__init__.py 16.8 KB
Newer Older
1
2
import abc
import collections
3
4
import logging
import os
5
from functools import partial
6
from typing import Dict, List, Union
&'s avatar
& committed
7

8
from lm_eval import utils
9
from lm_eval.api.task import ConfigurableTask, Task
lintangsutawika's avatar
lintangsutawika committed
10

11

12
13
14
class TaskManager:
    """TaskManager indexes all tasks from the default `lm_eval/tasks/`
    and an optional directory if provided.
15

16
17
    """

18
    def __init__(self, verbosity="INFO", include_path=None) -> None:
19
20
21
22
23
        self.verbosity = verbosity
        self.include_path = include_path
        self.logger = utils.eval_logger
        self.logger.setLevel(getattr(logging, f"{verbosity}"))

24
        self._task_index = self.initialize_tasks(include_path=include_path)
25
        self._all_tasks = sorted(list(self._task_index.keys()))
26

27
        self.task_group_map = collections.defaultdict(list)
28

29
30
31
32
33
34
35
36
37
38
39
40
41
42
    def initialize_tasks(self, include_path: str = None):
        """Creates an dictionary of tasks index.

        :param include_path: str = None
            An additional path to be searched for tasks

        :return
            Dictionary of task names as key and task metadata
        """
        all_paths = [os.path.dirname(os.path.abspath(__file__)) + "/"]
        if include_path is not None:
            if isinstance(include_path, str):
                include_path = [include_path]
            all_paths.extend(include_path)
43

44
45
46
47
        task_index = {}
        for task_dir in all_paths:
            tasks = self._get_task_and_group(task_dir)
            task_index = {**tasks, **task_index}
lintangsutawika's avatar
format  
lintangsutawika committed
48

49
50
51
52
53
54
55
56
57
58
59
        return task_index

    @property
    def all_tasks(self):
        return self._all_tasks

    @property
    def task_index(self):
        return self._task_index

    def match_tasks(self, task_list):
60
        return utils.pattern_match(task_list, self.all_tasks)
61
62
63
64
65
66

    def _name_is_registered(self, name):
        if name in self.all_tasks:
            return True
        return False

67
    def _name_is_task(self, name) -> bool:
68
69
70
71
72
        if self._name_is_registered(name) and ("task" in self.task_index[name]["type"]):
            return True
        return False

    def _name_is_group(self, name):
73
74
75
        if self._name_is_registered(name) and (
            self.task_index[name]["type"] == "group"
        ):
76
77
78
79
            return True
        return False

    def _name_is_python_task(self, name):
80
81
82
        if self._name_is_registered(name) and (
            self.task_index[name]["type"] == "python_task"
        ):
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
            return True
        return False

    def _config_is_task(self, config):
        if ("task" in config) and isinstance(config["task"], str):
            return True
        return False

    def _config_is_group(self, config):
        if ("task" in config) and isinstance(config["task"], list):
            return True
        return False

    def _config_is_python_task(self, config):
        if "class" in config:
            return True
        return False

    def _get_yaml_path(self, name):
        assert name in self.task_index
        return self.task_index[name]["yaml_path"]

    def _get_config(self, name):
        assert name in self.task_index
        yaml_path = self._get_yaml_path(name)
        if yaml_path == -1:
            return {}
        else:
            return utils.load_yaml_config(yaml_path, mode="full")

    def _get_tasklist(self, name):
114
        assert self._name_is_task(name) is False
115
116
117
118
119
120
121
122
123
124
125
126
        return self.task_index[name]["task"]

    def _process_alias(self, config, group=None):
        # If the group is not the same as the original
        # group which the group alias was intended for,
        # Set the group_alias to None instead.
        if ("group_alias" in config) and ("group" in config) and group is not None:
            if config["group"] != group:
                config["group_alias"] = None
        return config

    def _load_individual_task_or_group(
127
128
129
130
131
132
        self,
        name_or_config: Union[str, dict] = None,
        parent_name: str = None,
        update_config: dict = None,
        yaml_path: str = None,
    ) -> ConfigurableTask:
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
        def load_task(config, task, group=None, yaml_path=None):
            if "include" in config:
                assert yaml_path is not None
                config.update(
                    utils.load_yaml_config(
                        yaml_path,
                        yaml_config={"include": config.pop("include")},
                        mode="full",
                    )
                )
            if self._config_is_python_task(config):
                task_object = config["class"]()
            else:
                config = self._process_alias(config, group=group)
                task_object = ConfigurableTask(config=config)
            if group is not None:
                task_object = (group, task_object)
            return {task: task_object}

        if isinstance(name_or_config, str):
            if update_config is not None:
                # Process name_or_config as a dict instead
                name_or_config = {"task": name_or_config, **update_config}
            elif self._name_is_task(name_or_config):
                task_config = self._get_config(name_or_config)
                return load_task(task_config, task=name_or_config, group=parent_name)
159
            else:
160
161
162
163
164
165
166
167
168
169
170
                group_name = name_or_config
                subtask_list = self._get_tasklist(name_or_config)
                if subtask_list == -1:
                    group_config = self._get_config(name_or_config)
                    subtask_list = group_config["task"]

                # This checks if we're at the root.
                if parent_name is None:
                    group_config = self._get_config(name_or_config)
                    if set(group_config.keys()) > set(["task", "group"]):
                        update_config = {
171
172
173
                            k: v
                            for k, v in group_config.items()
                            if k not in ["task", "group"]
174
175
                        }
                    yaml_path = self._get_yaml_path(group_name)
176

177
178
179
                    if (update_config is not None) and ("group_alias" in update_config):
                        group_name = update_config["group_alias"]
                        update_config.pop("group_alias")
180

181
182
        if isinstance(name_or_config, dict):
            if update_config is not None:
183
                name_or_config = {
184
185
                    **name_or_config,
                    **update_config,
186
187
                }

188
189
190
191
192
193
            if self._config_is_task(name_or_config):
                name = name_or_config["task"]
                # If the name is registered as a group
                # if self._name_is_task(name) is False:
                if self._name_is_group(name):
                    group_name = name
194
195
196
                    update_config = {
                        k: v for k, v in name_or_config.items() if k != "task"
                    }
197
198
199
200
201
202
203
204
205
206
                    subtask_list = self._get_tasklist(name)
                    if subtask_list == -1:
                        subtask_list = self._get_config(name)["task"]
                else:
                    if self._name_is_registered(name):
                        base_task_config = self._get_config(name)

                        # Check if this is a duplicate.
                        if parent_name is not None:
                            name_or_config["group"] = parent_name
207
208
209
210
211
212
213
214
                            num_duplicate = len(
                                list(
                                    filter(
                                        lambda x: x.startswith(name),
                                        self.task_group_map[parent_name],
                                    )
                                )
                            )
215
216
217
218
                            if num_duplicate > 0:
                                name = f"{name}-{num_duplicate}"
                            self.task_group_map[parent_name].append(name)

219
220
221
222
                        task_config = {
                            **base_task_config,
                            **name_or_config,
                        }
223
224
                    else:
                        task_config = name_or_config
225
226
227
                    return load_task(
                        task_config, task=name, group=parent_name, yaml_path=yaml_path
                    )
228
229
230
231
232
            else:
                group_name = name_or_config["group"]
                subtask_list = name_or_config["task"]
                if set(name_or_config.keys()) > set(["task", "group"]):
                    update_config = {
233
234
235
                        k: v
                        for k, v in name_or_config.items()
                        if k not in ["task", "group"]
236
                    }
237

238
        all_subtasks = {}
239
        if parent_name is not None:
240
            all_subtasks = {group_name: (parent_name, None)}
241

242
243
244
245
246
247
248
249
250
251
        fn = partial(
            self._load_individual_task_or_group,
            parent_name=group_name,
            update_config=update_config,
            yaml_path=yaml_path,
        )
        all_subtasks = {
            **all_subtasks,
            **dict(collections.ChainMap(*map(fn, subtask_list))),
        }
252
        return all_subtasks
253

254
255
    def load_task_or_group(self, task_list: Union[str, list] = None) -> dict:
        """Loads a dictionary of task objects from a list
256

257
258
        :param task_list: Union[str, list] = None
            Single string or list of string of task names to be loaded
259

260
261
262
263
264
        :return
            Dictionary of task objects
        """
        if isinstance(task_list, str):
            task_list = [task_list]
265

266
        all_loaded_tasks = dict(
267
            collections.ChainMap(*map(self._load_individual_task_or_group, task_list))
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
        )
        return all_loaded_tasks

    def load_config(self, config: Dict):
        return self._load_individual_task_or_group(config)

    def _get_task_and_group(self, task_dir: str):
        """Creates an dictionary of tasks index with the following metadata,
        - `type`, that can be either `task`, `python_task`, or `group`.
            `task` refer to regular task configs, `python_task` are special
            yaml files that only consists of `task` and `class` parameters.
            `group` are group configs.
        - `yaml_path`, path to the yaml file. If the entry is a `group` that
            was configured through a task config, the yaml_path will be -1
            and all subtasks will be listed in `task` (see below)
        - `task`, reserved for entries with `type` as `group`. This will list
            all subtasks. When a group config is created (as opposed to task
            config having `group` parameter set), this will be set to -1 to
            avoid recursive indexing. The whole list of subtasks will be loaded
            at evaluation.

        :param task_dir: str
            A directory to check for tasks

        :return
            Dictionary of task names as key and task metadata
        """
        tasks_and_groups = collections.defaultdict()
        for root, _, file_list in os.walk(task_dir):
            for f in file_list:
                if f.endswith(".yaml"):
                    yaml_path = os.path.join(root, f)
                    config = utils.load_yaml_config(yaml_path, mode="simple")
                    if self._config_is_python_task(config):
                        # This is a python class config
                        tasks_and_groups[config["task"]] = {
                            "type": "python_task",
                            "yaml_path": yaml_path,
                        }
                    elif self._config_is_group(config):
                        # This is a group config
                        tasks_and_groups[config["group"]] = {
                            "type": "group",
311
312
313
314
315
                            "task": -1,  # This signals that
                            # we don't need to know
                            # the task list for indexing
                            # as it can be loaded
                            # when called.
316
317
                            "yaml_path": yaml_path,
                        }
lintangsutawika's avatar
lintangsutawika committed
318

319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
                        # # Registered the level 1 tasks from a group config
                        # for config in config["task"]:
                        #     if isinstance(config, dict) and self._config_is_task(config):
                        #         task = config["task"]
                        #         tasks_and_groups[task] = {
                        #             "type": "task",
                        #             "yaml_path": yaml_path,
                        #             }

                    elif self._config_is_task(config):
                        # This is a task config
                        task = config["task"]
                        tasks_and_groups[task] = {
                            "type": "task",
                            "yaml_path": yaml_path,
334
                        }
335

336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
                        if "group" in config:
                            groups = config["group"]
                            if isinstance(config["group"], str):
                                groups = [groups]

                            for group in groups:
                                if group not in tasks_and_groups:
                                    tasks_and_groups[group] = {
                                        "type": "group",
                                        "task": [task],
                                        "yaml_path": -1,
                                    }
                                else:
                                    tasks_and_groups[group]["task"].append(task)
                    else:
                        self.logger.debug(f"File {f} in {root} could not be loaded")

        return tasks_and_groups
lintangsutawika's avatar
lintangsutawika committed
354

355

356
357
358
359
360
361
362
363
def include_path(task_dir):
    logger = utils.eval_logger
    logger.setLevel(getattr(logging, "INFO"))
    logger.info(
        "To still use tasks loaded from args.include_path,"
        "see an example of the new TaskManager API in https://github.com/EleutherAI/lm-evaluation-harness/blob/main/docs/interface.md#external-library-usage"
    )
    return 0
lintangsutawika's avatar
lintangsutawika committed
364

365

366
367
368
369
370
371
372
373
374
def initialize_tasks(verbosity="INFO"):
    logger = utils.eval_logger
    logger.setLevel(getattr(logging, f"{verbosity}"))
    logger.info(
        "lm_eval.tasks.initialize_tasks() is deprecated and no longer necessary. "
        "It will be removed in v0.4.2 release. "
        "TaskManager will instead be used."
    )
    return 0
lintangsutawika's avatar
lintangsutawika committed
375

376

377
378
379
380
381
382
383
def get_task_name_from_config(task_config: Dict[str, str]) -> str:
    if "task" in task_config:
        return task_config["task"]
    if "dataset_name" in task_config:
        return "{dataset_path}_{dataset_name}".format(**task_config)
    else:
        return "{dataset_path}".format(**task_config)
lintangsutawika's avatar
lintangsutawika committed
384

385

lintangsutawika's avatar
lintangsutawika committed
386
def get_task_name_from_object(task_object):
387
388
    if hasattr(task_object, "config"):
        return task_object._config["task"]
lintangsutawika's avatar
lintangsutawika committed
389
390
391
392
393
394
395
396
397

    # TODO: scrap this
    # this gives a mechanism for non-registered tasks to have a custom name anyways when reporting
    return (
        task_object.EVAL_HARNESS_NAME
        if hasattr(task_object, "EVAL_HARNESS_NAME")
        else type(task_object).__name__
    )

398
399
400
401

def get_task_dict(
    task_name_list: List[Union[str, Dict, Task]], task_manager: TaskManager = None
):
402
    """Creates a dictionary of task objects from either a name of task, config, or prepared Task object.
lintangsutawika's avatar
lintangsutawika committed
403

404
405
406
407
408
409
410
    :param task_name_list: List[Union[str, Dict, Task]]
        Name of model or LM object, see lm_eval.models.get_model
    :param task_manager: TaskManager = None
        A TaskManager object that stores indexed tasks. If not set,
        task_manager will load one. This should be set by the user
        if there are additional paths that want to be included
        via `include_path`
411

412
413
414
415
    :return
        Dictionary of task objects
    """
    task_name_from_string_dict = {}
416
417
418
    task_name_from_config_dict = {}
    task_name_from_object_dict = {}

419
    if isinstance(task_name_list, str):
lintangsutawika's avatar
lintangsutawika committed
420
421
        task_name_list = [task_name_list]

422
423
424
425
426
    string_task_name_list = [task for task in task_name_list if isinstance(task, str)]
    others_task_name_list = [task for task in task_name_list if ~isinstance(task, str)]
    if len(string_task_name_list) > 0:
        if task_manager is None:
            task_manager = TaskManager()
lintangsutawika's avatar
lintangsutawika committed
427

428
429
430
        task_name_from_string_dict = task_manager.load_task_or_group(
            string_task_name_list
        )
431

432
433
    for task_element in others_task_name_list:
        if isinstance(task_element, dict):
434
435
            task_name_from_config_dict = {
                **task_name_from_config_dict,
436
                **task_manager.load_config(config=task_element),
437
438
439
440
441
            }

        elif isinstance(task_element, Task):
            task_name_from_object_dict = {
                **task_name_from_object_dict,
lintangsutawika's avatar
lintangsutawika committed
442
                get_task_name_from_object(task_element): task_element,
443
            }
lintangsutawika's avatar
lintangsutawika committed
444

445
    assert set(task_name_from_string_dict.keys()).isdisjoint(
lintangsutawika's avatar
lintangsutawika committed
446
447
        set(task_name_from_object_dict.keys())
    )
lintangsutawika's avatar
lintangsutawika committed
448
    return {
449
        **task_name_from_string_dict,
lintangsutawika's avatar
lintangsutawika committed
450
        **task_name_from_config_dict,
451
        **task_name_from_object_dict,
lintangsutawika's avatar
lintangsutawika committed
452
    }