def test_write_dta6(self):
original = self.read_csv(self.csv3)
writer = StataWriter(self.dta6, original, None, False)
writer.write_file()
written_and_read_again = self.read_dta(self.dta6)
tm.assert_frame_equal(written_and_read_again, original)
def test_write_dta6(self):
original = self.read_csv(self.csv3)
writer = StataWriter(self.dta6, original, None, False)
writer.write_file()
written_and_read_again = self.read_dta(self.dta6)
tm.assert_frame_equal(written_and_read_again, original)
def test_write_dta6(self):
original = self.read_csv(self.csv3)
with ensure_clean(self.dta6) as path:
writer = StataWriter(path, original, None, False)
writer.write_file()
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again, original)
def test_write_dta5(self):
original = DataFrame([(np.nan, np.nan, np.nan, np.nan, np.nan)],
columns=['float_miss', 'double_miss', 'byte_miss', 'int_miss', 'long_miss'])
writer = StataWriter(self.dta5, original, None, False)
writer.write_file()
written_and_read_again = self.read_dta(self.dta5)
tm.assert_frame_equal(written_and_read_again, original)
def test_write_dta6(self):
original = self.read_csv(self.csv3)
with ensure_clean(self.dta6) as path:
writer = StataWriter(path, original, None, False)
writer.write_file()
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again, original)
def test_write_dta5(self):
original = DataFrame([(np.nan, np.nan, np.nan, np.nan, np.nan)],
columns=[
'float_miss', 'double_miss', 'byte_miss',
'int_miss', 'long_miss'
])
writer = StataWriter(self.dta5, original, None, False)
writer.write_file()
written_and_read_again = self.read_dta(self.dta5)
tm.assert_frame_equal(written_and_read_again, original)
self._count = 0
self._print_progress()
return args
def _print_progress(self):
print('{} progress: {} %'.format(self._name, self._progress),
file=sys.stderr)
_sas_reader = SasReader(_input_file_path,
encoding='latin-1',
chunksize=_chunksize)
_number_of_observations = _sas_reader.row_count
print('Input has {} observations'.format(_number_of_observations),
file=sys.stderr)
_extracted_columns = list(
frozenset(_sas_reader.column_names).intersection(_wanted_columns))
_input_counter = ProgressCounter('input', _number_of_observations)
_input_row_generator = (_input_counter(row) for chunk in _sas_reader
for index, row in chunk)
_output_row_generator = (
row[_extracted_columns]
for row in filter(_is_interesting, _input_row_generator))
_result: pd.DataFrame = pd.DataFrame(_input_row_generator)
StataWriter(_output_file_path, _result, write_index=False,
version=118).write_file()
