def setUp(self):
self.y_features = ['classification', 'regression']
self.classification_model_types = [
'support_vector_machine_model_classifier',
'logistic_regression_model_classifier',
'decision_tree_model_classifier', 'random_forest_model_classifier',
'extra_trees_model_classifier', 'adaboost_model_classifier',
'nn_model_classifier'
]
self.regression_model_types = [
'linear_model_regressor', 'linear_model_lasso_regressor',
'support_vector_machine_model_regressor', 'lkrr_model_regressor',
'gkrr_model_regressor', 'decision_tree_model_regressor',
'extra_trees_model_regressor', 'randomforest_model_regressor',
'adaboost_model_regressor', 'nn_model_regressor'
]
self.configfile = 'test_unittest_featuregeneration.conf'
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1featureselection.csv')
del self.df1['Material compositions']
self.configdict = ConfigFileParser(
configfile='test_unittest_featuregeneration.conf').get_config_dict(
path_to_file=testdir)
self.target_feature = "O_pband_center_regression"
self.x_features = [
f for f in self.df1.columns.values.tolist()
if f != self.target_feature
]
return
def setUp(self):
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1.csv')
self.configdict = ConfigFileParser(
configfile='test_unittest_featuregeneration.conf').get_config_dict(
path_to_file=testdir)
self.files = list()
return
def setUp(self):
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1string.csv')
self.configdict = ConfigFileParser(
configfile='test_unittest_featuregeneration.conf').get_config_dict(
path_to_file=testdir)
self.target_feature = "O_pband_center_regression"
self.x_features = [f for f in self.df1.columns.values.tolist()]
return
def setUp(self):
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1matproj.csv')
self.configdict = ConfigFileParser(
configfile='test_unittest_featuregeneration.conf').get_config_dict(
path_to_file=testdir)
self.files = list()
self.api_key = self.configdict['Feature Generation']['citrine_apikey']
return
def test_plot_dataframe_histogram(self):
configdict = ConfigFileParser(
configfile='test_unittest_dataoperations.conf').get_config_dict(
path_to_file=testdir)
fname = DataframeUtilities().plot_dataframe_histogram(
dataframe=self.df1,
configdict=configdict,
y_feature="O_pband_center_regression")
self.files.append(fname)
return
def setUp(self):
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1.csv')
self.df2 = pd.read_csv(testdir + '/' + 'testcsv2.csv')
self.arr1 = np.array(self.df1)
self.arr2 = np.array(self.df2)
self.configfile = 'test_unittest_dataoperations.conf'
self.configdict = ConfigFileParser(
configfile=self.configfile).get_config_dict(path_to_file=testdir)
self.files = list()
return
def setUp(self):
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1.csv')
del self.df1['Material compositions']
self.configdict = ConfigFileParser(
configfile='test_unittest_featuregeneration.conf').get_config_dict(
path_to_file=testdir)
self.target_feature = "O_pband_center_regression"
self.x_features = [f for f in self.df1.columns.values.tolist()]
self.x_features.remove('O_pband_center_regression')
self.files = list()
return
def setUp(self):
self.df1constant = pd.read_csv(testdir + '/' + 'testcsv1constant.csv')
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1.csv')
del self.df1constant[
'Material compositions'] # Need to remove string entries before doing feature selection
del self.df1['Material compositions']
self.configdict = ConfigFileParser(
configfile='test_unittest_featuregeneration.conf').get_config_dict(
path_to_file=testdir)
self.target_feature = "O_pband_center_regression"
self.x_features = [
f for f in self.df1.columns.values.tolist()
if f != self.target_feature
]
return
def setUp(self):
self.df1 = pd.read_csv(testdir + '/' + 'testcsv1featureselection.csv')
del self.df1['Material compositions']
self.configdict = ConfigFileParser(
configfile='test_unittest_featuregeneration.conf').get_config_dict(
path_to_file=testdir)
self.target_feature = "O_pband_center_regression"
self.x_features = [
f for f in self.df1.columns.values.tolist()
if f != self.target_feature
]
self.model_type = 'gkrr_model_regressor'
self.files = list()
# Need to normalize features for feature selection
self.df1, scaler = FeatureNormalization(
dataframe=self.df1, configdict=self.configdict).normalize_features(
x_features=self.x_features,
y_feature=self.target_feature,
normalize_x_features=True,
normalize_y_feature=False,
to_csv=False)
return
def test_get_config_dict(self):
configdict = ConfigFileParser(
configfile=self.configfile).get_config_dict(path_to_file=testdir)
self.assertIsInstance(configdict, configobj.ConfigObj)
return