def test_read_pickles_0_11_0(self):
if not is_little_endian():
raise nose.SkipTest("known failure of test_read_pickles_0_11_0 on non-little endian")
pth = tm.get_data_path('legacy_pickle/0.11.0')
for f in os.listdir(pth):
vf = os.path.join(pth,f)
self.compare(vf)
def read_pickles(self, version):
if not is_little_endian():
raise nose.SkipTest("known failure on non-little endian")
pth = tm.get_data_path('legacy_pickle/{0}'.format(str(version)))
for f in os.listdir(pth):
vf = os.path.join(pth, f)
self.compare(vf)
def read_pickles(self, version):
if not is_little_endian():
raise nose.SkipTest("known failure on non-little endian")
pth = tm.get_data_path('legacy_pickle/{0}'.format(str(version)))
for f in os.listdir(pth):
vf = os.path.join(pth,f)
self.compare(vf)
def test_read_pickles_0_11_0(self):
if not is_little_endian():
raise nose.SkipTest(
"known failure of test_read_pickles_0_11_0 on non-little endian"
)
pth = tm.get_data_path('legacy_pickle/0.11.0')
for f in os.listdir(pth):
vf = os.path.join(pth, f)
self.compare(vf)
def test_write_dta6(self):
if not is_little_endian():
raise nose.SkipTest("known failure of test_write_dta6 on non-little endian")
original = self.read_csv(self.csv3)
original.index.name = 'index'
with ensure_clean(self.dta6) as path:
original.to_stata(path, None, False)
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index('index'), original)
def test_write_dta5(self):
if not is_little_endian():
raise nose.SkipTest("known failure of test_write_dta5 on non-little endian")
original = DataFrame([(np.nan, np.nan, np.nan, np.nan, np.nan)],
columns=['float_miss', 'double_miss', 'byte_miss', 'int_miss', 'long_miss'])
original.index.name = 'index'
with ensure_clean(self.dta5) as path:
original.to_stata(path, None, False)
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index('index'), original)
def test_write_dta6(self):
if not is_little_endian():
raise nose.SkipTest("known failure of test_write_dta6 on "
"non-little endian")
original = self.read_csv(self.csv3)
original.index.name = 'index'
with tm.ensure_clean() as path:
original.to_stata(path, None, False)
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index('index'),
original)
def test_read_write_dta5(self):
if not is_little_endian():
raise nose.SkipTest("known failure of test_write_dta5 on "
"non-little endian")
original = DataFrame([(np.nan, np.nan, np.nan, np.nan, np.nan)],
columns=['float_miss', 'double_miss', 'byte_miss',
'int_miss', 'long_miss'])
original.index.name = 'index'
with tm.ensure_clean() as path:
original.to_stata(path, None, False)
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index('index'),
original)
def read_pickles(self, version):
if not is_little_endian():
raise nose.SkipTest("known failure on non-little endian")
pth = tm.get_data_path('legacy_pickle/{0}'.format(str(version)))
for f in os.listdir(pth):
vf = os.path.join(pth,f)
data = self.compare(vf)
if data is None:
continue
if 'series' in data:
if 'ts' in data['series']:
self._validate_timeseries(data['series']['ts'], self.data['series']['ts'])
def test_read_write_dta10(self):
if not is_little_endian():
raise nose.SkipTest("known failure of test_write_dta10 on "
"non-little endian")
original = DataFrame(data=[["string", "object", 1, 1.1,
np.datetime64('2003-12-25')]],
columns=['string', 'object', 'integer', 'float',
'datetime'])
original["object"] = Series(original["object"], dtype=object)
original.index.name = 'index'
with tm.ensure_clean() as path:
original.to_stata(path, {'datetime': 'tc'}, False)
written_and_read_again = self.read_dta(path)
tm.assert_frame_equal(written_and_read_again.set_index('index'),
original)
def read_pickles(self, version):
if not is_little_endian():
raise nose.SkipTest("known failure on non-little endian")
pth = tm.get_data_path('legacy_pickle/{0}'.format(str(version)))
n = 0
for f in os.listdir(pth):
vf = os.path.join(pth, f)
data = self.compare(vf, version)
if data is None:
continue
if 'series' in data:
if 'ts' in data['series']:
self._validate_timeseries(data['series']['ts'], self.data['series']['ts'])
self._validate_frequency(data['series']['ts'])
if 'index' in data:
if 'period' in data['index']:
self._validate_periodindex(data['index']['period'],
self.data['index']['period'])
n += 1
assert n > 0, 'Pickle files are not tested'
def read_pickles(self, version):
if not is_little_endian():
raise nose.SkipTest("known failure on non-little endian")
pth = tm.get_data_path('legacy_pickle/{0}'.format(str(version)))
n = 0
for f in os.listdir(pth):
vf = os.path.join(pth, f)
data = self.compare(vf)
if data is None:
continue
if 'series' in data:
if 'ts' in data['series']:
self._validate_timeseries(data['series']['ts'],
self.data['series']['ts'])
self._validate_frequency(data['series']['ts'])
if 'index' in data:
if 'period' in data['index']:
self._validate_periodindex(data['index']['period'],
self.data['index']['period'])
n += 1
assert n > 0, 'Pickle files are not tested'
def skip_if_not_little_endian():
if not is_little_endian():
raise nose.SkipTest("known failure of test on non-little endian")
def skip_if_not_little_endian():
if not is_little_endian():
raise nose.SkipTest("known failure of test on non-little endian")
import nose
import sys
from distutils.version import LooseVersion
import numpy as np
import pandas as pd
from pandas.core.frame import DataFrame, Series
from pandas.io.parsers import read_csv
from pandas.io.stata import (read_stata, StataReader, InvalidColumnName,
PossiblePrecisionLoss)
import pandas.util.testing as tm
from pandas.util.misc import is_little_endian
from pandas import compat
if not is_little_endian():
raise nose.SkipTest("known failure of test_stata on non-little endian")
class TestStata(tm.TestCase):
def setUp(self):
# Unit test datasets for dta7 - dta9 (old stata formats 104, 105 and 107) can be downloaded from:
# http://stata-press.com/data/glmext.html
self.dirpath = tm.get_data_path()
self.dta1_114 = os.path.join(self.dirpath, 'stata1_114.dta')
self.dta1_117 = os.path.join(self.dirpath, 'stata1_117.dta')
self.dta2_113 = os.path.join(self.dirpath, 'stata2_113.dta')
self.dta2_114 = os.path.join(self.dirpath, 'stata2_114.dta')
self.dta2_115 = os.path.join(self.dirpath, 'stata2_115.dta')
self.dta2_117 = os.path.join(self.dirpath, 'stata2_117.dta')