def test_pickle():
import tempfile
from numpy.testing import assert_equal
tmpdir = tempfile.mkdtemp(prefix='pickle')
a = lrange(10)
save_pickle(a, tmpdir+'/res.pkl')
b = load_pickle(tmpdir+'/res.pkl')
assert_equal(a, b)
#cleanup, tested on Windows
try:
import os
os.remove(tmpdir+'/res.pkl')
os.rmdir(tmpdir)
except (OSError, IOError):
pass
assert not os.path.exists(tmpdir)
#test with file handle
fh = BytesIO()
save_pickle(a, fh)
fh.seek(0,0)
c = load_pickle(fh)
fh.close()
assert_equal(a,b)
def test_pickle_wrapper(self):
fh = BytesIO() # use cPickle with binary content
# test unwrapped results load save pickle
self.results._results.save(fh)
fh.seek(0, 0)
res_unpickled = self.results._results.__class__.load(fh)
assert_(type(res_unpickled) is type(self.results._results))
# test wrapped results load save
fh.seek(0, 0)
self.results.save(fh)
fh.seek(0, 0)
res_unpickled = self.results.__class__.load(fh)
fh.close()
# print type(res_unpickled)
assert_(type(res_unpickled) is type(self.results))
before = sorted(iterkeys(self.results.__dict__))
after = sorted(iterkeys(res_unpickled.__dict__))
assert_(before == after, msg='not equal %r and %r' % (before, after))
before = sorted(iterkeys(self.results._results.__dict__))
after = sorted(iterkeys(res_unpickled._results.__dict__))
assert_(before == after, msg='not equal %r and %r' % (before, after))
before = sorted(iterkeys(self.results.model.__dict__))
after = sorted(iterkeys(res_unpickled.model.__dict__))
assert_(before == after, msg='not equal %r and %r' % (before, after))
before = sorted(iterkeys(self.results._cache))
after = sorted(iterkeys(res_unpickled._cache))
assert_(before == after, msg='not equal %r and %r' % (before, after))
def test_plot_acf_kwargs():
# Just test that it runs.
fig = plt.figure()
ax = fig.add_subplot(111)
ar = np.r_[1., -0.9]
ma = np.r_[1., 0.9]
armaprocess = tsp.ArmaProcess(ar, ma)
rs = np.random.RandomState(1234)
acf = armaprocess.generate_sample(100, distrvs=rs.standard_normal)
buff = BytesIO()
plot_acf(acf, ax=ax)
fig.savefig(buff, format='rgba')
plt.close(fig)
buff_with_vlines = BytesIO()
fig_with_vlines = plt.figure()
ax = fig_with_vlines.add_subplot(111)
vlines_kwargs = {'linestyles': 'dashdot'}
plot_acf(acf, ax=ax, vlines_kwargs=vlines_kwargs)
fig_with_vlines.savefig(buff_with_vlines, format='rgba')
plt.close(fig_with_vlines)
buff.seek(0)
buff_with_vlines.seek(0)
plain = buff.read()
with_vlines = buff_with_vlines.read()
assert_(with_vlines != plain)
def test_stata_writer_pandas():
buf = BytesIO()
dta = macrodata.load_pandas().data
dta4 = dta.copy()
for col in ('year','quarter'):
dta[col] = dta[col].astype(np.int64)
dta4[col] = dta4[col].astype(np.int32)
# dta is int64 'i8' given to Stata writer
with pytest.warns(FutureWarning):
writer = StataWriter(buf, dta)
with warnings.catch_warnings(record=True) as w:
writer.write_file()
assert len(w) == 0
buf.seek(0)
with pytest.warns(FutureWarning):
dta2 = genfromdta(buf)
dta5 = DataFrame.from_records(dta2)
# dta2 is int32 'i4' returned from Stata reader
if dta5.dtypes[1] is np.dtype('int64'):
ptesting.assert_frame_equal(dta.reset_index(), dta5)
else:
# don't check index because it has different size, int32 versus int64
ptesting.assert_frame_equal(dta4, dta5[dta5.columns[1:]])
def test_pickle(self):
fh = BytesIO()
#test wrapped results load save pickle
self.res.save(fh)
fh.seek(0,0)
res_unpickled = self.res.__class__.load(fh)
assert_(type(res_unpickled) is type(self.res))
def test_pickle(self):
from statsmodels.compat.python import BytesIO
fh = BytesIO()
#test wrapped results load save pickle
self.res1.save(fh)
fh.seek(0,0)
res_unpickled = self.res1.__class__.load(fh)
assert_(type(res_unpickled) is type(self.res1))
def test_pickle(self):
from statsmodels.compat.python import BytesIO
fh = BytesIO()
#test wrapped results load save pickle
self.res1.save(fh)
fh.seek(0, 0)
res_unpickled = self.res1.__class__.load(fh)
assert type(res_unpickled) is type(self.res1) # noqa: E721
def test_pickle(self):
fh = BytesIO()
#test wrapped results load save pickle
del self.res.model.data.orig_endog
self.res.save(fh)
fh.seek(0, 0)
res_unpickled = self.res.__class__.load(fh)
assert type(res_unpickled) is type(self.res) # noqa: E721
def test_pickle(self):
fh = BytesIO()
#test wrapped results load save pickle
del self.res.model.data.orig_endog
self.res.save(fh)
fh.seek(0,0)
res_unpickled = self.res.__class__.load(fh)
assert type(res_unpickled) is type(self.res) # noqa: E721
def test_pickle_wrapper(self):
fh = BytesIO() # use cPickle with binary content
# test unwrapped results load save pickle
self.results._results.save(fh)
fh.seek(0, 0)
res_unpickled = self.results._results.__class__.load(fh)
assert_(type(res_unpickled) is type(self.results._results))
# test wrapped results load save
fh.seek(0, 0)
self.results.save(fh)
fh.seek(0, 0)
res_unpickled = self.results.__class__.load(fh)
fh.close()
# print type(res_unpickled)
assert_(type(res_unpickled) is type(self.results))
before = sorted(iterkeys(self.results.__dict__))
after = sorted(iterkeys(res_unpickled.__dict__))
assert_(before == after, msg='not equal %r and %r' % (before, after))
before = sorted(iterkeys(self.results._results.__dict__))
after = sorted(iterkeys(res_unpickled._results.__dict__))
assert_(before == after, msg='not equal %r and %r' % (before, after))
before = sorted(iterkeys(self.results.model.__dict__))
after = sorted(iterkeys(res_unpickled.model.__dict__))
assert_(before == after, msg='not equal %r and %r' % (before, after))
before = sorted(iterkeys(self.results._cache))
after = sorted(iterkeys(res_unpickled._cache))
assert_(before == after, msg='not equal %r and %r' % (before, after))
def test_stata_writer_structured():
buf = BytesIO()
dta = macrodata.load().data
dtype = dta.dtype
dta = dta.astype(np.dtype([('year', int),
('quarter', int)] + dtype.descr[2:]))
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
assert_array_equal(dta, dta2)
def test_stata_writer_array():
buf = BytesIO()
dta = macrodata.load(as_pandas=False).data
dta = DataFrame.from_records(dta)
dta.columns = ["v%d" % i for i in range(1,15)]
writer = StataWriter(buf, dta.values)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
dta = dta.to_records(index=False)
assert_array_equal(dta, dta2)
def test_stata_writer_array():
buf = BytesIO()
dta = macrodata.load().data
dta = DataFrame.from_records(dta)
dta.columns = ["v%d" % i for i in range(1, 15)]
writer = StataWriter(buf, dta.values)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
dta = dta.to_records(index=False)
assert_array_equal(dta, dta2)
def test_stata_writer_structured():
buf = BytesIO()
dta = macrodata.load().data
dtype = dta.dtype
dta = dta.astype(
np.dtype([('year', int), ('quarter', int)] + dtype.descr[2:]))
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
assert_array_equal(dta, dta2)
def test_stata_writer_structured():
buf = BytesIO()
dta = macrodata.load(as_pandas=False).data
dtype = dta.dtype
dt = [('year', int), ('quarter', int)] + dtype.descr[2:]
if not PY3: # Remove unicode
dt = [(name.encode('ascii'), typ) for name, typ in dt]
dta = dta.astype(np.dtype(dt))
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
assert_array_equal(dta, dta2)
def test_stata_writer_structured():
buf = BytesIO()
dta = macrodata.load(as_pandas=False).data
dtype = dta.dtype
dt = [('year', int), ('quarter', int)] + dtype.descr[2:]
if not PY3: # Remove unicode
dt = [(name.encode('ascii'), typ) for name, typ in dt]
dta = dta.astype(np.dtype(dt))
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
assert_array_equal(dta, dta2)
def test_datetime_roundtrip():
dta = np.array([(1, datetime(2010, 1, 1), 2),
(2, datetime(2010, 2, 1), 3),
(4, datetime(2010, 3, 1), 5)],
dtype=[('var1', float), ('var2', object), ('var3', float)])
buf = BytesIO()
with pytest.warns(FutureWarning):
writer = StataWriter(buf, dta, {"var2" : "tm"})
writer.write_file()
buf.seek(0)
with pytest.warns(FutureWarning):
dta2 = genfromdta(buf)
assert_equal(dta, dta2)
dta = DataFrame.from_records(dta)
buf = BytesIO()
with pytest.warns(FutureWarning):
writer = StataWriter(buf, dta, {"var2" : "tm"})
writer.write_file()
buf.seek(0)
with pytest.warns(FutureWarning):
dta2 = genfromdta(buf, pandas=True)
ptesting.assert_frame_equal(dta, dta2.drop('index', axis=1))
def test_plot_acf_kwargs():
# Just test that it runs.
fig = plt.figure()
ax = fig.add_subplot(111)
ar = np.r_[1., -0.9]
ma = np.r_[1., 0.9]
armaprocess = tsp.ArmaProcess(ar, ma)
rs = np.random.RandomState(1234)
acf = armaprocess.generate_sample(100, distrvs=rs.standard_normal)
buff = BytesIO()
plot_acf(acf, ax=ax)
fig.savefig(buff, format='rgba')
plt.close(fig)
buff_with_vlines = BytesIO()
fig_with_vlines = plt.figure()
ax = fig_with_vlines.add_subplot(111)
vlines_kwargs = {'linestyles': 'dashdot'}
plot_acf(acf, ax=ax, vlines_kwargs=vlines_kwargs)
fig_with_vlines.savefig(buff_with_vlines, format='rgba')
plt.close(fig_with_vlines)
buff.seek(0)
buff_with_vlines.seek(0)
plain = buff.read()
with_vlines = buff_with_vlines.read()
assert_(with_vlines != plain)
def test_missing_roundtrip():
buf = BytesIO()
dta = np.array([(np.nan, np.inf, "")],
dtype=[("double_miss", float), ("float_miss", np.float32),
("string_miss", "a1")])
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta = genfromdta(buf, missing_flt=np.nan)
assert_(isnull(dta[0][0]))
assert_(isnull(dta[0][1]))
assert_(dta[0][2] == asbytes(""))
dta = genfromdta(os.path.join(curdir, "results/data_missing.dta"),
missing_flt=-999)
assert_(np.all([dta[0][i] == -999 for i in range(5)]))
def test_missing_roundtrip():
buf = BytesIO()
dta = np.array([(np.nan, np.inf, "")],
dtype=[("double_miss", float), ("float_miss", np.float32),
("string_miss", "a1")])
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta = genfromdta(buf, missing_flt=np.nan)
assert_(isnull(dta[0][0]))
assert_(isnull(dta[0][1]))
assert_(dta[0][2] == asbytes(""))
dta = genfromdta(os.path.join(curdir, "results/data_missing.dta"),
missing_flt=-999)
assert_(np.all([dta[0][i] == -999 for i in range(5)]))
def test_stata_writer_structured():
buf = BytesIO()
dta = macrodata.load(as_pandas=False).data
dtype = dta.dtype
dt = [('year', int), ('quarter', int)] + dtype.descr[2:]
dta = dta.astype(np.dtype(dt))
with pytest.warns(FutureWarning):
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
with pytest.warns(FutureWarning):
dta2 = genfromdta(buf)
assert_array_equal(dta, dta2)
def check_pickle(obj):
fh = BytesIO()
cPickle.dump(obj, fh, protocol=cPickle.HIGHEST_PROTOCOL)
plen = fh.tell()
fh.seek(0, 0)
res = cPickle.load(fh)
fh.close()
return res, plen
def test_pickle():
import tempfile
from numpy.testing import assert_equal
tmpdir = tempfile.mkdtemp(prefix='pickle')
a = lrange(10)
save_pickle(a, tmpdir + '/res.pkl')
b = load_pickle(tmpdir + '/res.pkl')
assert_equal(a, b)
#cleanup, tested on Windows
try:
import os
os.remove(tmpdir + '/res.pkl')
os.rmdir(tmpdir)
except (OSError, IOError):
pass
assert not os.path.exists(tmpdir)
#test with file handle
fh = BytesIO()
save_pickle(a, fh)
fh.seek(0, 0)
c = load_pickle(fh)
fh.close()
assert_equal(a, b)
def check_pickle(obj):
fh = BytesIO()
cPickle.dump(obj, fh, protocol=cPickle.HIGHEST_PROTOCOL)
plen = fh.tell()
fh.seek(0, 0)
res = cPickle.load(fh)
fh.close()
return res, plen
def webuse(data, baseurl='http://www.stata-press.com/data/r11/', as_df=True):
"""
Download and return an example dataset from Stata.
Parameters
----------
data : str
Name of dataset to fetch.
baseurl : str
The base URL to the stata datasets.
as_df : bool
If True, returns a `pandas.DataFrame`
Returns
-------
dta : Record Array
A record array containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
# lazy imports
from statsmodels.iolib import genfromdta
url = urljoin(baseurl, data + '.dta')
dta = urlopen(url)
dta = BytesIO(dta.read()) # make it truly file-like
if as_df: # could make this faster if we don't process dta twice?
return DataFrame.from_records(genfromdta(dta))
else:
return genfromdta(dta)
def webuse(data, baseurl='http://www.stata-press.com/data/r11/', as_df=True):
"""
Download and return an example dataset from Stata.
Parameters
----------
data : str
Name of dataset to fetch.
baseurl : str
The base URL to the stata datasets.
as_df : bool
If True, returns a `pandas.DataFrame`
Returns
-------
dta : Record Array
A record array containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
# lazy imports
from statsmodels.iolib import genfromdta
url = urljoin(baseurl, data+'.dta')
dta = urlopen(url)
dta = BytesIO(dta.read()) # make it truly file-like
if as_df: # could make this faster if we don't process dta twice?
return DataFrame.from_records(genfromdta(dta))
else:
return genfromdta(dta)
def test_stata_writer_pandas():
buf = BytesIO()
dta = macrodata.load().data
dtype = dta.dtype
#as of 0.9.0 pandas only supports i8 and f8
dta = dta.astype(np.dtype([('year', 'i8'),
('quarter', 'i8')] + dtype.descr[2:]))
dta4 = dta.astype(np.dtype([('year', 'i4'),
('quarter', 'i4')] + dtype.descr[2:]))
dta = DataFrame.from_records(dta)
dta4 = DataFrame.from_records(dta4)
# dta is int64 'i8' given to Stata writer
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
dta5 = DataFrame.from_records(dta2)
# dta2 is int32 'i4' returned from Stata reader
if dta5.dtypes[1] is np.dtype('int64'):
ptesting.assert_frame_equal(dta.reset_index(), dta5)
else:
# don't check index because it has different size, int32 versus int64
ptesting.assert_frame_equal(dta4, dta5[dta5.columns[1:]])
def test_stata_writer_pandas():
buf = BytesIO()
dta = macrodata.load().data
dtype = dta.dtype
#as of 0.9.0 pandas only supports i8 and f8
dta = dta.astype(
np.dtype([('year', 'i8'), ('quarter', 'i8')] + dtype.descr[2:]))
dta4 = dta.astype(
np.dtype([('year', 'i4'), ('quarter', 'i4')] + dtype.descr[2:]))
dta = DataFrame.from_records(dta)
dta4 = DataFrame.from_records(dta4)
# dta is int64 'i8' given to Stata writer
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
dta5 = DataFrame.from_records(dta2)
# dta2 is int32 'i4' returned from Stata reader
if dta5.dtypes[1] is np.dtype('int64'):
ptesting.assert_frame_equal(dta.reset_index(), dta5)
else:
# don't check index because it has different size, int32 versus int64
ptesting.assert_frame_equal(dta4, dta5[dta5.columns[1:]])
cyl_labels = np.array(['USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'France',
'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'Japan', 'USA', 'USA', 'USA', 'Japan',
'Germany', 'France', 'Germany', 'Sweden', 'Germany', 'USA', 'USA', 'USA', 'USA', 'USA', 'Germany',
'USA', 'USA', 'France', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'Germany',
'Japan', 'USA', 'USA', 'USA', 'USA', 'Germany', 'Japan', 'Japan', 'USA', 'Sweden', 'USA', 'France',
'Japan', 'Germany', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA',
'Germany', 'Japan', 'Japan', 'USA', 'USA', 'Japan', 'Japan', 'Japan', 'Japan', 'Japan', 'Japan', 'USA',
'USA', 'USA', 'USA', 'Japan', 'USA', 'USA', 'USA', 'Germany', 'USA', 'USA', 'USA'])
#accommodate recfromtxt for python 3.2, requires bytes
ss = asbytes(ss)
ss2 = asbytes(ss2)
ss3 = asbytes(ss3)
ss5 = asbytes(ss5)
dta = np.recfromtxt(BytesIO(ss), names=("Rust","Brand","Replication"))
dta2 = np.recfromtxt(BytesIO(ss2), names = ("idx", "Treatment", "StressReduction"))
dta3 = np.recfromtxt(BytesIO(ss3), names = ("Brand", "Relief"))
dta5 = np.recfromtxt(BytesIO(ss5), names = ('pair', 'mean', 'lower', 'upper', 'sig'), delimiter='\t')
sas_ = dta5[[1,3,2]]
from statsmodels.stats.multicomp import (tukeyhsd, pairwise_tukeyhsd,
MultiComparison)
#import statsmodels.sandbox.stats.multicomp as multi
#print tukeyhsd(dta['Brand'], dta['Rust'])
def get_thsd(mci, alpha=0.05):
var_ = np.var(mci.groupstats.groupdemean(), ddof=len(mci.groupsunique))
means = mci.groupstats.groupmean
nobs = mci.groupstats.groupnobs
resi = tukeyhsd(means, nobs, var_, df=None, alpha=alpha,
'USA', 'France', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA',
'USA', 'USA', 'Germany', 'Japan', 'USA', 'USA', 'USA', 'USA', 'Germany',
'Japan', 'Japan', 'USA', 'Sweden', 'USA', 'France', 'Japan', 'Germany',
'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA',
'USA', 'USA', 'Germany', 'Japan', 'Japan', 'USA', 'USA', 'Japan', 'Japan',
'Japan', 'Japan', 'Japan', 'Japan', 'USA', 'USA', 'USA', 'USA', 'Japan',
'USA', 'USA', 'USA', 'Germany', 'USA', 'USA', 'USA'
])
#accommodate recfromtxt for python 3.2, requires bytes
ss = asbytes(ss)
ss2 = asbytes(ss2)
ss3 = asbytes(ss3)
ss5 = asbytes(ss5)
dta = pd.read_csv(BytesIO(ss), sep=r'\s+', header=None, engine='python')
dta.columns = "Rust", "Brand", "Replication"
dta2 = pd.read_csv(BytesIO(ss2), sep=r'\s+', header=None, engine='python')
dta2.columns = "idx", "Treatment", "StressReduction"
dta2["Treatment"] = dta2["Treatment"].map(lambda v: v.encode('utf-8'))
dta3 = pd.read_csv(BytesIO(ss3), sep=r'\s+', header=None, engine='python')
dta3.columns = ["Brand", "Relief"]
dta5 = pd.read_csv(BytesIO(ss5), sep=r'\t', header=None, engine='python')
dta5.columns = ['pair', 'mean', 'lower', 'upper', 'sig']
for col in ('pair', 'sig'):
dta5[col] = dta5[col].map(lambda v: v.encode('utf-8'))
sas_ = dta5.iloc[[1, 3, 2]]
from statsmodels.stats.multicomp import (tukeyhsd, pairwise_tukeyhsd,
MultiComparison)
'USA', 'France', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA',
'USA', 'USA', 'Germany', 'Japan', 'USA', 'USA', 'USA', 'USA', 'Germany',
'Japan', 'Japan', 'USA', 'Sweden', 'USA', 'France', 'Japan', 'Germany',
'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA', 'USA',
'USA', 'USA', 'Germany', 'Japan', 'Japan', 'USA', 'USA', 'Japan', 'Japan',
'Japan', 'Japan', 'Japan', 'Japan', 'USA', 'USA', 'USA', 'USA', 'Japan',
'USA', 'USA', 'USA', 'Germany', 'USA', 'USA', 'USA'
])
#accommodate recfromtxt for python 3.2, requires bytes
ss = asbytes(ss)
ss2 = asbytes(ss2)
ss3 = asbytes(ss3)
ss5 = asbytes(ss5)
dta = np.recfromtxt(BytesIO(ss), names=("Rust", "Brand", "Replication"))
dta2 = np.recfromtxt(BytesIO(ss2),
names=("idx", "Treatment", "StressReduction"))
dta3 = np.recfromtxt(BytesIO(ss3), names=("Brand", "Relief"))
dta5 = np.recfromtxt(BytesIO(ss5),
names=('pair', 'mean', 'lower', 'upper', 'sig'),
delimiter='\t')
dta = pd.DataFrame.from_records(dta)
dta2 = pd.DataFrame.from_records(dta2)
dta3 = pd.DataFrame.from_records(dta3)
dta5 = pd.DataFrame.from_records(dta5)
sas_ = dta5.iloc[[1, 3, 2]]
from statsmodels.stats.multicomp import (tukeyhsd, pairwise_tukeyhsd,
MultiComparison)