doczyai-pipelines/fieldExtraction/src/testbed/testbed_postprocess.py

# This script postprocesses the testbed data from an Excel file.  It uses a custom
# function `testbed_postprocess` from the `testbed_utils` module (similar to
# postprocess.postprocess() but skipping some steps)

# Run this from the fieldExtraction directory:
# poetry run python -m src.testbed.testbed_postprocess

#### CONFIG ####
testbed_filename = "src/testbed/v6_DoczyAI_all_test_bed_LIVE_5.6.25.xlsx"
testbed_sheetname = "all_test_bed_labels"
output_filename = "src/testbed/v6_DoczyAI_all_test_bed_LIVE_5.6.25_POSTPROCESSED.xlsx"

#### IMPORTS ####
import pandas as pd
from src.testbed.testbed_utils import testbed_postprocess

#### EXECUTION ####
# Load the testbed
df = pd.read_excel(testbed_filename, sheet_name=testbed_sheetname)
print(
    f"Loaded testbed from {testbed_filename} with {df.shape[0]} rows and {df.shape[1]} columns"
)

# Postprocess the testbed
testbed_postprocess(df).to_excel(output_filename, index=False)

print(f"Postprocessed testbed saved to {output_filename}")