Skip to content
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

chore: use polars instead of pandas in examples #3289

Merged
merged 1 commit into from
Dec 29, 2024
Merged

chore: use polars instead of pandas in examples #3289

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
3 changes: 2 additions & 1 deletion examples/sql/connect_to_motherduck.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,9 @@
# dependencies = [
# "altair==5.4.1",
# "duckdb==1.1.0",
# "polars==1.18.0",
# "pyarrow==18.1.0",
Comment on lines +6 to +7
Copy link
Contributor

@Light2Dark Light2Dark Dec 25, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

hey @akshayka , may want to consider "polars[pyarrow]>=1.18.0"
https://duckdb.org/docs/guides/python/polars.html

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks! Will keep this in mind for the future. I think serializing both accomplishes the same thing?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes it does. Maybe just a small thing for future maintenance since we don't need to update the pyarrow version. But yeah it's fine.

# "marimo",
# "pandas==2.2.3",
# ]
# ///

Expand Down
3 changes: 2 additions & 1 deletion examples/sql/connect_to_postgres.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@
# dependencies = [
# "duckdb==1.1.1",
# "marimo",
# "pandas==2.2.3",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# "requests==2.32.3",
# ]
# ///
Expand Down
19 changes: 10 additions & 9 deletions examples/sql/connect_to_sqlite.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,19 +3,20 @@
# dependencies = [
# "duckdb==1.1.1",
# "marimo",
# "pandas==2.2.3",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# "requests==2.32.3",
# ]
# ///

import marimo

__generated_with = "0.9.1"
__generated_with = "0.10.7"
app = marimo.App(width="medium")


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md(
r"""
# Connect to SQLite
Expand All @@ -31,7 +32,7 @@ def __(mo):


@app.cell(hide_code=True)
def __():
def _():
import marimo as mo


Expand All @@ -53,7 +54,7 @@ def download_sample_data():


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.accordion(
{
"Tip: Creating SQL Cells": mo.md(
Expand All @@ -73,7 +74,7 @@ def __(mo):


@app.cell
def __(INFORMATION_SCHEMA, mo):
def _(INFORMATION_SCHEMA, TABLES, mo):
_df = mo.sql(
f"""
-- Boilerplate: detach the database so this cell works when you re-run it
Expand All @@ -90,13 +91,13 @@ def __(INFORMATION_SCHEMA, mo):


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md(r"""Once the database is attached, you can query it with SQL. For example, the next cell computes the average track length of each composer in the chinook database.""")
return


@app.cell
def __(chinook, mo, track):
def _(chinook, mo, track):
_df = mo.sql(
f"""
SELECT composer, MEAN(Milliseconds) as avg_track_ms from chinook.track GROUP BY composer ORDER BY avg_track_ms DESC;
Expand All @@ -106,7 +107,7 @@ def __(chinook, mo, track):


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md(
f"""
You can explore the schemas of all your tables at a glance in the **data sources panel**: click
Expand Down
3 changes: 2 additions & 1 deletion examples/sql/misc/database_explorer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@
# dependencies = [
# "duckdb==1.1.1",
# "marimo",
# "pandas==2.2.3",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# ]
# ///

Expand Down
3 changes: 3 additions & 0 deletions examples/sql/misc/electric_vehicles.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,10 @@
# requires-python = ">=3.9"
# dependencies = [
# "altair==5.4.1",
# "duckdb==1.1.3",
# "marimo",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# ]
# ///

Expand Down
6 changes: 3 additions & 3 deletions examples/sql/misc/sql_cars.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,8 @@
# "altair==5.4.1",
# "duckdb==1.1.1",
# "marimo",
# "pandas==2.2.3",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# "vega-datasets==0.9.0",
# ]
# ///
Expand Down Expand Up @@ -233,11 +234,10 @@ def __(cars, mo, selected_cars):
@app.cell
def __():
import marimo as mo
import pandas as pd
import duckdb
import altair as alt
from vega_datasets import data
return alt, data, duckdb, mo, pd
return alt, data, duckdb, mo


if __name__ == "__main__":
Expand Down
3 changes: 2 additions & 1 deletion examples/sql/parametrizing_sql_queries.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@
# dependencies = [
# "duckdb==1.1.1",
# "marimo",
# "pandas==2.2.3",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# "vega-datasets==0.9.0",
# ]
# ///
Expand Down
3 changes: 2 additions & 1 deletion examples/sql/querying_dataframes.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,8 @@
# dependencies = [
# "duckdb==1.1.1",
# "marimo",
# "pandas==2.2.3",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# "vega-datasets==0.9.0",
# ]
# ///
Expand Down
38 changes: 20 additions & 18 deletions examples/sql/read_csv.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,19 +3,20 @@
# dependencies = [
# "duckdb==1.1.1",
# "marimo",
# "pandas==2.2.3",
# "polars==1.18.0",
# "pyarrow==18.1.0",
# "vega-datasets==0.9.0",
# ]
# ///

import marimo

__generated_with = "0.9.1"
__generated_with = "0.10.7"
app = marimo.App(width="medium")


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md(
"""
# Read CSV
Expand All @@ -27,22 +28,22 @@ def __(mo):


@app.cell(hide_code=True)
def __():
def _():
import marimo as mo
import pandas as pd
import polars as pl

pd.DataFrame({"A": [1, 2, 3], "B": ["a", "b", "c"]}).to_csv("data.csv")
return mo, pd
pl.DataFrame({"A": [1, 2, 3], "B": ["a", "b", "c"]}).write_csv("data.csv")
return mo, pl


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md("""Reading from a local CSV is as easy as `SELECT * from "data.csv"`, where `data.csv` is the path to your local file (or a URL to a CSV file).""")
return


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.accordion(
{
"Tip: Creating SQL Cells": mo.md(
Expand All @@ -62,19 +63,20 @@ def __(mo):


@app.cell
def __(data, mo):
def _(mo):
result = mo.sql(
f"""
-- Tip: you can also specify the data files using a glob, such as '/path/to/*.csv'
-- or '/path/**/to/*.csv'
SELECT * FROM "data.csv"
""", output=False
""",
output=False,
)
return (result,)


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.accordion(
{
"Tip: Query output": mo.md(
Expand All @@ -92,13 +94,13 @@ def __(mo):


@app.cell
def __(result):
def _(result):
result
return


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md(
r"""
## Create an in-memory table from a CSV file
Expand All @@ -110,7 +112,7 @@ def __(mo):


@app.cell
def __(data, mo):
def _(mo):
_df = mo.sql(
f"""
CREATE TABLE myTable AS SELECT * FROM "data.csv"
Expand All @@ -120,7 +122,7 @@ def __(data, mo):


@app.cell
def __(mo, myTable):
def _(mo, myTable):
_df = mo.sql(
f"""
SELECT * FROM myTable
Expand All @@ -130,13 +132,13 @@ def __(mo, myTable):


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md(r"""## Advanced usage""")
return


@app.cell(hide_code=True)
def __(mo):
def _(mo):
mo.md(r"""To customize how your CSV is read, including specifying the delimiter type, use [duckdb's `read_csv` function](https://duckdb.org/docs/data/csv/overview.html).""")
return

Expand Down
Loading
Loading