rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-09 13:22:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

Allow creation of an empty table (#254)

Browse Source 
It's inconvenient to always require data at table creation time.
Here we enable you to create an empty table and add data and set schema
later.

---------

Co-authored-by: Chang She <chang@lancedb.com>
This commit is contained in:
Chang She
2023-07-06 20:44:58 -07:00
committed by GitHub
parent 507eeae9c8
commit e2325c634b
5 changed files with 61 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
python/tests/test_table.py
View File

@@ -19,6 +19,7 @@ import numpy as np
import pandas as pd
import pyarrow as pa
import pytest
from lance.vector import vec_to_table
from lancedb.db import LanceDBConnection
from lancedb.table import LanceTable
@@ -89,7 +90,31 @@ def test_create_table(db):
assert expected == tbl
def test_empty_table(db):
schema = pa.schema(
[
pa.field("vector", pa.list_(pa.float32(), 2)),
pa.field("item", pa.string()),
pa.field("price", pa.float32()),
]
)
tbl = LanceTable.create(db, "test", schema=schema)
data = [
{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
]
tbl.add(data=data)
def test_add(db):
schema = pa.schema(
[
pa.field("vector", pa.list_(pa.float32(), 2)),
pa.field("item", pa.string()),
pa.field("price", pa.float64()),
]
)
table = LanceTable.create(
db,
"test",
@@ -98,7 +123,19 @@ def test_add(db):
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
],
)
_add(table, schema)
table = LanceTable.create(db, "test2", schema=schema)
table.add(
data=[
{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0},
],
)
_add(table, schema)
def _add(table, schema):
# table = LanceTable(db, "test")
assert len(table) == 2
@@ -113,13 +150,7 @@ def test_add(db):
pa.array(["foo", "bar", "new"]),
pa.array([10.0, 20.0, 30.0]),
],
schema=pa.schema(
[
pa.field("vector", pa.list_(pa.float32(), 2)),
pa.field("item", pa.string()),
pa.field("price", pa.float64()),
]
),
schema=schema,
)
assert expected == table.to_arrow()