mirror of
https://github.com/hwchase17/langchain
synced 2024-11-16 06:13:16 +00:00
ed58eeb9c5
Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
74 lines
2.5 KiB
Python
74 lines
2.5 KiB
Python
from typing import Any, Iterator, List
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
|
|
class GeoDataFrameLoader(BaseLoader):
|
|
"""Load `geopandas` Dataframe."""
|
|
|
|
def __init__(self, data_frame: Any, page_content_column: str = "geometry"):
|
|
"""Initialize with geopandas Dataframe.
|
|
|
|
Args:
|
|
data_frame: geopandas DataFrame object.
|
|
page_content_column: Name of the column containing the page content.
|
|
Defaults to "geometry".
|
|
"""
|
|
|
|
try:
|
|
import geopandas as gpd
|
|
except ImportError:
|
|
raise ImportError(
|
|
"geopandas package not found, please install it with "
|
|
"`pip install geopandas`"
|
|
)
|
|
|
|
if not isinstance(data_frame, gpd.GeoDataFrame):
|
|
raise ValueError(
|
|
f"Expected data_frame to be a gpd.GeoDataFrame, got {type(data_frame)}"
|
|
)
|
|
|
|
if page_content_column not in data_frame.columns:
|
|
raise ValueError(
|
|
f"Expected data_frame to have a column named {page_content_column}"
|
|
)
|
|
|
|
if not isinstance(data_frame[page_content_column], gpd.GeoSeries):
|
|
raise ValueError(
|
|
f"Expected data_frame[{page_content_column}] to be a GeoSeries"
|
|
)
|
|
|
|
self.data_frame = data_frame
|
|
self.page_content_column = page_content_column
|
|
|
|
def lazy_load(self) -> Iterator[Document]:
|
|
"""Lazy load records from dataframe."""
|
|
|
|
# assumes all geometries in GeoSeries are same CRS and Geom Type
|
|
crs_str = self.data_frame.crs.to_string() if self.data_frame.crs else None
|
|
geometry_type = self.data_frame.geometry.geom_type.iloc[0]
|
|
|
|
for _, row in self.data_frame.iterrows():
|
|
geom = row[self.page_content_column]
|
|
|
|
xmin, ymin, xmax, ymax = geom.bounds
|
|
|
|
metadata = row.to_dict()
|
|
metadata["crs"] = crs_str
|
|
metadata["geometry_type"] = geometry_type
|
|
metadata["xmin"] = xmin
|
|
metadata["ymin"] = ymin
|
|
metadata["xmax"] = xmax
|
|
metadata["ymax"] = ymax
|
|
|
|
metadata.pop(self.page_content_column)
|
|
|
|
# using WKT instead of str() to help GIS system interoperability
|
|
yield Document(page_content=geom.wkt, metadata=metadata)
|
|
|
|
def load(self) -> List[Document]:
|
|
"""Load full dataframe."""
|
|
return list(self.lazy_load())
|