def test_missing_value_generator(self):
types = ('b', 'h', 'l')
df = DataFrame([[0.0]], columns=['float_'])
with tm.ensure_clean() as path:
df.to_stata(path)
valid_range = StataReader(path).VALID_RANGE
expected_values = ['.' + chr(97 + i) for i in range(26)]
expected_values.insert(0, '.')
for t in types:
offset = valid_range[t][1]
for i in range(0, 27):
val = StataMissingValue(offset + 1 + i)
self.assertTrue(val.string == expected_values[i])
# Test extremes for floats
val = StataMissingValue(struct.unpack('<f', b'\x00\x00\x00\x7f')[0])
self.assertTrue(val.string == '.')
val = StataMissingValue(struct.unpack('<f', b'\x00\xd0\x00\x7f')[0])
self.assertTrue(val.string == '.z')
# Test extremes for floats
val = StataMissingValue(
struct.unpack('<d', b'\x00\x00\x00\x00\x00\x00\xe0\x7f')[0])
self.assertTrue(val.string == '.')
val = StataMissingValue(
struct.unpack('<d', b'\x00\x00\x00\x00\x00\x1a\xe0\x7f')[0])
self.assertTrue(val.string == '.z')
def test_missing_value_conversion(self):
columns = ['int8_', 'int16_', 'int32_', 'float32_', 'float64_']
smv = StataMissingValue(101)
keys = [key for key in iterkeys(smv.MISSING_VALUES)]
keys.sort()
data = []
for i in range(27):
row = [StataMissingValue(keys[i + (j * 27)]) for j in range(5)]
data.append(row)
expected = DataFrame(data, columns=columns)
parsed_113 = read_stata(self.dta17_113, convert_missing=True)
parsed_115 = read_stata(self.dta17_115, convert_missing=True)
parsed_117 = read_stata(self.dta17_117, convert_missing=True)
tm.assert_frame_equal(expected, parsed_113)
tm.assert_frame_equal(expected, parsed_115)
tm.assert_frame_equal(expected, parsed_117)
def _unpack(self, fmt, byt):
d = unpack(self._header['byteorder'] + fmt, byt)[0]
if fmt[-1] in self.MISSING_VALUES:
nmin, nmax = self.MISSING_VALUES[fmt[-1]]
if d < nmin or d > nmax:
if self._missing_values:
return StataMissingValue(nmax, d)
else:
return None
return d