Formatting and commenting, fix console scripts

demo/app.py

@@ -1,45 +1,45 @@
+import os
+
 import gradio as gr
-import pymarc
-from marcai.process import process
-from marcai.utils.parsing import record_dict
 import pandas as pd
+import pymarc
+
 from marcai.predict import predict_onnx
+from marcai.process import process
 from marcai.utils import load_config
-import os
+from marcai.utils.parsing import record_dict
 
 demo_dir = os.path.dirname(os.path.realpath(__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)
 
-    # Load model config
+    # Load config
     config = load_config(os.path.join(demo_dir, "config.yaml"))
-    model_onnx = os.path.join(demo_dir, "model.onnx")
 
     # Run ONNX model
+    model_onnx = os.path.join(demo_dir, "model.onnx")
     input_df = df[config["model"]["features"]]
-    prediction = predict_onnx(model_onnx, input_df)
-
-    prediction = prediction.item()
+    prediction = predict_onnx(model_onnx, 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")
-    ],
+    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"
+    allow_flagging="never",
 )
 interface.launch()

marcai/find_matches.py

@@ -1,13 +1,14 @@
 import argparse
-from process import multiprocess_pairs
-from predict import predict_onnx
-from tqdm import tqdm
+import csv
+
 import pandas as pd
+from tqdm import tqdm
 
-from marcai.utils.parsing import load_records, record_dict
+from marcai.predict import predict_onnx
+from marcai.process import multiprocess_pairs
 from marcai.utils import load_config
+from marcai.utils.parsing import load_records, record_dict
 
-import csv
 
 def main():
     parser = argparse.ArgumentParser()

marcai/process.py

@@ -1,8 +1,8 @@
 import argparse
 import concurrent.futures
 import csv
-import itertools
 import time
+from multiprocessing import get_context
 
 import numpy as np
 import pandas as pd
@@ -12,8 +12,6 @@ import marcai.processing.comparisons as comps
 import marcai.processing.normalizations as norms
 from marcai.utils.parsing import load_records, record_dict
 
-from multiprocessing import get_context
-
 
 def multiprocess_pairs(
     records_df,

marcai/train.py

@@ -1,13 +1,15 @@
-import pytorch_lightning as lightning
-from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
-import warnings
-import yaml
 import argparse
 import os
+import tarfile
+import warnings
+
+import pytorch_lightning as lightning
 import torch
+import yaml
+from pytorch_lightning.callbacks import EarlyStopping, ModelCheckpoint
+
 from marcai.pl import MARCDataModule, SimilarityVectorModel
 from marcai.utils import load_config
-import tarfile
 
 
 def train(name=None):

setup.cfg

@@ -10,5 +10,5 @@ console_scripts =
     process = marcai:process.main
     predict = marcai:predict.main
     train = marcai:train.main
-    compare_records = marcai:compare_records.main
-    
+    find_matches = marcai:find_matches.main
+