def to_pandas(self):
"""
Convert Frame to a pandas DataFrame, or raise an error if `pandas`
module is not installed.
"""
pandas = load_module("pandas")
numpy = load_module("numpy")
if not hasattr(pandas, "DataFrame"): # pragma: no cover
raise ImportError("Unsupported pandas version: `%s`" %
(getattr(pandas, "__version__", "???"), ))
nas = {
stype.bool8: -128,
stype.int8: -128,
stype.int16: -32768,
stype.int32: -2147483648,
stype.int64: -9223372036854775808
}
self.materialize()
srcdt = self._dt
srccols = collections.OrderedDict()
for i in range(self.ncols):
name = self.names[i]
column = srcdt.column(i)
dtype = self.stypes[i].dtype
if dtype == numpy.bool:
dtype = numpy.int8
if dtype == numpy.dtype("object"):
# Variable-width types can only be represented in Numpy as
# dtype='object'. However Numpy cannot ingest a buffer of
# PyObject types -- getting error
# ValueError: cannot create an OBJECT array from memory buffer
# Thus, the only alternative remaining is to convert such column
# into plain Python list and pass it to Pandas like that.
x = self[:, i].to_list()[0]
else:
x = numpy.frombuffer(column, dtype=dtype)
na = nas.get(self.stypes[i])
if na is not None:
x = numpy.ma.masked_equal(x, na, copy=False)
srccols[name] = x
pd = pandas.DataFrame(srccols)
return pd
def tonumpy(self, stype=None):
"""
Convert Frame into a numpy array, optionally forcing it into a
specific stype/dtype.
Parameters
----------
stype: datatable.stype, numpy.dtype or str
Cast datatable into this dtype before converting it into a numpy
array.
"""
numpy = load_module("numpy")
st = 0
if stype:
st = datatable.stype(stype).value
self.internal.use_stype_for_buffers(st)
res = numpy.array(self.internal)
self.internal.use_stype_for_buffers(0)
return res
def to_numpy(self, stype=None):
"""
Convert Frame into a numpy array, optionally forcing it into a
specific stype/dtype.
Parameters
----------
stype: datatable.stype, numpy.dtype or str
Cast datatable into this dtype before converting it into a numpy
array.
"""
numpy = load_module("numpy")
if not hasattr(numpy, "array"): # pragma: no cover
raise ImportError("Unsupported numpy version: `%s`"
% (getattr(numpy, "__version__", "???"), ))
st = 0
if stype:
st = datatable.stype(stype).value
self.internal.use_stype_for_buffers(st)
res = numpy.array(self.internal)
self.internal.use_stype_for_buffers(0)
return res
