def test_genfromdta_datetime():
results = [
(datetime(2006, 11, 19, 23, 13, 20), 1479596223000,
datetime(2010, 1, 20), datetime(2010, 1, 8), datetime(2010, 1, 1),
datetime(1974, 7, 1), datetime(2010, 1, 1), datetime(2010, 1, 1)),
(datetime(1959, 12, 31, 20, 3, 20), -1479590, datetime(1953, 10, 2),
datetime(1948, 6, 10), datetime(1955, 1, 1), datetime(1955, 7, 1),
datetime(1955, 1, 1), datetime(2, 1, 1))
]
with pytest.warns(FutureWarning):
dta = genfromdta(
os.path.join(curdir, "results/time_series_examples.dta"))
assert_array_equal(dta[0].tolist(), results[0])
assert_array_equal(dta[1].tolist(), results[1])
with warnings.catch_warnings(record=True):
with pytest.warns(FutureWarning):
dta = genfromdta(os.path.join(curdir,
"results/time_series_examples.dta"),
pandas=True)
for i, row in enumerate(results):
new = []
for val in row:
if isinstance(val, datetime) and val.year > 2:
new.append(Timestamp(val))
else:
new.append(val)
results[i] = new
assert dta.iloc[0].tolist() == results[0]
assert dta.iloc[1].tolist() == results[1]
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_genfromdta_datetime():
results = [
(datetime(2006, 11, 19, 23, 13, 20), 1479596223000,
datetime(2010, 1, 20), datetime(2010, 1, 8), datetime(2010, 1, 1),
datetime(1974, 7, 1), datetime(2010, 1, 1), datetime(2010, 1, 1)),
(datetime(1959, 12, 31, 20, 3, 20), -1479590, datetime(1953, 10, 2),
datetime(1948, 6, 10), datetime(1955, 1, 1), datetime(1955, 7, 1),
datetime(1955, 1, 1), datetime(2, 1, 1))
]
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter('always')
dta = genfromdta(
os.path.join(curdir, "results/time_series_examples.dta"))
assert_(len(w) > 0) # should get a warning for that format.
assert_array_equal(dta[0].tolist(), results[0])
assert_array_equal(dta[1].tolist(), results[1])
with warnings.catch_warnings(record=True):
dta = genfromdta(os.path.join(curdir,
"results/time_series_examples.dta"),
pandas=True)
assert_array_equal(dta.iloc[0].tolist(), results[0])
assert_array_equal(dta.iloc[1].tolist(), results[1])
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)
assert_frame_equal(dta, dta2.drop('index', axis=1))
def test_genfromdta_datetime():
results = [(datetime(2006, 11, 19, 23, 13, 20), 1479596223000,
datetime(2010, 1, 20), datetime(2010, 1, 8), datetime(2010, 1, 1),
datetime(1974, 7, 1), datetime(2010, 1, 1), datetime(2010, 1, 1)),
(datetime(1959, 12, 31, 20, 3, 20), -1479590, datetime(1953, 10, 2),
datetime(1948, 6, 10), datetime(1955, 1, 1), datetime(1955, 7, 1),
datetime(1955, 1, 1), datetime(2, 1, 1))]
dta = genfromdta("results/time_series_examples.dta")
assert_array_equal(dta[0].tolist(), results[0])
assert_array_equal(dta[1].tolist(), results[1])
dta = genfromdta("results/time_series_examples.dta", pandas=True)
assert_array_equal(dta.irow(0).tolist(), results[0])
assert_array_equal(dta.irow(1).tolist(), results[1])
def test_missing_roundtrip():
buf = StringIO()
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] == "")
dta = genfromdta("./data_missing.dta", missing_flt=-999)
assert_(np.all([dta[0][i] == -999 for i in range(5)]))
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'):
assert_frame_equal(dta.reset_index(), dta5)
else:
# do not check index because it has different size, int32 versus int64
assert_frame_equal(dta4, dta5[dta5.columns[1:]])
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_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_genfromdta():
#Test genfromdta vs. results/macrodta.npy created with genfromtxt.
#NOTE: Stata handles data very oddly. Round tripping from csv to dta
# to ndarray 2710.349 (csv) -> 2510.2491 (stata) -> 2710.34912109375
# (dta/ndarray)
from .results.macrodata import macrodata_result as res2
res1 = genfromdta(curdir+'/../../datasets/macrodata/macrodata.dta')
assert_array_equal(res1 == res2, True)
def test_genfromdta():
#Test genfromdta vs. results/macrodta.npy created with genfromtxt.
#NOTE: Stata handles data very oddly. Round tripping from csv to dta
# to ndarray 2710.349 (csv) -> 2510.2491 (stata) -> 2710.34912109375
# (dta/ndarray)
from .results.macrodata import macrodata_result as res2
res1 = genfromdta(curdir + '/../../datasets/macrodata/macrodata.dta')
assert_array_equal(res1 == res2, True)
def test_genfromdta_pandas():
dta = macrodata.load_pandas().data
curdir = os.path.dirname(os.path.abspath(__file__))
with pytest.warns(FutureWarning):
res1 = genfromdta(curdir + '/../../datasets/macrodata/macrodata.dta',
pandas=True)
res1 = res1.astype(float)
assert_frame_equal(res1, dta.astype(float))
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_genfromdta_pandas():
from pandas.util.testing import assert_frame_equal
dta = macrodata.load_pandas().data
curdir = os.path.dirname(os.path.abspath(__file__))
with pytest.warns(FutureWarning):
res1 = genfromdta(curdir+'/../../datasets/macrodata/macrodata.dta',
pandas=True)
res1 = res1.astype(float)
assert_frame_equal(res1, dta.astype(float))
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_genfromdta_datetime():
results = [(datetime(2006, 11, 19, 23, 13, 20), 1479596223000,
datetime(2010, 1, 20), datetime(2010, 1, 8), datetime(2010, 1, 1),
datetime(1974, 7, 1), datetime(2010, 1, 1), datetime(2010, 1, 1)),
(datetime(1959, 12, 31, 20, 3, 20), -1479590, datetime(1953, 10, 2),
datetime(1948, 6, 10), datetime(1955, 1, 1), datetime(1955, 7, 1),
datetime(1955, 1, 1), datetime(2, 1, 1))]
with warnings.catch_warnings(record=True) as w:
dta = genfromdta(os.path.join(curdir, "results/time_series_examples.dta"))
assert_(len(w) == 1) # should get a warning for that format.
assert_array_equal(dta[0].tolist(), results[0])
assert_array_equal(dta[1].tolist(), results[1])
with warnings.catch_warnings(record=True):
dta = genfromdta(os.path.join(curdir, "results/time_series_examples.dta"),
pandas=True)
assert_array_equal(dta.iloc[0].tolist(), results[0])
assert_array_equal(dta.iloc[1].tolist(), results[1])
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().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_genfromdta():
#Test genfromdta vs. results/macrodta.npy created with genfromtxt.
#NOTE: Stata handles data very oddly. Round tripping from csv to dta
# to ndarray 2710.349 (csv) -> 2510.2491 (stata) -> 2710.34912109375
# (dta/ndarray)
curdir = os.path.dirname(os.path.abspath(__file__))
#res2 = np.load(curdir+'/results/macrodata.npy')
#res2 = res2.view((float,len(res2[0])))
from results.macrodata import macrodata_result as res2
res1 = genfromdta(curdir+'/../../datasets/macrodata/macrodata.dta')
#res1 = res1.view((float,len(res1[0])))
assert_array_equal(res1 == res2, True)
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:]))
dta = DataFrame.from_records(dta)
writer = StataWriter(buf, dta)
writer.write_file()
buf.seek(0)
dta2 = genfromdta(buf)
ptesting.assert_frame_equal(dta.reset_index(), DataFrame.from_records(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_genfromdta_datetime():
results = [(datetime(2006, 11, 19, 23, 13, 20), 1479596223000,
datetime(2010, 1, 20), datetime(2010, 1, 8),
datetime(2010, 1, 1), datetime(1974, 7, 1),
datetime(2010, 1, 1), datetime(2010, 1, 1)),
(datetime(1959, 12, 31, 20, 3, 20), -1479590,
datetime(1953, 10, 2), datetime(1948, 6, 10),
datetime(1955, 1, 1), datetime(1955, 7, 1),
datetime(1955, 1, 1), datetime(2, 1, 1))]
with pytest.warns(FutureWarning):
dta = genfromdta(os.path.join(curdir,
"results/time_series_examples.dta"))
assert_array_equal(dta[0].tolist(), results[0])
assert_array_equal(dta[1].tolist(), results[1])
with warnings.catch_warnings(record=True):
with pytest.warns(FutureWarning):
dta = genfromdta(os.path.join(curdir,
"results/time_series_examples.dta"),
pandas=True)
assert_array_equal(dta.iloc[0].tolist(), results[0])
assert_array_equal(dta.iloc[1].tolist(), results[1])
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 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:]])
Created on Fri Dec 16 12:52:13 2011
Author: Josef Perktold
"""
import numpy as np
from numpy.testing import assert_almost_equal
import statsmodels.api as sm
import statsmodels.stats.sandwich_covariance as sw
#http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/srs.dta
import statsmodels.iolib.foreign as dta
try:
srs = dta.genfromdta("srs.dta")
print 'using local file'
except IOError:
import urllib
urllib.urlretrieve('http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/srs.dta', 'srs.dta')
print 'downloading file'
srs = dta.genfromdta("srs.dta")
# from statsmodels.tools.tools import webuse
# srs = webuse('srs', 'http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/')
# #does currently not cache file
y = srs['api00']
#older numpy don't reorder
#x = srs[['growth', 'emer', 'yr_rnd']].view(float).reshape(len(y), -1)
#force sequence
x = np.column_stack([srs[ii] for ii in ['growth', 'emer', 'yr_rnd']])
Author: Josef Perktold
"""
from urllib.request import urlretrieve
import numpy as np
from numpy.testing import assert_almost_equal
import statsmodels.api as sm
import statsmodels.stats.sandwich_covariance as sw
#http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/srs.dta
import statsmodels.iolib.foreign as dta
try:
srs = dta.genfromdta("srs.dta")
print('using local file')
except IOError:
urlretrieve('http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/srs.dta', 'srs.dta')
print('downloading file')
srs = dta.genfromdta("srs.dta")
# from statsmodels.datasets import webuse
# srs = webuse('srs', 'http://www.ats.ucla.edu/stat/stata/seminars/svy_stata_intro/')
# #does currently not cache file
y = srs['api00']
#older numpy do not reorder
#x = srs[['growth', 'emer', 'yr_rnd']].view(float).reshape(len(y), -1)
#force sequence
x = np.column_stack([srs[ii] for ii in ['growth', 'emer', 'yr_rnd']])
group = srs['dnum']
