def test_io(doc = DOC_1):
p = docstring_to_file(doc, "test_yaml_doc.txt")
assert doc == "\n".join([x[0] for x in yield_csv_rows(p)])
y = get_yaml(p)
assert y[0][0] == 'Something looking like a yaml'
assert y[1]["key1"] == 'with two documents'
delete_file(p)
def test_raw_data_import_from_csv_file(self):
csvpath = self.csvfile()
raw_rows = list(yield_csv_rows(csv_filename=csvpath))
for i_raw_rows, j_investment_doc in zip(
raw_rows, self.doc_as_iterable(self.INVESTMENT_DOC)):
self.assertEqual(i_raw_rows, j_investment_doc)
os.remove(csvpath)
def test_io(doc=DOC_1):
p = docstring_to_file(doc, "test_yaml_doc.txt")
assert doc == "\n".join([x[0] for x in yield_csv_rows(p)])
y = get_yaml(p)
assert y[0][0] == 'Something looking like a yaml'
assert y[1]["key1"] == 'with two documents'
delete_file(p)
def test_raw_data_import_from_csv_file():
csvpath = csvfile()
raw_rows = list(yield_csv_rows(csv_filename=csvpath))
for i_raw_rows, j_investment_doc in zip(raw_rows,
doc_as_iterable(INVESTMENT_DOC)):
assert i_raw_rows == j_investment_doc
os.remove(csvpath)
def test_raw_data_import_from_csv_file():
csvpath = csvfile()
raw_rows = list(yield_csv_rows(csv_filename=csvpath))
for i_raw_rows, j_investment_doc in zip(raw_rows, doc_as_iterable(INVESTMENT_DOC)):
assert i_raw_rows == j_investment_doc
os.remove(csvpath)
def emit_raw_non_data_rows(raw_data_file):
for row in yield_csv_rows(raw_data_file):
if not is_year(row[0]):
yield row
def get_labelled_rows_by_segment(raw_data_file, yaml_spec_file, yaml_cfg_file):
raw_rows = list(yield_csv_rows(raw_data_file))
default_dicts = load_spec(yaml_spec_file)
segment_specs = load_cfg(yaml_cfg_file)
return label_raw_rows_by_segment(raw_rows, default_dicts, segment_specs)
def get_labelled_rows_no_segments(raw_data_file, yaml_spec_file):
raw_rows = yield_csv_rows(raw_data_file)
spec_dicts = load_spec(yaml_spec_file)
return raw_to_labelled_rows(raw_rows, spec_dicts)
def test_io(self):
p = docstring_to_file(self.DOC_1, "test_yaml_doc.txt")
self.assertEqual(self.DOC_1, "\n".join([x[0] for x in yield_csv_rows(p)]))
y = get_yaml(p)
self.assertEqual(y[0][0], 'Something looking like a yaml')
self.assertEqual(y[1]["key1"], 'with two documents')
def emit_raw_non_data_rows(raw_data_file):
for row in yield_csv_rows(raw_data_file):
if not is_year(row[0]):
yield row
def get_labelled_rows_by_segment(raw_data_file, yaml_spec_file, yaml_cfg_file):
raw_rows = list(yield_csv_rows(raw_data_file))
default_dicts = load_spec(yaml_spec_file)
segment_specs = load_cfg(yaml_cfg_file)
return label_raw_rows_by_segment(raw_rows, default_dicts, segment_specs)
def get_labelled_rows_no_segments(raw_data_file, yaml_spec_file):
raw_rows = yield_csv_rows(raw_data_file)
spec_dicts = load_spec(yaml_spec_file)
return raw_to_labelled_rows(raw_rows, spec_dicts)
def test_raw_data_import_from_csv_file(self):
csvpath = self.csvfile()
raw_rows = list(yield_csv_rows(csv_filename=csvpath))
for i_raw_rows, j_investment_doc in zip(raw_rows, self.doc_as_iterable(self.INVESTMENT_DOC)):
self.assertEqual(i_raw_rows, j_investment_doc)
os.remove(csvpath)