def value_counts(self, method='sort'):
if method != 'sort':
msg = 'non sort based value_count() not implemented yet'
raise NotImplementedError(msg)
segs, sortedvals = self._unique_segments()
# Return both values and their counts
out_col = cpp_copying.apply_gather_array(sortedvals, segs)
out = cudautils.value_count(segs, len(sortedvals))
out_vals = self.replace(data=out_col.data, mask=None)
out_counts = numerical.NumericalColumn(data=Buffer(out), dtype=np.intp)
return out_vals, out_counts
def build_column(buffer, dtype, mask=None, categories=None):
from cudf.dataframe import numerical, categorical, datetime
if dtype == 'datetime64[ms]':
return datetime.DatetimeColumn(data=buffer,
dtype=np.dtype(dtype),
mask=mask)
elif pd.api.types.is_categorical_dtype(dtype):
return categorical.CategoricalColumn(data=buffer,
dtype='categorical',
categories=categories,
ordered=False,
mask=mask)
else:
return numerical.NumericalColumn(data=buffer, dtype=dtype, mask=mask)
def build_column(buffer, dtype, mask=None, categories=None):
from cudf.dataframe import numerical, categorical, datetime, string
if np.dtype(dtype).type == np.datetime64:
return datetime.DatetimeColumn(data=buffer,
dtype=np.dtype(dtype),
mask=mask)
elif pd.api.types.is_categorical_dtype(dtype):
return categorical.CategoricalColumn(data=buffer,
dtype='categorical',
categories=categories,
ordered=False,
mask=mask)
elif np.dtype(dtype).type in (np.object_, np.str_):
if not isinstance(buffer, nvstrings.nvstrings):
raise TypeError
return string.StringColumn(data=buffer)
else:
return numerical.NumericalColumn(data=buffer, dtype=dtype, mask=mask)
def sort_by_values(self, ascending=True, na_position="last"):
if na_position == "last":
nullfirst = False
elif na_position == "first":
nullfirst = True
idx_dev_arr = rmm.device_array(len(self), dtype='int32')
dev_ptr = get_ctype_ptr(idx_dev_arr)
self.data.order(2, asc=ascending, nullfirst=nullfirst, devptr=dev_ptr)
col_inds = numerical.NumericalColumn(data=Buffer(idx_dev_arr),
mask=None,
null_count=0,
dtype=idx_dev_arr.dtype)
col_keys = self[col_inds.data.mem]
return col_keys, col_inds
def build_column(buffer,
dtype,
mask=None,
categories=None,
name=None,
null_count=None):
from cudf.dataframe import numerical, categorical, datetime, string
dtype = pd.api.types.pandas_dtype(dtype)
if is_categorical_dtype(dtype):
return categorical.CategoricalColumn(
data=buffer,
dtype="categorical",
categories=categories,
ordered=False,
mask=mask,
name=name,
null_count=null_count,
)
elif dtype.type is np.datetime64:
return datetime.DatetimeColumn(
data=buffer,
dtype=dtype,
mask=mask,
name=name,
null_count=null_count,
)
elif dtype.type in (np.object_, np.str_):
if not isinstance(buffer, nvstrings.nvstrings):
raise TypeError
return string.StringColumn(data=buffer,
name=name,
null_count=null_count)
else:
return numerical.NumericalColumn(
data=buffer,
dtype=dtype,
mask=mask,
name=name,
null_count=null_count,
)
def as_column(arbitrary, nan_as_null=True, dtype=None):
"""Create a Column from an arbitrary object
Currently support inputs are:
* ``Column``
* ``Buffer``
* ``Series``
* ``Index``
* numba device array
* cuda array interface
* numpy array
* pyarrow array
* pandas.Categorical
Returns
-------
result : subclass of TypedColumnBase
- CategoricalColumn for pandas.Categorical input.
- DatetimeColumn for datetime input
- NumericalColumn for all other inputs.
"""
from cudf.dataframe import numerical, categorical, datetime, string
from cudf.dataframe.series import Series
from cudf.dataframe.index import Index
if isinstance(arbitrary, Column):
categories = None
if hasattr(arbitrary, "categories"):
categories = arbitrary.categories
data = build_column(arbitrary.data,
arbitrary.dtype,
mask=arbitrary.mask,
categories=categories)
elif isinstance(arbitrary, Series):
data = arbitrary._column
elif isinstance(arbitrary, Index):
data = arbitrary._values
elif isinstance(arbitrary, Buffer):
data = numerical.NumericalColumn(data=arbitrary, dtype=arbitrary.dtype)
elif isinstance(arbitrary, nvstrings.nvstrings):
data = string.StringColumn(data=arbitrary)
elif cuda.devicearray.is_cuda_ndarray(arbitrary):
data = as_column(Buffer(arbitrary))
if (data.dtype in [np.float16, np.float32, np.float64]
and arbitrary.size > 0):
if nan_as_null:
mask = cudautils.mask_from_devary(arbitrary)
data = data.set_mask(mask)
elif cuda.is_cuda_array(arbitrary):
# Use cuda array interface to do create a numba device array by
# reference
new_dev_array = cuda.as_cuda_array(arbitrary)
# Allocate new output array using rmm and copy the numba device array
# to an rmm owned device array
out_dev_array = rmm.device_array_like(new_dev_array)
out_dev_array.copy_to_device(new_dev_array)
data = as_column(out_dev_array)
elif isinstance(arbitrary, np.ndarray):
# CUDF assumes values are always contiguous
if not arbitrary.flags['C_CONTIGUOUS']:
arbitrary = np.ascontiguousarray(arbitrary)
if arbitrary.dtype.kind == 'M':
data = datetime.DatetimeColumn.from_numpy(arbitrary)
elif arbitrary.dtype.kind in ('O', 'U'):
data = as_column(pa.Array.from_pandas(arbitrary))
else:
data = as_column(rmm.to_device(arbitrary), nan_as_null=nan_as_null)
elif isinstance(arbitrary, pa.Array):
if isinstance(arbitrary, pa.StringArray):
count = len(arbitrary)
null_count = arbitrary.null_count
buffers = arbitrary.buffers()
# Buffer of actual strings values
if buffers[2] is not None:
sbuf = np.frombuffer(buffers[2], dtype='int8')
else:
sbuf = np.empty(0, dtype='int8')
# Buffer of offsets values
obuf = np.frombuffer(buffers[1], dtype='int32')
# Buffer of null bitmask
nbuf = None
if null_count > 0:
nbuf = np.frombuffer(buffers[0], dtype='int8')
data = as_column(
nvstrings.from_offsets(sbuf,
obuf,
count,
nbuf=nbuf,
ncount=null_count))
elif isinstance(arbitrary, pa.NullArray):
new_dtype = dtype
if (type(dtype) == str and dtype == 'empty') or dtype is None:
new_dtype = np.dtype(arbitrary.type.to_pandas_dtype())
if pd.api.types.is_categorical_dtype(new_dtype):
arbitrary = arbitrary.dictionary_encode()
else:
if nan_as_null:
arbitrary = arbitrary.cast(_gdf.np_to_pa_dtype(new_dtype))
else:
# casting a null array doesn't make nans valid
# so we create one with valid nans from scratch:
if new_dtype == np.dtype("object"):
arbitrary = utils.scalar_broadcast_to(
None, (len(arbitrary), ), dtype=new_dtype)
else:
arbitrary = utils.scalar_broadcast_to(
np.nan, (len(arbitrary), ), dtype=new_dtype)
data = as_column(arbitrary, nan_as_null=nan_as_null)
elif isinstance(arbitrary, pa.DictionaryArray):
pamask, padata = buffers_from_pyarrow(arbitrary)
data = categorical.CategoricalColumn(
data=padata,
mask=pamask,
null_count=arbitrary.null_count,
categories=arbitrary.dictionary.to_pylist(),
ordered=arbitrary.type.ordered,
)
elif isinstance(arbitrary, pa.TimestampArray):
arbitrary = arbitrary.cast(pa.timestamp('ms'))
pamask, padata = buffers_from_pyarrow(arbitrary, dtype='M8[ms]')
data = datetime.DatetimeColumn(data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=np.dtype('M8[ms]'))
elif isinstance(arbitrary, pa.Date64Array):
pamask, padata = buffers_from_pyarrow(arbitrary, dtype='M8[ms]')
data = datetime.DatetimeColumn(data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=np.dtype('M8[ms]'))
elif isinstance(arbitrary, pa.Date32Array):
# No equivalent np dtype and not yet supported
warnings.warn(
"Date32 values are not yet supported so this will "
"be typecast to a Date64 value", UserWarning)
arbitrary = arbitrary.cast(pa.date64())
data = as_column(arbitrary)
elif isinstance(arbitrary, pa.BooleanArray):
# Arrow uses 1 bit per value while we use int8
dtype = np.dtype(np.bool)
# Needed because of bug in PyArrow
# https://issues.apache.org/jira/browse/ARROW-4766
if len(arbitrary) > 0:
arbitrary = arbitrary.cast(pa.int8())
else:
arbitrary = pa.array([], type=pa.int8())
pamask, padata = buffers_from_pyarrow(arbitrary, dtype=dtype)
data = numerical.NumericalColumn(data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=dtype)
else:
pamask, padata = buffers_from_pyarrow(arbitrary)
data = numerical.NumericalColumn(
data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=np.dtype(arbitrary.type.to_pandas_dtype()))
elif isinstance(arbitrary, pa.ChunkedArray):
gpu_cols = [
as_column(chunk, dtype=dtype) for chunk in arbitrary.chunks
]
if dtype and dtype != 'empty':
new_dtype = dtype
else:
pa_type = arbitrary.type
if pa.types.is_dictionary(pa_type):
new_dtype = 'category'
else:
new_dtype = np.dtype(pa_type.to_pandas_dtype())
data = Column._concat(gpu_cols, dtype=new_dtype)
elif isinstance(arbitrary, (pd.Series, pd.Categorical)):
if pd.api.types.is_categorical_dtype(arbitrary):
data = as_column(pa.array(arbitrary, from_pandas=True))
elif arbitrary.dtype == np.bool:
# Bug in PyArrow or HDF that requires us to do this
data = as_column(pa.array(np.array(arbitrary), from_pandas=True))
else:
data = as_column(pa.array(arbitrary, from_pandas=nan_as_null))
elif isinstance(arbitrary, pd.Timestamp):
# This will always treat NaTs as nulls since it's not technically a
# discrete value like NaN
data = as_column(pa.array(pd.Series([arbitrary]), from_pandas=True))
elif np.isscalar(arbitrary) and not isinstance(arbitrary, memoryview):
if hasattr(arbitrary, 'dtype'):
data_type = _gdf.np_to_pa_dtype(arbitrary.dtype)
if data_type in (pa.date64(), pa.date32()):
# PyArrow can't construct date64 or date32 arrays from np
# datetime types
arbitrary = arbitrary.astype('int64')
data = as_column(pa.array([arbitrary], type=data_type))
else:
data = as_column(pa.array([arbitrary]), nan_as_null=nan_as_null)
elif isinstance(arbitrary, memoryview):
data = as_column(np.array(arbitrary),
dtype=dtype,
nan_as_null=nan_as_null)
else:
try:
data = as_column(memoryview(arbitrary))
except TypeError:
try:
pa_type = None
if dtype is not None:
if pd.api.types.is_categorical_dtype(dtype):
raise TypeError
else:
np_type = np.dtype(dtype).type
if np_type == np.bool_:
pa_type = pa.bool_()
else:
pa_type = _gdf.np_to_pa_dtype(np.dtype(dtype).type)
data = as_column(pa.array(arbitrary,
type=pa_type,
from_pandas=nan_as_null),
nan_as_null=nan_as_null)
except (pa.ArrowInvalid, pa.ArrowTypeError, TypeError):
np_type = None
if pd.api.types.is_categorical_dtype(dtype):
data = as_column(pd.Series(arbitrary, dtype='category'),
nan_as_null=nan_as_null)
else:
if dtype is None:
np_type = None
else:
np_type = np.dtype(dtype)
data = as_column(np.array(arbitrary, dtype=np_type),
nan_as_null=nan_as_null)
return data
def as_column(arbitrary, nan_as_null=True, dtype=None, name=None):
"""Create a Column from an arbitrary object
Currently support inputs are:
* ``Column``
* ``Buffer``
* ``Series``
* ``Index``
* numba device array
* cuda array interface
* numpy array
* pyarrow array
* pandas.Categorical
* Object exposing ``__cuda_array_interface__``
Returns
-------
result : subclass of TypedColumnBase
- CategoricalColumn for pandas.Categorical input.
- DatetimeColumn for datetime input.
- StringColumn for string input.
- NumericalColumn for all other inputs.
"""
from cudf.dataframe import numerical, categorical, datetime, string
from cudf.dataframe.series import Series
from cudf.dataframe.index import Index
from cudf.bindings.cudf_cpp import np_to_pa_dtype
if name is None and hasattr(arbitrary, "name"):
name = arbitrary.name
if isinstance(arbitrary, Column):
categories = None
if hasattr(arbitrary, "categories"):
categories = arbitrary.categories
data = build_column(
arbitrary.data,
arbitrary.dtype,
mask=arbitrary.mask,
categories=categories,
)
elif isinstance(arbitrary, Series):
data = arbitrary._column
if dtype is not None:
data = data.astype(dtype)
elif isinstance(arbitrary, Index):
data = arbitrary._values
if dtype is not None:
data = data.astype(dtype)
elif isinstance(arbitrary, Buffer):
data = numerical.NumericalColumn(data=arbitrary, dtype=arbitrary.dtype)
elif isinstance(arbitrary, nvstrings.nvstrings):
data = string.StringColumn(data=arbitrary)
elif cuda.devicearray.is_cuda_ndarray(arbitrary):
data = as_column(Buffer(arbitrary))
if (data.dtype in [np.float16, np.float32, np.float64]
and arbitrary.size > 0):
if nan_as_null:
mask = cudf.bindings.utils.mask_from_devary(data)
data = data.set_mask(mask)
elif hasattr(arbitrary, "__cuda_array_interface__"):
from cudf.bindings.cudf_cpp import count_nonzero_mask
desc = arbitrary.__cuda_array_interface__
data = _data_from_cuda_array_interface_desc(desc)
mask = _mask_from_cuda_array_interface_desc(desc)
if mask is not None:
nelem = len(data.mem)
nnz = count_nonzero_mask(mask.mem, size=nelem)
null_count = nelem - nnz
else:
null_count = 0
return build_column(data,
dtype=data.dtype,
mask=mask,
name=name,
null_count=null_count)
elif isinstance(arbitrary, np.ndarray):
# CUDF assumes values are always contiguous
if not arbitrary.flags["C_CONTIGUOUS"]:
arbitrary = np.ascontiguousarray(arbitrary)
if dtype is not None:
arbitrary = arbitrary.astype(dtype)
if arbitrary.dtype.kind == "M":
data = datetime.DatetimeColumn.from_numpy(arbitrary)
elif arbitrary.dtype.kind in ("O", "U"):
data = as_column(pa.Array.from_pandas(arbitrary))
else:
data = as_column(rmm.to_device(arbitrary), nan_as_null=nan_as_null)
elif isinstance(arbitrary, pa.Array):
if isinstance(arbitrary, pa.StringArray):
count = len(arbitrary)
null_count = arbitrary.null_count
buffers = arbitrary.buffers()
# Buffer of actual strings values
if buffers[2] is not None:
sbuf = np.frombuffer(buffers[2], dtype="int8")
else:
sbuf = np.empty(0, dtype="int8")
# Buffer of offsets values
obuf = np.frombuffer(buffers[1], dtype="int32")
# Buffer of null bitmask
nbuf = None
if null_count > 0:
nbuf = np.frombuffer(buffers[0], dtype="int8")
data = as_column(
nvstrings.from_offsets(sbuf,
obuf,
count,
nbuf=nbuf,
ncount=null_count))
elif isinstance(arbitrary, pa.NullArray):
new_dtype = pd.api.types.pandas_dtype(dtype)
if (type(dtype) == str and dtype == "empty") or dtype is None:
new_dtype = pd.api.types.pandas_dtype(
arbitrary.type.to_pandas_dtype())
if is_categorical_dtype(new_dtype):
arbitrary = arbitrary.dictionary_encode()
else:
if nan_as_null:
arbitrary = arbitrary.cast(np_to_pa_dtype(new_dtype))
else:
# casting a null array doesn't make nans valid
# so we create one with valid nans from scratch:
if new_dtype == np.dtype("object"):
arbitrary = utils.scalar_broadcast_to(
None, (len(arbitrary), ), dtype=new_dtype)
else:
arbitrary = utils.scalar_broadcast_to(
np.nan, (len(arbitrary), ), dtype=new_dtype)
data = as_column(arbitrary, nan_as_null=nan_as_null)
elif isinstance(arbitrary, pa.DictionaryArray):
pamask, padata = buffers_from_pyarrow(arbitrary)
data = categorical.CategoricalColumn(
data=padata,
mask=pamask,
null_count=arbitrary.null_count,
categories=arbitrary.dictionary,
ordered=arbitrary.type.ordered,
)
elif isinstance(arbitrary, pa.TimestampArray):
dtype = np.dtype("M8[{}]".format(arbitrary.type.unit))
pamask, padata = buffers_from_pyarrow(arbitrary, dtype=dtype)
data = datetime.DatetimeColumn(
data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=dtype,
)
elif isinstance(arbitrary, pa.Date64Array):
pamask, padata = buffers_from_pyarrow(arbitrary, dtype="M8[ms]")
data = datetime.DatetimeColumn(
data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=np.dtype("M8[ms]"),
)
elif isinstance(arbitrary, pa.Date32Array):
# No equivalent np dtype and not yet supported
warnings.warn(
"Date32 values are not yet supported so this will "
"be typecast to a Date64 value",
UserWarning,
)
data = as_column(arbitrary.cast(pa.int32())).astype("M8[ms]")
elif isinstance(arbitrary, pa.BooleanArray):
# Arrow uses 1 bit per value while we use int8
dtype = np.dtype(np.bool)
# Needed because of bug in PyArrow
# https://issues.apache.org/jira/browse/ARROW-4766
if len(arbitrary) > 0:
arbitrary = arbitrary.cast(pa.int8())
else:
arbitrary = pa.array([], type=pa.int8())
pamask, padata = buffers_from_pyarrow(arbitrary, dtype=dtype)
data = numerical.NumericalColumn(
data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=dtype,
)
else:
pamask, padata = buffers_from_pyarrow(arbitrary)
data = numerical.NumericalColumn(
data=padata,
mask=pamask,
null_count=arbitrary.null_count,
dtype=np.dtype(arbitrary.type.to_pandas_dtype()),
)
elif isinstance(arbitrary, pa.ChunkedArray):
gpu_cols = [
as_column(chunk, dtype=dtype) for chunk in arbitrary.chunks
]
if dtype and dtype != "empty":
new_dtype = dtype
else:
pa_type = arbitrary.type
if pa.types.is_dictionary(pa_type):
new_dtype = "category"
else:
new_dtype = np.dtype(pa_type.to_pandas_dtype())
data = Column._concat(gpu_cols, dtype=new_dtype)
elif isinstance(arbitrary, (pd.Series, pd.Categorical)):
if is_categorical_dtype(arbitrary):
data = as_column(pa.array(arbitrary, from_pandas=True))
elif arbitrary.dtype == np.bool:
# Bug in PyArrow or HDF that requires us to do this
data = as_column(pa.array(np.array(arbitrary), from_pandas=True))
else:
data = as_column(pa.array(arbitrary, from_pandas=nan_as_null))
elif isinstance(arbitrary, pd.Timestamp):
# This will always treat NaTs as nulls since it's not technically a
# discrete value like NaN
data = as_column(pa.array(pd.Series([arbitrary]), from_pandas=True))
elif np.isscalar(arbitrary) and not isinstance(arbitrary, memoryview):
if hasattr(arbitrary, "dtype"):
data_type = np_to_pa_dtype(arbitrary.dtype)
# PyArrow can't construct date64 or date32 arrays from np
# datetime types
if pa.types.is_date64(data_type) or pa.types.is_date32(data_type):
arbitrary = arbitrary.astype("int64")
data = as_column(pa.array([arbitrary], type=data_type))
else:
data = as_column(pa.array([arbitrary]), nan_as_null=nan_as_null)
elif isinstance(arbitrary, memoryview):
data = as_column(np.array(arbitrary),
dtype=dtype,
nan_as_null=nan_as_null)
else:
try:
data = as_column(memoryview(arbitrary),
dtype=dtype,
nan_as_null=nan_as_null)
except TypeError:
pa_type = None
np_type = None
try:
if dtype is not None:
dtype = pd.api.types.pandas_dtype(dtype)
if is_categorical_dtype(dtype):
raise TypeError
else:
np_type = np.dtype(dtype).type
if np_type == np.bool_:
pa_type = pa.bool_()
else:
pa_type = np_to_pa_dtype(np.dtype(dtype))
data = as_column(
pa.array(arbitrary, type=pa_type, from_pandas=nan_as_null),
dtype=dtype,
nan_as_null=nan_as_null,
)
except (pa.ArrowInvalid, pa.ArrowTypeError, TypeError):
if is_categorical_dtype(dtype):
data = as_column(
pd.Series(arbitrary, dtype="category"),
nan_as_null=nan_as_null,
)
else:
data = as_column(
np.array(arbitrary, dtype=np_type),
nan_as_null=nan_as_null,
)
if hasattr(data, "name") and (name is not None):
data.name = name
return data