def test_truncated_float_support(self):
# Test with paxraw_d_short.xpt, a shortened version of:
# http://wwwn.cdc.gov/Nchs/Nhanes/2005-2006/PAXRAW_D.ZIP
# This file has truncated floats (5 bytes in this case).
# GH 11713
data_csv = pd.read_csv(self.file04.replace(".xpt", ".csv"))
data = XportReader(self.file04).read()
tm.assert_frame_equal(data.astype('int64'), data_csv)
data = read_sas(self.file04)
tm.assert_frame_equal(data.astype('int64'), data_csv)
def test_truncated_float_support(self):
# Test with paxraw_d_short.xpt, a shortened version of:
# http://wwwn.cdc.gov/Nchs/Nhanes/2005-2006/PAXRAW_D.ZIP
# This file has truncated floats (5 bytes in this case).
# GH 11713
data_csv = pd.read_csv(self.file04.replace(".xpt", ".csv"))
data = XportReader(self.file04).read()
tm.assert_frame_equal(data.astype("int64"), data_csv)
data = read_sas(self.file04)
tm.assert_frame_equal(data.astype("int64"), data_csv)
def test1_index(self):
# Tests with DEMO_G.xpt using index (all numeric file)
# Compare to this
data_csv = pd.read_csv(self.file01.replace(".xpt", ".csv"))
data_csv = data_csv.set_index("SEQN")
numeric_as_float(data_csv)
# Read full file
data = XportReader(self.file01, index="SEQN").read()
tm.assert_frame_equal(data, data_csv, check_index_type=False)
# Test incremental read with `read` method.
reader = XportReader(self.file01, index="SEQN")
data = reader.read(10)
tm.assert_frame_equal(data,
data_csv.iloc[0:10, :],
check_index_type=False)
# Test incremental read with `get_chunk` method.
reader = XportReader(self.file01, index="SEQN", chunksize=10)
data = reader.get_chunk()
tm.assert_frame_equal(data,
data_csv.iloc[0:10, :],
check_index_type=False)
def test2(self):
# Test with SSHSV1_A.xpt
# Compare to this
data_csv = pd.read_csv(self.file02.replace(".xpt", ".csv"))
numeric_as_float(data_csv)
data = XportReader(self.file02).read()
tm.assert_frame_equal(data, data_csv)
def test1_incremental(self):
# Test with DEMO_G.xpt, reading full file incrementally
data_csv = pd.read_csv(self.file01.replace(".xpt", ".csv"))
data_csv = data_csv.set_index("SEQN")
numeric_as_float(data_csv)
reader = XportReader(self.file01, index="SEQN", chunksize=1000)
all_data = [x for x in reader]
data = pd.concat(all_data, axis=0)
tm.assert_frame_equal(data, data_csv, check_index_type=False)
reader = XportReader(self.file01, index="SEQN", chunksize=1000)
data = pd.concat(reader, axis=0)
tm.assert_frame_equal(data, data_csv, check_index_type=False)
def test_multiple_types(self):
# Test with DRXFCD_G.xpt (contains text and numeric variables)
# Compare to this
data_csv = pd.read_csv(self.file03.replace(".xpt", ".csv"))
data = XportReader(self.file03).read()
tm.assert_frame_equal(data, data_csv)
data = read_sas(self.file03)
tm.assert_frame_equal(data, data_csv)
def test1_index(self):
# Tests with DEMO_G.XPT using index (all numeric file)
# Compare to this
data_csv = pd.read_csv(self.file01.replace(".XPT", ".csv"))
data_csv = data_csv.set_index("SEQN")
numeric_as_float(data_csv)
# Read full file
data = XportReader(self.file01, index="SEQN").read()
tm.assert_frame_equal(data, data_csv, check_index_type=False)
# Test incremental read with `read` method.
reader = XportReader(self.file01, index="SEQN")
data = reader.read(10)
tm.assert_frame_equal(data, data_csv.iloc[0:10, :], check_index_type=False)
# Test incremental read with `get_chunk` method.
reader = XportReader(self.file01, index="SEQN", chunksize=10)
data = reader.get_chunk()
tm.assert_frame_equal(data, data_csv.iloc[0:10, :], check_index_type=False)
def test1(self):
# Tests with DEMO_G.XPT (all numeric file)
# Compare to this
data_csv = pd.read_csv(self.file01.replace(".XPT", ".csv"))
numeric_as_float(data_csv)
# Read full file
data = XportReader(self.file01).read()
tm.assert_frame_equal(data, data_csv)
# Test incremental read with `read` method.
reader = XportReader(self.file01)
data = reader.read(10)
tm.assert_frame_equal(data, data_csv.iloc[0:10, :])
# Test incremental read with `get_chunk` method.
reader = XportReader(self.file01, chunksize=10)
data = reader.get_chunk()
tm.assert_frame_equal(data, data_csv.iloc[0:10, :])
# Read full file with `read_sas` method
data = read_sas(self.file01)
tm.assert_frame_equal(data, data_csv)
def test1_basic(self):
# Tests with DEMO_G.xpt (all numeric file)
# Compare to this
data_csv = pd.read_csv(self.file01.replace(".xpt", ".csv"))
numeric_as_float(data_csv)
# Read full file
data = XportReader(self.file01).read()
tm.assert_frame_equal(data, data_csv)
# Test incremental read with `read` method.
reader = XportReader(self.file01)
data = reader.read(10)
tm.assert_frame_equal(data, data_csv.iloc[0:10, :])
# Test incremental read with `get_chunk` method.
reader = XportReader(self.file01, chunksize=10)
data = reader.get_chunk()
tm.assert_frame_equal(data, data_csv.iloc[0:10, :])
# Read full file with `read_sas` method
data = read_sas(self.file01)
tm.assert_frame_equal(data, data_csv)