Spaces:
Running
Running
File size: 2,145 Bytes
cb5b71d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 |
import pandas as pd
import streamlit as st
from core.state import Metadata
import mlcroissant as mlc
def render_jsonld():
if not st.session_state[Metadata]:
return st.code({}, language="json")
try:
croissant = st.session_state[Metadata]
distribution = []
for file in croissant.distribution:
distribution.append(
mlc.FileObject(
name=file.name,
description=file.description,
content_url=file.content_url,
encoding_format=file.encoding_format,
sha256=file.sha256,
)
)
record_sets = []
for record_set in croissant.record_sets:
fields = []
for _, field in record_set.get("fields", pd.DataFrame()).iterrows():
fields.append(
mlc.Field(
name=field["name"],
description=field["description"],
data_types=field["data_type"],
source=mlc.Source(
uid=file.name,
node_type="distribution",
extract=mlc.Extract(column=field["name"]),
),
)
)
record_sets.append(
mlc.RecordSet(
name=record_set["name"],
description=record_set["description"],
fields=fields,
)
)
if croissant.metadata:
metadata = mlc.Metadata(
name=croissant.metadata.name,
citation=croissant.metadata.citation,
license=croissant.metadata.license,
description=croissant.metadata.description,
url=croissant.metadata.url,
distribution=distribution,
record_sets=record_sets,
)
return st.json(metadata.to_json(), expanded=True)
except Exception as exception:
return st.code(exception, language="text")
|