Spaces:
Sleeping
Sleeping
File size: 1,151 Bytes
c19ce61 a85bc9a c19ce61 5334ec8 c19ce61 5334ec8 478308a 5334ec8 c19ce61 a85bc9a c19ce61 a85bc9a c19ce61 a85bc9a 5334ec8 a85bc9a d7838fe 5334ec8 a85bc9a c19ce61 a85bc9a c19ce61 a85bc9a 478308a |
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 |
import os
import gradio as gr
import pandas as pd
import pymarc
from marcai.predict import predict
from marcai.process import process
from marcai.utils.parsing import record_dict
from marcai.pl import SimilarityVectorModel
root = os.path.dirname(os.path.abspath(__file__))
def compare(file1, file2):
# Load records
record1 = pymarc.parse_xml_to_array(file1)[0]
record2 = pymarc.parse_xml_to_array(file2)[0]
# Turn into dataframes
df1 = pd.DataFrame.from_dict([record_dict(record1)])
df2 = pd.DataFrame.from_dict([record_dict(record2)])
df = process(df1, df2)
model = SimilarityVectorModel.from_pretrained("cdlib/marc-match-ai")
input_df = df[model.features]
# Run model
prediction = predict(model, input_df).item()
return {"match": prediction, "not match": 1 - prediction}
interface = gr.Interface(
fn=compare,
inputs=[gr.File(label="MARC XML File 1"), gr.File(label="MARC XML File 2")],
outputs=gr.Label(label="Classification"),
title="MARC Record Matcher",
description="Upload two MARC XML files with one record each.",
allow_flagging="never",
)
interface.launch()
|