rust/lancedb
1
0
Fork 0
mirror of https://github.com/lancedb/lancedb.git synced 2026-01-05 19:32:56 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: switch python examples to be row based (#554)

Browse Source
This commit is contained in:
Rok Mihevc
2023-10-14 23:07:43 +02:00
committed by Weston Pace
parent 7b5bfadab2
commit 377a564904
5 changed files with 41 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
docs/src/guides/tables.md
View File

@@ -251,8 +251,9 @@ After a table has been created, you can always add more data to it using
### Adding Pandas DataFrame
```python
df = pd.DataFrame([{"vector": [1.3, 1.4], "item": "fizz", "price": 100.0},
{"vector": [9.5, 56.2], "item": "buzz", "price": 200.0}])
df = pd.DataFrame({
"vector": [[1.3, 1.4], [9.5, 56.2]], "item": ["fizz", "buzz"], "price": [100.0, 200.0]
})
tbl.add(df)
```
@@ -261,17 +262,12 @@ After a table has been created, you can always add more data to it using
### Adding to table using Iterator
```python
import pandas as pd
def make_batches():
for i in range(5):
yield pd.DataFrame(
{
"vector": [[3.1, 4.1], [1, 1]],
"item": ["foo", "bar"],
"price": [10.0, 20.0],
})
yield [
{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0}
]
tbl.add(make_batches())
```
@@ -306,9 +302,10 @@ Use the `delete()` method on tables to delete rows from a table. To choose which
```python
import lancedb
import pandas as pd
data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
data = [{"x": 1, "vector": [1, 2]},
{"x": 2, "vector": [3, 4]},
{"x": 3, "vector": [5, 6]}]
db = lancedb.connect("./.lancedb")
table = db.create_table("my_table", data)
table.to_pandas()

42
docs/src/notebooks/tables_guide.ipynb
View File

@@ -114,13 +114,10 @@
}
],
"source": [
"import pandas as pd\n",
"\n",
"data = pd.DataFrame({\n",
" \"vector\": [[1.1, 1.2], [0.2, 1.8]],\n",
" \"lat\": [45.5, 40.1],\n",
" \"long\": [-122.7, -74.1]\n",
"})\n",
"data = [\n",
" {\"vector\": [1.1, 1.2], \"lat\": 45.5, \"long\": -122.7},\n",
" {\"vector\": [0.2, 1.8], \"lat\": 40.1, \"long\": -74.1},\n",
"]\n",
"\n",
"db.create_table(\"table2\", data)\n",
"\n",
@@ -366,11 +363,11 @@
"def make_batches():\n",
" for i in range(5):\n",
" yield pd.DataFrame(\n",
" {\n",
" \"vector\": [[3.1, 4.1], [1, 1]],\n",
" \"item\": [\"foo\", \"bar\"],\n",
" \"price\": [10.0, 20.0],\n",
" })\n",
" {\n",
" \"vector\": [[3.1, 4.1], [1, 1]],\n",
" \"item\": [\"foo\", \"bar\"],\n",
" \"price\": [10.0, 20.0],\n",
" })\n",
"\n",
"tbl = db.create_table(\"table5\", make_batches(), schema=PydanticSchema)\n",
"tbl.schema"
@@ -572,9 +569,11 @@
"metadata": {},
"outputs": [],
"source": [
"df = pd.DataFrame([{\"vector\": [1.3, 1.4], \"item\": \"fizz\", \"price\": 100.0},\n",
" {\"vector\": [9.5, 56.2], \"item\": \"buzz\", \"price\": 200.0}])\n",
"tbl.add(df)"
"data = [\n",
" {\"vector\": [1.3, 1.4], \"item\": \"fizz\", \"price\": 100.0},\n",
" {\"vector\": [9.5, 56.2], \"item\": \"buzz\", \"price\": 200.0}\n",
"]\n",
"tbl.add(data)"
]
},
{
@@ -596,17 +595,12 @@
"metadata": {},
"outputs": [],
"source": [
"\n",
"import pandas as pd\n",
"\n",
"def make_batches():\n",
" for i in range(5):\n",
" yield pd.DataFrame(\n",
" {\n",
" \"vector\": [[3.1, 4.1], [1, 1]],\n",
" \"item\": [\"foo\", \"bar\"],\n",
" \"price\": [10.0, 20.0],\n",
" })\n",
" yield [\n",
" {\"vector\": [3.1, 4.1], \"item\": \"foo\", \"price\": 10.0},\n",
" {\"vector\": [1, 1], \"item\": \"bar\", \"price\": 20.0},\n",
" ]\n",
"tbl.add(make_batches())"
]
},

1
docs/src/python/arrow.md
View File

@@ -39,7 +39,6 @@ to lazily generate data:
from typing import Iterable
import pyarrow as pa
import lancedb
def make_batches() -> Iterable[pa.RecordBatch]:
for i in range(5):

10
docs/src/python/duckdb.md
View File

@@ -11,15 +11,13 @@ pip install duckdb lancedb
We will re-use [the dataset created previously](./arrow.md):
```python
import pandas as pd
import lancedb
db = lancedb.connect("data/sample-lancedb")
data = pd.DataFrame({
"vector": [[3.1, 4.1], [5.9, 26.5]],
"item": ["foo", "bar"],
"price": [10.0, 20.0]
})
data = [
{"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
{"vector": [5.9, 26.5], "item": "bar", "price": 20.0}
]
table = db.create_table("pd_table", data=data)
arrow_table = table.to_arrow()
```

15
python/lancedb/table.py
View File

@@ -291,8 +291,9 @@ class Table(ABC):
Examples
--------
>>> import lancedb
>>> import pandas as pd
>>> data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
>>> data = [
... {"x": 1, "vector": [1, 2]}, {"x": 2, "vector": [3, 4]}, {"x": 3, "vector": [5, 6]}
... ]
>>> db = lancedb.connect("./.lancedb")
>>> table = db.create_table("my_table", data)
>>> table.to_pandas()
@@ -713,8 +714,9 @@ class LanceTable(Table):
Examples
--------
>>> import lancedb
>>> import pandas as pd
>>> data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
>>> data = [
... {"x": 1, "vector": [1, 2]}, {"x": 2, "vector": [3, 4]}, {"x": 3, "vector": [5, 6]}
... ]
>>> db = lancedb.connect("./.lancedb")
>>> table = db.create_table("my_table", data)
>>> table.to_pandas()
@@ -829,8 +831,9 @@ class LanceTable(Table):
Examples
--------
>>> import lancedb
>>> import pandas as pd
>>> data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1, 2], [3, 4], [5, 6]]})
>>> data = [
... {"x": 1, "vector": [1, 2]}, {"x": 2, "vector": [3, 4]}, {"x": 3, "vector": [5, 6]}
... ]
>>> db = lancedb.connect("./.lancedb")
>>> table = db.create_table("my_table", data)
>>> table.to_pandas()