def test_equals(self):
"""Test the DataManager.equals() and __eq__() methods"""
df1 = create_random_dataframe()
dm1 = DataManager(df1)
dm2 = DataManager(df1)
self.assertTrue(dm1.equals(dm2))
self.assertTrue(dm1 == dm2)
df3 = create_random_dataframe()
dm3 = DataManager(df3)
self.assertFalse(dm1.equals(dm3))
self.assertFalse(dm1 == dm3)
self.assertTrue(dm1 != dm3)
def test_deepcopy(self):
"""Test the deepcopy functionality of instances of the DataManager class"""
df = create_random_dataframe()
dm1 = DataManager(df)
dm2 = copy.deepcopy(dm1)
self.assertTrue(dm1.equals(dm2))
self.assertIsNot(dm1, dm2)
def test_get_data(self):
"""A simple test case of the DataManager.get_data method"""
# create a DataManager from a DataFrame with random data
data_df = create_random_dataframe()
data_manager = DataManager(data_df)
# get data from the DataManager
results_df = data_manager.get_data()
# test if the data manager returns a copy of the DataFrame
pd.testing.assert_frame_equal(data_manager.get_data(), data_df)
self.assertIsNot(results_df, data_df)
def test_to_hdf_path(self):
"""Test the DataManager.to_hdf() and DataManager.read_hdf() methods when saving with a file path"""
key = '/dm'
data = create_random_dataframe()
data_origin = DataManager.create_data_origin(data, 'test')
dm1 = DataManager(data, data_origin)
dm1.to_hdf(self.temp_hdf_path, key)
dm2 = DataManager.read_hdf(self.temp_hdf_path, key)
self.assertTrue(dm1.equals(dm2))
def test_add_data_manager_simple(self):
"""Test a simple case of DataManager.add_data_manager() usage"""
# create a data manager with random data
df = create_random_dataframe(number_of_rows=50)
dm = DataManager(df)
# split the data up and add the results together
dm1 = DataManager(df.iloc[:25])
dm2 = DataManager(df.iloc[25:])
dm_add_result = dm1.add_data_manager(dm2)
# test that the original data set and the add result are equal
self.assertTrue(dm.equals(dm_add_result))
def test_init_without_origin(self):
"""Test the initialization method of DataManager with no origin DataFrame"""
data_df = create_random_dataframe()
variable_names = data_df.keys()
origin_data = [[var, np.nan] for var in variable_names]
nan_origin_df = pd.DataFrame(data=origin_data, columns=['variable', 'origin'])
data_manager_without_origin = DataManager(data_df)
# test that data is being stored correctly
pd.testing.assert_frame_equal(data_manager_without_origin.get_data(), data_df)
pd.testing.assert_frame_equal(data_manager_without_origin.get_origin(), nan_origin_df)
# test that DataFrames aren't the same instance
self.assertFalse(data_manager_without_origin.get_data() is data_df)
self.assertFalse(data_manager_without_origin.get_origin() is nan_origin_df)
def test_to_hdf_buf(self):
"""Test the DataManager.to_hdf() and DataManager.read_hdf() methods when saving with a pd.HDFStore instance"""
key = '/dm/'
data = create_random_dataframe()
data_origin = DataManager.create_data_origin(data, 'test')
dm1 = DataManager(data, data_origin)
with pd.HDFStore(self.temp_hdf_path) as store:
dm1.to_hdf(store, key)
with pd.HDFStore(self.temp_hdf_path) as store:
dm2 = DataManager.read_hdf(store, key)
self.assertTrue(dm1.equals(dm2))