def _parse_header(self, file_object):
self._file = file_object
encoding = self._encoding
# parse headers
self._header["ds_format"] = unpack("b", self._file.read(1))[0]
if self._header["ds_format"] not in [113, 114, 115]:
raise ValueError(
"Only file formats >= 113 (Stata >= 9)"
" are supported. Got format %s. Please report "
"if you think this error is incorrect." % self._header["ds_format"]
)
byteorder = self._header["byteorder"] = unpack("b", self._file.read(1))[0] == 0x1 and ">" or "<"
self._header["filetype"] = unpack("b", self._file.read(1))[0]
self._file.read(1)
nvar = self._header["nvar"] = unpack(byteorder + "h", self._file.read(2))[0]
self._header["nobs"] = unpack(byteorder + "i", self._file.read(4))[0]
self._header["data_label"] = self._null_terminate(self._file.read(81), encoding)
self._header["time_stamp"] = self._null_terminate(self._file.read(18), encoding)
# parse descriptors
typlist = [ord(self._file.read(1)) for i in range(nvar)]
self._header["typlist"] = [self.TYPE_MAP[typ] for typ in typlist]
self._header["dtyplist"] = [self.DTYPE_MAP[typ] for typ in typlist]
self._header["varlist"] = [self._null_terminate(self._file.read(33), encoding) for i in range(nvar)]
self._header["srtlist"] = unpack(byteorder + ("h" * (nvar + 1)), self._file.read(2 * (nvar + 1)))[:-1]
if self._header["ds_format"] <= 113:
self._header["fmtlist"] = [self._null_terminate(self._file.read(12), encoding) for i in range(nvar)]
else:
self._header["fmtlist"] = [self._null_terminate(self._file.read(49), encoding) for i in range(nvar)]
self._header["lbllist"] = [self._null_terminate(self._file.read(33), encoding) for i in range(nvar)]
self._header["vlblist"] = [self._null_terminate(self._file.read(81), encoding) for i in range(nvar)]
# ignore expansion fields
# When reading, read five bytes; the last four bytes now tell you the
# size of the next read, which you discard. You then continue like
# this until you read 5 bytes of zeros.
while True:
data_type = unpack(byteorder + "b", self._file.read(1))[0]
data_len = unpack(byteorder + "i", self._file.read(4))[0]
if data_type == 0:
break
self._file.read(data_len)
# other state vars
self._data_location = self._file.tell()
self._has_string_data = len(lfilter(lambda x: isinstance(x, int), self._header["typlist"])) > 0
self._col_size()
def in_domain(self, xs, ys, x):
"""
Returns the filtered (xs, ys) based on the Kernel domain centred on x
"""
# Disable black-list functions: filter used for speed instead of
# list-comprehension
# pylint: disable-msg=W0141
def isInDomain(xy):
"""Used for filter to check if point is in the domain"""
u = (xy[0]-x)/self.h
return u >= self.domain[0] and u <= self.domain[1]
if self.domain is None:
return (xs, ys)
else:
filtered = lfilter(isInDomain, lzip(xs, ys))
if len(filtered) > 0:
xs, ys = lzip(*filtered)
return (xs, ys)
else:
return ([], [])
def in_domain(self, xs, ys, x):
"""
Returns the filtered (xs, ys) based on the Kernel domain centred on x
"""
# Disable black-list functions: filter used for speed instead of
# list-comprehension
# pylint: disable-msg=W0141
def isInDomain(xy):
"""Used for filter to check if point is in the domain"""
u = (xy[0]-x)/self.h
return u >= self.domain[0] and u <= self.domain[1]
if self.domain is None:
return (xs, ys)
else:
filtered = lfilter(isInDomain, lzip(xs, ys))
if len(filtered) > 0:
xs, ys = lzip(*filtered)
return (xs, ys)
else:
return ([], [])
def _parse_header(self, file_object):
self._file = file_object
encoding = self._encoding
# parse headers
self._header['ds_format'] = unpack('b', self._file.read(1))[0]
if self._header['ds_format'] not in [113, 114, 115]:
raise ValueError("Only file formats >= 113 (Stata >= 9)"
" are supported. Got format %s. Please report "
"if you think this error is incorrect." %
self._header['ds_format'])
byteorder = self._header['byteorder'] = unpack(
'b', self._file.read(1))[0] == 0x1 and '>' or '<'
self._header['filetype'] = unpack('b', self._file.read(1))[0]
self._file.read(1)
nvar = self._header['nvar'] = unpack(byteorder + 'h',
self._file.read(2))[0]
self._header['nobs'] = unpack(byteorder + 'i', self._file.read(4))[0]
self._header['data_label'] = self._null_terminate(
self._file.read(81), encoding)
self._header['time_stamp'] = self._null_terminate(
self._file.read(18), encoding)
# parse descriptors
typlist = [ord(self._file.read(1)) for i in range(nvar)]
self._header['typlist'] = [self.TYPE_MAP[typ] for typ in typlist]
self._header['dtyplist'] = [self.DTYPE_MAP[typ] for typ in typlist]
self._header['varlist'] = [
self._null_terminate(self._file.read(33), encoding)
for i in range(nvar)
]
self._header['srtlist'] = unpack(byteorder + ('h' * (nvar + 1)),
self._file.read(2 * (nvar + 1)))[:-1]
if self._header['ds_format'] <= 113:
self._header['fmtlist'] = \
[self._null_terminate(self._file.read(12), encoding) \
for i in range(nvar)]
else:
self._header['fmtlist'] = \
[self._null_terminate(self._file.read(49), encoding) \
for i in range(nvar)]
self._header['lbllist'] = [
self._null_terminate(self._file.read(33), encoding)
for i in range(nvar)
]
self._header['vlblist'] = [
self._null_terminate(self._file.read(81), encoding)
for i in range(nvar)
]
# ignore expansion fields
# When reading, read five bytes; the last four bytes now tell you the
# size of the next read, which you discard. You then continue like
# this until you read 5 bytes of zeros.
while True:
data_type = unpack(byteorder + 'b', self._file.read(1))[0]
data_len = unpack(byteorder + 'i', self._file.read(4))[0]
if data_type == 0:
break
self._file.read(data_len)
# other state vars
self._data_location = self._file.tell()
self._has_string_data = len(
lfilter(lambda x: isinstance(x, int), self._header['typlist'])) > 0
self._col_size()
