mirror of
https://github.com/run-llama/llama-hub.git
synced 2025-08-14 03:31:41 +00:00
e97bb81915
* cr * cr * cr --------- Co-authored-by: Jerry Liu <jerry@robustintelligence.com> Co-authored-by: Jesse Zhang <jessetanzhang@gmail.com>
71 lines
2.2 KiB
Python
71 lines
2.2 KiB
Python
"""Pandas CSV reader.
|
|
|
|
A parser for tabular data files using pandas.
|
|
|
|
"""
|
|
from pathlib import Path
|
|
from typing import Any, Dict, List, Optional
|
|
|
|
from llama_index.readers.base import BaseReader
|
|
from llama_index.readers.schema.base import Document
|
|
|
|
|
|
class PandasCSVReader(BaseReader):
|
|
r"""Pandas-based CSV parser.
|
|
|
|
Parses CSVs using the separator detection from Pandas `read_csv`function.
|
|
If special parameters are required, use the `pandas_config` dict.
|
|
|
|
Args:
|
|
concat_rows (bool): whether to concatenate all rows into one document.
|
|
If set to False, a Document will be created for each row.
|
|
True by default.
|
|
|
|
col_joiner (str): Separator to use for joining cols per row.
|
|
Set to ", " by default.
|
|
|
|
row_joiner (str): Separator to use for joining each row.
|
|
Only used when `concat_rows=True`.
|
|
Set to "\n" by default.
|
|
|
|
pandas_config (dict): Options for the `pandas.read_csv` function call.
|
|
Refer to https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html
|
|
for more information.
|
|
Set to empty dict by default, this means pandas will try to figure
|
|
out the separators, table head, etc. on its own.
|
|
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
*args: Any,
|
|
concat_rows: bool = True,
|
|
col_joiner: str = ", ",
|
|
row_joiner: str = "\n",
|
|
pandas_config: dict = {},
|
|
**kwargs: Any
|
|
) -> None:
|
|
"""Init params."""
|
|
super().__init__(*args, **kwargs)
|
|
self._concat_rows = concat_rows
|
|
self._col_joiner = col_joiner
|
|
self._row_joiner = row_joiner
|
|
self._pandas_config = pandas_config
|
|
|
|
def load_data(
|
|
self, file: Path, extra_info: Optional[Dict] = None
|
|
) -> List[Document]:
|
|
"""Parse file."""
|
|
import pandas as pd
|
|
|
|
df = pd.read_csv(file, **self._pandas_config)
|
|
|
|
text_list = df.apply(
|
|
lambda row: (self._col_joiner).join(row.astype(str).tolist()), axis=1
|
|
).tolist()
|
|
|
|
if self._concat_rows:
|
|
return [Document((self._row_joiner).join(text_list), extra_info=extra_info)]
|
|
else:
|
|
return [Document(text, extra_info=extra_info) for text in text_list]
|