Skip to content

fix: add pandas to filesystem source dependencies #3887

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Bhagwat-45 wants to merge 3 commits into from
Closed

fix: add pandas to filesystem source dependencies #3887

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b6f4b24
fix: add pandas dependency to filesystem source read_csv
Bhagwat-45 Apr 23, 2026
9447ffd
fix mypy attr-defined issue for pandas wrapper
Bhagwat-45 May 20, 2026
33cf7b8
fix: use pandas wrapper correctly and clean up whitespace
Bhagwat-45 May 21, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 3 additions & 6 deletions dlt/sources/filesystem/readers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,9 @@
from typing import TYPE_CHECKING, Any, Iterable, Iterator, Optional

from dlt.common import json
from dlt.common.typing import copy_sig_any
from dlt.sources import TDataItems, DltResource, DltSource
from dlt.sources.filesystem import FileItemDict
from dlt.common.libs.pandas import pandas

from .helpers import fetch_arrow, fetch_json

Expand All @@ -23,8 +23,6 @@ def _read_csv(
Returns:
TDataItem: The file content
"""
import pandas as pd

# apply defaults to pandas kwargs
kwargs = {**{"header": "infer", "chunksize": chunksize}, **pandas_kwargs}
# For some remote file systems (for example, sftp/paramiko), decoding may happen before
Expand All @@ -42,10 +40,9 @@ def _read_csv(
# Here we use pandas chunksize to read the file in chunks and avoid loading the whole file
# in memory.
with file_obj.open(mode=open_mode, **open_kwargs) as file:
for df in pd.read_csv(file, **kwargs):
for df in pandas.read_csv(file, **kwargs):
yield df.to_dict(orient="records")


# NOTE inconsistent kwarg convention across readers `chunk_size` vs. `chunksize`
# snakecased `chunk_size` is the more appropriate Python convention
def _read_jsonl(items: Iterable[FileItemDict], chunksize: int = 1000) -> Iterator[TDataItems]:
Expand Down Expand Up @@ -156,4 +153,4 @@ def read_parquet(self) -> DltResource: ...
def read_csv_duckdb(self) -> DltResource: ...

else:
ReadersSource = DltSource
ReadersSource = DltSource
Loading