test_csv_to_db(self):
self.assertTrue(self._data.csv_to_db())
def test_fit_model(self):
with self.assertRaises(RegressionException):
self._data.fit_model(1, Data('ideal'), 'real')
self.df = pd.DataFrame(
[[1.5555555, 2.55555555], [4.5555555, 5.5555555]],
columns=['x', 'y1'])
self.df.to_csv('./tests/unittest.csv')
self._data.csv_to_df()
with self.assertRaises(Exception):
self._data.fit_model(1, None, 'linear')
# test print_table arg
with open('./datasets/ideal.csv', 'r') as idf:
ideal = Data('ideal', _create=False)
ideal.csv_to_df()
self.assertFalse(ideal.is_empty(), 'df obj should be populated')
model = self._data.fit_model(1,
ideal,
'linear',
print_table=True,
table_name='./tests/unittest')
self.assertEqual(type(model),
type(Model(self.df['x'], self.df['y1'], 1)))
self.assertEqual(model.x[0], self.df['x'][0])
def tearDown(self):
try:
self._data.drop_test_table()
except AttributeError:
print('table not dropped')
class Interface:
"""
"""
def __init__(self, **kwargs):
"""
:keyword map_train: run Model functions entirely and
plot matched ideal vs test data
:keyword to_db: create SQLite db table for created Data obj
:keyword plt_type: which type of fit algorithm to run, 'linear' or 'best fit'
:keyword with_rmse: include rmse values in graph
:keyword print_table: save stats from model comparisons as a .pdf table
:keyword plot: plot data and save
:keyword plot_training_subplots: display and save training data as subplots
:keyword compare_models: shortcut to just plot comparison of fitted models,
values is dict of fitted model dicts
"""
to_db = kwargs.get('to_db', True)
_create = kwargs.get('create_tables', True)
self.train = Data('training_data', to_db=to_db)
self.ideal = Data('ideal_functions', to_db=to_db)
self.test = Data('test_data')
self.train_master = self.train.csv_to_df()
self.train_graph = Graph("Training Data", df=self.train.csv_to_df())
self.ideal_fn_dict = {'x': self.train.df['x']}
self._n = kwargs.get('_n', {})
self.plt_type = kwargs.get('plt_type', 'best fit')
self.with_rmse = kwargs.get('with_rmse', True)
self.print_table = kwargs.get('print_table', True)
self.plot = kwargs.get('plot', True)
map_train = kwargs.get('map_train', True)
continue_matching = kwargs.get('continue_matching', True)
self.models = dict()
self.models_master_1 = dict()
self.models_master_2 = dict()
self.models_master_3 = dict()
self.result = tuple()
global model
if 'compare_models' in kwargs.keys():
models = kwargs.get('compare_models')
self.train_graph.make_subplots('Model Comparison',
models={
'm1': models['m1'],
'm2': models['m2'],
'm3': models['m3']
})
if 'plot_training_subplots' in kwargs.keys():
self.train_graph.make_subplots(self.train_graph.title)
if continue_matching:
check_n_size(self._n)
idx = 1
while self._n['y1']:
n = {
'y1': self._n['y1'].pop(0),
'y2': self._n['y2'].pop(0),
'y4': self._n['y4'].pop(0)
}
self._fit(n, idx)
idx += 1
self.ideal_fn_df = pd.DataFrame(data=self.ideal_fn_dict)
self.ideal_fn_df = self.ideal_fn_df.set_index('x')
self.test_df = self.test.csv_to_df()
test_model = Model(self.test_df['x'],
self.test_df['y'],
1,
df=self.test_df)
finals = test_model.match_ideal_functions(self.ideal_fn_df,
self.train_master,
self.models,
map_train=map_train)
if 'run_complete' in kwargs.keys():
self.test.df_to_db(finals[0])
else:
self.result = finals
def _fit(self, n, idx):
_m = f'm{idx}'
new_models = dict()
for i in range(1, 5):
col = f'y{i}'
_if, _max, _bf = f'y{i}_if', f'y{i}_max_err', f'y{i}_best_fit'
if i != 3:
model = self.train.fit_model(i,
self.ideal,
'poly.fit',
order=n[col],
print_table=self.print_table)
else:
model = self.train.fit_model(i,
self.ideal,
'linear',
print_table=self.print_table)
new_models[col] = model
self.models[col] = model
self.ideal_fn_dict[model.ideal_col] = model.ideal_col_array
self.train_master[_if] = model.ideal_col
self.train_master[_max] = model.max_dev
self.train_master[_bf] = model
if self.plot:
self.train_graph.plot_model(model,
plt_type=self.plt_type,
with_rmse=self.with_rmse)
if idx == 1:
self.models_master_1[_m] = new_models
if idx == 2:
self.models_master_2[_m] = new_models
if idx == 3:
self.models_master_3[_m] = new_models