chore - Remove unneeded dependencies from main poetry (All-Hands-AI#7772)

Author: raymyers

openhands/resolver/utils.py

@@ -1,4 +1,3 @@
-import json
 import logging
 import multiprocessing as mp
 import os
@@ -7,7 +6,6 @@
 from typing import Callable
 
 import httpx
-import pandas as pd
 
 from openhands.controller.state.state import State
 from openhands.core.logger import get_console_handler
@@ -134,43 +132,6 @@ def cleanup() -> None:
         process.join()
 
 
-def prepare_dataset(
-    dataset: pd.DataFrame, output_file: str, eval_n_limit: int
-) -> pd.DataFrame:
-    assert 'instance_id' in dataset.columns, (
-        "Expected 'instance_id' column in the dataset. You should define your own "
-        "unique identifier for each instance and use it as the 'instance_id' column."
-    )
-    id_column = 'instance_id'
-    logger.info(f'Writing evaluation output to {output_file}')
-    finished_ids = set()
-    if os.path.exists(output_file):
-        with open(output_file, 'r') as f:
-            for line in f:
-                data = json.loads(line)
-                finished_ids.add(data[id_column])
-        logger.warning(
-            f'Output file {output_file} already exists. Loaded '
-            f'{len(finished_ids)} finished instances.'
-        )
-
-    if eval_n_limit:
-        dataset = dataset.head(eval_n_limit)
-        logger.info(f'Limiting evaluation to first {eval_n_limit} instances.')
-
-    new_dataset = [
-        instance
-        for _, instance in dataset.iterrows()
-        if instance[id_column] not in finished_ids
-    ]
-    logger.info(
-        f'Finished instances: {len(finished_ids)}, '
-        f'Remaining instances: {len(new_dataset)}'
-    )
-
-    return pd.DataFrame(new_dataset)
-
-
 def reset_logger_for_multiprocessing(
     logger: logging.Logger, instance_id: str, log_dir: str
 ) -> None:

poetry.lock

@@ -14,16 +14,13 @@ packages = [
 
 [tool.poetry.dependencies]
 python = "^3.12"
-datasets = "*"
-pandas = "*"
 litellm = "^1.60.0"
 aiohttp = ">=3.9.0,!=3.11.13"  # Pin to avoid yanked version 3.11.13
 google-generativeai = "*" # To use litellm with Gemini Pro API
 google-api-python-client = "^2.164.0" # For Google Sheets API
 google-auth-httplib2 = "*" # For Google Sheets authentication
 google-auth-oauthlib = "*" # For Google Sheets OAuth
 termcolor = "*"
-seaborn = "*"
 docker = "*"
 fastapi = "*"
 toml = "*"
@@ -39,8 +36,6 @@ jinja2 = "^3.1.3"
 python-multipart = "*"
 boto3 = "*"
 minio = "^7.2.8"
-gevent = "^24.2.1"
-pyarrow = "19.0.1" # transitive dependency, pinned here to avoid conflicts
 tenacity = ">=8.5,<10.0"
 zope-interface = "7.2"
 pathspec = "^0.12.1"
@@ -96,6 +91,7 @@ pytest-xdist = "*"
 openai = "*"
 pandas = "*"
 reportlab = "*"
+gevent = "^24.2.1"
 
 [tool.coverage.run]
 concurrency = ["gevent"]
@@ -149,6 +145,8 @@ browsergym-webarena = "0.13.3"
 browsergym-miniwob = "0.13.3"
 browsergym-visualwebarena = "0.13.3"
 boto3-stubs = {extras = ["s3"], version = "^1.37.19"}
+pyarrow = "19.0.1" # transitive dependency, pinned here to avoid conflicts
+datasets = "*"
 
 [tool.poetry-dynamic-versioning]
 enable = true