Fix imports to match new directory structure under evaluation/benchma…

…rks/

evaluation/benchmarks/EDA/run_infer.py

@@ -4,7 +4,7 @@
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.EDA.game import Q20Game, Q20GameCelebrity
+from evaluation.benchmarks.EDA.game import Q20Game, Q20GameCelebrity
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/benchmarks/agent_bench/run_infer.py

@@ -7,7 +7,7 @@
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.agent_bench.helper import (
+from evaluation.benchmarks.agent_bench.helper import (
     FAKE_RESPONSES,
     INST_SUFFIXES,
     compare_results,

evaluation/benchmarks/aider_bench/run_infer.py

@@ -7,7 +7,7 @@
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.aider_bench.helper import (
+from evaluation.benchmarks.aider_bench.helper import (
     FAKE_RESPONSES,
     INST_SUFFIXES,
     INSTRUCTIONS_ADDENDUM,

evaluation/benchmarks/biocoder/run_infer.py

@@ -8,7 +8,7 @@
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.biocoder.utils import BiocoderData
+from evaluation.benchmarks.biocoder.utils import BiocoderData
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/benchmarks/discoverybench/run_infer.py

@@ -5,10 +5,10 @@
 import git
 import pandas as pd
 
-from evaluation.discoverybench.eval_utils.eval_w_subhypo_gen import (
+from evaluation.benchmarks.discoverybench.eval_utils.eval_w_subhypo_gen import (
     run_eval_gold_vs_gen_NL_hypo_workflow,
 )
-from evaluation.discoverybench.eval_utils.response_parser import (
+from evaluation.benchmarks.discoverybench.eval_utils.response_parser import (
     extract_gen_hypo_from_logs,
 )
 from evaluation.utils.shared import (

evaluation/benchmarks/gaia/run_infer.py

@@ -7,7 +7,7 @@
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.gaia.scorer import question_scorer
+from evaluation.benchmarks.gaia.scorer import question_scorer
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/benchmarks/gorilla/run_infer.py

@@ -5,7 +5,7 @@
 import pandas as pd
 import requests
 
-from evaluation.gorilla.utils import encode_question, get_data_for_hub
+from evaluation.benchmarks.gorilla.utils import encode_question, get_data_for_hub
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/benchmarks/mint/run_infer.py

@@ -6,10 +6,10 @@
 import pandas as pd
 from datasets import load_dataset
 
-from evaluation.mint.datatypes import TaskState
-from evaluation.mint.env import SimplifiedEnv
-from evaluation.mint.prompts import ToolPromptTemplate
-from evaluation.mint.tasks import Task
+from evaluation.benchmarks.mint.datatypes import TaskState
+from evaluation.benchmarks.mint.env import SimplifiedEnv
+from evaluation.benchmarks.mint.prompts import ToolPromptTemplate
+from evaluation.benchmarks.mint.tasks import Task
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/benchmarks/mint/tasks/__init__.py

@@ -1,6 +1,6 @@
-from evaluation.mint.tasks.base import Task
-from evaluation.mint.tasks.codegen import HumanEvalTask, MBPPTask
-from evaluation.mint.tasks.reasoning import (
+from evaluation.benchmarks.mint.tasks.base import Task
+from evaluation.benchmarks.mint.tasks.codegen import HumanEvalTask, MBPPTask
+from evaluation.benchmarks.mint.tasks.reasoning import (
     MultipleChoiceTask,
     ReasoningTask,
     TheoremqaTask,

evaluation/benchmarks/mint/tasks/codegen.py

@@ -2,7 +2,7 @@
 
 from utils import check_correctness
 
-from evaluation.mint.tasks.base import Task
+from evaluation.benchmarks.mint.tasks.base import Task
 
 LOGGER = logging.getLogger('MINT')
 

evaluation/benchmarks/swe_bench/eval_infer.py

@@ -12,7 +12,7 @@
 from swebench.harness.test_spec import SWEbenchInstance, TestSpec, make_test_spec
 from swebench.harness.utils import load_swebench_dataset
 
-from evaluation.swe_bench.run_infer import get_instance_docker_image
+from evaluation.benchmarks.swe_bench.run_infer import get_instance_docker_image
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,

evaluation/benchmarks/swe_bench/run_infer.py

@@ -9,7 +9,7 @@
 from datasets import load_dataset
 
 import openhands.agenthub
-from evaluation.swe_bench.prompt import CODEACT_SWE_PROMPT
+from evaluation.benchmarks.swe_bench.prompt import CODEACT_SWE_PROMPT
 from evaluation.utils.shared import (
     EvalException,
     EvalMetadata,

evaluation/benchmarks/swe_bench/scripts/docker/push_docker_instance_images.py

@@ -32,7 +32,7 @@
 from openhands.core.logger import openhands_logger as logger
 
 logger.setLevel('ERROR')
-from evaluation.swe_bench.run_infer import get_instance_docker_image  # noqa
+from evaluation.benchmarks.swe_bench.run_infer import get_instance_docker_image  # noqa
 
 parser = argparse.ArgumentParser()
 parser.add_argument('--dataset', type=str, default='princeton-nlp/SWE-bench_Lite')

evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_output_to_md.py

@@ -8,7 +8,7 @@
 import pandas as pd
 from tqdm import tqdm
 
-from evaluation.swe_bench.eval_infer import process_git_patch
+from evaluation.benchmarks.swe_bench.eval_infer import process_git_patch
 from openhands.events.serialization import event_from_dict
 
 tqdm.pandas()

evaluation/benchmarks/swe_bench/scripts/eval/convert_oh_output_to_swe_json.py

@@ -3,7 +3,7 @@
 
 import pandas as pd
 
-from evaluation.swe_bench.eval_infer import process_git_patch
+from evaluation.benchmarks.swe_bench.eval_infer import process_git_patch
 
 parser = argparse.ArgumentParser()
 parser.add_argument('oh_output_file', type=str)

evaluation/benchmarks/toolqa/run_infer.py

@@ -4,7 +4,7 @@
 
 import pandas as pd
 
-from evaluation.toolqa.utils import encode_question, eval_answer, get_data
+from evaluation.benchmarks.toolqa.utils import encode_question, eval_answer, get_data
 from evaluation.utils.shared import (
     EvalMetadata,
     EvalOutput,