Spaces:
Runtime error
Runtime error
File size: 17,414 Bytes
9cddcfd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 |
# DataFrame Interchange Protocol Types
# Copied from https://data-apis.org/dataframe-protocol/latest/API.html
#
# These classes are only for use in type signatures
from abc import (
ABC,
abstractmethod,
)
import enum
from typing import (
Any,
Dict,
Iterable,
Optional,
Sequence,
Tuple,
TypedDict,
)
class DlpackDeviceType(enum.IntEnum):
"""Integer enum for device type codes matching DLPack."""
CPU = 1
CUDA = 2
CPU_PINNED = 3
OPENCL = 4
VULKAN = 7
METAL = 8
VPI = 9
ROCM = 10
class DtypeKind(enum.IntEnum):
"""
Integer enum for data types.
Attributes
----------
INT : int
Matches to signed integer data type.
UINT : int
Matches to unsigned integer data type.
FLOAT : int
Matches to floating point data type.
BOOL : int
Matches to boolean data type.
STRING : int
Matches to string data type (UTF-8 encoded).
DATETIME : int
Matches to datetime data type.
CATEGORICAL : int
Matches to categorical data type.
"""
INT = 0
UINT = 1
FLOAT = 2
BOOL = 20
STRING = 21 # UTF-8
DATETIME = 22
CATEGORICAL = 23
Dtype = Tuple[DtypeKind, int, str, str] # see Column.dtype
class ColumnNullType(enum.IntEnum):
"""
Integer enum for null type representation.
Attributes
----------
NON_NULLABLE : int
Non-nullable column.
USE_NAN : int
Use explicit float NaN value.
USE_SENTINEL : int
Sentinel value besides NaN.
USE_BITMASK : int
The bit is set/unset representing a null on a certain position.
USE_BYTEMASK : int
The byte is set/unset representing a null on a certain position.
"""
NON_NULLABLE = 0
USE_NAN = 1
USE_SENTINEL = 2
USE_BITMASK = 3
USE_BYTEMASK = 4
class ColumnBuffers(TypedDict):
# first element is a buffer containing the column data;
# second element is the data buffer's associated dtype
data: Tuple["Buffer", Dtype]
# first element is a buffer containing mask values indicating missing data;
# second element is the mask value buffer's associated dtype.
# None if the null representation is not a bit or byte mask
validity: Optional[Tuple["Buffer", Dtype]]
# first element is a buffer containing the offset values for
# variable-size binary data (e.g., variable-length strings);
# second element is the offsets buffer's associated dtype.
# None if the data buffer does not have an associated offsets buffer
offsets: Optional[Tuple["Buffer", Dtype]]
class CategoricalDescription(TypedDict):
# whether the ordering of dictionary indices is semantically meaningful
is_ordered: bool
# whether a dictionary-style mapping of categorical values to other objects exists
is_dictionary: bool
# Python-level only (e.g. ``{int: str}``).
# None if not a dictionary-style categorical.
categories: "Optional[Column]"
class Buffer(ABC):
"""
Data in the buffer is guaranteed to be contiguous in memory.
Note that there is no dtype attribute present, a buffer can be thought of
as simply a block of memory. However, if the column that the buffer is
attached to has a dtype that's supported by DLPack and ``__dlpack__`` is
implemented, then that dtype information will be contained in the return
value from ``__dlpack__``.
This distinction is useful to support both data exchange via DLPack on a
buffer and (b) dtypes like variable-length strings which do not have a
fixed number of bytes per element.
"""
@property
@abstractmethod
def bufsize(self) -> int:
"""
Buffer size in bytes.
"""
pass
@property
@abstractmethod
def ptr(self) -> int:
"""
Pointer to start of the buffer as an integer.
"""
pass
@abstractmethod
def __dlpack__(self):
"""
Produce DLPack capsule (see array API standard).
Raises:
- TypeError : if the buffer contains unsupported dtypes.
- NotImplementedError : if DLPack support is not implemented
Useful to have to connect to array libraries. Support optional because
it's not completely trivial to implement for a Python-only library.
"""
raise NotImplementedError("__dlpack__")
@abstractmethod
def __dlpack_device__(self) -> Tuple[DlpackDeviceType, Optional[int]]:
"""
Device type and device ID for where the data in the buffer resides.
Uses device type codes matching DLPack.
Note: must be implemented even if ``__dlpack__`` is not.
"""
pass
class Column(ABC):
"""
A column object, with only the methods and properties required by the
interchange protocol defined.
A column can contain one or more chunks. Each chunk can contain up to three
buffers - a data buffer, a mask buffer (depending on null representation),
and an offsets buffer (if variable-size binary; e.g., variable-length
strings).
TBD: Arrow has a separate "null" dtype, and has no separate mask concept.
Instead, it seems to use "children" for both columns with a bit mask,
and for nested dtypes. Unclear whether this is elegant or confusing.
This design requires checking the null representation explicitly.
The Arrow design requires checking:
1. the ARROW_FLAG_NULLABLE (for sentinel values)
2. if a column has two children, combined with one of those children
having a null dtype.
Making the mask concept explicit seems useful. One null dtype would
not be enough to cover both bit and byte masks, so that would mean
even more checking if we did it the Arrow way.
TBD: there's also the "chunk" concept here, which is implicit in Arrow as
multiple buffers per array (= column here). Semantically it may make
sense to have both: chunks were meant for example for lazy evaluation
of data which doesn't fit in memory, while multiple buffers per column
could also come from doing a selection operation on a single
contiguous buffer.
Given these concepts, one would expect chunks to be all of the same
size (say a 10,000 row dataframe could have 10 chunks of 1,000 rows),
while multiple buffers could have data-dependent lengths. Not an issue
in pandas if one column is backed by a single NumPy array, but in
Arrow it seems possible.
Are multiple chunks *and* multiple buffers per column necessary for
the purposes of this interchange protocol, or must producers either
reuse the chunk concept for this or copy the data?
Note: this Column object can only be produced by ``__dataframe__``, so
doesn't need its own version or ``__column__`` protocol.
"""
@abstractmethod
def size(self) -> int:
"""
Size of the column, in elements.
Corresponds to DataFrame.num_rows() if column is a single chunk;
equal to size of this current chunk otherwise.
Is a method rather than a property because it may cause a (potentially
expensive) computation for some dataframe implementations.
"""
pass
@property
@abstractmethod
def offset(self) -> int:
"""
Offset of first element.
May be > 0 if using chunks; for example for a column with N chunks of
equal size M (only the last chunk may be shorter),
``offset = n * M``, ``n = 0 .. N-1``.
"""
pass
@property
@abstractmethod
def dtype(self) -> Dtype:
"""
Dtype description as a tuple ``(kind, bit-width, format string, endianness)``.
Bit-width : the number of bits as an integer
Format string : data type description format string in Apache Arrow C
Data Interface format.
Endianness : current only native endianness (``=``) is supported
Notes:
- Kind specifiers are aligned with DLPack where possible (hence the
jump to 20, leave enough room for future extension)
- Masks must be specified as boolean with either bit width 1 (for bit
masks) or 8 (for byte masks).
- Dtype width in bits was preferred over bytes
- Endianness isn't too useful, but included now in case in the future
we need to support non-native endianness
- Went with Apache Arrow format strings over NumPy format strings
because they're more complete from a dataframe perspective
- Format strings are mostly useful for datetime specification, and
for categoricals.
- For categoricals, the format string describes the type of the
categorical in the data buffer. In case of a separate encoding of
the categorical (e.g. an integer to string mapping), this can
be derived from ``self.describe_categorical``.
- Data types not included: complex, Arrow-style null, binary, decimal,
and nested (list, struct, map, union) dtypes.
"""
pass
@property
@abstractmethod
def describe_categorical(self) -> CategoricalDescription:
"""
If the dtype is categorical, there are two options:
- There are only values in the data buffer.
- There is a separate non-categorical Column encoding categorical values.
Raises TypeError if the dtype is not categorical
Returns the dictionary with description on how to interpret the data buffer:
- "is_ordered" : bool, whether the ordering of dictionary indices is
semantically meaningful.
- "is_dictionary" : bool, whether a mapping of
categorical values to other objects exists
- "categories" : Column representing the (implicit) mapping of indices to
category values (e.g. an array of cat1, cat2, ...).
None if not a dictionary-style categorical.
TBD: are there any other in-memory representations that are needed?
"""
pass
@property
@abstractmethod
def describe_null(self) -> Tuple[ColumnNullType, Any]:
"""
Return the missing value (or "null") representation the column dtype
uses, as a tuple ``(kind, value)``.
Value : if kind is "sentinel value", the actual value. If kind is a bit
mask or a byte mask, the value (0 or 1) indicating a missing value. None
otherwise.
"""
pass
@property
@abstractmethod
def null_count(self) -> Optional[int]:
"""
Number of null elements, if known.
Note: Arrow uses -1 to indicate "unknown", but None seems cleaner.
"""
pass
@property
@abstractmethod
def metadata(self) -> Dict[str, Any]:
"""
The metadata for the column. See `DataFrame.metadata` for more details.
"""
pass
@abstractmethod
def num_chunks(self) -> int:
"""
Return the number of chunks the column consists of.
"""
pass
@abstractmethod
def get_chunks(self, n_chunks: Optional[int] = None) -> Iterable["Column"]:
"""
Return an iterator yielding the chunks.
See `DataFrame.get_chunks` for details on ``n_chunks``.
"""
pass
@abstractmethod
def get_buffers(self) -> ColumnBuffers:
"""
Return a dictionary containing the underlying buffers.
The returned dictionary has the following contents:
- "data": a two-element tuple whose first element is a buffer
containing the data and whose second element is the data
buffer's associated dtype.
- "validity": a two-element tuple whose first element is a buffer
containing mask values indicating missing data and
whose second element is the mask value buffer's
associated dtype. None if the null representation is
not a bit or byte mask.
- "offsets": a two-element tuple whose first element is a buffer
containing the offset values for variable-size binary
data (e.g., variable-length strings) and whose second
element is the offsets buffer's associated dtype. None
if the data buffer does not have an associated offsets
buffer.
"""
pass
# def get_children(self) -> Iterable[Column]:
# """
# Children columns underneath the column, each object in this iterator
# must adhere to the column specification.
# """
# pass
class DataFrame(ABC):
"""
A data frame class, with only the methods required by the interchange
protocol defined.
A "data frame" represents an ordered collection of named columns.
A column's "name" must be a unique string.
Columns may be accessed by name or by position.
This could be a public data frame class, or an object with the methods and
attributes defined on this DataFrame class could be returned from the
``__dataframe__`` method of a public data frame class in a library adhering
to the dataframe interchange protocol specification.
"""
version = 0 # version of the protocol
@abstractmethod
def __dataframe__(
self, nan_as_null: bool = False, allow_copy: bool = True
) -> "DataFrame":
"""
Construct a new exchange object, potentially changing the parameters.
``nan_as_null`` is a keyword intended for the consumer to tell the
producer to overwrite null values in the data with ``NaN``.
It is intended for cases where the consumer does not support the bit
mask or byte mask that is the producer's native representation.
``allow_copy`` is a keyword that defines whether or not the library is
allowed to make a copy of the data. For example, copying data would be
necessary if a library supports strided buffers, given that this protocol
specifies contiguous buffers.
"""
pass
@property
@abstractmethod
def metadata(self) -> Dict[str, Any]:
"""
The metadata for the data frame, as a dictionary with string keys. The
contents of `metadata` may be anything, they are meant for a library
to store information that it needs to, e.g., roundtrip losslessly or
for two implementations to share data that is not (yet) part of the
interchange protocol specification. For avoiding collisions with other
entries, please add name the keys with the name of the library
followed by a period and the desired name, e.g, ``pandas.indexcol``.
"""
pass
@abstractmethod
def num_columns(self) -> int:
"""
Return the number of columns in the DataFrame.
"""
pass
@abstractmethod
def num_rows(self) -> Optional[int]:
# TODO: not happy with Optional, but need to flag it may be expensive
# why include it if it may be None - what do we expect consumers
# to do here?
"""
Return the number of rows in the DataFrame, if available.
"""
pass
@abstractmethod
def num_chunks(self) -> int:
"""
Return the number of chunks the DataFrame consists of.
"""
pass
@abstractmethod
def column_names(self) -> Iterable[str]:
"""
Return an iterator yielding the column names.
"""
pass
@abstractmethod
def get_column(self, i: int) -> Column:
"""
Return the column at the indicated position.
"""
pass
@abstractmethod
def get_column_by_name(self, name: str) -> Column:
"""
Return the column whose name is the indicated name.
"""
pass
@abstractmethod
def get_columns(self) -> Iterable[Column]:
"""
Return an iterator yielding the columns.
"""
pass
@abstractmethod
def select_columns(self, indices: Sequence[int]) -> "DataFrame":
"""
Create a new DataFrame by selecting a subset of columns by index.
"""
pass
@abstractmethod
def select_columns_by_name(self, names: Sequence[str]) -> "DataFrame":
"""
Create a new DataFrame by selecting a subset of columns by name.
"""
pass
@abstractmethod
def get_chunks(self, n_chunks: Optional[int] = None) -> Iterable["DataFrame"]:
"""
Return an iterator yielding the chunks.
By default (None), yields the chunks that the data is stored as by the
producer. If given, ``n_chunks`` must be a multiple of
``self.num_chunks()``, meaning the producer must subdivide each chunk
before yielding it.
Note that the producer must ensure that all columns are chunked the
same way.
"""
pass
|