Spaces:
Sleeping
Sleeping
File size: 31,927 Bytes
33d4721 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 |
import io
import os
import uuid
import zipfile
from dataclasses import dataclass
from typing import Dict, List, Optional
import pandas as pd
from autotrain.preprocessor.tabular import (
TabularBinaryClassificationPreprocessor,
TabularMultiClassClassificationPreprocessor,
TabularMultiColumnRegressionPreprocessor,
TabularMultiLabelClassificationPreprocessor,
TabularSingleColumnRegressionPreprocessor,
)
from autotrain.preprocessor.text import (
LLMPreprocessor,
SentenceTransformersPreprocessor,
Seq2SeqPreprocessor,
TextBinaryClassificationPreprocessor,
TextExtractiveQuestionAnsweringPreprocessor,
TextMultiClassClassificationPreprocessor,
TextSingleColumnRegressionPreprocessor,
TextTokenClassificationPreprocessor,
)
from autotrain.preprocessor.vision import (
ImageClassificationPreprocessor,
ImageRegressionPreprocessor,
ObjectDetectionPreprocessor,
)
from autotrain.preprocessor.vlm import VLMPreprocessor
def remove_non_image_files(folder):
"""
Remove non-image files from a specified folder and its subfolders.
This function iterates through all files in the given folder and its subfolders,
and removes any file that does not have an allowed image file extension. The allowed
extensions are: .jpg, .jpeg, .png, .JPG, .JPEG, .PNG, and .jsonl.
Args:
folder (str): The path to the folder from which non-image files should be removed.
Returns:
None
"""
# Define allowed image file extensions
allowed_extensions = {".jpg", ".jpeg", ".png", ".JPG", ".JPEG", ".PNG", ".jsonl"}
# Iterate through all files in the folder
for root, dirs, files in os.walk(folder):
for file in files:
# Get the file extension
file_extension = os.path.splitext(file)[1]
# If the file extension is not in the allowed list, remove the file
if file_extension.lower() not in allowed_extensions:
file_path = os.path.join(root, file)
os.remove(file_path)
print(f"Removed file: {file_path}")
# Recursively call the function on each subfolder
for subfolder in dirs:
remove_non_image_files(os.path.join(root, subfolder))
@dataclass
class AutoTrainImageClassificationDataset:
"""
A class to handle image classification datasets for AutoTrain.
Attributes:
train_data (str): Path to the training data.
token (str): Authentication token.
project_name (str): Name of the project.
username (str): Username of the project owner.
valid_data (Optional[str]): Path to the validation data. Default is None.
percent_valid (Optional[float]): Percentage of training data to use for validation. Default is None.
local (bool): Flag to indicate if the data is local. Default is False.
Methods:
__str__() -> str:
Returns a string representation of the dataset.
__post_init__():
Initializes the dataset and sets default values for validation data.
prepare():
Prepares the dataset for training by extracting and preprocessing the data.
"""
train_data: str
token: str
project_name: str
username: str
valid_data: Optional[str] = None
percent_valid: Optional[float] = None
local: bool = False
def __str__(self) -> str:
info = f"Dataset: {self.project_name} ({self.task})\n"
info += f"Train data: {self.train_data}\n"
info += f"Valid data: {self.valid_data}\n"
return info
def __post_init__(self):
self.task = "image_multi_class_classification"
if not self.valid_data and self.percent_valid is None:
self.percent_valid = 0.2
elif self.valid_data and self.percent_valid is not None:
raise ValueError("You can only specify one of valid_data or percent_valid")
elif self.valid_data:
self.percent_valid = 0.0
def prepare(self):
valid_dir = None
if not isinstance(self.train_data, str):
cache_dir = os.environ.get("HF_HOME")
if not cache_dir:
cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface")
random_uuid = uuid.uuid4()
train_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(train_dir, exist_ok=True)
self.train_data.seek(0)
content = self.train_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(train_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(train_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(train_dir)
if self.valid_data:
random_uuid = uuid.uuid4()
valid_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(valid_dir, exist_ok=True)
self.valid_data.seek(0)
content = self.valid_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(valid_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(valid_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(valid_dir)
else:
train_dir = self.train_data
if self.valid_data:
valid_dir = self.valid_data
preprocessor = ImageClassificationPreprocessor(
train_data=train_dir,
valid_data=valid_dir,
token=self.token,
project_name=self.project_name,
username=self.username,
local=self.local,
)
return preprocessor.prepare()
@dataclass
class AutoTrainObjectDetectionDataset:
"""
A dataset class for AutoTrain object detection tasks.
Attributes:
train_data (str): Path to the training data.
token (str): Authentication token.
project_name (str): Name of the project.
username (str): Username of the project owner.
valid_data (Optional[str]): Path to the validation data. Default is None.
percent_valid (Optional[float]): Percentage of training data to be used for validation. Default is None.
local (bool): Flag indicating if the data is local. Default is False.
Methods:
__str__() -> str:
Returns a string representation of the dataset.
__post_init__():
Initializes the dataset and sets default values for validation data.
prepare():
Prepares the dataset for training by extracting and preprocessing the data.
"""
train_data: str
token: str
project_name: str
username: str
valid_data: Optional[str] = None
percent_valid: Optional[float] = None
local: bool = False
def __str__(self) -> str:
info = f"Dataset: {self.project_name} ({self.task})\n"
info += f"Train data: {self.train_data}\n"
info += f"Valid data: {self.valid_data}\n"
return info
def __post_init__(self):
self.task = "image_object_detection"
if not self.valid_data and self.percent_valid is None:
self.percent_valid = 0.2
elif self.valid_data and self.percent_valid is not None:
raise ValueError("You can only specify one of valid_data or percent_valid")
elif self.valid_data:
self.percent_valid = 0.0
def prepare(self):
valid_dir = None
if not isinstance(self.train_data, str):
cache_dir = os.environ.get("HF_HOME")
if not cache_dir:
cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface")
random_uuid = uuid.uuid4()
train_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(train_dir, exist_ok=True)
self.train_data.seek(0)
content = self.train_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(train_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(train_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(train_dir)
if self.valid_data:
random_uuid = uuid.uuid4()
valid_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(valid_dir, exist_ok=True)
self.valid_data.seek(0)
content = self.valid_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(valid_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(valid_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(valid_dir)
else:
train_dir = self.train_data
if self.valid_data:
valid_dir = self.valid_data
preprocessor = ObjectDetectionPreprocessor(
train_data=train_dir,
valid_data=valid_dir,
token=self.token,
project_name=self.project_name,
username=self.username,
local=self.local,
)
return preprocessor.prepare()
@dataclass
class AutoTrainVLMDataset:
"""
A class to handle dataset for AutoTrain Vision-Language Model (VLM) task.
Attributes:
-----------
train_data : str
Path to the training data or a file-like object containing the training data.
token : str
Authentication token for accessing the dataset.
project_name : str
Name of the project.
username : str
Username of the project owner.
column_mapping : Dict[str, str]
Mapping of columns in the dataset.
valid_data : Optional[str], default=None
Path to the validation data or a file-like object containing the validation data.
percent_valid : Optional[float], default=None
Percentage of the training data to be used for validation if `valid_data` is not provided.
local : bool, default=False
Flag indicating whether the dataset is stored locally.
Methods:
--------
__str__() -> str:
Returns a string representation of the dataset.
__post_init__():
Initializes the dataset and sets default values for validation data percentage.
prepare():
Prepares the dataset for training by extracting and processing the data.
"""
train_data: str
token: str
project_name: str
username: str
column_mapping: Dict[str, str]
valid_data: Optional[str] = None
percent_valid: Optional[float] = None
local: bool = False
def __str__(self) -> str:
info = f"Dataset: {self.project_name} ({self.task})\n"
info += f"Train data: {self.train_data}\n"
info += f"Valid data: {self.valid_data}\n"
return info
def __post_init__(self):
self.task = "vlm"
if not self.valid_data and self.percent_valid is None:
self.percent_valid = 0.2
elif self.valid_data and self.percent_valid is not None:
raise ValueError("You can only specify one of valid_data or percent_valid")
elif self.valid_data:
self.percent_valid = 0.0
def prepare(self):
valid_dir = None
if not isinstance(self.train_data, str):
cache_dir = os.environ.get("HF_HOME")
if not cache_dir:
cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface")
random_uuid = uuid.uuid4()
train_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(train_dir, exist_ok=True)
self.train_data.seek(0)
content = self.train_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(train_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(train_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(train_dir)
if self.valid_data:
random_uuid = uuid.uuid4()
valid_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(valid_dir, exist_ok=True)
self.valid_data.seek(0)
content = self.valid_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(valid_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(valid_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(valid_dir)
else:
train_dir = self.train_data
if self.valid_data:
valid_dir = self.valid_data
preprocessor = VLMPreprocessor(
train_data=train_dir,
valid_data=valid_dir,
token=self.token,
project_name=self.project_name,
username=self.username,
local=self.local,
column_mapping=self.column_mapping,
)
return preprocessor.prepare()
@dataclass
class AutoTrainImageRegressionDataset:
"""
AutoTrainImageRegressionDataset is a class designed for handling image regression datasets in the AutoTrain framework.
Attributes:
train_data (str): Path to the training data.
token (str): Authentication token.
project_name (str): Name of the project.
username (str): Username of the project owner.
valid_data (Optional[str]): Path to the validation data. Default is None.
percent_valid (Optional[float]): Percentage of training data to be used for validation if valid_data is not provided. Default is None.
local (bool): Flag indicating if the data is local. Default is False.
Methods:
__str__() -> str:
Returns a string representation of the dataset information.
__post_init__():
Initializes the task attribute and sets the percent_valid attribute based on the presence of valid_data.
prepare():
Prepares the dataset for training by extracting and organizing the data, and returns a preprocessor object.
"""
train_data: str
token: str
project_name: str
username: str
valid_data: Optional[str] = None
percent_valid: Optional[float] = None
local: bool = False
def __str__(self) -> str:
info = f"Dataset: {self.project_name} ({self.task})\n"
info += f"Train data: {self.train_data}\n"
info += f"Valid data: {self.valid_data}\n"
return info
def __post_init__(self):
self.task = "image_single_column_regression"
if not self.valid_data and self.percent_valid is None:
self.percent_valid = 0.2
elif self.valid_data and self.percent_valid is not None:
raise ValueError("You can only specify one of valid_data or percent_valid")
elif self.valid_data:
self.percent_valid = 0.0
def prepare(self):
valid_dir = None
if not isinstance(self.train_data, str):
cache_dir = os.environ.get("HF_HOME")
if not cache_dir:
cache_dir = os.path.join(os.path.expanduser("~"), ".cache", "huggingface")
random_uuid = uuid.uuid4()
train_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(train_dir, exist_ok=True)
self.train_data.seek(0)
content = self.train_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(train_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(train_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(train_dir)
if self.valid_data:
random_uuid = uuid.uuid4()
valid_dir = os.path.join(cache_dir, "autotrain", str(random_uuid))
os.makedirs(valid_dir, exist_ok=True)
self.valid_data.seek(0)
content = self.valid_data.read()
bytes_io = io.BytesIO(content)
zip_ref = zipfile.ZipFile(bytes_io, "r")
zip_ref.extractall(valid_dir)
# remove the __MACOSX directory
macosx_dir = os.path.join(valid_dir, "__MACOSX")
if os.path.exists(macosx_dir):
os.system(f"rm -rf {macosx_dir}")
remove_non_image_files(valid_dir)
else:
train_dir = self.train_data
if self.valid_data:
valid_dir = self.valid_data
preprocessor = ImageRegressionPreprocessor(
train_data=train_dir,
valid_data=valid_dir,
token=self.token,
project_name=self.project_name,
username=self.username,
local=self.local,
)
return preprocessor.prepare()
@dataclass
class AutoTrainDataset:
"""
AutoTrainDataset class for handling various types of datasets and preprocessing tasks.
Attributes:
train_data (List[str]): List of file paths or DataFrames for training data.
task (str): The type of task to perform (e.g., "text_binary_classification").
token (str): Authentication token.
project_name (str): Name of the project.
username (Optional[str]): Username of the project owner. Defaults to None.
column_mapping (Optional[Dict[str, str]]): Mapping of column names. Defaults to None.
valid_data (Optional[List[str]]): List of file paths or DataFrames for validation data. Defaults to None.
percent_valid (Optional[float]): Percentage of training data to use for validation. Defaults to None.
convert_to_class_label (Optional[bool]): Whether to convert labels to class labels. Defaults to False.
local (bool): Whether the data is local. Defaults to False.
ext (Optional[str]): File extension of the data files. Defaults to "csv".
Methods:
__str__(): Returns a string representation of the dataset.
__post_init__(): Initializes validation data and preprocesses the data.
_preprocess_data(): Preprocesses the training and validation data.
num_samples(): Returns the total number of samples in the dataset.
prepare(): Prepares the dataset for the specified task using the appropriate preprocessor.
"""
train_data: List[str]
task: str
token: str
project_name: str
username: Optional[str] = None
column_mapping: Optional[Dict[str, str]] = None
valid_data: Optional[List[str]] = None
percent_valid: Optional[float] = None
convert_to_class_label: Optional[bool] = False
local: bool = False
ext: Optional[str] = "csv"
def __str__(self) -> str:
info = f"Dataset: {self.project_name} ({self.task})\n"
info += f"Train data: {self.train_data}\n"
info += f"Valid data: {self.valid_data}\n"
info += f"Column mapping: {self.column_mapping}\n"
return info
def __post_init__(self):
if self.valid_data is None:
self.valid_data = []
if not self.valid_data and self.percent_valid is None:
self.percent_valid = 0.2
elif self.valid_data and self.percent_valid is not None:
raise ValueError("You can only specify one of valid_data or percent_valid")
elif self.valid_data:
self.percent_valid = 0.0
self.train_df, self.valid_df = self._preprocess_data()
def _preprocess_data(self):
train_df = []
for file in self.train_data:
if isinstance(file, pd.DataFrame):
train_df.append(file)
else:
if self.ext == "jsonl":
train_df.append(pd.read_json(file, lines=True))
else:
train_df.append(pd.read_csv(file))
if len(train_df) > 1:
train_df = pd.concat(train_df)
else:
train_df = train_df[0]
valid_df = None
if len(self.valid_data) > 0:
valid_df = []
for file in self.valid_data:
if isinstance(file, pd.DataFrame):
valid_df.append(file)
else:
if self.ext == "jsonl":
valid_df.append(pd.read_json(file, lines=True))
else:
valid_df.append(pd.read_csv(file))
if len(valid_df) > 1:
valid_df = pd.concat(valid_df)
else:
valid_df = valid_df[0]
return train_df, valid_df
@property
def num_samples(self):
return len(self.train_df) + len(self.valid_df) if self.valid_df is not None else len(self.train_df)
def prepare(self):
if self.task == "text_binary_classification":
text_column = self.column_mapping["text"]
label_column = self.column_mapping["label"]
preprocessor = TextBinaryClassificationPreprocessor(
train_data=self.train_df,
text_column=text_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
convert_to_class_label=self.convert_to_class_label,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "text_multi_class_classification":
text_column = self.column_mapping["text"]
label_column = self.column_mapping["label"]
preprocessor = TextMultiClassClassificationPreprocessor(
train_data=self.train_df,
text_column=text_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
convert_to_class_label=self.convert_to_class_label,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "text_token_classification":
text_column = self.column_mapping["text"]
label_column = self.column_mapping["label"]
preprocessor = TextTokenClassificationPreprocessor(
train_data=self.train_df,
text_column=text_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
convert_to_class_label=self.convert_to_class_label,
)
return preprocessor.prepare()
elif self.task == "text_single_column_regression":
text_column = self.column_mapping["text"]
label_column = self.column_mapping["label"]
preprocessor = TextSingleColumnRegressionPreprocessor(
train_data=self.train_df,
text_column=text_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "seq2seq":
text_column = self.column_mapping["text"]
label_column = self.column_mapping["label"]
preprocessor = Seq2SeqPreprocessor(
train_data=self.train_df,
text_column=text_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "lm_training":
text_column = self.column_mapping["text"]
prompt_column = self.column_mapping.get("prompt")
rejected_text_column = self.column_mapping.get("rejected_text")
preprocessor = LLMPreprocessor(
train_data=self.train_df,
text_column=text_column,
prompt_column=prompt_column,
rejected_text_column=rejected_text_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "sentence_transformers":
sentence1_column = self.column_mapping["sentence1"]
sentence2_column = self.column_mapping["sentence2"]
sentence3_column = self.column_mapping.get("sentence3")
target_column = self.column_mapping.get("target")
preprocessor = SentenceTransformersPreprocessor(
train_data=self.train_df,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
sentence1_column=sentence1_column,
sentence2_column=sentence2_column,
sentence3_column=sentence3_column,
target_column=target_column,
convert_to_class_label=self.convert_to_class_label,
)
return preprocessor.prepare()
elif self.task == "text_extractive_question_answering":
text_column = self.column_mapping["text"]
question_column = self.column_mapping["question"]
answer_column = self.column_mapping["answer"]
preprocessor = TextExtractiveQuestionAnsweringPreprocessor(
train_data=self.train_df,
text_column=text_column,
question_column=question_column,
answer_column=answer_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "tabular_binary_classification":
id_column = self.column_mapping["id"]
label_column = self.column_mapping["label"][0]
if len(id_column.strip()) == 0:
id_column = None
preprocessor = TabularBinaryClassificationPreprocessor(
train_data=self.train_df,
id_column=id_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "tabular_multi_class_classification":
id_column = self.column_mapping["id"]
label_column = self.column_mapping["label"][0]
if len(id_column.strip()) == 0:
id_column = None
preprocessor = TabularMultiClassClassificationPreprocessor(
train_data=self.train_df,
id_column=id_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "tabular_single_column_regression":
id_column = self.column_mapping["id"]
label_column = self.column_mapping["label"][0]
if len(id_column.strip()) == 0:
id_column = None
preprocessor = TabularSingleColumnRegressionPreprocessor(
train_data=self.train_df,
id_column=id_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "tabular_multi_column_regression":
id_column = self.column_mapping["id"]
label_column = self.column_mapping["label"]
if len(id_column.strip()) == 0:
id_column = None
preprocessor = TabularMultiColumnRegressionPreprocessor(
train_data=self.train_df,
id_column=id_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
elif self.task == "tabular_multi_label_classification":
id_column = self.column_mapping["id"]
label_column = self.column_mapping["label"]
if len(id_column.strip()) == 0:
id_column = None
preprocessor = TabularMultiLabelClassificationPreprocessor(
train_data=self.train_df,
id_column=id_column,
label_column=label_column,
username=self.username,
project_name=self.project_name,
valid_data=self.valid_df,
test_size=self.percent_valid,
token=self.token,
seed=42,
local=self.local,
)
return preprocessor.prepare()
else:
raise ValueError(f"Task {self.task} not supported")
|