Skip to content

Fix some pandas warnings #394

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

Open
bobokvsky wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix some pandas warnings #394

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 6 additions & 5 deletions datapipe/store/database.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@
import math
from typing import Any, Callable, Iterator, cast

import numpy as np
import pandas as pd
from opentelemetry import trace
from sqlalchemy import Column, MetaData, Table, create_engine, func, text
Expand Down Expand Up @@ -239,10 +238,12 @@ def update_rows(self, df: DataDF) -> None:
if df.empty:
return

# TODO разобраться, нужен ли этот блок кода, написать тесты на заполнение None/NULL
insert_sql = self.dbconn.insert(self.data_table).values(
df.fillna(np.nan).replace({np.nan: None}).to_dict(orient="records")
)
# SQLAlchemy expects Python None for SQL NULL; keep object dtype to avoid
# pandas downcasting warnings while preserving scalar values.
df_records = df.astype(object)
df_records[pd.isna(df_records)] = None
records = df_records.to_dict(orient="records")
insert_sql = self.dbconn.insert(self.data_table).values(records)

if len(self.data_keys) > 0:
sql = insert_sql.on_conflict_do_update(
Expand Down
2 changes: 1 addition & 1 deletion datapipe/store/table_store.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ def hash_keys(self) -> list[str]:
return self.primary_keys + self.meta_keys

def hash_rows(self, df: DataDF) -> HashDF:
hash_df = df[self.hash_keys]
hash_df = df[self.hash_keys].copy()
hash_df["hash"] = df.apply(lambda x: str(list(x)), axis=1).apply(
lambda x: int.from_bytes(cityhash.CityHash32(x).to_bytes(4, "little"), "little", signed=True)
)
Expand Down
Loading