mirror of
https://github.com/lancedb/lancedb.git
synced 2026-01-14 07:42:58 +00:00
[Python] FIx Contextualizer validation to arguments (#168)
Closes #164 --------- Co-authored-by: Will Jones <willjones127@gmail.com>
This commit is contained in:
@@ -13,7 +13,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import pandas as pd
|
||||
|
||||
from .exceptions import MissingValueError, MissingColumnError
|
||||
|
||||
def contextualize(raw_df: pd.DataFrame) -> Contextualizer:
|
||||
"""Create a Contextualizer object for the given DataFrame.
|
||||
@@ -140,6 +140,17 @@ class Contextualizer:
|
||||
def to_df(self) -> pd.DataFrame:
|
||||
"""Create the context windows and return a DataFrame."""
|
||||
|
||||
if self._text_col not in self._raw_df.columns.tolist():
|
||||
raise MissingColumnError(self._text_col)
|
||||
|
||||
if self._window is None or self._window < 1:
|
||||
raise MissingValueError("The value of window is None or less than 1. Specify the "
|
||||
"window size (number of rows to include in each window)")
|
||||
|
||||
if self._stride is None or self._stride < 1:
|
||||
raise MissingValueError("The value of stride is None or less than 1. Specify the "
|
||||
"stride (number of rows to skip between each window)")
|
||||
|
||||
def process_group(grp):
|
||||
# For each group, create the text rolling window
|
||||
text = grp[self._text_col].values
|
||||
|
||||
Reference in New Issue
Block a user