Visualize catfact data with catfact

catfact_with_catfact.py

# https://dlthub.com/docs/general-usage/http/overview
import dlt
from dlt.sources.helpers.rest_client import RESTClient

catfact_client = RESTClient(base_url="https://catfact.ninja")


@dlt.resource
def get_breeds():
    for page in catfact_client.paginate(
        "/breeds",
        params={
            "per_page": 100,
        },
    ):
        yield page


pipeline = dlt.pipeline(
    pipeline_name="catfact_breeds",
    destination="duckdb",
    dataset_name="catfact_data",
)
load_info = pipeline.run(get_breeds)
print(load_info)

# https://dlthub.com/docs/general-usage/dataset-access/dataset
dataset = pipeline.dataset()
breeds_relation = dataset["get_breeds"]

# https://github.com/machow/catfact
import catfact as fct
import polars as pl
from plotnine import ggplot, aes, geom_bar, coord_flip

(
    pl.from_arrow(breeds_relation.arrow())
    .with_columns(
        fct.infreq(pl.col("origin"))
    )
    >> ggplot(aes("origin"))
    + geom_bar()
    + coord_flip()
).show()

requirements.txt

catfact
dlt[duckdb]
ibis-framework[duckdb]
plotnine

visualize_breed_origins.png