__init__.py 8.93 KB
Newer Older
1
import os
2
import abc
lintangsutawika's avatar
lintangsutawika committed
3
import yaml
4
import collections
lintangsutawika's avatar
lintangsutawika committed
5

lintangsutawika's avatar
lintangsutawika committed
6
from functools import partial
7
from typing import List, Union, Dict
&'s avatar
& committed
8

9
from lm_eval import utils
10
from lm_eval import prompts
11
from lm_eval.api.task import TaskConfig, Task, ConfigurableTask
lintangsutawika's avatar
lintangsutawika committed
12

lintangsutawika's avatar
lintangsutawika committed
13
import logging
lintangsutawika's avatar
lintangsutawika committed
14

lintangsutawika's avatar
lintangsutawika committed
15
# import python tasks
16
17
18
19
20
21
22
23
24
25
26
import squadv2
import scrolls
python_tasks = {
    "squadv2": squadv2.task.SQuAD2,
    "scrolls_quality": scrolls.task.QuALITY,
    "scrolls_narrativeqa": scrolls.task.NarrativeQA,
    "scrolls_contractnli": scrolls.task.ContractNLI,
    "scrolls_govreport": scrolls.task.GovReport,
    "scrolls_summscreenfd": scrolls.task.SummScreenFD,
    "scrolls_qmsum": scrolls.task.QMSum,
}
lintangsutawika's avatar
lintangsutawika committed
27

28
eval_logger = utils.eval_logger
29

lintangsutawika's avatar
lintangsutawika committed
30

31
class TaskManager(abc.ABC):
32

33
    def __init__(
lintangsutawika's avatar
lintangsutawika committed
34
        self,
35
36
37
        verbosity="INFO",
        include_path=None
        ) -> None:
38

lintangsutawika's avatar
lintangsutawika committed
39
40
        self.verbosity = verbosity
        self.include_path = include_path
lintangsutawika's avatar
lintangsutawika committed
41
        self.logger = eval_logger.setLevel(getattr(logging, f"{verbosity}"))
lintangsutawika's avatar
lintangsutawika committed
42
43

        self.ALL_TASKS = self.initialize_tasks(
44
45
            include_path=include_path
            )
46
            #  + {k:v, "type":"task" for k,v in python_tasks.items()}
47

lintangsutawika's avatar
lintangsutawika committed
48
    def initialize_tasks(self, include_path=None):
lintangsutawika's avatar
lintangsutawika committed
49

lintangsutawika's avatar
lintangsutawika committed
50
51
52
53
54
55
56
57
        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)

        ALL_TASKS = {}
        for task_dir in all_paths:
lintangsutawika's avatar
lintangsutawika committed
58
            tasks = self._get_task_and_group(task_dir)
lintangsutawika's avatar
lintangsutawika committed
59
60
61
62
            ALL_TASKS = {**tasks, **ALL_TASKS}

        return ALL_TASKS

63
    def all_tasks(self):
lintangsutawika's avatar
lintangsutawika committed
64
        return sorted(list(self.ALL_TASKS.keys()))
65

lintangsutawika's avatar
lintangsutawika committed
66
67
68
69
70
71
    def _name_is_registered(self, name):
        if name in self.ALL_TASKS:
            return True
        return False

    def _name_is_task(self, name):
72
        if self._name_is_registered(name) and (self.ALL_TASKS[name]["type"] == "task"):
lintangsutawika's avatar
lintangsutawika committed
73
74
75
76
            return True
        return False

    def _config_is_task(self, config):
77
        if set(config.keys()) <= ["group", "task", "weight_by_size"]:
lintangsutawika's avatar
lintangsutawika committed
78
79
80
            return False
        return True

lintangsutawika's avatar
lintangsutawika committed
81
82
83
84
    def _get_yaml_path(self, name):
        assert name in self.ALL_TASKS
        return self.ALL_TASKS[name]["yaml_path"]

lintangsutawika's avatar
lintangsutawika committed
85
86
    def _get_config(self, name):
        assert name in self.ALL_TASKS
lintangsutawika's avatar
lintangsutawika committed
87
        yaml_path = self._get_yaml_path(name)
lintangsutawika's avatar
lintangsutawika committed
88
89
90
91
92
93
        return utils.load_yaml_config(yaml_path)

    def _get_tasklist(self, name):
        assert self._name_is_task(name) == False
        return self.ALL_TASKS[name]["task"]

94
95
96
97
98
99
    def _load_individual_task_or_group(
            self,
            name_or_config: Union[str, dict] = None,
            parent_name: str = None,
            update_config: dict = None
        ) -> ConfigurableTask:
lintangsutawika's avatar
lintangsutawika committed
100

lintangsutawika's avatar
lintangsutawika committed
101
102
103
104
105
106
        def load_task(config, task, group=None):
            task_object = ConfigurableTask(config=config)
            if group is not None:
                task_object = (group, task_object)
            return {task: task_object}

lintangsutawika's avatar
lintangsutawika committed
107
        if isinstance(name_or_config, str):
108
109
110
            if update_config is not None:
                name_or_config = {"task": name_or_config, **update_config}
            elif self._name_is_task(name_or_config):
lintangsutawika's avatar
lintangsutawika committed
111
                task_config = self._get_config(name_or_config)
lintangsutawika's avatar
lintangsutawika committed
112
                return load_task(task_config, task=name_or_config, group=parent_name)
113
            else:
lintangsutawika's avatar
lintangsutawika committed
114
115
                group_name = name_or_config
                subtask_list = self._get_tasklist(name_or_config)
116
                if subtask_list == -1:
lintangsutawika's avatar
lintangsutawika committed
117
118
                    subtask_list = self._get_config(name_or_config)["task"]

119
120
121
122
123
124
125
126
        if isinstance(name_or_config, dict):

            if update_config is not None:
                name_or_config={
                    **name_or_config,
                    **update_config,
                }

lintangsutawika's avatar
lintangsutawika committed
127
            if self._config_is_task(name_or_config):
128
129
130
131
132
133
134
                name = name_or_config["task"]
                if self._name_is_task(name) is False:
                    group_name = name
                    update_config = {k:v for k,v in name_or_config.items() if k is not "task"}
                    subtask_list = self._get_tasklist(name)
                    if subtask_list == -1:
                        subtask_list = self._get_config(name)["task"]
135
                else:
136
137
138
139
140
141
142
143
144
                    if self._name_is_registered(name):
                        base_task_config = self._get_config(name)
                        task_config={
                                **base_task_config,
                                **name_or_config,
                            }
                    else:
                        task_config = name_or_config
                    return load_task(task_config, task=name, group=parent_name)
145
            else:
lintangsutawika's avatar
lintangsutawika committed
146
147
148
                group_name = name_or_config["group"]
                subtask_list = name_or_config["task"]

lintangsutawika's avatar
lintangsutawika committed
149
        if (self._name_is_registered(group_name) is False) or (self._get_yaml_path(group_name) == -1):
lintangsutawika's avatar
lintangsutawika committed
150
151
152
153
            all_subtasks = {group_name: (parent_name, None)}
        else:
            all_subtasks = {}

154
        fn = partial(self._load_individual_task_or_group, parent_name=group_name, update_config=update_config)
lintangsutawika's avatar
lintangsutawika committed
155
        all_subtasks = {**all_subtasks, **dict(collections.ChainMap(*map(fn, subtask_list)))}
lintangsutawika's avatar
lintangsutawika committed
156
157
        return all_subtasks

158
159
160
161
162
163

    def load_task_or_group(self, task_list: Union[str, list] = None) -> dict:

        if isinstance(task_list, str):
            task_list = [task_list]

lintangsutawika's avatar
lintangsutawika committed
164
165
166
167
168
169
        all_loaded_tasks = dict(
            collections.ChainMap(
                *map(
                    self._load_individual_task_or_group,
                    task_list
                )
170
            )
lintangsutawika's avatar
lintangsutawika committed
171
        )
172
        return all_loaded_tasks
173

lintangsutawika's avatar
lintangsutawika committed
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
    def _get_task_and_group(self, task_dir: str):
        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.simple_load_yaml_config(yaml_path)
                    if list(config.keys()) == ["group", "task"]:
                        # This is a group config
                        tasks_and_groups[config["group"]] = {
                            "type": "group",
                            "task": -1, # This signals that
                                        # we don't need to know
                                        # the task list for indexing
                                        # as it can be loaded
                                        # when called.
                            "yaml_path": yaml_path,
                        }
                    else:
                        # This is a task config
                        task = config["task"]
                        tasks_and_groups[task] = {
                            "type": "task",
                            "yaml_path": yaml_path,
                            }

                        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)

        return tasks_and_groups
216

lintangsutawika's avatar
format  
lintangsutawika committed
217

lintangsutawika's avatar
lintangsutawika committed
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
# def check_prompt_config(
#     config: Dict[str, str], yaml_path: str = None
# ) -> List[Dict[str, str]]:
#     all_configs = []
#     if "use_prompt" in config:
#         prompt_list = prompts.load_prompt_list(
#             use_prompt=config["use_prompt"],
#             dataset_name=config["dataset_path"],
#             subset_name=config["dataset_name"] if "dataset_name" in config else None,
#             yaml_path=yaml_path,
#         )
#         for idx, prompt_variation in enumerate(prompt_list):
#             all_configs.append(
#                 {
#                     **config,
#                     **{"use_prompt": prompt_variation},
#                     **{
#                         "task": "_".join(
#                             [
#                                 config["task"]
#                                 if "task" in config
#                                 else get_task_name_from_config(config),
#                                 prompt_variation.split("/")[-1]
#                                 if ".yaml" in prompt_variation
#                                 else prompt_variation,
#                             ]
#                         )
#                     },
#                     **{"output_type": "generate_until"},
#                 }
#             )
#     else:
#         all_configs.append(config)
#     return all_configs