def test_create_sparams_file(self, caplog):
clust = wrapper.Input()
name = os.path.join(here, dir_data, "sample-real-location.tsv")
clust.add_input_data(name, "real location")
clust.prepare_input_data()
clust.create_sparams_file()
assert os.path.isfile("autoclass.s-params")
def test_create_sparams_file_repro_run(self, caplog):
clust = wrapper.Input()
name = os.path.join(here, dir_data, "sample-real-location.tsv")
clust.add_input_data(name, "real location")
clust.prepare_input_data()
clust.create_sparams_file(reproducible_run=True)
assert os.path.isfile("autoclass.s-params")
f_content = open("autoclass.s-params", "r").read()
assert "randomize_random_p = false" in f_content
assert 'start_fn_type = "block"' in f_content
def test_create_hd2_file(self, caplog):
clust = wrapper.Input()
name1 = os.path.join(here, dir_data, "sample-real-location.tsv")
clust.add_input_data(name1, "real location")
name2 = os.path.join(here, dir_data, "sample-discrete.tsv")
clust.add_input_data(name2, "discrete")
name3 = os.path.join(here, dir_data, "sample-real-scalar.tsv")
clust.add_input_data(name3, "real scalar")
clust.prepare_input_data()
clust.create_hd2_file()
assert os.path.isfile("autoclass.hd2")
def test_prepare_input_data(self, caplog):
clust = wrapper.Input()
name1 = os.path.join(here, dir_data, "sample-real-location.tsv")
clust.add_input_data(name1, "real location")
name2 = os.path.join(here, dir_data, "sample-discrete.tsv")
clust.add_input_data(name2, "discrete")
name3 = os.path.join(here, dir_data, "sample-real-scalar.tsv")
clust.add_input_data(name3, "real scalar")
clust.prepare_input_data()
print(caplog.text)
assert "Final dataframe has 10 lines and 8 columns" in caplog.text
def test_create_rparams_file(self):
filename = "autoclass.r-params"
clust = wrapper.Input()
clust.create_rparams_file()
assert os.path.isfile(filename)
content_ref = ""
filename_ref = os.path.join(here, "test_data", filename)
with open(filename_ref, "r") as f:
content_ref = f.read()
content = ""
with open(filename, "r") as f:
content = f.read()
assert content == content_ref
def test_print_files(self):
clust = wrapper.Input()
name = os.path.join(here, dir_data, "sample-real-location.tsv")
clust.add_input_data(name, "real location")
clust.prepare_input_data()
clust.create_hd2_file()
clust.create_model_file()
clust.create_sparams_file()
clust.create_rparams_file()
content = clust.print_files()
assert "autoclass.hd2" in content
assert "autoclass.model" in content
assert "autoclass.s-params" in content
assert "autoclass.r-params" in content
def test_init(self, tmp_dir):
clust = wrapper.Input()
assert clust.root_name == "autoclass"
assert clust.db2_missing_char == "?"
assert clust.db2_separator_char == "\t"
assert clust.tolerate_error == False
def test_add_input_data_dup_col_names(self, caplog):
clust = wrapper.Input()
name = os.path.join(here, dir_data, "input-dup-col.tsv")
clust.add_input_data(name, "real location")
assert "Found duplicate column names" in caplog.text
def test_add_input_data(self):
clust = wrapper.Input()
name = os.path.join(here, dir_data, "sample-real-location.tsv")
clust.add_input_data(name)